Review

Applications of Machine Learning in Cancer Imaging: A Review

of Diagnostic Methods for Six Major Cancer Types
Andreea Ionela Dumachi * and Cătălin Buiu

Department of Automatic Control and Systems Engineering, National University of Science and Technology
POLITEHNICA Bucharest, 060042 Bucharest, Romania; [email protected]
* Correspondence: [email protected]

Abstract: Machine learning (ML) methods have revolutionized cancer analysis by enhancing the
accuracy of diagnosis, prognosis, and treatment strategies. This paper presents an extensive study
on the applications of machine learning in cancer analysis, with a focus on three primary areas: a
comparative analysis of medical imaging techniques (including X-rays, mammography, ultrasound,
CT, MRI, and PET), various AI and ML techniques (such as deep learning, transfer learning, and
ensemble learning), and the challenges and limitations associated with utilizing ML in cancer analysis.
The study highlights the potential of ML to improve early detection and patient outcomes while
also addressing the technical and practical challenges that must be overcome for its effective clinical
integration. Finally, the paper discusses future directions and opportunities for advancing ML
applications in cancer research.

Keywords: machine learning; lung cancer; breast cancer; brain cancer; cervical cancer; colorectal
cancer; liver cancer; tumor classification; tumor segmentation

1. Introduction
Globally, cancer continues to be a significant public health challenge, with nearly
20 million new cases and 9.7 million deaths that occurred in 2022 alone [1]. In 2024,
Citation: Dumachi, A.I.; Buiu, C. the American Cancer Society estimated there would be 2,001,140 new cancer cases and
Applications of Machine Learning in
611,720 cancer-related deaths. The projected 611,720 deaths translate to approximately
Cancer Imaging: A Review of
1671 fatalities daily, with lung, prostate, and colorectal cancers being the primary causes in
Diagnostic Methods for Six Major
men, and lung, breast, and colorectal cancers being the primary causes in women [2]. These
Cancer Types. Electronics 2024, 13,
data underscore the ongoing challenges posed by cancer and the importance of continued
4697. https://doi.org/10.3390/
research and innovation in cancer analysis and care.
electronics13234697
Cancer analysis refers to the comprehensive examination and study of cancer, involv-
Academic Editor: Alejandro L. Borja ing various methods and techniques to understand its development, progression, diagnosis,
Received: 8 September 2024
treatment, and prognosis. It encompasses several key areas, illustrated in Figure 1.
Revised: 20 November 2024
Diagnosis is the foundational step, involving the identification of cancer through
Accepted: 25 November 2024
methods like imaging (MRI, CT scans) or biopsy. This phase is crucial, as early and
Published: 27 November 2024 precise detection greatly impacts treatment decisions and patient outcomes. Prognosis
follows, focusing on predicting the likely course of the disease, including survival rates
and the risk of recurrence. Prognostic models consider factors like tumor size, stage,
histological grade, and molecular markers. With advancements in ML, these models can
Copyright: © 2024 by the authors. now incorporate complex datasets, such as imaging and genomic information, to enhance
Licensee MDPI, Basel, Switzerland. prediction accuracy and guide tailored treatment strategies. Treatment is another vital
This article is an open access article
area, centered on developing and optimizing therapeutic plans based on the cancer type
distributed under the terms and
and individual patient characteristics. Standard modalities include surgery, chemotherapy,
conditions of the Creative Commons
radiation therapy, targeted therapy, and immunotherapy. The emergence of personalized
Attribution (CC BY) license (https://
medicine has enabled the use of treatments specifically targeting genetic mutations within
creativecommons.org/licenses/by/
tumors, improving effectiveness and minimizing side effects. ML and AI assist in predicting
4.0/).

Electronics 2024, 13, 4697. https://doi.org/10.3390/electronics13234697 https://www.mdpi.com/journal/electronics

Electronics 2024, 13, 4697 2 of 40

patient responses to different therapies, optimizing treatment selection, and adjusting plans
as cancer progresses or responds to interventions. Research plays a critical role in advancing
cancer analysis by investigating the biological mechanisms underlying cancer, identifying
new therapeutic targets, and exploring novel diagnostic methods. With the integration
of genomics, proteomics, and bioinformatics, research efforts have accelerated, providing
deeper insights into tumor behavior and potential treatment pathways. In parallel, data
analysis leverages statistical and computational techniques, including ML, to analyze vast
datasets from imaging, clinical records, and genetic profiles. This analysis aids in identifying
patterns, classifying cancer types, segmenting tumors, and making predictive assessments
regarding patient outcomes. Epidemiology studies the distribution and determinants of
cancer across populations to identify risk factors, assess the impact of preventive measures,
and inform public health policies. Understanding trends in cancer incidence, survival,
and mortality is essential for developing effective screening programs and educational
campaigns. Finally, patient outcomes focus on evaluating the success of treatments in
terms of survival, quality of life, and recurrence rates. By analyzing outcomes, healthcare
providers can refine treatment protocols, improve supportive care, and ensure optimal
patient well-being during and after their cancer journey. Together, these key areas form an
Electronics 2024, 13, x FOR PEER REVIEW
integrated approach to cancer analysis, driving progress in diagnosis, treatment, research, 2 o
and patient care.

•Identifying the presence and type of cancer through medical

Diagnosis imaging, biopsy, and other diagnostic tests.

•Predicting the likely course and outcome of the disease,

Prognosis including survival rates and potential for recurrence.

•Developing and optimizing treatment plans, which may include

Treatment surgery, chemotherapy, radiation therapy, immunotherapy, and
targeted therapies.

•Investigating the biological mechanisms underlying cancer,

Research studying genetic and molecular profiles, and exploring new
therapeutic targets.

•Utilizing statistical and computational methods, including ML

Data Analysis and AI, to analyze large datasets, identify patterns, and make
predictions about cancer behavior and treatment responses.

•Studying the distribution and determinants of cancer in

Epidemiology populations to understand risk factors and inform prevention
strategies.

•Assessing the effectiveness of treatments and interventions in

Patient Outcomes improving patient quality of life and survival.

Figure 1. KeyFigure
areas of1.cancer
Key areas of cancer analysis.
analysis.

Medical imaging data analysis

Diagnosis is crucial forstep,
is the foundational effectively and accurately
involving detecting
the identification of and
cancer thro
diagnosing various
methodstypes of cancer.
like imaging Expert
(MRI, CTradiologists and pathologists
scans) or biopsy. This phase isrely on medical
crucial, as early and pre
images to identify
detectionanomalous growthstreatment
greatly impacts or abnormalities
decisionswithin the patient’s
and patient body,Prognosis
outcomes. deter- follo
mining the staging
focusing andonmetastasis
predictingofthe
cancer through
likely coursemeticulous analysis.
of the disease, A diverse
including rangerates and
survival
of imaging modalities is used forPrognostic
risk of recurrence. diagnosingmodels
different cancer factors
consider types, significantly enhancing
like tumor size, stage, histolog
diagnostic precision
grade, and by molecular
providing markers.
exceptionally
With accurate and clear
advancements depictions
in ML, of tissues
these models can now in
and internal porate
organs.complex datasets, such as imaging and genomic information, to enhance predic
In recent years, extensive
accuracy and guideresearch
tailoredhas focusedstrategies.
treatment on AI andTreatment
ML, identifying numerous
is another vital area, cente
areas where onthese
developing and optimizing therapeutic plans based on the canceradvance-
techniques can be applied to yield superior results [3]. These type and individ
ments offer promising avenues for enhancing
patient characteristics. Standardcancer diagnosis
modalities and care,
include as such
surgery, algorithms radia
chemotherapy,
can analyze therapy,
medical images
targetedwith unprecedented
therapy, efficiency, aiding
and immunotherapy. in early detection
The emergence and medi
of personalized
personalizedhastreatment strategies for cancer patients. Moreover, they can assist in automat-
enabled the use of treatments specifically targeting genetic mutations within tum
improving effectiveness and minimizing side effects. ML and AI assist in predicting
tient responses to different therapies, optimizing treatment selection, and adjusting p
as cancer progresses or responds to interventions. Research plays a critical role in adva
ing cancer analysis by investigating the biological mechanisms underlying cancer, ide
fying new therapeutic targets, and exploring novel diagnostic methods. With the inte
Electronics 2024, 13, 4697 3 of 40

ing repetitive tasks, freeing up valuable time for healthcare professionals to focus on more
complex aspects of patient care.

1.1. Paper Structure

This paper presents a comprehensive study on the utilization of ML methods for
cancer analysis and is divided into four key sections. The first section provides an in-depth
presentation of various medical imaging techniques, including X-rays, mammography,
ultrasound, CT, PET, MRI, and endoscopy, highlighting their effectiveness in cancer detec-
tion and diagnosis. The next section presents a detailed literature review of lung, breast,
brain, cervical, colorectal, and liver cancers, examining how ML techniques have been
applied to these cancer types to enhance diagnostic and prognostic accuracy. Lastly, the
various challenges and limitations associated with the use of ML in cancer analysis, such as
data quality, model interpretability, and the need for extensive validation before clinical
application, are explored.

1.2. Motivation and Contribution

The survey explores recent advancements in AI and ML for various cancers (lung,
breast, brain, cervical, colorectal, and liver) and aims at updating researchers on new
developments and tackling major challenges in cancer care, such as complexity, the need
for personalized treatments, and the large volume of healthcare data. The paper highlights
how AI and ML can overcome these issues, offering insights into potential solutions and
improvements. It emphasizes improving patient outcomes through successful case studies
and algorithms, and informs healthcare professionals about the benefits of computer-aided
techniques in early detection, accurate diagnosis, personalized treatment planning, and
patient monitoring.
The main contributions of this paper can be summarized as follows:
■ Analyzes and highlights the most important aspects of the aforementioned six
cancer types.
■ Analyzes various ML methods based on benchmark datasets and several performance
evaluation metrics.
■ Identifies the majority of datasets utilized in the reviewed papers.
■ Outlined various research challenges, potential solutions, and opportunities for cancer
analysis and care suggested for future researchers.

1.3. Summary
In the following paragraphs, a concise overview of the six cancer types discussed in
this paper is provided along with the imaging modalities commonly employed for their
detection and diagnosis.
■ Lung cancer originates in the tissues of the lungs, usually in the cells lining the
air passages. It is strongly associated with smoking, but can also occur in non-
smokers due to other risk factors like exposure to secondhand smoke, radon, or
certain chemicals. Lung cancer is one of the leading causes of cancer-related deaths
worldwide, emphasizing the importance of early detection and smoking cessation
efforts. It is detected primarily through chest X-rays, CT scans, and PET scans. CT
scans offer high-resolution images and are particularly useful for detecting small
lung nodules, while PET scans help assess the metabolic activity of suspected tumors,
aiding in staging and treatment planning.
■ Breast cancer develops in the cells of the breasts, most commonly in the ducts or
lobules. It predominantly affects women, but men can also develop it, although it
is much less common. This cancer is often diagnosed using mammography, ultra-
sound, and MRI modalities. Mammography remains the gold standard for screening,
while ultrasound and MRI are utilized for further evaluation of suspicious findings,
particularly in dense breast tissue.
Electronics 2024, 13, 4697 4 of 40

■ Brain cancer refers to tumors that develop within the brain or its surrounding tissues.
These tumors can be benign or malignant. It is diagnosed using imaging modalities
like MRI, CT scans, PET scans, and sometimes biopsy for histological confirmation.
MRI is the preferred imaging modality for evaluating brain tumors due to its superior
soft tissue contrast, allowing for precise localization and characterization of lesions.
■ Cervical cancer starts in the cells lining the cervix, which is the lower part of the
uterus that connects to the vagina. It is primarily caused by certain strains of human
papillomavirus (HPV). Regular screening tests such as Pap smear tests, HPV DNA
tests, colposcopy, and biopsy can help detect cervical cancer early, when it is most
treatable.
■ Colorectal cancer develops in the colon or rectum, typically starting as polyps on
the inner lining of the colon or rectum. These polyps can become cancerous over
time if not removed. Screening tests rely on various imaging modalities, including
colonoscopy, sigmoidoscopy, fecal occult blood tests, and CT colonography (virtual
colonoscopy). Colonoscopy is considered the gold standard for detecting colorectal
polyps and cancers, allowing for both visualization and tissue biopsy during the
procedure.
■ Liver cancer arises from the cells of the liver and can either start within the liver itself
(primary liver cancer) or spread to the liver from other parts of the body (secondary
liver cancer). Chronic liver diseases such as hepatitis B or C infection, cirrhosis, and
excessive alcohol consumption are major risk factors for primary liver cancer. Its
diagnosis relies on imaging modalities such as ultrasound, CT scans, MRI, and PET
scans, along with blood tests for tumor markers such as alpha-fetoprotein (AFP).
These imaging techniques enable the detection of liver lesions, nodules, or masses,
Electronics 2024, 13, x FOR PEER REVIEW
aiding in the diagnosis, staging, and treatment planning for liver cancer patients.
ML algorithms used for cancer detection typically follow a pattern recognition ap-
proach, where the algorithm learns patterns and features from input data to distinguish
indicating
between cancerous the presencecases.
and non-cancerous or absence
Such of cancer. Lastly,
algorithms followpostprocessing steps may be a
a specific framework,
to refine the model predictions or interpret its outputs.
presented in Figure 2. Each step in the framework will be detailed in following sections.

Data
Data Feature Model Model Postproces
Preprocess Prediction
Collection Extraction Training Evaluation sing
ing

Figure 2.for
Figure 2. ML framework ML framework
cancer for cancer analysis.
analysis.

The first step

1.4. involves
Methods collecting a large dataset containing features extracted from
various sources such as medical imaging scans. Next, the collected data undergo prepro-
The studies included in this paper focus on the application of ML techniques
cessing steps to clean, normalize, and standardize them for analysis. This may include
cer analysis, particularly for the diagnosis, classification, and treatment of the si
removing noise, handling missing values, and scaling features to ensure consistency across
frequent cancer types: lung, breast, brain, cervical, colorectal, and liver cancers. S
the dataset. Relevant features are then extracted from the preprocessed data, depending on
were eligible if they involved analyses of medical imaging techniques (X-rays, mam
the type of cancer and the available input data. For medical imaging data, features may
raphy, ultrasound, CT, MRI, PET), various AI/ML methods (e.g., deep learning, t
include texture, shape, intensity, or structural characteristics of tumors. The ML algorithm
learning, ensemble learning), and discussed challenges or limitations of ML in cance
is trained using the labeled dataset, where each instance is associated with a binary label
Studies were grouped based on the cancer type and ML methodology applied. Th
indicating the presence or absence of cancer. The trained model is then evaluated using
acteristics of each study were summarized in a table that focused on the ML mode
separate validation datasets to assess its performance using relevant metrics that will be
and their diagnostic performance.
detailed in the upcoming section. Once the model is trained and validated, it can be used
A comprehensive literature search was conducted on the following database
to predict the likelihood of cancer for new, unseen cases. The input data are fed into the
trained model, of Science,
which PubMed,
outputs and IEEEscore
a probability Xplore.
or aAdditional sources included
binary classification reference
indicating the lists o
tified articles and conference proceedings in the fields of medical imaging and onc
Non-English studies and reviews published before 2020 were excluded. The terms u
in the search process were related to cancer types (“lung cancer,” “breast cancer,
ML methodologies (“deep learning,” “transfer learning,” etc.), medical imaging
niques (“CT,” “MRI,” “ultrasound,” etc.), and key areas of focus (“classification,”
Electronics 2024, 13, 4697 5 of 40

presence or absence of cancer. Lastly, postprocessing steps may be applied to refine the
model predictions or interpret its outputs.

1.4. Methods
The studies included in this paper focus on the application of ML techniques in cancer
analysis, particularly for the diagnosis, classification, and treatment of the six most frequent
cancer types: lung, breast, brain, cervical, colorectal, and liver cancers. Studies were
eligible if they involved analyses of medical imaging techniques (X-rays, mammography,
ultrasound, CT, MRI, PET), various AI/ML methods (e.g., deep learning, transfer learning,
ensemble learning), and discussed challenges or limitations of ML in cancer care. Studies
were grouped based on the cancer type and ML methodology applied. The characteristics
of each study were summarized in a table that focused on the ML models used and their
diagnostic performance.
A comprehensive literature search was conducted on the following databases: Web of
Science, PubMed, and IEEE Xplore. Additional sources included reference lists of identified
articles and conference proceedings in the fields of medical imaging and oncology. Non-
English studies and reviews published before 2020 were excluded. The terms utilized in
the search process were related to cancer types (“lung cancer”, “breast cancer”, etc.), ML
methodologies (“deep learning”, “transfer learning”, etc.), medical imaging techniques
(“CT”, “MRI”, “ultrasound”, etc.), and key areas of focus (“classification”, “segmentation”).
A single reviewer conducted the screening of titles, abstracts, and full-text articles
to identify studies meeting the inclusion criteria. No automation tools were used in the
selection process. The same reviewer performed the data extraction, collecting information
such as study characteristics (e.g., author, year, cancer type, ML model, dataset used) and
outcomes (e.g., accuracy). No formal risk-of-bias assessment was performed.

2. Medical Imaging and Diagnostic Techniques: An Overview of Key Modalities

Medical imaging techniques, together with deep learning (DL) methods, have emerged
as powerful tools in the field of cancer analysis. The intersection of advanced imaging
technologies and AI has led to more accurate, efficient, and early detection of cancer, revo-
lutionizing the way healthcare professionals diagnose and treat the disease. This section
briefly presents some of the key medical imaging techniques, including their underlying
principles, applications, and comparative advantages when used for DL applications in
cancer analysis.

2.1. X-Rays
X-rays are a type of invisible light that can pass through solid objects, including
human tissue. When X-rays are directed at the body, they can create images of the inside
of the body, like bones or organs, by showing how much of the X-rays are absorbed or
passed through different tissues. The resulting image, typically a 2D projection, can have
resolutions as fine as 100 microns, with intensities indicating X-ray absorption levels [4].

2.2. Mammography
Mammography is a specialized medical imaging technique used primarily for breast
cancer screening and diagnosis [5]. It involves taking low-dose X-ray images [6] of the
breast tissue to detect abnormalities such as tumors, cysts, or calcifications. These images,
called mammograms, can help physicians detect early signs of breast cancer [6], such as
abnormal lumps or masses, before they can be felt.

