MALLA REDDY COLLEGE OF ENGINEERING & TECHNOLOGY
DEPARTMENT OF INFORMATION TECHNOLOGY
CLASSIFICATION OF PNEUMONIA AMONG CHEST X-RAYS
USING CNN
Year / Sem : IV B.Tech / I Sem
Presented by:
21N31A12G2 – R.Siddartha Reddy Guided By :
21N31A12J6 – V.Mounika
Mr. P. Harikrishna
Asst professor
Batch: 07
1
AGENDA
1.ABSTRACT
2.INTRODUCTION
3.EXISTING SYSTEM
4.PROPOSED SYSTEM
5.FUNCTIONAL AND NON-FUNCTIONAL REQUIREMENTS
6.SYSTEM ANALYSIS
7.SYSTEM ARCHITECTURE
8.UML DIAGRAMS
9.EXECUTION
10.CONCLUSION
11.REFERENCES
2
ABSTRACT
• Pneumonia is a life-threatening infectious disease affecting one or both lungs in humans commonly caused
by bacteria called Streptococcus pneumoniae. One in three deaths in India is caused due to pneumonia as
reported by World Health Organization (WHO).
• Chest X-Rays which are used to diagnose pneumonia need expert radiotherapists for evaluation. Thus,
developing an automatic system for classifying pneumonia would be beneficial for treating the disease
without any delay particularly in remote areas. Due to the success of deep learning algorithms in analyzing
medical images, Convolutional Neural Networks (CNNs) have gained much attention for disease
classification. In addition, features learned by pre-trained CNN models on large-scale datasets are much
useful in image classification tasks.
3
INTRODUCTION
Pneumonia, an infection that inflames the air sacs in one or both lungs, presents a significant global
health challenge, causing considerable morbidity and mortality across all age groups. Accurate and
timely diagnosis is critical for effective treatment and management of this condition. Chest X-rays
(CXR) have long been a cornerstone in the diagnostic process, offering a non-invasive means to
visualize and assess pulmonary abnormalities associated with pneumonia.
Purpose of the project:
To set up the model for recognizing whether or not the individual has pneumonia, A Convolutional
Neural Network (CNN) is used. The CNN can set up the photos of chest X-rays and thereafter it can
expect high precision. Content may be subject to copyright.
4
Scope of the project:
The CNN-based approach leveraged the power of deep learning to automatically extract relevant features from chest X-ray images, enabling
the model to discriminate between normal and pneumonia-infected lung patterns with high sensitivity and specificity.
Existing System :
Involves radiologists manually examining chest X-rays to identify signs of pneumonia. This method is time-
consuming and subject to human error, which can lead to variability in diagnoses.
Proposed System :
Develop a custom Convolutional Neural Network tailored specifically for the task of pneumonia
classification from chest X-rays. This involves designing a network architecture that includes multiple
convolutional layers, pooling layers, and fully connected layers optimized for feature extraction and
classification
5
Functional Requirements :
• Image Preprocessing
•Feature Extraction
•Model Training
•Prediction
Non-Functional Requirements:
•Accuracy
•Performance
•Scalability
6
SYSTEM ANALYSIS
HARDWARE REQUIREMENTS:
• Processor : i3 Minimum
• Hard Disk : 500 GB.
• RAM: 4 GB.
SOFTWARE REQUIREMENTS:
• Operating system : Windows XP/7/10
• Coding Language: Python 3.6
7
System architecture:
8
UML DIAGRAMS:
Class Diagram:
9
Use Case Diagram:
10
Activity Diagram:
11
Sequence Diagram
12
EXECUTION
13
14
CONCLUSION
• In conclusion, this project successfully demonstrates the application of a Convolutional
Neural Network (CNN) for the classification of pneumonia from chest X-ray images. By
utilizing the Chest X-Ray dataset, the system effectively identifies and differentiates
between normal and pneumonia-affected images, showcasing the potential of deep
learning techniques in medical diagnostics.
• The implemented CNN model, trained on a diverse set of images, achieved notable
accuracy in classification, validating the effectiveness of this approach. The image
processing steps, including resizing and normalization, significantly enhanced the model's
performance by ensuring consistency in input data.
• The accuracy