2.3. Ultrasound
Ultrasound (US) is a non-invasive and safe imaging method with extensive availability
and patient comfort [7] that uses high-frequency sound waves. These waves reflect back
when they hit tissues, and the returning echoes are captured to create real-time images
of internal structures. The non-ionizing nature of US makes it safer for patients, as the
Electronics 2024, 13, 4697 6 of 40

absence of radiation reduces health risks and enhances patient comfort during diagnostic
procedures. However, it fails to provide comprehensive images of organs or specific
areas under examination, as its penetration capability into deeper tissues is reduced. This
limitation results in incomplete images, impacting the overall visualization quality of
organs, which may hinder the diagnostic accuracy and thorough assessment of certain
medical conditions.

2.4. Computed Tomography

Computed tomography (CT) stands out as a fast and readily available imaging method.
A CT scan is a diagnostic tool that employs X-ray images taken from various angles around
the body, utilizing computer processing to generate detailed cross-sectional images (slices)
of bones, blood vessels, and soft tissues. CT scan images provide superior information
compared to plain X-rays, enabling a comprehensive assessment of various anatomical
structures. This imaging technique allows for the identification of abnormalities in bones,
blood vessels, and soft tissues, facilitating a thorough examination [8].

2.5. Positron Emission Tomography

Positron-emission tomography (PET) has transitioned from a primarily research-
focused tool to an indispensable imaging modality for evaluating cancer. It uses a ra-
dioactive tracer to emit gamma rays, which are detected to create detailed images of the
body’s metabolic processes. While PET offers high sensitivity for malignancy detection, its
practical use as a standalone imaging modality is often limited, as it provides imprecise
anatomical localization due to limited spatial resolution [9]. The advent of integrated
PET–CT, a combination of PET and CT in a single device, has addressed this limitation.
This approach allows for the merging of PET and CT datasets acquired during a single
examination, providing both morphological and metabolic information and enhancing the
accuracy and reliability of cancer staging.

2.6. Magnetic Resonance Imaging

Magnetic resonance imaging (MRI) is a precise and accurate method for tumor diag-
nosis, leveraging high contrasts among soft tissues in the obtained images. Although this
characteristic makes it particularly effective in identifying and characterizing tumors, the
diagnostic accuracy of MRI can be influenced by both patient- and operator-related factors.
Patient-related considerations, such as claustrophobia, implanted materials, or devices,
and uncomfortable situations, may pose limitations on the application of MRI and impact
the quality of the results [10]. In contrast to CT, MRI operates without ionizing radiation,
relying on magnetic stimulation of hydrogen atoms to create detailed images of targeted
tissues. MRI uses powerful magnetic fields and radio waves to produce precise images of
the internal structures within the body and relies on the behavior of hydrogen atoms in the
body’s tissues when exposed to these magnetic fields.

2.7. Endoscopic Biopsy

Endoscopic biopsy is a procedure commonly used to obtain tissue samples from the
gastrointestinal tract [11] and respiratory system [12] and involves using an endoscope,
which is a long, flexible tube with a camera and light at its tip, to visualize the inside of
these organs and guide the biopsy procedure. Endoscopic biopsy may be performed in
various areas of the body, as presented below.

2.7.1. Colonoscopy
Colonoscopy [11,13] is a medical procedure used to examine the inside of the colon
and rectum. During the procedure, if any suspicious growths or polyps are found, they can
be removed or biopsied for further examination. Colonoscopy, with or without removal of a
lesion, is an invasive procedure and can carry some risks, such as bleeding and perforation,
although these are considered to be low.
Electronics 2024, 13, 4697 7 of 40

2.7.2. Bronchoscopy
Bronchoscopy [12,14] is a medical procedure used to examine the inside of the airways
and lungs. If a suspicious mass or lesion is found during the procedure, a biopsy can be
taken for further examination under a microscope. The risks associated with bronchoscopy
are generally considered to be low, and include bleeding, infection, and pneumothorax.

3. Machine Learning Framework

In cancer analysis, building effective ML models is crucial for accurate diagnosis,
prognosis, and treatment planning. This section outlines the essential workflow stages
previously presented in Figure 2: gathering data, preprocessing it for quality, extracting
relevant features, training and evaluating the model, and finally, making predictions
and refining outputs. Each stage plays a vital role in creating models that are accurate
and robust.

3.1. Data Collection

In cancer analysis, data collection involves gathering various types of medical data,
including imaging data (such as MRI, CT, or histopathology images), clinical records,
genetic information, and biomarker levels. High-quality, annotated datasets are crucial,
especially for tasks such as tumor classification and segmentation. Data may come from
hospital databases, clinical trials, or publicly available medical repositories. It is important
to collect diverse data across different patient demographics and cancer types to build a
robust and generalizable model [15].

3.2. Data Preprocessing

Medical data, particularly images, require extensive preprocessing to handle noise,
artifacts, and varying imaging conditions. Preprocessing steps include normalization (e.g.,
adjusting intensity values in images), resizing to a consistent scale, removing artifacts
(e.g., motion blur in MRIs) using filters, and enhancing the contrast. For segmentation
tasks, creating accurate masks that outline the tumor is vital for model training. Data
augmentation techniques, such as rotation, flipping, or contrast adjustment, can help to
increase the dataset’s variability and improve model robustness. Handling missing or
inconsistent clinical data, such as incomplete patient records, is also part of this stage [16].

3.3. Feature Extraction

In cancer analysis, feature extraction often involves identifying key characteristics from
imaging data, such as tumor size, shape, texture, and intensity patterns. Advanced methods
like radiomics can quantify these features to capture the heterogeneity within a tumor. For
segmentation tasks, features may include pixel intensity gradients or edge detection to
outline tumor boundaries accurately. In classification, features might encompass not only
image characteristics but also clinical data like patient age, genetic markers, and lab results.

3.4. Model Training

Model training in cancer analysis involves using annotated datasets (e.g., labeled
images indicating tumor presence or delineated tumor regions) to teach the model to
recognize cancerous patterns. For classification, algorithms like CNNs, SVMs, or ensemble
methods are commonly used to differentiate between benign and malignant cases. For
segmentation, more specialized architectures like U-Net are employed to accurately identify
and delineate tumor regions.
Table 1 summarizes some of the most common algorithms utilized for model training
in cancer analysis [17].
Electronics 2024, 13, 4697 8 of 40

Table 1. Overview of the key model training algorithms.

Algorithm Description Strengths Weaknesses Applications

■ Effective for
smaller datasets. ■ Computationally
■ Performs well in expensive for ■ Binary (e.g., benign vs.
Finds the hyperplane that high-dimensional spaces. large datasets. malignant) or
SVM [18] best separates the data ■ Works well for binary ■ Less effective with multi-class
points of different classes. classification. complex image patterns or classification.
■ Can handle linear and overlapping features. ■ Regression.
non-linear classification ■ Difficult to interpret.
using kernel tricks.
■ Easy to implement. ■ Binary (e.g., benign vs.
■ Handles noise reasonably malignant) or
■ High computational cost
Classifies data based on well when imaging multi-class
for large datasets.
the majority class of the features are carefully classification.
k-NN [18] ■ Sensitive to irrelevant
k-nearest neighbors in the preprocessed. ■ Used in preliminary
features and data scaling.
dataset. ■ Intuitive and analysis or
interpretable. quick tumor
identification.
■ Binary or multi-class
■ Easy to interpret. ■ Prone to overfitting. classification.
A tree-like model of ■ Works well for small ■ Sensitive to noise, ■ Regression.
Decision Tree [18] decisions and their datasets. especially with ■ Can assist in feature
possible consequences. ■ Handles both categorical high-dimensional importance
and numerical data. imaging data. identification in
tumor images.
■ Reduces overfitting.
■ Binary or multi-class
■ Handles large ■ Resource-intensive and
An EL method that builds classification.
datasets well. slower for very
Random multiple decision trees ■ Regression.
■ Can detect multiple high-resolution imaging.
Forest [18] and combines them for a ■ Helpful in feature
feature types (e.g., color, ■ Difficult to interpret
more accurate prediction. selection for detailed
shape, texture) across a individual feature impact.
tumor analysis.
large image dataset.
■ Faster training than ■ Slower and more
random forest. resource-intensive for
Similar to random forest,
■ Less prone to overfitting large datasets. ■ Binary or multi-class
but selects splits at
due to the use of ■ Prone to overfitting if classification.
random rather than
Extra Trees [18] random splits. hyperparameters are not ■ Regression.
calculating the best
■ Capable of extracting well-tuned. ■ Tissue differentiation,
possible split, leading to
important diagnostic ■ Less interpretable in terms cell segmentation.
faster training times.
features even from of specific imaging
noisy data. feature impact.
■ Simple and easy to
implement. ■ Can underperform with
■ Outputs probabilities, complex data without
Estimates the probability ■ Binary classification
Logistic making predictions feature engineering.
that a given input belongs (e.g., benign vs.
Regression [18] interpretable. ■ Limited to linearly
to a particular class. malignant).
■ Provides insight into separable data, which may
which features contribute be insufficient for complex
most to cancer presence. cancer imaging tasks.
■ Reduces bias and variance ■ Slow to train and
in cancer imaging models. computationally intensive. ■ Binary or multi-class
An EL method that builds
■ Flexible with ■ Prone to overfitting classification.
models sequentially,
hyperparameter tuning to without proper ■ Regression.
GBM [19] minimizing the loss at
fine-tune for complex regularization. ■ Useful for difficult
each stage to improve
image data. ■ Sensitive to noisy data image differentiation.
accuracy.
■ Handles non-linear common in medical
relationships well. imaging.
■ Highly efficient. ■ Binary or multi-class
■ Performs well on large ■ Complex and sensitive to classification.
A fast and efficient hyperparameter tuning.
datasets. ■ Regression.
implementation of GBM Requires substantial
XGBoost [19] ■ High performance in ■ ■ Tumor growth
designed for computational resources
feature extraction for prediction, feature
large-scale datasets. for large-scale cancer
complex patterns (e.g., importance in tumor
texture, edges). imaging data. identification.
Electronics 2024, 13, 4697 9 of 40

Table 1. Cont.

Algorithm Description Strengths Weaknesses Applications

An ensemble method that ■ Reduces overfitting. ■ Less effective on small, ■ Binary or multi-class
trains multiple models on ■ Works well with noisy and balanced datasets with classification.
different subsets of the high-variance data in low variance. ■ Regression.
Bagging [18] imaging contexts.
data and combines their ■ May not provide ■ Helpful for enhancing
predictions to reduce ■ Simple and effective. substantial improvements stability in difficult
variance. on simpler imaging tasks. image sets.
A boosting algorithm that ■ Effective with weak
■ Sensitive to noisy data in ■ Binary or multi-class
combines weak learners learners.
imaging, which may result classification.
into a strong learner by ■ Can focus on ambiguous
AdaBoost [18] in misclassification of ■ Suitable for refining
adjusting weights to focus areas of cancer images
high-variance or complex edges or boundaries
on harder-to-classify where differentiation is
regions. in segmentation.
examples. challenging.
■ Fast and simple to ■ Assumes independence
implement. between features.
■ Works well with ■ The assumption of feature
A probabilistic classifier Binary classification
high-dimensional data. independence may not ■
Gaussian Naïve that assumes features are for rapid, preliminary
■ Performs well on small hold true in imaging,
Bayes [18] normally distributed and image screening tasks.
datasets. leading to inaccurate
independent of each other.
■ Works well for preliminary results.
screening applications or ■ Prone to bias if
low-variance feature data. assumptions don’t hold.
■ Learns hierarchical
■ Requires large annotated
features automatically.
datasets for training. Binary or multi-class
■ Handles complex ■
■ Computationally classification.
image data.
A DL algorithm primarily intensive, particularly Segmentation (e.g.,
■ Excellent for identifying ■
CNN [20] used for image with high-resolution organs, tumors).
complex spatial
recognition. medical images. Object detection (e.g.,
relationships in tumor ■
■ Black-box model, harder organs, tumors).
structure.
to interpret.
■ Widely used in medical
imaging analysis.
■ Strong performance in ■ Memory-intensive and
A CNN architecture with identifying fine-grained computationally ■ Binary or multi-class
16 layers known for using cancer features. expensive. classification.
VGG-16 [21]
small convolutional filters ■ Simple yet effective deep ■ Limited interpretability in ■ Object detection (e.g.,
(3 × 3) and deep layers. structure. context of specific image organs, tumors).
■ Performs well with TL. features.
■ Ideal for precise medical ■ Tumor boundary
■ High computational cost.
A type of CNN tailored image segmentation. segmentation.
■ Sensitive to tuning.
for biomedical image ■ Handles small datasets ■ Highly effective for
■ Performance depends on
U-Net [22] segmentation that uses an well with data delineating cancerous
high-quality annotations,
encoder–decoder augmentation. tissues from
which can be challenging
structure. ■ Widely used in cancer surrounding
in cancer imaging.
imaging. structures.
■ Solves vanishing gradient ■ Computationally
A DNN that introduces problem. expensive. ■ Binary or multi-class
“residual connections” to ■ Ideal for training on very ■ Requires significant classification.
solve the vanishing deep networks with memory and processing ■ Segmentation in
ResNet [23]
gradient problem, high-dimensional cancer power for large image complex cancer
allowing the training of imaging data. datasets. imaging.
much deeper networks. ■ Retains high accuracy ■ More complex to train and ■ Object detection.
without overfitting. tune.

3.5. Model Evaluation

In medical applications, false negatives (missing a cancerous region) can have serious
implications, so the evaluation must be thorough to ensure reliable clinical performance.
The evaluation metrics for the performance of an ML algorithm can be categorized based
on the task at hand, whether it is classification or segmentation. The following subsections
will delve into the specifics of each.
 Electronics 2024, 13, x FOR PEER REVIEW 11 of 42
Electronics 2024, 13, 4697 10 of 40

3.5.1. Classification
3.5.1. Classification
In ML classification tasks, several performance metrics are used to evaluate the effec-
In ML classification tasks, several performance metrics are used to evaluate the effec-
tiveness of a classifier, typically derived from a confusion matrix [24], which is a means to
tiveness of a classifier, typically derived from a confusion matrix [24], which is a means
evaluate the performance of a classification model by presenting a summary of the
to evaluate the performance of a classification model by presenting a summary of the
model’s predictions compared to the actual labels in a tabular format, as presented in Fig-
model’s predictions compared to the actual labels in a tabular format, as presented in
ure 3, where:
Figure 3, where:
■
 TrueTrue Positives (TP): Instances that are correctly predicted as belonging to the positive
Positives (TP): Instances that are correctly predicted as belonging to the
class. class.
positive
■
 False
False Positives
Positives (FP):
(FP): Instances
Instances that
that are
areincorrectly
incorrectlypredicted
predictedasasbelonging
belongingtotothe
theposi-
pos-
itive class when they actually belong to the negative
tive class when they actually belong to the negative class. class.
■
 True Negatives
True Negatives (TN):
(TN):Instances
Instancesthat
thatareare
correctly predicted
correctly as belonging
predicted to thetonega-
as belonging the
tive class.
negative class.
■
 False
False Negatives
Negatives (FN):
(FN):Instances
Instancesthat
thatare incorrectly
are predicted
incorrectly as belonging
predicted to the
as belonging to neg-
the
ative class when they actually belong to the positive class.
negative class when they actually belong to the positive class.

Figure3.3.Confusion
Figure Confusionmatrix
matrixstructure.
structure.

The
Themost
mostwidely
widelyused
usedperformance
performance metrics
metrics for
for classification
classification problems
problems are
are accuracy,
accuracy,
precision,
precision,recall,
recall,specificity,
specificity,sensitivity, F1 F1
sensitivity, score, PR curve,
score, AUC-PR
PR curve, curve,
AUC-PR ROCROC
curve, curve,curve,
and
AUC-ROC
and AUC-ROCcurve,curve,
whichwhich
are described belowbelow
are described [24,25].
[24,25].
■ Accuracy measures
Accuracy measures thethe proportion
proportion ofof correctly
correctly classified
classified instances
instances out
out of
of the
thetotal
total
instances
instances and
and is
is calculated
calculatedas as the
the number
numberof of true
truepositives
positivesand
andtrue
truenegatives
negativesdivided
divided
by
by the
the total
total number
number of of instances:
instances:
TP 𝑇𝑃 + 𝑇𝑁
+ TN
𝐴𝑐𝑐𝑢𝑟𝑎𝑐𝑦
Accuracy = =
TP 𝑇𝑃 + 𝑇𝑁
+ TN + 𝐹𝑁
+ FN ++FP𝐹𝑃
■ Precision measures
Precision measures thethe proportion
proportion of of true
true positive
positive predictions
predictions among
among all
allpositive
positive
predictions made
predictions made byby the
the classifier
classifier and
and isis calculated
calculated as
asthe
thenumber
numberofoftrue
truepositives
positives
divided by
divided by the
the total
total number
number of of instances
instances predicted
predictedasaspositive:
positive:
𝑇𝑃
𝑃𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛 = TP
Precision = 𝑇𝑃 + 𝐹𝑃
TP + FP
 Recall or sensitivity measures the proportion of true positives that are correctly iden-
■ Recall or the
tified by sensitivity measures
classifier the proportion
and is calculated as theofnumber
true positives that are correctly
of true positives dividedidenti-
by the
fied by the classifier and is calculated
total number of actual positive instances: as the number of true positives divided by the
total number of actual positive instances:
𝑇𝑃
𝑅𝑒𝑐𝑎𝑙𝑙 (𝑆𝑒𝑛𝑠𝑖𝑡𝑖𝑣𝑖𝑡𝑦) =
𝑇𝑃
TP + 𝐹𝑁
Recall (Sensitivity) =
 Specificity measures the proportion of true negatives TP + FNthat are correctly identified by
■
the classifier
Specificity and is calculated
measures as theofnumber
the proportion of true that
true negatives negatives dividedidentified
are correctly by the total
by
number of actual negative instances:
the classifier and is calculated as the number of true negatives divided by the total
number of actual negative instances:
Electronics 2024, 13, 4697 11 of 40

TN
Speci f icity =
TN + FP
■ F1 score is the harmonic mean of precision and recall, providing a balance between
the two metrics and is calculated as the harmonic mean of precision and recall:

2 × Precision × Recall
F1-score =
Precision + Recall
■ Precision–recall (PR) curves plot the precision against the recall for different threshold
values used by the classifier to make predictions. Each point on the curve corresponds
to a different threshold setting used by the classifier, where a higher threshold leads
to higher precision but lower recall, and vice versa.
■ Area under the PR (AUC-PR) curves summarize the performance of the classifier
across all possible threshold values, with a higher AUC-PR indicating better overall
performance in terms of both precision and recall.
■ Receiver operating characteristic (ROC) curves plot the recall against the false-positive
rate (FPR, which measures the proportion of false-positive predictions among all
actual negative instances) for various threshold values used by the classifier to make
predictions. Each point on the curve corresponds to a different threshold setting used
by the classifier, where a higher threshold leads to higher specificity but lower recall,
and vice versa.
■ Area under the ROC curve (AUC-ROC or simply AUC) summarizes the performance
of the classifier across all possible threshold values, with a higher AUC indicating
better overall performance in terms of both recall and specificity.

3.5.2. Segmentation
In ML segmentation tasks, key metrics include the following [25–27].
■ Intersection over union (IOU) measures the overlap between the predicted and
ground-truth masks by calculating the ratio of the intersection to the union of the
two masks:

|A B|
T
TP
IoU = or IoU = S , where :
TP + FP + FN |A B|
A = the predicted segmentation mask
B = the ground − truth mask
\
A B = the number o f overlapping pixels
[
A B = the total number o f unique pixels in both masks

■ Dice similarity coefficient (DSC) measures the spatial overlap between the predicted
segmentation mask and the ground-truth mask and is calculated as twice the intersec-
tion of the predicted and ground-truth masks divided by the sum of their volumes:

2 × TP 2 × IoU
Dice = = or :
2 × TP + FP + FN 1 + IoU
2 × | A B|
T
Dice = , where
| A| + | B|
A = the predicted segmentation mask
B = the ground − truth mask
\
A B = the number of over lapping pixels
Electronics 2024, 13, 4697 12 of 40

| A| = the total number of pixels in the predicted mask

| B| = the total number of pixels in the ground − truth mask
■ Mean intersection over union (mIoU) measures the average IoU across all classes or
segments in the image:

1 N
N ∑ i =1
mIoU = IoU i , where :

N = the number of classes

IoUi = the IoU for each class i
■ Pixel accuracy measures the proportion of correctly classified pixels in the segmenta-
tion mask and is calculated as the number of pixels correctly classified divided by the
total number of pixels in the image:

Number o f correctly classi f ied pixels

Pixel Accuracy =
Total number o f pixels
■ Mean average precision (mAP) summarizes the precision–recall (PR) curve across
multiple classes or categories and is calculated in three steps:
1. For each class or category in the dataset, the PR curve is computed based on the
model’s predictions and ground-truth annotations.
2. The AUC-AP curve is computed for each class.
3. The mAP is calculated by taking the mean of the average precision values across
all classes in the dataset.
1 N
N ∑ i =1
mAP = APi , where :

C = the total number of classes in the dataset

APi = the average precision for class i
■ Hausdorff distance (HD) measures the similarity between two sets of points in a
metric space. It quantifies the maximum distance from a point in one set to the closest
point in the other set, and vice versa.
The directed Hausdorff distance from set A to set B is defined as:

h( A, B) = max a∈ A minb∈ B d( a, b), where :

d(a, b) = the distance between points a and b (where a ∈ A and b ∈ B)

Similarly, the directed Hausdorff distance from set B to set A is defined as:

h( B, A) = max b∈ B min a∈ A d(b, a)

The Hausdorff distance between sets A and B is therefore defined as the maximum of
the directed Hausdorff distances:

H ( A, B) = max (h( A, b), h( B, A))

3.6. Prediction
Once trained and evaluated, the model is deployed to predict cancer presence or
segment tumors in new, unseen patient data. The same algorithms used for model training
are employed to take in new input data, apply the patterns and parameters learned during
training, and output predictions. In general, for classification, the model outputs a proba-
bility score indicating the likelihood of cancer, which can aid in early diagnosis, while for
Electronics 2024, 13, 4697 13 of 40

segmentation tasks, the model provides a pixel-wise mask outlining the tumor boundaries,
assisting radiologists and oncologists in treatment planning.

3.7. Postprocessing
Postprocessing is essential to refine the model’s output into clinically actionable
insights. In segmentation, postprocessing might involve smoothing tumor boundaries,
removing noise, or filling gaps in the predicted mask to improve visual clarity. For classifica-
tion, probability scores might be converted into binary labels (cancerous or non-cancerous)
based on a decision threshold. Additionally, postprocessing can include combining pre-
dictions with other clinical data, generating reports, or highlighting regions of interest on
images for further review by medical experts.
A critical aspect of postprocessing in cancer analysis is model interpretability. After an
ML model has made its predictions, interpretability techniques can be applied to explain the
reasoning behind those predictions. These interpretability methods provide crucial insights,
especially in medical applications, where understanding how and why the model arrived
at a specific decision is essential for gaining clinical trust and ensuring the transparency of
the model. Commonly used interpretability methods include:
■ Shapley additive explanation (SHAP) [28] values explain individual predictions by
attributing the contribution of each feature (e.g., patient characteristics or image pixels)
to the final outcome. SHAP helps clinicians understand which variables had the most
significant influence on the prediction.
■ Local interpretable model-agnostic explanations (LIME) [29] approximate complex
models by perturbing input data slightly and analyzing the effect on predictions. It
provides local explanations for individual instances, making it particularly useful in
understanding predictions made by complex, black-box models.
■ Gradient-weighted class activation mapping (Grad-CAM) [30] generates visual expla-
nations of model decisions by highlighting the regions of an image that were most
influential in the model’s decision-making process. This is particularly important in
cancer imaging, where clinicians need to verify that the model is focusing on relevant
areas when diagnosing or classifying cancer.
■ Score-weighted class activation mapping (Score-CAM) [31] provides visual expla-
nations for the decisions made by CNNs, particularly in image classification and
object detection tasks. It extends the concept of Grad-CAM by using the activation
maps directly from the network to generate class-specific attention maps, but without
relying on the gradients.

4. Literature Review
This section provides an in-depth analysis of existing research and developments in the
field of ML-based cancer analysis, with a specific focus on the most prevalent and deadly
six types of cancer: lung, breast, brain, cervical, colorectal, and liver cancers. These specific
types of cancer are associated with high mortality rates and are frequently diagnosed at
advanced stages. Recent research has demonstrated that early detection plays a crucial role
in reducing mortality rates and improving patient survival rates. A notable trend observed
in recent years is the extensive research efforts dedicated to the detection and diagnosis of
these cancers utilizing ML-based techniques. This section aims to review the current state
of the art, methodologies, and advancements in utilizing ML techniques for the diagnosis,
prognosis, and treatment of these selected cancers. By examining a wide range of studies
and approaches within these specific cancer types, this review offers insights into the
various ML algorithms, data sources, and evaluation methods used in cancer analysis.

4.1. Lung Cancer

Lung cancer accounts for approximately 14% of the annual new cancer cases in the
United States, surpassing the combined deaths caused by breast, prostate, and colon can-
cers [32]. Early-stage lung cancer typically lacks symptoms, leading to late-stage diagnoses.
Electronics 2024, 13, 4697 14 of 40

The 5-year survival rate for locally detected lung cancers is 55%, but most patients receive
diagnoses at advanced stages, resulting in significantly lower survival rates (overall 5-year
survival rate of 18%) [33]. The utilization of ML has the potential to revolutionize the
early detection of lung cancer, leading to enhanced accuracy in results and more targeted
treatment approaches, which could substantially increase patient survival rates.
Jassim et al. [34] present a transfer DL ensemble model for predicting lung cancer
using CT images. The Chest CT-Scan images dataset [35] comprises 1000 CT images
across four classes relevant to lung cancer. The classes include adenocarcinoma, large
cell carcinoma, squamous cell carcinoma, and normal tissue. The model leverages the
capabilities of three ImageNet dataset pre-trained DL architectures, namely, EfficientNetB3,
ResNet50, and ResNet101, with TL and applied data augmentation techniques for training.
These models are further trained on the lung cancer dataset to fine-tune the weights for
specific features relevant to lung cancer classification. Each model configuration includes
modifications specific to lung cancer imaging, such as adjustments in layer depths and
learning rates. EfficientNetB3 emerged as the top-performing model, displaying the most
effective convergence with average precision of 94%, recall of 93%, and F1 score of 93%. In
comparison, the ResNet50 model achieved precision, recall, and F1 score values of 88%,
81%, and 81%, respectively, while the ResNet101 model achieved values of 94%, 93%, and
93%, respectively. The maximum accuracy achieved by the models presented in this paper
is 99.44%.
Muhtasim et al. [36] propose a multi-classification approach for detecting lung nodules
using AI on CT scan images from the IQ-OTHNCCD lung cancer dataset [37], consisting
of 1190 CT scan images classified into normal, benign, and malignant. It employs TL
with the VGG16 model and morphological segmentation to enhance the accuracy and
computational efficiency of lung cancer detection. Morphological operations are applied to
segment the region of interest and extract distinct morphological features. The classification
task implements a DL architecture combined with seven different ML algorithms, namely,
decision tree, k-NN, random forest, extra trees, extreme gradient boosting, SVM, and logistic
regression, to classify lung nodules into malignant, benign, and normal categories. The
proposed stacked ensemble model combines the CNN with the VGG16 TL model to achieve
accuracy, precision, recall, and F1 score of 99.55%, 0.996, 0.995, and 0.995, respectively.
Luo [38] introduces the LLC-QE model, an innovative approach combining EL and
reinforcement learning to improve lung cancer classification. The model classifies lung
cancer into four classes: adenocarcinoma, squamous cell carcinoma, large-cell carcinoma,
and small-cell carcinoma. The study utilizes the LIDC-IDRI dataset [39] comprising 1018 CT
scans, primarily composed of non-cancer cases, to train and validate the model. To address
dataset imbalances, the training employs strategies that involve differential reward systems
in reinforcement learning, focusing on underrepresented classes to improve model sensitiv-
ity to less frequent cases. The artificial bee colony algorithm is used during pre-training
to enhance the initialization of network weights, and a series of CNNs act as feature ex-
tractors. The reinforcement learning mechanism views image classification as a series of
decisions made by the network within a Markov decision process framework and adopts
a nuanced reward system where correct classifications of minority classes receive higher
rewards compared to majority classes, encouraging the model to pay more attention to the
harder-to-detect instances. The features extracted by individual CNNs are then merged
to harness the collective power of multiple models, resulting in an average classification
accuracy of 92.9%.
Mamun et al. [40] assess the effectiveness of various EL techniques in binary classifying
lung cancer using the Lung Cancer dataset [41] from Kaggle, containing 309 instances with
16 attributes. These attributes included various symptoms and patient characteristics, such
as age, smoking status, chronic disease, alcohol consumption, coughing, shortness of breath,
and chest pain. The ensemble methods applied include XGBoost, LightGBM, Bagging, and
AdaBoost. The data underwent preprocessing to handle missing values and balance the
dataset using the synthetic minority over-sampling technique (SMOTE). The models were
Electronics 2024, 13, 4697 15 of 40

evaluated based on accuracy, precision, recall, F1 score, and AUC. XGBoost performed the
best among the tested models, achieving accuracy of 94.42%, precision of 95.66%, and AUC
of 98.14%, highlighting its capability in handling imbalanced and complex datasets. The
LightGBM, AdaBoost, and Bagging methods achieved accuracy values of 92.55%, 90.70%,
and 89.76%, respectively.
Venkatesh and Raamesh [42] examine the application of EL techniques for predicting
lung cancer survivability through binary classification methods using the Surveillance,
Epidemiology, and End Results (SEER) dataset [43]. The study evaluates the effectiveness of
bagging and AdaBoost ensemble methods combined with k-NN, decision tree, and neural
network classifiers. The dataset consists of 1000 samples with 149 attributes initially, which
was reduced to 24 attributes after preprocessing, including smoking, gender, air pollution,
chronic lung disease, chest pain, wheezing, dry cough, snoring, and swallowing difficulty.
The previously mentioned ensemble techniques are used to improve the predictive per-
formance by reducing variance (bagging) and bias (AdaBoost), as well as improving the
accuracy of weak classifiers. The outputs from the different models are combined using a
systematic voting mechanism to finalize the survival prediction. The results indicate that
both bagging and AdaBoost techniques improve the performance of individual models.
Specifically, the accuracy scores for decision trees with bagging and AdaBoost were 0.973
and 0.982, respectively, for k-NN, bagging and AdaBoost achieved scores of 0.932 and 0.951,
and for neural networks, bagging and AdaBoost attained scores of 0.912 and 0.931. The
integrated model achieved an accuracy score of 0.983, surpassing the scores of individual
algorithms both with and without ensemble methods.
Said et al. [44] present a system for lung cancer diagnosis using segmentation and
binary classification techniques based on DL architectures, specifically utilizing UNETR for
segmentation and a self-supervised network for classification. The Decathlon dataset [45],
consisting of 96 3D CT scan volumes, is utilized for training and testing. The segmentation
part employs the UNETR neural network, a combination of U-Net and transformers, to
achieve an DSC of 96.42%. The classification part uses a self-supervised neural network
to classify segmented nodules as either benign or malignant, achieving a classification
accuracy of 98.77%.
Table 2 provides an overview of lung cancer studies, including model name, dataset
details, and preprocessing methods. No interpretability methods were presented in of any
these papers.

Table 2. Summary of Lung Cancer studies.

Dataset
Author Model Data Type Preprocessing
Size Classes
Normal
Conversion to RGB
Jassim Transfer DL Adenocarcinoma
CT 1000 Resizing
et al. [34] Ensemble Large cell
Data augmentation
Squamous cell
Resizing
Ensemble Normal Normalization
Muhtasim
CNN + VGG16 CT 1190 Benign Smoothing
et al. [36]
TL Malignant Enhancement
Morphological segmentation
Non-nodule > or =3 mm
Luo [38] LLC-QE CT 1018 Nodule > or =3 mm -
Nodule < 3 mm
Electronics 2024, 13, 4697 16 of 40

Table 2. Cont.

Dataset
Author Model Data Type Preprocessing
Size Classes
Feature extraction
XGBoost Data cleaning
Mamun LightGBM Normal Missing value handling
16 attributes 309
et al. [40] AdaBoost Cancer Categorical variables
Bagging transformation
SMOTE
Bagging
Venkatesh & Normal Interpolation
AdaBoost 24 attributes 1000
Raamesh [42] Cancer Normalization
Integrated
Benign
Said et al. [44] UNETR CT 96 Segmentation
Malignant

4.2. Breast Cancer

Breast cancer is a common type of cancer among women, accounting for approx-
imately 30% of all annual new cancer cases among women [46]. Globally, there were
2.3 million women (11.6% of the total new cases of cancer) diagnosed with breast cancer
and 670,000 deaths (6.9% of the total cancer deaths) attributed to the disease in 2022 [47].
Early detection through screening mammography can decrease breast cancer mortality
by up to 20% [48]. Breast US faces challenges due to image complexity, including noise,
artifacts, and low contrast. Manual analysis by sonographers is time-consuming, subjective,
and can result in unintended misdiagnoses due to fatigue. Therefore, the integration of
computer-aided detection or AI is crucial for enhancing the accuracy of screening breast US,
reducing both false positives and false negatives, and minimizing unnecessary biopsies [49].
Interlenghi et al. [50] developed a radiomics-based ML binary classification model
that predicts the BI-RADS category of suspicious breast lesions detected through US with
an accuracy of approximately 92%. A dataset of 821 images, comprising 834 suspicious
breast masses from 819 patients, was collected retrospectively from US-guided core needle
biopsies performed by four certified breast radiologists using six different US systems.
The dataset consists of 404 malignant and 430 benign lesions based on histopathology.
A balanced image set of biopsy-proven benign and malignant lesions (299 each) is used
to train and cross-validate ensembles of ML algorithms supervised by histopathological
diagnosis. An ensemble of SVMs, using a majority vote, demonstrated the ability to reduce
the biopsy rate of benign lesions by 15% to 18% while maintaining a sensitivity of over
94% in external testing. This model was tested on two additional image sets, resulting in
positive predictive values (PPV) of 45.9% and 50.5% and sensitivity of 98.0% and 94.4%,
respectively, outperforming the radiologists’ PPVs. The model achieved low error rates in
assigning BI-RADS categories, and the radiologists accepted the model’s classifications for
most masses, indicating instances where the model performed better than the radiologists
by assigning a more accurate BI-RADS classification.
Kavitha et al. [51] propose a novel optimal multi-level thresholding-based segmenta-
tion with DL-enabled capsule network (OMLTS-DLCN) model for breast cancer diagnosis
and multi-class classification. The model incorporates an adaptive fuzzy-based median
filtering procedure to eliminate noise. The segmentation technique employed is the optimal
Kapur’s multilevel thresholding with shell game optimization (OKMT-SGO) algorithm,
which effectively detects the diseased portion in mammogram images. Feature extraction
is performed using the CapsNet model, and the final classification is achieved using the
backpropagation neural network (BPNN) model, determining appropriate class labels.
The performance evaluation on the Mini-MIAS [52] (322 images) and CBIS-DDSM [53]
(13,128 images) datasets, containing normal, benign, and malignant classes, demonstrates
Electronics 2024, 13, 4697 17 of 40

that the presented OMLTS-DLCN model outperforms other methods in terms of classifica-
tion accuracy, with an accuracy of 98.50% and 97.56%, respectively.
Chen et al. [54] introduce a novel approach called DSEU-Net (squeeze-and-excitation
(SE) attention U-Net with deep supervision) for the segmentation of medical US images. The
proposed method combines several key elements to enhance the accuracy and robustness of
the segmentation process. Firstly, a deeper U-Net architecture is employed as a benchmark
network to effectively capture the intricate features present in complex US images. Next,
the SE block is integrated as a bridge between the encoder and decoder, allowing for
enhanced attention on relevant object regions. The SE block not only strengthens the
connections between distant but useful information but also suppresses the introduction
of irrelevant information, improving the overall segmentation quality. Furthermore, deep
supervised constraints are incorporated into the decoding stage of the network to refine
the prediction masks of US images, which further improves the accuracy and reliability
of the segmentation results. The performance of DSEU-Net in US image segmentation
was evaluated using extensive experiments on two clinical US breast datasets. Specifically,
when applied to the first dataset (BUSI [55]), DSEU-Net achieved IOU, precision, recall,
specificity, DSC, and accuracy values of 70.36%, 79.73%, 82.70%, 97.42%, 78.51%, and 95.81%,
respectively. Similarly, for the second dataset, the method achieved Jaccard coefficient,
precision, recall, specificity, and DSC values of 73.17%, 82.58%, 84.02%, 99.05%, and 81.50%,
respectively. These results demonstrate the significant improvement of DSEU-Net over
the original U-Net, with an average increase of 8.28% and 12.55% on the five-evaluation
metrics for the two breast US datasets.
Dogiwal’s paper [56] investigates the effectiveness of supervised ML techniques in
predicting breast cancer using histopathological data. The dataset used in this study
was sourced from the UCI Machine Learning Repository, specifically the Breast Cancer
Wisconsin (Diagnostic) dataset [57], which consists of 699 samples with 458 benign (65.5%)
and 241 malignant (34.5%) instances with 32 attributes. This study utilizes PCA to reduce
the number of dimensions while preserving the most significant information. The approach
also involves feature engineering to enhance model performance by selecting the most
relevant features. The study focuses on the application of three prominent algorithms,
namely, random forest, logistic regression, and SVM, for breast cancer binary classification.
The random forest algorithm achieved an accuracy of 98.6%, with precision and recall scores
of 0.99 and 0.98, respectively. In comparison, the logistic regression algorithm attained
an accuracy of 94.41%, with precision and recall scores both at 0.94. Similarly, the SVM
algorithm yielded an accuracy of 93.71%, with precision and recall scores also at 0.93.
Al-Azzam and Shatnawi’s study [58] evaluates the effectiveness of both SL and semi-
SL algorithms in diagnosing breast cancer using the Breast Cancer Wisconsin (Diagnostic)
dataset [57], containing 569 instances with 30 features extracted from digital images of
fine needle-aspirates (FNAs) of breast masses. The dataset is split into training (80%) and
testing (20%) sets for both approaches, noting that for the semi-SL algorithm, the training
data was divided into 50% labeled data and 50% unlabeled data. Several models, such as
logistic regression, Gaussian naïve Bayes, SVM (both linear and RBF), decision tree, random
forest, XGBoost, GBM, and k-NN, are trained using the labeled dataset for both approaches.
All algorithms demonstrated strong performance on the test data, a minimal disparity in
accuracy between the SL and semi-SL techniques being observed. Results showed that
logistic regression (SL = 97%, SSL = 98%) and k-NN (SL = 98%, SSL = 97%) achieved the
highest accuracy for classifying malignant and benign tumors.
Ayana et al. [59] explore a novel multistage TL (MSTL) approach tailored for US
breast cancer image binary classification. The dataset consists of 20,400 cancer cell line
microscopic images and US images from two datasets: Mendeley [60] (200 images) and MT-
Small-Dataset [55,61] (400 images). The presented TL approach begins with a pre-trained
model on ImageNet, adapted to cancer cell line microscopic images. This stage involves
fine-tuning the model to recognize features relevant to medical contexts, particularly those
that are morphologically similar to features in US images. Then, it uses the tuned model as
Electronics 2024, 13, 4697 18 of 40

a base to further train on US breast cancer images. This two-step process allows the model
to refine its ability to differentiate between malignant and benign features with higher
accuracy. The study employs three different CNN models: EfficientNetB2, InceptionV3,
and ResNet50. The best performance was achieved using the ResNet50 with the Adagrad
optimizer, resulting in a test accuracy of 99.0% on the Mendeley dataset and 98.7% on the
MT-Small-Dataset.
Umer et al. [61] propose an innovative approach for breast cancer binary classification
using a combination of convoluted features extracted through DL techniques and an
ensemble of ML algorithms. The study employs a custom CNN model designed to extract
deep convoluted features from mammographic images from the Breast Cancer Wisconsin
(Diagnostic) dataset [57] consisting of 32 features. After feature extraction, multiple ML
algorithms, such as random forest, decision trees, SVM, and k-NN, are employed to classify
the images into benign or malignant. The final classification is determined through a
majority voting system where each algorithm contributes equally to the decision-making
process. The dataset was split into 70% training and 30% testing. This ensemble approach
reduces the likelihood of misclassification by leveraging the diverse strengths of different
algorithms, reaching accuracy of 99.89%, precision of 99.89%, recall of 99.92%, and F1 score
of 99.90%.
The study conducted by Hekal et al. [62] proposes an ensemble DL system designed
for binary classification of breast cancer. The system processes suspected nodule regions
(SNRs) extracted from mammogram images, utilizing four different TL CNNs and subse-
quent binary SVM classifiers. The study uses the CBIS-DDSM [53] dataset, which provides
3549 region-of-interest (ROI) images with both mass and calcification cases containing
annotations for both malignant and benign findings. SNRs are extracted from ROI im-
ages using an optimal dynamic thresholding method specifically tailored to adjust the
threshold based on the detailed characteristics of each image. Four CNN architectures,
namely, AlexNet, DenseNet-201, ResNet-50, and ResNet-101, are used and followed by
a binary SVM classifier that determines if the processed SNRs are malignant or benign.
The outputs from each CNN-SVM pipeline are combined using a first-order momentum
method, which considers the training accuracies of the individual models. This fusion
approach is designed to enhance decision-making by weighting the contribution of each
model based on its performance. The proposed ensemble DL system achieved an accuracy
of 94% for distinguishing benign and malignant cases and 95% for distinguishing between
benign and malignant masses.
Deb et al. [63] provide a detailed analysis of segmenting mammogram images using
DL architectures, specifically U-Net and BCDU-Net, which is an advanced variant of U-Net
that incorporates bidirectional ConvLSTM and densely connected convolutional blocks.
The INBreast dataset [64] is utilized, comprising 410 mammograms from 115 patients.
Initial experiments are conducted on full mammograms to segment regions indicative
of potential masses. Further experiments focus on ROIs extracted from mammograms,
where the network segments smaller, more focused areas. Both U-Net and BCDU-Net
are evaluated on their ability to segment whole mammograms and ROIs. The models
achieved a DSC of 0.8376 and IOU of 0.7872 for the full mammogram, while for the ROI
segmentation, they reported a DSC of 0.8723 and IOU of 0.8098. The study concludes that
BCDU-Net provides better segmentation results, especially when focusing on ROIs.
Haris et al. [65] introduce a novel approach for breast cancer segmentation using a
combination of Harris hawks optimization (HHO) with cuckoo search (CS) and an SVM
classifier that aims to optimize segmentation by fine-tuning hyperparameters for enhanced
accuracy in mammographic image analysis. The study utilizes the CBIS-DDSM [40] dataset.
The hybrid model starts with initializing a population of hawks in the image matrix, where
each hawk represents a potential solution. The fitness of each hawk is evaluated based on
pixel intensity and neighboring intensities. This evaluation guides the optimization process,
focusing on improving segmentation accuracy. The hybrid approach leverages the strengths
of both HHO and CS, enabling a dynamic adjustment between exploration and exploitation
Electronics 2024, 13, 4697 19 of 40

phases, ultimately fine-tuning SVM parameters for optimal segmentation. The study
concludes that the integration of HHO and CS with SVM significantly improves breast
cancer segmentation in mammographic images, demonstrating an accuracy of 98.93%, a
DSC of 98.77%, and an IOU of 97.68%.
Table 3 provides a concise overview of each paper’s details, including the model types,
data preprocessing, and dataset characteristics. No interpretability methods were presented
in any of these papers.

Table 3. Summary of breast cancer studies.

Dataset
Author Model Data Type Preprocessing
Size Classes
Image balancing
Radiomics-based Benign
Interlenghi et al. [50] US 821 Histogram
ML Malignant
equalization
Normal Noise reduction
322 +
Kavitha et al. [51] OMLTS-DLCN Mammogram Benign Thresholding
13,128
Malignant Segmentation
Normal
Chen et al. [54] DSEU-Net US 780 Benign -
Malignant
Random Forest
Benign Feature extraction
Dogiwal [56] Logistic Regression 32 attributes 699
Malignant Feature selection
SVM
Exploratory Data
Al-Azzam & SL Benign
32 features 569 Analysis
Shatnawi [58] Semi-SL Malignant
Correlation analysis
Adaptive thresholding
Benign
Ayana et al. [59] ResNet50 US 200 + 400 Noise reduction
Malignant
Data augmentation
Benign Feature extraction
Umer et al. [61] Voting CNN 32 features -
Malignant Label encoder
ROI extraction
Benign
Hekal et al. [62] Ensemble DL SVM Mammogram 3549 Smoothing
Malignant
Otsu thresholding
Masses
Calcifications ROI extraction
Deb et al. [63] BCDU-Net Mammogram 410
Asymmetries Otsu thresholding
Distortions Resizing
Histogram
Normal
equalization
Haris et al. [65] HHO-CS SVM Mammogram 2620 Benign
Contrast stretching
Malignant
Adaptive equalization

4.3. Brain Cancer

Brain cancer ranks as the leading cause of cancer death for females aged 20 and
younger, as well as males aged 40 and younger [66]. Each year, approximately 13,000 cases
of glioblastoma are diagnosed in the United States, corresponding to an incidence rate of
3.2 per 100,000 individuals [67]. Given the pressing demand for precise and automated
analysis of brain tumors, coupled with the exponential expansion of clinical imaging data,
the significance of image-based ML techniques is steadily escalating.
Khan et al. [68] present an advanced method for detecting and segmenting brain
tumors using a region-based CNN (RCNN). This approach utilizes MRI images from the
BraTS 2020 dataset [69–71], which contains a total of 369 training, 125 validation, and
Electronics 2024, 13, 4697 20 of 40

169 test multi-modal MRI studies, to identify and delineate tumor regions. The proposed
approach consists of three phases: preprocessing, tumor localization using the RCNN,
and segmentation using an active contour algorithm. The RCNN, which integrates region
proposal mechanisms with CNNs, is employed to accurately localize and segment tumors
in brain MRI scans. It makes use of an AlexNet pre-trained network to extract features from
regions of interest within the brain scans, which are then used to identify and segment the
tumors. After the initial detection and rough segmentation by the RCNN, the active contour
model, also known as “snakes,” is used for precise segmentation. This method refines the
boundaries of the tumor by minimizing an energy function that delineates the tumor’s
shape more accurately. The proposed system achieved a mean average precision of 0.92
for tumor localization performance and an average DSC of 0.92 for tumor segmentation
performance, demonstrating an accuracy of 88.9%.
Sharma et al. [72] introduce a hybrid multilevel thresholding image segmentation
method for brain MRI images from the publicly available Figshare database [73] using a
novel dynamic opposite bald eagle search (DOBES) optimization algorithm. The brain
MRI dataset contains T1-weighted images of 233 patients, categorized into meningioma,
glioma, and pituitary tumors. The DOBES algorithm is an enhancement of the traditional
bald eagle search (BES) algorithm, incorporating dynamic opposition learning (DOL) to
improve initialization and exploitation phases, aiming to avoid local optima and enhance
convergence speed. This algorithm is used for selecting optimal multilevel threshold values
for image segmentation to accurately isolate tumor regions from normal brain tissues. The
segmentation process combines optimized thresholding with morphological operations to
refine the segmented images, removing noise and non-tumor areas to enhance the clarity
and accuracy of tumor delineation. The results showed structural similarity indices of
0.9997, 0.9999, and 0.9998 for meningioma, glioma, and pituitary tumors, respectively, with
an average accuracy of 99.98%.
A study presented by Ngo et al. [74] explores an advanced approach to brain tumor
segmentation, particularly focusing on small tumors, which are often challenging to detect
and delineate accurately in medical imaging. It utilizes multi-task learning, integrating
feature reconstruction tasks alongside the main segmentation task, and makes use of the
BraTS 2018 dataset [69–71], which includes 3D MRI scans of 285 patients for training and
66 patients for validation. The primary task is the segmentation of brain tumors using a
U-Net-based architecture modified for 3D analysis to accommodate the full complexity of
brain structures in MRI. An auxiliary task of feature reconstruction using an autoencoder-
like module called U-Module is implemented. The U-Module helps retain critical features
that are often lost during down-sampling in traditional CNN architectures, therefore pre-
serving important features through the encoding–decoding process, which is particularly
useful for capturing the characteristics of small tumors. The model’s effectiveness is evalu-
ated using the DSC, which showed a value of 0.4499 for tumors smaller than 2000 voxels.
For overall segmentation performance, the model achieved 81.82% DSC for enhancing
tumors, 89.75% for tumor cores, and 84.05% for whole tumors.
Ullah et al. [75] introduce an evolutionary lightweight model for the grading and
classification of brain cancer using MRI images. It is a multi-class classification task
where the brain tumors are categorized into four grades (I, II, III, and IV). The model,
which combines weighted average and lightweight XGBoost decision trees, is a modified
version of multimodal lightweight XGBoost. Features such as intensity, texture, and shape
were extracted from the MRI images. Intensity features include mean intensity, standard
deviation, skewness, and kurtosis. Texture features are derived using the gray-level co-
occurrence matrix (GLCM) method, while shape features include area, perimeter, and
eccentricity. The proposed lightweight XGBoost ensemble model is an ensemble of multiple
XGBoost decision trees. Each tree in the ensemble is trained on different subsets of the data
and with different hyperparameters to capture diverse patterns and improve generalization.
The XGBoost algorithm constructs decision trees iteratively, optimizing for a specific loss
function, their predictions being then combined using a weighted average approach. Using
Electronics 2024, 13, 4697 21 of 40

the BraTS 2020 dataset [69–71], which includes 285 MRI scans of patients with gliomas, the
proposed model achieved an accuracy of 93.0%, precision of 0.94, recall of 0.93, F1 score of
0.94, and an AUC value of 0.984.
Saha et al. [76] propose the BCM-VEMT model, which integrates DL and EL tech-
niques for accurate multi-class classification of brain tumors from MRI images. The model
combines various DL methods to improve the detection and classification accuracy of brain
cancer. The paper utilizes a dataset comprising MRI scans obtained from three publicly
available sources, namely, Figshare’s Brain Tumor dataset [77], Kaggle’s Brain MRI Images
for Brain Tumor Detection [78], and Brain Tumor Classification (MRI) [79] datasets. The
final dataset includes 3787 MRI images divided into four classes (glioma, meningioma, pitu-
itary, and normal) and is preprocessed using techniques like normalization, skull stripping,
and image augmentation to ensure uniformity and enhance the training process. Next,
significant features are extracted from the MRI images, focusing on intensity, texture, and
shape. The model employs CNNs to automatically learn and extract features from the MRI
images. To further enhance accuracy, the study combines multiple ML models, including
SVMs and random forests, in an ensemble approach. The model achieved 97.90% accuracy
for glioma, 98.94% for meningioma, 98.92% for pituitary, and 98.00% for normal cases,
resulting in an overall accuracy of 98.42%.
Table 4 provides a structured overview of the previously presented studies. No
interpretability methods were presented in any of these papers.

Table 4. Summary of brain cancer studies.

Dataset
Author Model Data Type Preprocessing
Size Classes
Khan et al. [68] RCNN MRI 663 Glioma Denoising
Multilevel thresholding
Kapur’s method
Meningioma
DOBES algorithm
Sharma et al. [72] DOBES MRI 3064 Glioma
Morphological
Pituitary
operations based
postprocessing
Cropping
Ngo et al. [74] U-Net MRI 351 Glioma Normalization
Data augmentation
Image registration
Lightweight Glioma grade II
Skull stripping
Ullah et al. [75] XGBoost MRI 285 Glioma grade III
Intensity
Ensemble Glioma grade IV
Resizing
Normal Resizing
Glioma Cropping
Saha et al. [76] BCM-VEMT MRI 3787
Meningioma Normalization
Pituitary Data augmentation

4.4. Cervical Cancer

Cervical cancer, which has claimed the lives of millions of women globally, ranks as the
third-leading cause of cancer-related mortality in women [1]. There were 661,044 women di-
agnosed with cervical cancer and 348,186 deaths attributed to the disease in 2022 [47]. Given
that the Papanicolaou (Pap) test can diagnose precancerous lesions, regular screenings are
essential to mitigate the significant risks associated with cervical cancer [80]. However,
traditional cervical cell screening heavily relies on pathologists’ expertise, resulting in low
efficiency and accuracy. Medical image processing combined with ML and DL techniques
offers a notable advantage in the classification and detection of cervical cancerous cells,
surpassing traditional methods in terms of effectiveness and precision.
Electronics 2024, 13, 4697 22 of 40

Zhang et al. [81] proposed DeepPap, a deep CNN model designed for the binary
classification of cervical cells into “normal” and “abnormal” categories. The study utilized
two datasets: the Herlev [82] dataset, consisting of 917 cervical cell images across seven
classes, and the HEMLBC [83] dataset, which includes 989 abnormal cells and 1381 normal
cells. The DeepPap architecture leverages TL using a pre-trained network on the ImageNet
dataset, followed by fine-tuning on cervical cell images. This architecture includes several
convolutional layers for feature extraction, pooling layers for downsampling, and fully
connected layers for final classification. The model achieved a classification accuracy of
98.3% and an AUC of 0.99.
A study presented by Guo et al. [84] employed an unsupervised DL registration
approach to align cervix images taken during colposcopic examinations. It utilizes uterine
cervix images collected from four different databases, namely, CVT [85,86] (3398 images),
ALTS [87] (939 images), Kaggle [88] (1950 images), and DYSIS (5100 images). These
datasets consist of cervix images captured at different time intervals during the application
of acetic acid, covering various conditions and imaging variations, such as changes in
cervix positioning, lighting intensity, and texture. The focus is on using DL architectures
employing transformers, such as DeTr, for object detection. The architecture comprises
a backbone network for feature extraction, a transformer encoder–decoder module, and
prediction heads. The encoder–decoder module includes 3 encoder layers, 3 decoder layers,
and 4 attention heads, with a feedforward network (FFN) of 256 layers and an embedding
size of 128. The model employs 20 object query slots to accommodate the varying number
of objects in each image. The training strategy involves two stages: initially training a DeTr-
based object detection network, then replacing the bounding box prediction heads with a
mask prediction head and training the network with mask ground truth. The segmentation
network derived from this process is utilized to extract cervix region boundaries from
original and registered images for performance evaluation of the registration network. The
segmentation approach was then applied to registered time sequences, achieving Dice/IoU
scores of 0.917/0.870 and 0.938/0.885 on two datasets, resulting in a 12.62% increase in
Dice scores for cervix boundary detection compared to unregistered images.
Angara et al. [89] focus on enhancing the binary classification of cervical precancer
using semi-SL techniques applied to cervical photographic images. The study utilizes
data derived from two large studies conducted by the U.S. National Cancer Institute,
namely, ALTS [87] and the Guanacaste Natural History Study (NHS). The combined
dataset consists of 3384 labeled images and over 26,000 unlabeled images. The authors
employ novel data augmentation techniques like random sun flares and grid drop to tackle
challenges such as specular reflections in cervix images. The semi-SL framework employs
the ResNeSt50 architecture, which includes a split-attention block that allows it to focus
on relevant features within an image by grouping feature maps and applying attention
mechanisms within these groups. It also relies on a model pre-trained on ImageNet to
utilize learned features applicable to general visual recognition tasks. The semi-supervised
approach includes generating pseudo-labels for unlabeled images using a teacher model
trained on available labeled data. These pseudo-labels are then used to train a student
model, improving its learning from both labeled and unlabeled data. The student model’s
predictions refine the training process iteratively, progressively enhancing the model’s
ability to classify new and unseen images accurately. The model’s effectiveness is measured
through accuracy, precision, recall, and F1 score, the results on the test set being 82%, 0.84,
0.57, and 0.68, respectively. The accuracy on the test dataset is enhanced to 82.02% when
utilizing the semi-supervised method compared to the 76.81% of ImageNet TL.
Kudva et al.’s paper [90] presents a novel hybrid TL (HTL) approach that integrates DL
techniques with traditional image processing to improve the binary classification of uterine
cervix images for cervical cancer screening. The study used 2198 cervix images, comprising
1090 negative and 1108 positive cases, sourced from Kasturba Medical College and the
National Cancer Institute. The study first identified relevant filters from pre-trained models
(AlexNet and VGG-16) that were effective in highlighting cervical features, particularly
Electronics 2024, 13, 4697 23 of 40

acetowhite regions. Two shallow-layer CNN models were developed: CNN-1, which
incorporated the selected filters that were resized and adapted to the specific dimensions
required for the initial convolutional layers of the CNN, and CNN-2, which included an
additional step of adapting filters from the second convolutional layers of AlexNet and
VGG-16, providing deeper and more detailed feature extraction capabilities. The results
show that the HTL approach outperformed traditional methods that rely solely on either
full training of deep CNNs or basic ML techniques, achieving an accuracy of 91.46%,
sensitivity of 89.16%, and specificity of 93.83%.
Ahishakiye et al. [91] focus on a binary classification task to predict cervical cancer
based on risk factors using EL techniques. The dataset was sourced from the UCI Machine
Learning Repository and included records for 858 patients with 36 attributes related to
cervical cancer risk factors. Feature selection consisted of selecting five main predictors
deemed the most influential for predicting cervical cancer based on previous studies and
expert recommendations. The EL techniques used were k-NN, classification and regression
trees (CARTs), naïve Bayes classifier, and SVM. The models were integrated using a voting
ensemble method and the final prediction was based on the majority vote. The proposed
ensemble model achieved an accuracy of 87.21%, demonstrating its potential as a diagnostic
tool in clinical settings.
Hodneland et al. [92] examine a fully automatic method for whole-volume tumor
segmentation in cervical cancer using advanced DL techniques. The study included 131 pa-
tients with uterine cervical cancer who underwent pretreatment pelvic MRI. The dataset
was divided into 90 patients for training, 15 for validation, and 26 for testing. The perfor-
mance of the proposed enhanced residual U-Net architecture was assessed using the DSC,
comparing the DL-generated segmentations against those done by two human radiologists.
The DL algorithm achieved median DSCs of 0.60 and 0.58 when compared to the two
radiologists, respectively, while the DSC for inter-rater comparisons was 0.78, showing a
respectable but not perfect alignment with human expert segmentation.
Table 5 provides an overview of the previously presented articles, including the data
type, preprocessing methods, and model interpretability information.

Table 5. Summary of cervical cancer studies.

Dataset
Author Model Data Type Preprocessing Interpretability
Size Classes
Pap smear Abnormal Patch extraction
Zhang et al. [81] DeepPap 917 + 1978 -
Pap staining Normal Data augmentation
3398 + 939 + Normal
Guo et al. [84] DeTr Colposcopic Resizing -
1950 + 5100 Cancer
Resizing
Cytology
Cropping
Angara HPV Normal
ResNeSt50 3384 + 26,000 Data augmentation Score-CAM
et al. [89] Testing Cancer
PCA noise
Cervicography
Normalizing
Kudva Benign
HTL Pap smear 2198 Data augmentation -
et al. [90] Malignant
Ahishakiye Normal Normalization
Voting EL 36 attributes 858 -
et al. [91] Cancer Standardization
Resampling
Interpolation
Hodneland
ResU-Net MRI 131 Cancer Z-normalization -
et al. [92]
Resizing
Data augmentation
Electronics 2024, 13, 4697 24 of 40

4.5. Colorectal Cancer

Colorectal cancer (CRC) is the second-deadliest cancer globally [93], with its incidence
and mortality expected to rise significantly in the coming decades. Early detection of
colorectal cancer allows for complete cure through surgery and medication, but access
to early diagnosis and treatment is more prevalent in developed countries, whereas such
facilities are scarce in developing regions. Globally, there were 1.9 million people (9.6%
of the total new cases of cancer) diagnosed with CRC and 900,000 deaths (9.3% of the
total cancer deaths) attributed to the disease in 2022 [47]. ML can significantly enhance
the diagnosis and survival prediction of colorectal cancer through various innovative
applications. For example, ML algorithms can be trained to analyze histopathological
images or real-time videos from colonoscopies to identify polyps or other abnormalities,
leading to more accurate diagnoses and effective treatment strategies.
The core of Guo et al.’s study [94] is the development of the RK-net, which combines
UL techniques with DL to optimize the preprocessing and feature extraction processes for
colorectal cancer diagnosis. It utilizes data that includes imaging and clinical information
stored in a standardized DICOM format from 360 colorectal cancer patients, divided into
300 patients for training and 60 patients for testing. Initially, the images undergo prepro-
cessing where they are normalized for intensity and resized to fit the input requirements
of the network. The unsupervised component involves a k-means clustering algorithm,
which segments the images into clusters based on similarities in texture, color, and spatial
characteristics, effectively isolating relevant features from the background and noise. This
network then takes the clustered images and performs feature extraction using the Mo-
bileNetV2 architecture and learns to identify and prioritize features that are most indicative
of cancerous tissues. The UL component helps in reducing the training data size by focusing
only on relevant clusters, thereby decreasing the computational costs and speeding up the
training process. RK-net demonstrated a significant reduction in training time by up to 50%
compared to traditional methods and achieved 95% accuracy in differentiating two types
of colorectal cancer.
Zhou et al. [95] introduce a weakly supervised DL approach for classifying and local-
izing colorectal cancer in histopathology images using only global labels. The proposed
DL model classifies whole-slide images (WSIs) into multiple classes, including different
stages of colorectal cancer and normal tissue. The study utilizes two datasets: 1346 WSIs,
including 134 normal and 1212 cancerous images, from the Cancer Genome Atlas (TCGA)
and 50 newly collected WSIs from three hospitals. The study experiments with various
CNN architectures, including ResNet, which was chosen due to its superior performance
in patch-based classification tasks, and designs three frameworks. The image-level frame-
work processes low-resolution thumbnails of WSIs to predict the cancerous probability of
tissues by examining the entire image, which mimics the preliminary evaluations typically
performed by pathologists. The cell-level framework focuses on detailed pathological
information present at the cellular level and employs a CNN model to distinguish between
cancerous and non-cancerous cells based on features extracted from normal tissue samples,
thus avoiding the need for precise cancer annotations. The combination framework com-
bines features from both the image-level and cell-level frameworks to improve diagnostic
accuracy. The model achieved 94.6% accuracy on the TCGA dataset and 92.0% accuracy on
the external dataset.
Venkatayogi et al. [96] propose a novel approach for the multi-class classification of
colorectal cancer polyps using TL and a vision-based surface tactile sensor (VS-TS). The
research team designed and additively manufactured 48 types of realistic polyp phantoms,
varying in hardness, type, and texture. The dataset was then augmented through rotation
and flipping to generate a total of 384 samples. These phantoms are used to mimic real
CRC polyps and generate a dataset of textural images using the VS-TS. VS-TS consists of a
deformable silicone membrane, an optics module, and an array of LEDs that illuminate the
polyp during imaging. The sensor detects the deformation of the silicone upon contact with
polyp phantoms, creating detailed textural images. Each phantom is systematically pressed
Electronics 2024, 13, 4697 25 of 40

against the sensor to record the detailed textural patterns that characterize different polyp
types. The ResNet-18 network is pre-trained on the ImageNet dataset and a SVM algorithm
is employed and trained to classify polyps based on the textural features extracted by the
VS-TS. The classification is performed on two versions of ResNet-18: one starting with
random weights (ResNet1) and the other pre-trained on ImageNet (ResNet2). ResNet2
demonstrated a test accuracy of 91.93%, surpassing the metrics of ResNet1, which exhibited
an accuracy of 54.95%.
Tamang et al. [97] present a TL-based binary classifier to effectively distinguish be-
tween tumor and stroma in colorectal cancer patients using histological images obtained
from a publicly available dataset by Kather et al. [98], containing 5000 tissue tiles of
colorectal cancer histological images. The TL framework employs four different CNN archi-
tectures, namely, VGG19, EfficientNetB1, InceptionResNetV2, and DenseNet121, which are
pre-trained on the ImageNet dataset. The bottleneck layer features (deep features just before
the fully connected layers) from these models are used, as this layer typically contains rich
feature representations that are broadly applicable across different tasks, including medical
imaging. The classifier is then fine-tuned on the CRC dataset while keeping the pre-trained
layers frozen to retain the learned features. VGG19, EfficientNetB1, and InceptionResNetV2
architectures achieved accuracies of 96.4%, 96.87%, and 97.65%, respectively, surpassing the
reference values presented in the study and therefore demonstrating that the application of
TL using pre-trained CNNs significantly enhances the ability to classify tumor and stroma
regions in colorectal cancer histological images.
Liu et al. [99] explore the application of Fovea-UNet, a DL model inspired by the fovea
of the human eye for the detection and segmentation of lymph node metastases (LNM)
in colorectal cancer using CT images. The study used a dataset containing 81 WSIs of
LNM, with a total of 624 metastatic regions that were manually extracted and annotated.
The dataset was divided into a training set with 57 WSIs (451 metastatic regions) and a
test set with 24 WSIs (173 metastatic regions). The architecture includes an importance-
aware module that adjusts the pooling operation based on feature relevance, enhancing
the model’s focus on significant areas. The authors introduce a novel pooling method that
adjusts the pooling radius based on pixel-level importance, helping to aggregate detailed
and non-local contextual information effectively. The feature extraction process utilizes
a lightweight backbone modified with a feature-based regularization strategy (GhostNet
backbone) to reduce computational demands while maintaining feature extraction efficiency.
The proposed model demonstrated superior segmentation performance with a 79.38% IOU
and 88.51% DSC, outperforming other state-of-the-art models.
Fang et al. [100] developed an advanced approach called area-boundary constraint
network (ABC-Net) for segmenting colorectal polyps in colonoscopy images. The study
utilizes three public colorectal polyp datasets, namely, EndoScene [101] (912 images),
Kvasir-SEG [102] (1000 images), and ETIS-Larib [103] (196 images), which include various
colorectal polyp images captured through colonoscopy. ABC-Net consists of a shared
encoder and two decoders. The decoders are tasked with segmenting the polyp area
and boundary. The network integrates selective kernel modules (SKMs) to dynamically
select and fuse multi-scale feature representations, optimizing the network’s focus on
the most relevant features for segmentation. The SKMs help in adapting the receptive
fields dynamically, allowing the network to focus more on informative features and less
on irrelevant ones. The dual decoders operate under mutual constraints, where one
decoder focuses on the polyp area and the other on the boundary, with each influencing
the performance of the other to improve overall segmentation accuracy. A novel boundary-
sensitive loss function models the interdependencies between the area and boundary
predictions, enhancing the accuracy of both. This function includes terms that encourage
consistency between the predicted area and its boundary, thereby refining the segmentation
output. ABC-Net achieved DSCs of 0.857, 0.914, and 0.864, and IOU scores of 0.762, 0.848,
and 0.770 on the EndoScene, Kvasir-SEG, and ETIS-Larib datasets, respectively.
Electronics 2024, 13, 4697 26 of 40

Elkarazle et al. [104] introduce a novel approach to colorectal polyp segmentation

using an enhanced version of the multi-scale attention network (MA-NET) integrated with
a modified Mix-ViT transformer. This combination leverages the transformer’s capability
to perform ultrafine-grained visual categorization, which is crucial for the accurate seg-
mentation of challenging polyp types. The Mix-ViT transformer, adapted for this specific
application, replaces the typical convolution-based encoder in MA-NET. This allows for
better feature extraction at multiple scales, improving the model’s ability to distinguish
between polypoid and non-polypoid regions effectively. The network includes a prepro-
cessing layer that applies contrast-limited adaptive histogram equalization (CLAHE) in
the CIELAB color space to enhance features in the input images. This enhancement aims
to address the challenges of segmenting small and flat polyps. The segmentation model
undergoes training on the Kvasir-SEG [102] (1000 images) and CVC-ClinicDB [105] (612 im-
ages) datasets with additional cross-validation on CVC-ColonDB [106] (300 images) and
ETIS-LaribDB [103] (196 images) to test its robustness and generalizability. The proposed
model achieved an accuracy, IOU, DSC, and F1 score of 0.9890, 0.985, 0.989, and 0.992,
respectively, for the ETIS-LaribDB dataset, while for the CVC-ColonDB the results were
0.983, 0.973, 0.983, and 0.985, respectively.
Table 6 summarizes the colorectal cancer studies presented above. No interpretability
methods were presented in any of these papers.

Table 6. Summary of colorectal cancer studies. The asterisks (*) are used to denote that the values are
derived from a mathematically defined color space.

Dataset
Author Model Data Type Preprocessing
Size Classes
Cancer Normalization
Guo et al. [94] RK-net Histopathology 360
Normal Resizing
Cancer Feature
Zhou et al. [95] CNN Histopathology 1346
Normal combination
IIa
Cropping
Venkatayogi ResNet1 IIc
Fabricated 48 Resizing
et al. [96] ResNet2 Ip
Data augmentation
LST
EfficientNetB1 Tumor
Tamang et al. [97] Histopathology 625 Data augmentation
InceptionResNetV2 Stroma
Liu et al. [99] Fovea-UNet CT 624 Metastatic regions Resizing
Polyps Resizing
Fang et al. [100] ABC-Net Colonoscopy 912 + 1000 + 196
Non-polyps Data augmentation
Resizing
Normalization
Elkarazle Polyps
MA-NET Mix-ViT Colonoscopy 1000 + 612 + 196 CIEL*A*B* color
et al. [104] Non-polyps
space conversion
CLAHE

4.6. Liver Cancer

In 2020, liver cancer was the sixth-most common cancer, with 841,000 cases, and the
fourth-leading cause of cancer deaths globally, with 782,000 fatalities [107]. These numbers
saw a slight decrease in 2022, with 865,269 new cases of liver cancer reported globally
(4.3% of all new cancer cases) and 757,948 liver cancer deaths recorded (7.8% of all cancer
deaths) [1]. Hepatocellular carcinoma (HCC) is the most prevalent type of liver cancer,
accounting for 75–85% of cases [108]. Significant progress has been made in both curative
and palliative treatments for HCC. Early diagnosis and appropriate treatments, from the
initial to advanced stages of liver cancer, are essential for improving overall survival
(OS) [108].
Electronics 2024, 13, 4697 27 of 40

Napte et al. [109] presents the ESP-UNet, an encoder–decoder CNN designed to

improve liver segmentation accuracy in CT images. The study utilizes the publicly available
Liver Tumor Segmentation (LiTS) dataset [110], containing 131 CT volumes with various
tissue abnormalities and tumor levels, each image being preprocessed to enhance edge
details and contrast using Kirsch’s filter. The ESP-UNet architecture incorporates two
parallel U-Net models: the first U-Net processes the original CT images for general liver
segmentation, while the second U-Net handles edge-enhanced images to focus on precise
border delineation. The outputs of both U-Nets are combined using logical operations
to reconcile the general segmentation with the edge-focused segmentation, aiming to
reduce both over-segmentation and under-segmentation by refining the liver borders. The
proposed ESP-UNet achieved a DSC of 0.959, a volume overlapping error of 0.089, a IOU
of 0.921, a relative volume difference of 0.09, and a volume overlapping error of 0.089,
demonstrating higher accuracy and reliability in liver segmentation when compared to
existing state-of-the-art methods.
Suganeshwari et al. [111] introduce a novel DL-based system, En-DeNet, aimed at
improving liver cancer diagnosis through advanced segmentation and binary classification
techniques using CT images. The core of the system is an encoder–decoder network
(En–DeNet), which uses U-Net for encoding and a pre-trained EfficientNet for decoding.
Additionally, the gradational modular network (GraMNet) optimizes the classification
process using a hierarchy of SubNets, each adding progressively to the complexity and
capability of the model. This allows for flexibility in network depth and complexity,
enabling detailed tuning to specific features of liver tumors. The study utilizes two public
datasets, namely, 3DIRCADb01 [112] (20 patients with 2000 images in total) and LiTS [110]
(131 patients with over 58,000 images), for training and testing. The average results for LiTS
showcased an accuracy of 92.17% and a DSC of 85.94% for segmentation tasks, whereas for
3DIRCADb01, the mean results revealed an accuracy of 88.08% and a DSC of 84.81%. For
the classification task, the mean accuracy for 3DIRCADb01 was 97.86% with an AUC of
99.16%, while for LiTS, the mean accuracy was 93.13% with an AUC of 95.38%.
Araújo et al. [113] presents an automatic method for liver segmentation from CT
images in the LiTS [110] dataset (131 patients with over 58,000 images) utilizing a cascade
DL approach. The method involves four main steps: image preprocessing, initial segmen-
tation, reconstruction, and final segmentation. This approach uses two cascading U-Net
architectures: the first U-Net is aimed at defining an ROI to reduce the computational load,
and the second is used for more detailed liver segmentation within the defined ROI. The
reconstruction step is implemented to recover liver regions potentially excluded in the
initial segmentation due to lesions altering liver texture. This uses another U-Net model
trained specifically for identifying and segmenting lesions within the liver. Refinement
techniques are applied after the initial segmentation and reconstruction steps to enhance
the segmentation results. This includes reduction of false positives and morphological op-
erations to fill segmentation gaps. The proposed architecture achieved an average accuracy
of 97.66%, sensitivity of 95.45%, specificity of 99.86%, DSC of 95.64%, volumetric overlap
error of 8.28%, HD of 26.60 mm, and relative volume difference of −0.41%.
Table 7 provides the overview for liver cancer studies, including model types, dataset
details, and preprocessing methods. No interpretability methods were presented in any of
these papers.
This section has provided a comprehensive overview of the research conducted in the
field of ML-based cancer analysis techniques. Table 8 presents a comprehensive summary
of the classification ML models utilized for the diagnosis of the previously mentioned
cancer types, while Table 9 summarizes the aforementioned segmentation models. Each
entry in the table includes the type of cancer, the authors of the study, the machine learning
model employed, the dataset utilized, and the achieved performance. This summary aims
to present an overview of the current state-of-the-art approaches and their effectiveness in
cancer segmentation and classification.
Electronics 2024, 13, 4697 28 of 40

Table 7. Summary of liver cancer studies.

Dataset
Author Model Data Type Preprocessing
Size Classes
Normal Kirsch’s filter
Napte et al. [109] ESP-UNet CT 131
Cancer Segmentation
Data augmentation
Normal
Suganeshwari et al. [111] En-DeNet CT 2346 Resizing
Cancer
Normalization
Windowing
Normal Voxel rescaling
Araújo et al. [113] U-Net CT 131
Cancer False-positive reduction
Hole filling

Table 8. Summary of the classification studies.

Cancer Type Author ML Model Type Dataset Accuracy

Transfer DL Chest CT-Scan images
Jassim et al. [34] Multi-class 99.44%
Ensemble [35]
Ensemble
Muhtasim et al. [36] Multi-class IQ-OTHNCCD [37] 99.55%
CNN+VGG16 TL
Luo [38] LLC-QE Multi-class LIDC-IDRI [39] 92.90%
XGBoost 94.42%
Lung
Cancer LightGBM Lung Cancer 92.55%
Mamun et al. [40] Binary
AdaBoost Dataset [41] 90.70%
Bagging 89.76%
Bagging 93.90%
Venkatesh & Raamesh [42] AdaBoost Binary SEER [43] 95.46%
Integrated 98.30%
Said et al. [44] UNETR Binary Decathlon [45] 98.77%
Radiomics-
Interlenghi et al. [50] Binary - 92.70%
based ML
Mini-MIAS [52] 98.50%
Kavitha et al. [51] OMLTS-DLCN Multi-class
CBIS-DDSM [53] 97.56%
Random Forest 98.60%
Breast Cancer Wisconsin
Dogiwal [56] Logistic Regression Binary 94.41%
(Diagnostic) [57]
SVM 93.71%
Breast
SL Breast Cancer Wisconsin 97.00%
Cancer Al-Azzam & Shatnawi [58] Binary
Semi-SL (Diagnostic) [57] 98.00%
Mendeley [60] 99.00%
Ayana et al. [59] ResNet50 Binary MT-Small-Dataset
98.70%
[55,114]
Breast Cancer Wisconsin
Umer et al. [61] Voting CNN Binary 99.89%
(Diagnostic) [57]
CBIS-DDSM [53]—case 94.00%
Hekal et al. [62] Ensemble DL SVM Binary
CBIS-DDSM [53]—mass 95.00%
Electronics 2024, 13, 4697 29 of 40

Table 8. Cont.

Cancer Type Author ML Model Type Dataset Accuracy

Lightweight
Ullah et al. [75] XGBoost Multi-class BraTS 2020 [69–71] 93.00%
Brain
Ensemble
Cancer
Figshare [64],
Saha et al. [76] BCM-VEMT Multi-class 98.42%
Kaggle [78,79]
Herlev [82],
Zhang et al. [81] DeepPap Binary 98.30%
HEMLBC [83]
Angara et al. [89] ResNeSt50 Binary ALTS [87], NHS 82.02%
Cervical
Cancer Kasturba Medical
Kudva et al. [90] HTL Binary College, National 91.46%
Cancer Institute
Ahishakiye et al. [91] Voting EL Binary UCI ML Repository 87.21%
Guo et al. [94] RK-net Binary - 95.00%
Zhou et al. [95] CNN Multi-class TCGA 94.60%
ResNet1 54.95%
Venkatayogi et al. [96] Multi-class -
Colorectal ResNet2 91.93%
Cancer
VGG19 96.40%
ImageNet, Kather
Tamang et al. [97] EfficientNetB1 Binary 96.87%
et al. [98]
InceptionResNetV2 97.65%

Liver 3DIRCADb01 [112] 97.22%

Suganeshwari et al. [101] En-DeNet Binary
Cancer LiTS [110] 88.08%
Ensemble IQ-OTHNCCD
Muhtasim et al. [36] - -
Lung Cancer CNN+VGG16 TL [37]
Said et al. [44] UNETR Decathlon [45] 0.9642 0.9309
Mini-MIAS
- -
Kavitha et al. [51] OMLTS-DLCN [52]
CBIS-DDSM
- -
[53]
Breast Cancer
Chen et al. [54] DSEU-Net BUSI [55] 0.7851 0.7036
U-Net 0.8781 0.7827
Deb et al. [63] INBreast [64]
BCDU-Net 0.8949 0.8098
CBIS-DDSM
Haris et al. [65] HHO+CS SVM 0.9877 0.9768
[53]
BraTS 2020
Khan et al. [68] RCNN 0.9200 0.8519
[69–71]
Brain Cancer Sharma et al. [72] DOBES Figshare [73] - -
BraTS 2018
Ngo et al. [74] U-Net 0.4499 0.2902
[69–71]
CVT [85,86],
ALTS [87],
Guo et al. [84] DeTr 0.9380 0.8850
Cervical Cancer Kaggle [88],
DYSIS
Hodneland et al. [92] ResU-Net - 0.7800 0.6393
Electronics 2024, 13, 4697 30 of 40

Table 9. Summary of the segmentation studies.

Cancer Type Author ML Model Dataset DSC IOU

Liu et al. [99] Fovea-UNet LMN [99] 0.8851 0.7938
EndoScene [101] 0.8570 0.7620

Colorectal Cancer Fang et al. [100] ABC-Net Kvasir-SEG [102] 0.9140 0.8480
ETIS-LaribDB [103] 0.8640 0.7700
CVC-ColonDB [106] 0.9830 0.9730
Elkarazle et al. [104] MA-NET Mix-ViT
ETIS-LaribDB [103] 0.9890 0.9850
Napte et al. [109] ESP-UNet LiTS [110] 0.9590 0.9210
3DIRCADb01 [112] 0.8481 0.7363
Liver Cancer Suganeshwari et al. [111] En-DeNet
LiTS [110] 0.8594 0.7535
Araújo et al. [113] U-Net LiTS [110] 0.9564 0.9164

The findings of the reviewed literature revealed a clear consensus regarding the
importance of early detection in improving survival rates. Researchers have dedicated
considerable efforts to developing and refining ML-based approaches for the detection
and diagnosis of these diseases. Medical imaging modalities have been particularly in-
strumental in this regard, enabling the extraction of valuable information from various
imaging scans.
The extensive literature review presented in this section demonstrates the transforma-
tive impact of ML in the field of cancer analysis across various types, namely, lung, breast,
brain, cervical, colorectal, and liver cancers. By harnessing the power of ML, researchers
and clinicians can enhance diagnostic accuracy, predict patient outcomes with greater
precision, and develop more effective personalized treatment plans. Although significant
progress has been made, ongoing research and development are essential to fully exploit
the potential of ML in oncology.

5. Challenges and Limitations

Although ML holds significant potential in cancer analysis, diagnosis, prediction, and
treatment, several challenges hinder its full integration into cancer care. These include data
and technical limitations, clinical adoption hurdles, and ethical considerations. Robust
computing infrastructure is needed to manage large datasets, while data heterogeneity,
poor quality, and biases can cause overfitting and poor generalizability. Lack of model
transparency and ethical concerns regarding data usage, fairness, and privacy further
impede clinical integration. The following paragraphs detail these challenges.

5.1. Computing Infrastructure and Scalability

ML models, especially DL models, demand substantial computing power and re-
sources for training and deployment. Scaling up infrastructure for high-resolution imaging,
genomics, or multimodal data is costly and technically challenging. Additionally, inte-
grating ML models into existing healthcare IT systems faces compatibility issues, data
interoperability challenges, and data transfer security concerns [115].
Google Colab can be a practical solution, particularly for researchers or smaller-scale
projects with limited resources. It provides free access to GPUs and TPUs for training ML
models and supports integration with cloud storage like Google Drive, allowing researchers
to handle high-resolution imaging data more efficiently.

5.2. Data Quality and Availability

Training and validating ML models require large, diverse, and high-quality datasets,
which are challenging to obtain due to data fragmentation, limited access, and privacy
concerns. Limited annotated data hamper model accuracy and generalizability. Lack of
Electronics 2024, 13, 4697 31 of 40

standardization in data formats and protocols further complicates data aggregation and
integration. Imbalanced datasets, due to varying cancer prevalence, can lead to biased
model performance and poor representation of less common cancer types [116].
To address this challenge, researchers can use data augmentation techniques to ar-
tificially increase the size and diversity of existing datasets. Additionally, employing TL
allows models pre-trained on larger, similar datasets (e.g., ImageNet) to be fine-tuned on
smaller, specific cancer datasets, improving model generalizability.

5.3. Limited Data for Rare Cancer Types

Obtaining large and diverse datasets for rare types of cancer can be challenging and
can lead to limitations in developing robust and reliable ML models specific to those cancer
types. The lack of sufficient data for rare cancer types leads to imbalanced datasets [117],
where the minority class is underrepresented, leading to biased or inaccurate predictions
for that class.
To address this challenge, data augmentation and synthetic data generation techniques,
such as generative adversarial networks, can be used to create realistic synthetic samples
of the minority class. This can help balance the dataset and provide the model with more
examples of rare cancer types, improving its ability to recognize these cases.

5.4. Model Overfitting, Robustness, and Adaptability

ML models often struggle to generalize to unseen data [117], leading to overfitting and
sensitivity to variations in data distribution, noise, and perturbations. Ensuring robustness
and adaptability across different clinical settings and patient populations is challenging.
Deploying ML models in real-world clinical settings requires rigorous validation and
testing to maintain consistent and reliable performance, despite variations in data collection,
imaging techniques, and treatment modalities. Additionally, the evolving nature of cancer
research and clinical practice demands adaptable models to stay relevant and accurate.
To address overfitting and improve robustness, techniques like regularization, data
augmentation, and k-fold cross-validation can be employed to ensure models generalize
well to new data.

5.5. Model Validation and Generalizability

Validating ML models across different cancer types, populations, and healthcare
settings is challenging due to the need for transferability and generalizability. Achieving
the latter is difficult because of variations in data distributions, patient characteristics, and
clinical practices across institutions. Extensive data collection and expert annotations are
necessary to obtain high-quality validation datasets that represent diverse clinical scenarios
and populations [118].
To enhance model validation and generalizability, researchers can use multi-center
datasets and cross-institutional studies to capture diverse patient populations, imaging
techniques, and clinical practices. This ensures that the model is trained and validated on a
wide range of data distributions, enhancing its ability to generalize to new settings.

5.6. Model Interpretability and Explainability

Frequently, ML models operate as black boxes, which makes it difficult to interpret
the reasoning behind their predictions [119]. In cancer care, each decision has critical
implications, making the development of methods that explain the decision-making process
of ML models a requirement essential to build trust and facilitate clinical acceptance.
Techniques like Shapley additive explanations (SHAP) and local interpretable model-
agnostic explanations (LIME) can be used to provide insights into a model’s decision-
making process by highlighting which features most influence predictions. For image-based
models, gradient-weighted class activation mapping (Grad-CAM) can generate heatmaps
showing regions in the image that the model focuses on for its classification, offering visual
explanations.
Electronics 2024, 13, 4697 32 of 40

5.7. Clinical Adoption and Usability

Introducing ML technologies into clinical practice requires user-friendly tools that
integrate seamlessly into workflows and provide clear benefits to healthcare providers
and patients [119]. The success of ML-driven systems depends on model interpretability
and explainability. Additionally, the lack of standardized data formats complicates the
integration of ML models with electronic health record (EHR) systems and other clinical
information systems, essential for seamless data exchange and decision support [115].
To facilitate the integration of ML technologies into clinical practice, user-friendly
interfaces and visualization tools that present model outputs in an interpretable manner
can be developed. Techniques like Grad-CAM for visual explanations and LIME for feature
importance can provide clinicians with insights into model decisions, enhancing trust
and usability.

5.8. Integration with Clinical Workflows

Integrating ML models into clinical workflows faces challenges in compatibility with
EHR systems, IT infrastructure, and data exchange standards. Training healthcare profes-
sionals to use and interpret ML models is essential for informed decision-making in cancer
analysis and treatment. Ensuring ML models are interpretable is crucial for clinicians to
understand and effectively incorporate predictions and recommendations.
Providing user-friendly dashboards and visual tools can help present predictions in
an easily interpretable way, supporting clinicians in decision-making. Training healthcare
professionals through workshops and interactive tutorials is also essential, ensuring they
can effectively use the models and incorporate their insights into patient care.

5.9. Ethical Considerations in Data Usage

Ensuring patient privacy and data security, along with informed consent, is crucial
when using ML in cancer care [116]. Key ethical challenges include potential misuse of
patient data [120], balancing data access with privacy protection, and biases in training
data [117] leading to unequal treatment. Transparency and explainability in data use are
also essential for patient and provider understanding.
Implementing data anonymization and encryption techniques can ensure patient
privacy and security. Informed consent processes should be enhanced to clearly commu-
nicate how patient data will be used for ML purposes. Additionally, using bias detection
and mitigation techniques during model development can reduce biases in training data,
promoting equitable treatment.

5.10. Regulatory and Legal Frameworks

Ensuring patient safety and regulatory adherence in ML models for cancer care re-
quires clear guidelines, standards, and regulations. Regulatory requirements vary across
jurisdictions, complicating compliance. Intellectual property rights and ownership of
models, especially those trained on proprietary datasets, present legal challenges. Privacy
and data protection regulations, like GDPR, add complexities in data handling, consent
management, and cross-border transfers [119].
Developers should collaborate with regulatory bodies to ensure adherence to estab-
lished guidelines and obtain necessary certifications for ML models in cancer care. Legal
agreements, such as data usage licenses and intellectual property contracts, can clarify
ownership rights, especially when using proprietary datasets.
Overcoming these challenges depends on interdisciplinary collaboration, robust vali-
dation methods, transparent and explainable models, regulatory compliance, user-centered
design, and ongoing monitoring and evaluation. The technology-related limitations require
ongoing research and development, innovation in algorithm design, infrastructure im-
provements, and advancements in interpretability techniques to harness the full potential
of ML in cancer care. By addressing these challenges, ML can significantly contribute to
Electronics 2024, 13, 4697 33 of 40

cancer analysis by improving diagnosis, prediction, treatment decision-making, and patient

outcomes.

6. Discussion and Future Directions

ML techniques have shown remarkable improvements in the accuracy and efficiency
of cancer diagnosis. The ability to process large datasets from diverse medical imaging
modalities, such as X-rays, mammography, ultrasound, CT, PET, and MRI, allows for more
precise identification and classification of cancerous tissues. Notably, the use of DL, EL, and
TL has enhanced model performance, enabling higher precision in detecting early-stage
cancers, which is crucial for improving patient outcomes.
For lung cancer, the highest accuracy achieved for tumor classification was 99.55%,
utilizing the Ensemble CNN+VGG16 TL model by Muhtasim et al. [36], while for segmen-
tation, the UNETR model by Said et al. [44] achieved a notable accuracy of 97.83%. In the
context of breast cancer, Umer et al.’s [61] custom CNN model attained the best classifi-
cation accuracy at 99.89%. Segmentation tasks for breast cancer were effectively handled
by the OMLTS-DLCN model by Kavitha et al. [51], which recorded accuracy of 98.50%
on the Mini-MIAS dataset and 97.56% on the CBIS-DDSM dataset. For brain cancer, the
DOBES model by Sharma et al. [72] reached an accuracy of 99.98% for tumor segmentation,
while for classification tasks, Saha et al.’s [76] BCM-VEMT model demonstrated the highest
accuracy of 98.42%. For cervical cancer, the DeepPap model by Zhang et al. [81] achieved
the highest classification accuracy at 98.30%, and Guo et al. [84] reported a significant
cervical cancer segmentation accuracy of 93.80% using the DeTr model. Colorectal cancer
analysis showed that the InceptionResNetV2 model by Tamang et al. [97] achieved the best
classification accuracy at 97.65%, while the ABC-Net model by Fang et al. [100] attained
an average segmentation accuracy of 98.80%. For liver cancer, the En-DeNet model by
Suganeshwari et al. [111] achieved the highest classification accuracy at 97.86%, and the
U-Net model proposed by Araújo et al. [113] recorded a segmentation accuracy of 97.66%.
The application of ML in cancer diagnosis offers several promising opportunities,
such as early detection and diagnosis and personalized treatment plans. However, several
challenges must be addressed to fully realize the potential of ML in cancer care. The per-
formance of ML models heavily depends on the quality and quantity of data available for
training. Issues such as data fragmentation, inconsistent annotations, and privacy concerns
limit the accessibility of high-quality datasets. Moreover, many ML models, especially
deep learning algorithms, operate as “black boxes”, making it difficult to understand the
reasoning behind their predictions. This lack of transparency poses a barrier to clinical
adoption, as healthcare providers need to trust and understand the tools they use. Ad-
ditionally, training and deploying ML models require substantial computational power,
which may not be readily available in all clinical settings, while the use of patient data in
ML models raises ethical and legal issues related to privacy, consent, and data security.
Addressing these concerns is crucial to widespread adoption, maintaining patient trust,
and complying with regulations.
Future research should concentrate on enhancing data quality through standardized
protocols for collection and annotation, alongside employing techniques like data augmen-
tation and synthetic data generation to address data scarcity for rare cancers. Efforts to
increase model transparency with explainable AI are crucial for fostering trust among clini-
cians and patients. Additionally, optimizing computational efficiency through hardware
and software innovations can make ML models more practical for clinical applications.
Lastly, addressing ethical concerns by developing robust frameworks for data privacy,
informed consent, and algorithmic fairness is essential for the responsible deployment of
ML in healthcare.
One critical observation from the reviewed studies is the lack of emphasis on model
interpretability. Despite the increasing complexity and accuracy of ML models in cancer
diagnosis, most authors did not employ widely recognized interpretability techniques such
as SHAP, LIME, Grad-CAM, or Score-CAM. These methods are essential for providing
Electronics 2024, 13, 4697 34 of 40

transparency and explaining how the models arrive at their predictions, especially in high-
stakes fields like healthcare, where clinical decisions must be well understood and trusted
by practitioners. By incorporating these interpretability methods, future studies can offer
more insights into model behavior, improve clinician trust in AI systems, and make the
models more suitable for real-world medical applications. Addressing this gap will be
crucial for the responsible deployment of ML models in clinical settings.

7. Conclusions
The integration of AI and ML techniques in cancer analysis has shown significant
promise in enhancing the accuracy, efficiency, and effectiveness of cancer diagnosis, prog-
nosis, and treatment. This paper highlights the transformative potential of ML applications
across various cancer types, focusing on lung, breast, brain, cervical, colorectal, and liver
cancers. Despite the advancements, the implementation of ML in clinical settings encoun-
ters several challenges that have been identified. Issues related to data quality, model
interpretability, and ethical considerations need to be addressed to ensure the safe and
effective use of ML in cancer care. ML offers a potent set of tools for advancing cancer
diagnosis, prognosis, and treatment. While significant progress has been made, ongoing
research and innovation are crucial to fully employ the potential of ML in improving cancer
care and patient outcomes. The insights gained from this comprehensive review underscore
the importance of integrating ML into clinical practice, paving the way for more accurate,
efficient, and personalized cancer care solutions.

Author Contributions: Conceptualization, A.I.D.; methodology, A.I.D.; investigation, A.I.D.; re-

sources, A.I.D.; data curation, A.I.D.; writing—original draft preparation, A.I.D.; writing—review
and editing, A.I.D. and C.B.; supervision, C.B. All authors have read and agreed to the published
version of the manuscript.
Funding: This research received no external funding.
Data Availability Statement: No new data were created or analyzed in this study. Data sharing is
not applicable to this article.
Conflicts of Interest: The authors declare no conflicts of interest.

Abbreviations
Abbreviation Definition
ABC area-boundary constraint
AI artificial intelligence
ALTS ASCUS/LSIL Triage Study
ANN artificial neural network
ASCUS atypical squamous cells of undetermined significance
AUC area under curve
BES bald eagle search
BPNN backpropagation neural network
BUSI breast ultrasound image
CARTs classification and regression trees
CBIS curated breast imaging subset
CLAHE contrast limited adaptive histogram equalization
CNN convolutional neural network
CRC colorectal cancer
CS cuckoo search
CT computed tomography
DDSM Digital Database for Screening Mammography
DICOM Digital Imaging and Communications in Medicine
DL deep learning
DLCN deep learning capsule network
DNN deep neural network
DOBES dynamic opposite bald eagle search
Electronics 2024, 13, 4697 35 of 40

DOL dynamic opposition learning

DSC dice similarity coefficient
EHR electronic health record
EL ensemble learning
FFN feedforward network
FN false negative
FP false positive
GBM gradient boosting machines
GDPR general data protection regulation
GMMs Gaussian mixture models
Grad-CAM gradient-weighted class activation mapping
HCC hepatocellular carcinoma
HD Hausdorff distance
HHO Harris hawks optimization
HTL hybrid transfer learning
LBC liquid-based cytology
LIME local interpretable model-agnostic explanations
LNM lymph node metastases
LSIL low-grade squamous intraepithelial lesion
MA multi-scale attention
MIAS Mammographic Image Analysis Society
ML machine learning
MR magnetic resonance
MRI magnetic resonance imaging
NHS natural history study
OKMT optimal Kapur’s multilevel thresholding
OMLTS optimal multi-level thresholding-based segmentation
OS overall survival
PCA principal component analysis
PET positron emission tomography
PPV positive predictive values
PR precision–recall
RBF radial basis function
RCNN region-based CNN
ROC receiver operating characteristic
ROI region of interest
Score-CAM score-weighted class activation mapping
SE squeeze and excitation
SEER Surveillance, Epidemiology, and End Results
SGO shell game optimization
SHAP Shapley additive explanation
SKMs selective kernel modules
SL supervised learning
SMOTE synthetic minority over-sampling technique
SNR suspected nodule regions
SSL semi-supervised learning
SVM support vector machine
TCGA The Cancer Genome Atlas
TL transfer learning
TN true negative
TP true positive
TS tactile sensor
UL unsupervised learning
US ultrasound
VGG visual geometry group
VS vision-based surface
WHO World Health Organization
WSIs whole-slide images
Electronics 2024, 13, 4697 36 of 40

References
1. Bray, F.; Laversanne, M.; Sung, H.; Ferlay, J.; Siegel, R.L.; Soerjomataram, I.; Jemal, A. Global cancer statistics 2022: GLOBOCAN
estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J. Clin. 2024, 74, 229–263. [CrossRef]
[PubMed]
2. Siegel, R.L.; Giaquinto, A.N.; Jemal, A. Cancer statistics, 2024. CA Cancer J. Clin. 2024, 74, 12–49. [CrossRef] [PubMed]
3. Manhas, J.; Gupta, R.K.; Roy, P.P. A Review on Automated Cancer Detection in Medical Images using Machine Learning and
Deep Learning based Computational Techniques: Challenges and Opportunities. Arch. Comput. Methods Eng. 2022, 29, 2893–2933.
[CrossRef]
4. Panayides, A.S.; Amini, A.; Filipovic, N.D.; Sharma, A.; Tsaftaris, S.A.; Young, A.; Foran, D.; Do, N.; Golemati, S.; Kurç, T.; et al.
AI in medical imaging informatics: Current challenges and future directions. IEEE J. Biomed. Health Inform. 2020, 24, 1837–1857.
[CrossRef]
5. Tian, Y.; Fu, S. A descriptive framework for the field of deep learning applications in medical images. Knowl.-Based Syst. 2020, 210,
106445. [CrossRef]
6. Suckling, J. Medical image processing. In Webb’s Physics of Medical Imaging 2016, 2nd ed.; CRC Press: Boca Raton, FL, USA, 2016;
pp. 713–738. [CrossRef]
7. Debongnie, J.C.; Pauls, C.; Fievez, M.; Wibin, E. Prospective evaluation of the diagnostic accuracy of liver ultrasonography. Gut
1981, 22, 130–135. [CrossRef]
8. Wan, Y.; Wang, D.; Li, H.; Xu, Y. The imaging techniques and diagnostic performance of ultrasound, CT, and MRI in detecting
liver steatosis and fat quantification: A systematic review. J. Radiat. Res. Appl. Sci. 2023, 16, 100658. [CrossRef]
9. Kim, H.S.; Lee, K.S.; Ohno, Y.; Van Beek, E.J.R.; Biederer, J. PET/CT versus MRI for diagnosis, staging, and follow-up of lung
cancer. J. Magn. Reson. Imaging 2015, 42, 247–260. [CrossRef]
10. de Savornin Lohman, E.A.J.; de Bitter, T.J.J.; van Laarhoven, C.J.H.M.; Hermans, J.J.; de Haas, R.J.; de Reuver, P.R. The diagnostic
accuracy of CT and MRI for the detection of lymph node metastases in gallbladder cancer: A systematic review and meta-analysis.
Eur. J. Radiol. 2019, 110, 156–162. [CrossRef]
11. Fiocca, R.; Ceppa, P. Endoscopic biopsies. J. Clin. Pathol. 2003, 56, 321–322. [CrossRef]
12. Ahn, J.H. An update on the role of bronchoscopy in the diagnosis of pulmonary disease. Yeungnam Univ. J. Med. 2020, 37, 253–261.
[CrossRef] [PubMed]
13. Stauffer, C.M.; Pfeifer, C. Colonoscopy. StatPearls [Internet]. 2024. Available online: https://www.ncbi.nlm.nih.gov/books/
NBK559274 (accessed on 20 January 2024).
14. Mahmoud, N.; Vashisht, R.; Sanghavi, D.K.; Kalanjeri, S.; Bronchoscopy. StatPearls [Internet]. 2024. Available online: https:
//www.ncbi.nlm.nih.gov/books/NBK448152 (accessed on 20 January 2024).
15. Gillies, R.J.; Kinahan, P.E.; Hricak, H. Radiomics: Images are more than pictures, they are data. Radiology 2016, 278, 563–577.
[CrossRef] [PubMed]
16. Sharma, A.; Saurabh, S. Medical image preprocessing: A literature review. Int. J. Comput. Intell. Res. 2020, 16, 5–20.
17. Litjens, G.; Kooi, T.; Bejnordi, B.E.; Setio, A.A.A.; Ciompi, F.; Ghafoorian, M.; van Ginneken, B. A survey on deep learning in
medical image analysis. Med. Image Anal. 2017, 42, 60–88. [CrossRef]
18. Franklin, J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Math. Intell. 2005, 27, 83–85. [CrossRef]
19. Chen, T.; Guestrin, C. XGBoost: A scalable tree boosting system. In Proceedings of the ACM SIGKDD International Conference
on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August 2016; pp. 785–794. [CrossRef]
20. Goodfellow, I.; Bengio, Y.; Courville, A. Deep Learning; MIT Press: Cambridge, MA, USA, 2016. Available online: http://www.
deeplearningbook.org (accessed on 20 January 2024).
21. Simonyan, K.; Zisserman, A. Very deep convolutional networks for large-scale image recognition. In Proceedings of the 3rd
International Conference on Learning Representations, ICLR 2015—Conference Track Proceedings, San Diego, CA, USA, 7–9 May
2015; pp. 1–14. [CrossRef]
22. Ronneberger, O.; Fischer, P.; Brox, T. U-Net: Convolutional networks for biomedical image segmentation. arXiv 2015. [CrossRef]
23. He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Computer Society
Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 770–778. [CrossRef]
24. Naser, M.Z.; Alavi, A.H. Error metrics and performance fitness indicators for artificial intelligence and machine learning in
engineering and sciences. Archit. Struct. Constr. 2023, 3, 499–517. [CrossRef]
25. Maurya, S.; Tiwari, S.; Mothukuri, M.C.; Tangeda, C.M.; Nandigam, R.N.S.; Addagiri, D.C. A review on recent developments in
cancer detection using machine learning and deep learning models. Biomed. Signal Process. Control 2023, 80, 104398. [CrossRef]
26. Faghani, S.; Khosravi, B.; Zhang, K.; Moassefi, M.; Jagtap, J.M.; Nugen, F.; Vahdati, S.; Kuanar, S.P.; Rassoulinejad-Mousavi, S.M.;
Singh, Y.; et al. Mitigating bias in radiology machine learning: 3. Performance metrics. Radiol. Artif. Intell. 2022, 4, e220061.
[CrossRef]
27. Erickson, B.J.; Kitamura, F. Magician’s corner: 9. Performance metrics for machine learning models. Radiol. Artif. Intell. 2021, 3,
e200126. [CrossRef]
28. Lundberg, S.M.; Lee, S.-I. A unified approach to interpreting model predictions. arXiv 2017. [CrossRef]
Electronics 2024, 13, 4697 37 of 40

29. Ribeiro, M.T.; Singh, S.; Guestrin, C. “Why should I trust you?” Explaining the predictions of any classifier. In Proceedings of the
22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August
2016; pp. 1135–1144. [CrossRef]
30. Selvaraju, R.R.; Cogswell, M.; Das, A.; Vedantam, R.; Parikh, D.; Batra, D. Grad-CAM: Visual explanations from deep networks
via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 22–29
October 2017; pp. 618–626. [CrossRef]
31. Wang, H.; Wang, Z.; Du, M.; Yang, F.; Zhang, Z.; Ding, S.; Mardziel, P. Score-CAM: Score-weighted Visual Explanations for
Convolutional Neural Networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
Workshops (CVPRW), Seattle, WA, USA, 14–19 June 2020. Available online: https://arxiv.org/abs/1910.01279 (accessed on 20
January 2024).
32. American Cancer Society. Key Statistics for Lung Cancer. 2017. Available online: https://www.cancer.org/cancer/non-small-
cell-lung-cancer/about/key-statistics.html (accessed on 14 February 2024).
33. American Cancer Society. Cancer Facts and Figures 2017. 2017. Available online: https://www.cancer.org/content/dam/cancer-
org/research/cancer-facts-and-statistics/annualcancer-facts-and-figures/2017/cancer-facts-and-figures-2017.pdf (accessed on
14 February 2024).
34. Jassim, O.A.; Abed, M.J.; Saied, Z.H. Deep learning techniques in the cancer-related medical domain: A transfer deep learning
ensemble model for lung cancer prediction. Baghdad Sci. J. 2024, 21, 1101–1118. [CrossRef]
35. Hany, M. Chest CT-Scan Images Dataset. Kaggle. 2020. Available online: https://www.kaggle.com/datasets/mohamedhanyyy/
chest-ctscan-images (accessed on 14 February 2024).
36. Muhtasim, N.; Hany, U.; Islam, T.; Nawreen, N.; Al Mamun, A. Artificial intelligence for detection of lung cancer using transfer
learning and morphological features. J. Supercomput. 2024, 80, 13576–13606. [CrossRef]
37. Al-Yasriy, H.F.; Al-Husieny, M.S.; Mohsen, F.Y.; Khalil, E.A.; Hassan, Z.S. Diagnosis of lung cancer based on CT scans using CNN.
IOP Conf. Ser. Mater. Sci. Eng. 2020, 928, 022035. [CrossRef]
38. Luo, S. Lung cancer classification using reinforcement learning-based ensemble learning. Int. J. Adv. Comput. Sci. Appl. 2023, 14,
1112–1122. [CrossRef]
39. Armato, I.; Samuel, G.; McLennan, G.; Bidaut, L.; McNitt-Gray, M.F.; Meyer, C.R.; Reeves, A.P.; Clarke, L.P. Data from LIDC-IDRI
[Data Set]; The Cancer Imaging Archive: Palo Alto, CA, USA, 2015. [CrossRef]
40. Mamun, M.; Farjana, A.; Al Mamun, M.; Ahammed, M.S. Lung cancer prediction model using ensemble learning techniques and
a systematic review analysis. In Proceedings of the 2022 IEEE World AI IoT Congress (AIIoT 2022), Seattle, WA, USA, 6–9 June
2022; pp. 187–193. [CrossRef]
41. Das, S. Lung Cancer Dataset—Does Smoking Cause Lung Cancer. Kaggle. 2022. Available online: https://www.kaggle.com/
datasets/shuvojitdas/lung-cancer-dataset (accessed on 14 February 2024).
42. Venkatesh, S.P.; Raamesh, L. Predicting lung cancer survivability: A machine learning ensemble method on SEER data. Int.
J. Cancer Res. Ther. 2023, 8, 148–154. [CrossRef]
43. Altekruse, S.F.; Rosenfeld, G.E.; Carrick, D.M.; Pressman, E.J.; Schully, S.D.; Mechanic, L.E.; Cronin, K.A.; Hernandez, B.Y.; Lynch,
C.F.; Cozen, W.; et al. SEER cancer registry biospecimen research: Yesterday and tomorrow. Cancer Epidemiol. Biomark. Prev. 2014,
23, 2681–2687. [CrossRef]
44. Said, Y.; Alsheikhy, A.A.; Shawly, T.; Lahza, H. Medical images segmentation for lung cancer diagnosis based on deep learning
architectures. Diagnostics 2023, 13, 546. [CrossRef]
45. Antonelli, M.; Reinke, A.; Bakas, S.; Farahani, K.; Kopp-Schneider, A.; Landman, B.A.; Litjens, G.; Menze, B.; Ronneberger, O.;
Summers, R.M.; et al. The medical segmentation decathlon. Nat. Commun. 2022, 13, 4128. [CrossRef]
46. Siegel, R.L.; Miller, K.D.; Jemal, A. Cancer statistics, 2019. CA Cancer J. Clin. 2019, 69, 7–34. [CrossRef]
47. World Health Organization. Global Cancer Burden Growing, Amidst Mounting Need for Services. 2024. Available online:
https://www.who.int/news/item/01-02-2024-global-cancer-burden-growing--amidst-mounting-need-for-services (accessed
on 6 March 2024).
48. Oeffinger, K.C.; Fontham, E.T.; Etzioni, R.; Herzig, A.; Michaelson, J.S.; Shih, Y.C.T.; Walter, L.C.; Church, T.R.; Flowers, C.R.;
LaMonte, S.J.; et al. Breast cancer screening for women at average risk: 2015 guideline update from the American Cancer Society.
JAMA 2015, 314, 1599–1614. [CrossRef] [PubMed]
49. Stower, H. AI for breast-cancer screening. Nat. Med. 2020, 26, 163. [CrossRef]
50. Interlenghi, M.; Salvatore, C.; Magni, V.; Caldara, G.; Schiavon, E.; Cozzi, A.; Schiaffino, S.; Carbonaro, L.A.; Castiglioni, I.;
Sardanelli, F. A Machine Learning Ensemble Based on Radiomics to Predict BI-RADS Category and Reduce the Biopsy Rate of
Ultrasound-Detected Suspicious Breast Masses. Diagnostics 2022, 12, 187. [CrossRef]
51. Kavitha, T.; Mathai, P.P.; Karthikeyan, C.; Ashok, M.; Kohar, R.; Avanija, J.; Neelakandan, S. Deep learning based capsule neural
network model for breast cancer diagnosis using mammogram images. Interdiscip. Sci. Comput. Life Sci. 2022, 14, 113–129.
[CrossRef] [PubMed]
52. Ionkina, K.; Svistunov, A.; Galin, I.; Onykiy, B.; Pronicheva, L. MIAS database semantic structure. Procedia Comput. Sci. 2018, 145,
254–259. [CrossRef]
53. Sawyer-Lee, R.; Gimenez, F.; Hoogi, A.; Rubin, D. Curated Breast Imaging Subset of Digital Database for Screening Mammography
(CBIS-DDSM) [Data Set]; The Cancer Imaging Archive: Palo Alto, CA, USA, 2016. [CrossRef]
Electronics 2024, 13, 4697 38 of 40

54. Chen, G.; Liu, Y.; Qian, J.; Zhang, J.; Yin, X.; Cui, L.; Dai, Y. DSEU-net: A novel deep supervision SEU-net for medical ultrasound
image segmentation. Expert Syst. Appl. 2023, 223, 119939. [CrossRef]
55. Al-Dhabyani, W.; Gomaa, M.; Khaled, H.; Fahmy, A. Dataset of breast ultrasound images. Data Brief 2020, 28, 104863. [CrossRef]
56. Dogiwal, S.R. Breast cancer prediction using supervised machine learning techniques. J. Inf. Optim. Sci. 2023, 44, 383–392.
57. Wolberg, W.; Mangasarian, O.; Street, N.; Street, W. Breast Cancer Wisconsin (Diagnostic); UCI Machine Learning Repository: Irvine,
CA, USA, 1995. [CrossRef]
58. Al-Azzam, N.; Shatnawi, I. Comparing supervised and semi-supervised machine learning models on diagnosing breast cancer.
Ann. Med. Surg. 2021, 62, 53–64. [CrossRef]
59. Ayana, G.; Park, J.; Jeong, J.W.; Choe, S.W. A novel multistage transfer learning for ultrasound breast cancer image classification.
Diagnostics 2022, 12, 135. [CrossRef]
60. Rodrigues, P.S. Breast Ultrasound Image. Mendeley Data 2017, V1. Available online: https://data.mendeley.com/datasets/
wmy84gzngw/1 (accessed on 24 November 2024).
61. Umer, M.; Naveed, M.; Alrowais, F.; Ishaq, A.; Hejaili, A.A.; Alsubai, S.; Eshmawi, A.A.; Mohamed, A.; Ashraf, I. Breast Cancer
Detection Using Convoluted Features and Ensemble Machine Learning Algorithm. Cancers 2022, 14, 6015. [CrossRef]
62. Hekal, A.A.; Moustafa, H.E.D.; Elnakib, A. Ensemble deep learning system for early breast cancer detection. Evol. Intell. 2023, 16,
1045–1054. [CrossRef]
63. Deb, S.D.; Jha, R.K. Segmentation of mammogram images using deep learning for breast cancer detection. In Proceedings of the
2022 2nd International Conference on Image Processing and Robotics (ICIPRob), Colombo, Sri Lanka, 12–13 March 2022; pp. 1–6.
[CrossRef]
64. Moreira, I.C.; Amaral, I.; Domingues, I.; Cardoso, A.; Cardoso, M.J.; Cardoso, J.S. INBreast: Toward a full-field digital mammo-
graphic database. Acad. Radiol. 2012, 19, 236–248. [CrossRef]
65. Haris, U.; Kabeer, V.; Afsal, K. Breast cancer segmentation using hybrid HHO-CS SVM optimization techniques. Multimed. Tools
Appl. 2024, 83, 69145–69167. [CrossRef]
66. Walker, D.; Hamilton, W.; Walter, F.M.; Watts, C. Strategies to accelerate diagnosis of primary brain tumors at the primary-
secondary care interface in children and adults. CNS Oncol. 2013, 2, 447–462. [CrossRef]
67. Hanif, F.; Muzaffar, K.; Perveen, K.; Malhi, S.M.; Simjee, S.U. Glioblastoma multiforme: A review of its epidemiology and
pathogenesis through clinical presentation and treatment. Asian Pac. J. Cancer Prev. 2017, 18, 3–9. [CrossRef]
68. Khan, M.; Shah, S.A.; Ali, T.; Quratulain; Khan, A.; Choi, G.S. Brain tumor detection and segmentation using RCNN. Comput.
Mater. Contin. 2022, 71, 5005–5020. [CrossRef]
69. Menze, B.H.; Jakab, A.; Bauer, S.; Kalpathy-Cramer, J.; Farahani, K.; Kirby, J.; Burren, Y.; Porz, N.; Slotboom, J.; Wiest, R.; et al. The
multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans. Med. Imaging 2015, 34, 1993–2024. [CrossRef]
70. Bakas, S.; Akbari, H.; Sotiras, A.; Bilello, M.; Rozycki, M.; Kirby, J.S.; Freymann, J.B.; Farahani, K.; Davatzikos, C. Advancing
The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features. Nat. Sci. Data 2017, 4,
170117. [CrossRef]
71. Bakas, S.; Reyes, M.; Jakab, A.; Bauer, S.; Rempfler, M.; Crimi, A.; Shinohara, R.T.; Berger, C.; Ha, S.M.; Rozycki, M.; et al.
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction
in the BRATS Challenge; Apollo—University of Cambridge Repository: Cambridge, UK, 2018. [CrossRef]
72. Sharma, S.R.; Alshathri, S.; Singh, B.; Kaur, M.; Mostafa, R.R.; El-Shafai, W. Hybrid multilevel thresholding image segmentation
approach for brain MRI. Diagnostics 2023, 13, 925. [CrossRef]
73. Brima, Y.; Hossain, M.; Tushar, K.; Kabir, U.; Islam, T. Brain MRI Dataset [Data Set]; Figshare: London, UK, 2021. [CrossRef]
74. Ngo, D.K.; Tran, M.T.; Kim, S.H.; Yang, H.J.; Lee, G.S. Multi-task learning for small brain tumor segmentation from MRI. Appl. Sci.
2020, 10, 7790. [CrossRef]
75. Ullah, F.; Nadeem, M.; Abrar, M.; Amin, F.; Salam, A.; Alabrah, A.; AlSalman, H. Evolutionary Model for Brain Cancer-Grading
and Classification. IEEE Access 2023, 11, 126182–126194. [CrossRef]
76. Saha, P.; Das, R.; Das, S.K. BCM-VEMT: Classification of brain cancer from MRI images using deep learning and ensemble of
machine learning techniques. Multimed. Tools Appl. 2023, 82, 44479–44506. [CrossRef]
77. Cheng, J. Brain Tumor Dataset [Data Set]. Figshare. 2017. Available online: https://figshare.com/articles/dataset/brain_tumor_
dataset/1512427 (accessed on 25 March 2024).
78. Chakrabarty, N. Brain MRI Images for Brain Tumor Detection [Data Set]. Kaggle. 2019. Available online: https://www.kaggle.
com/datasets/navoneel/brain-mri-images-for-brain-tumor-detection (accessed on 25 March 2024).
79. Bhuvaji, S.; Kadam, A.; Bhumkar, P.; Dedge, S.; Kanchan, S. Brain Tumor Classification (MRI) [Data Set]; Kaggle: San Francisco, CA,
USA, 2020. [CrossRef]
80. Kessler, T.A. Cervical cancer: Prevention and early detection. Semin. Oncol. Nurs. 2017, 33, 172–183. [CrossRef]
81. Zhang, L.; Lu, L.; Nogues, I.; Summers, R.M.; Liu, S.; Yao, J. DeepPap: Deep convolutional networks for cervical cell classification.
IEEE J. Biomed. Health Inform. 2017, 21, 1633–1643. [CrossRef]
82. Albuquerque, T.; Cruz, R.; Cardoso, J.S. Ordinal losses for classification of cervical cancer risk. PeerJ Comput. Sci. 2021, 7, 1–21.
[CrossRef]
83. Hussain, E.; Mahanta, L.B.; Borah, H.; Das, C.R. Liquid based-cytology Pap smear dataset for automated multi-class diagnosis of
pre-cancerous and cervical cancer lesions. Data Brief 2020, 30, 105589. [CrossRef]
Electronics 2024, 13, 4697 39 of 40

84. Guo, P.; Xue, Z.; Angara, S.; Antani, S.K. Unsupervised deep learning registration of uterine cervix sequence images. Cancers 2022,
14, 2401. [CrossRef]
85. Herrero, R.; Hildesheim, A.; Rodríguez, A.C.; Wacholder, S.; Bratti, C.; Solomon, D.; González, P.; Porras, C.; Jiménez, S.; Guillen,
D.; et al. Rationale and design of a community-based double-blind randomized clinical trial of an HPV 16 and 18 vaccine in
Guanacaste, Costa Rica. Vaccine 2008, 26, 4795–4808. [CrossRef]
86. Herrero, R.; Wacholder, S.; Rodríguez, A.C.; Solomon, D.; González, P.; Kreimer, A.R.; Porras, C.; Schussler, J.; Jiménez, S.;
Sherman, M.E.; et al. Prevention of persistent human papillomavirus infection by an HPV16/18 vaccine: A community-based
randomized clinical trial in Guanacaste, Costa Rica. Cancer Discov. 2011, 1, 408–419. [CrossRef]
87. The Atypical Squamous Cells of Undetermined Significance/Low-Grade Squamous Intraepithelial Lesions Triage Study (ALTS)
Group. Human papillomavirus testing for triage of women with cytologic evidence of low-grade squamous intraepithelial
lesions: Baseline data from a randomized trial. J. Natl. Cancer Inst. 2000, 92, 397–402. [CrossRef]
88. Intel & MobileODT Cervical Cancer Screening Competition. (2017, March). Kaggle. Available online: https://www.kaggle.com/
c/intel-mobileodt-cervical-cancer-screening (accessed on 15 May 2024).
89. Angara, S.; Guo, P.; Xue, Z.; Antani, S. Semi-supervised learning for cervical precancer detection. In Proceedings of the 2021
IEEE 34th International Symposium on Computer-Based Medical Systems (CBMS), Aveiro, Portugal, 7–9 June 2021; pp. 202–206.
[CrossRef]
90. Kudva, V.; Prasad, K.; Guruvare, S. Transfer learning for classification of uterine cervix images for cervical cancer screening. Lect.
Notes Electr. Eng. 2020, 614, 299–312. [CrossRef]
91. Ahishakiye, E.; Wario, R.; Mwangi, W.; Taremwa, D. Prediction of cervical cancer basing on risk factors using ensemble learning.
In Proceedings of the 2020 IST-Africa Conference (IST-Africa 2020), Kampala, Uganda, 18–22 May 2020.
92. Hodneland, E.; Kaliyugarasan, S.; Wagner-Larsen, K.S.; Lura, N.; Andersen, E.; Bartsch, H.; Smit, N.; Halle, M.K.; Krakstad,
C.; Lundervold, A.S.; et al. Fully Automatic Whole-Volume Tumor Segmentation in Cervical Cancer. Cancers 2022, 14, 2372.
[CrossRef]
93. World Health Organization. Cancer. 2022. Available online: https://www.who.int/news-room/fact-sheets/detail/cancer
(accessed on 15 May 2024).
94. Guo, J.; Cao, W.; Nie, B.; Qin, Q. Unsupervised learning composite network to reduce training cost of deep learning model for
colorectal cancer diagnosis. IEEE J. Transl. Eng. Health Med. 2023, 11, 54–59. [CrossRef] [PubMed]
95. Zhou, C.; Jin, Y.; Chen, Y.; Huang, S.; Huang, R.; Wang, Y.; Zhao, Y.; Chen, Y.; Guo, L.; Liao, J. Histopathology classification and
localization of colorectal cancer using global labels by weakly supervised deep learning. Comput. Med. Imaging Graph. 2021, 88,
101861. [CrossRef]
96. Venkatayogi, N.; Kara, O.C.; Bonyun, J.; Ikoma, N.; Alambeigi, F. Classification of colorectal cancer polyps via transfer learning
and vision-based tactile sensing. In Proceedings of the 2022 IEEE Sensors, Dallas, TX, USA, 8 December 2022; pp. 1–4. [CrossRef]
97. Tamang, L.D.; Kim, M.T.; Kim, S.J.; Kim, B.W. Tumor-stroma classification in colorectal cancer patients with transfer learning
based binary classifier. In Proceedings of the 2021 International Conference on Information and Communication Technology
Convergence (ICTC), Jeju Island, Republic of Korea, 20–22 October 2021; pp. 1645–1648. [CrossRef]
98. Kather, J.N.; Weis, C.A.; Bianconi, F.; Melchers, S.M.; Schad, L.R.; Gaiser, T.; Marx, A.; Zöllner, F.G. Multi-class texture analysis in
colorectal cancer histology. Sci. Rep. 2016, 6, 27988. [CrossRef]
99. Liu, Y.; Wang, J.; Wu, C.; Liu, L.; Zhang, Z.; Yu, H. Fovea-UNet: Detection and segmentation of lymph node metastases in
colorectal cancer with deep learning. Biomed. Eng. Online 2023, 22, 74. [CrossRef]
100. Fang, Y.; Zhu, D.; Yao, J.; Yuan, Y.; Tong, K.Y. ABC-Net: Area-boundary constraint network with dynamical feature selection for
colorectal polyp segmentation. IEEE Sens. J. 2021, 21, 11799–11809. [CrossRef]
101. Vázquez, D.; Bernal, J.; Sánchez, F.J.; Fernández-Esparrach, G.; López, A.M.; Romero, A.; Drozdzal, M.; Courville, A. A benchmark
for endoluminal scene segmentation of colonoscopy images. J. Healthc. Eng. 2017, 2017, 4037190. [CrossRef]
102. Jha, D.; Smedsrud, P.H.; Riegler, M.A.; Halvorsen, P.; Lange, T.D.; Johansen, D.; Johansen, H.D. Kvasir-SEG: A segmented polyp
dataset. In Proceedings of the 26th International Conference on Multimedia Modeling, Daejeon, Republic of Korea, 5–8 January
2020; pp. 451–462. [CrossRef]
103. Silva, J.S.; Histace, A.; Romain, O.; Dray, X.; Granado, B. Toward embedded detection of polyps in WCE images for early diagnosis
of colorectal cancer. Int. J. Comput. Assist. Radiol. Surg. 2014, 9, 283–293. [CrossRef]
104. Elkarazle, K.; Raman, V.; Then, P.; Chua, C. Improved colorectal polyp segmentation using enhanced MA-NET and modified
Mix-ViT transformer. IEEE Access 2023, 11, 69295–69309. [CrossRef]
105. Bernal, J.; Sánchez, F.J.; Fernández-Esparrach, G.; Gil, D.; Rodríguez, C.; Vilariño, F. WM-DOVA maps for accurate polyp
highlighting in colonoscopy: Validation vs. saliency maps from physicians. Comput. Med. Imaging Graph. 2015, 43, 99–111.
[CrossRef]
106. Bernal, J.; Sánchez, J.; Vilariño, F. Towards automatic polyp detection with a polyp appearance model. Pattern Recognit. 2012, 45,
3166–3182. [CrossRef]
107. Arnold, M.; Abnet, C.C.; Neale, R.E.; Vignat, J.; Giovannucci, E.L.; McGlynn, K.A.; Bray, F. Global burden of 5 major types of
gastrointestinal cancer. Gastroenterology 2020, 159, 335–349. [CrossRef]
108. Masuzaki, R. Liver cancer: Improving standard diagnosis and therapy. Cancers 2023, 15, 4602. [CrossRef]
Electronics 2024, 13, 4697 40 of 40

109. Napte, K.; Mahajan, A.; Urooj, S. ESP-UNet: Encoder-decoder convolutional neural network with edge-enhanced features for
liver segmentation. Trait. Du Signal 2023, 40, 2275–2281. [CrossRef]
110. Bilic, P.; Christ, P.; Li, H.B.; Vorontsov, E.; Ben-Cohen, A.; Kaissis, G.; Szeskin, A.; Jacobs, C.; Mamani, G.E.H.; Chartrand, G.; et al.
The liver tumor segmentation benchmark (LiTS). Med. Image Anal. 2023, 84, 102680. [CrossRef]
111. Suganeshwari, G.; Appadurai, J.P.; Kavin, B.P.; Kavitha, C.; Lai, W.C. En–DeNet based segmentation and gradational modular
network classification for liver cancer diagnosis. Biomedicines 2023, 11, 1309. [CrossRef]
112. Soler, L.; Hostettler, A.; Agnus, V.; Charnoz, A.; Fasquel, J.; Moreau, J.; Osswald, A.; Bouhadjar, M.; Marescaux, J. 3D Image
Reconstruction for Comparison of Algorithm Database: A Patient Specific Anatomical and Medical Image Database. IRCAD. 2010.
Available online: https://www.ircad.fr/research/data-sets/liver-segmentation-3d-ircadb-01 (accessed on 24 November 2024).
113. Araújo, J.D.L.; da Cruz, L.B.; Diniz, J.O.B.; Ferreira, J.L.; Silva, A.C.; de Paiva, A.C.; Gattass, M. Liver segmentation from computed
tomography images using cascade deep learning. Comput. Biol. Med. 2022, 140, 105095. [CrossRef] [PubMed]
114. Badawy, S.M.; Mohamed, A.E.-N.A.; Hefnawy, A.A.; Zidan, H.E.; GadAllah, M.T.; El-Banby, G.M. Automatic semantic segmenta-
tion of breast tumors in ultrasound images based on combining fuzzy logic and deep learning—A feasibility study. PLoS ONE
2021, 16, e0251899. [CrossRef] [PubMed]
115. United States Government Accountability Office. Artificial Intelligence in Health Care: Benefits and Challenges of Machine Learning
Technologies for Medical Diagnostics; United States Government Accountability Office: Washington, DC, USA, 2022; pp. 3–30.
Available online: https://www.gao.gov/assets/gao-22-104629.pdf (accessed on 24 November 2024).
116. Sebastian, A.M.; Peter, D. Artificial intelligence in cancer research: Trends, challenges and future directions. Life 2022, 12, 1991.
[CrossRef] [PubMed]
117. Ellis, R.J.; Sander, R.M.; Limon, A. Twelve key challenges in medical machine learning and solutions. Intell. Med. 2022, 6, 100068.
[CrossRef]
118. Maleki, F.; Muthukrishnan, N.; Ovens, K.; Reinhold, C.; Forghani, R. Machine learning algorithm validation: From essentials to
advanced applications and implications for regulatory certification and deployment. Neuroimaging Clin. N. Am. 2020, 30, 433–445.
[CrossRef] [PubMed]
119. Shreve, J.T.; Khanani, S.A.; Haddad, T.C. Artificial intelligence in oncology: Current capabilities, future opportunities, and ethical
considerations. ASCO Educ. Book 2022, 42, 842–851. [CrossRef]
120. Carter, S.M.; Rogers, W.; Win, K.T.; Frazer, H.; Richards, B.; Houssami, N. The ethical, legal and social implications of using
artificial intelligence systems in breast cancer care. Breast 2020, 49, 25–32. [CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.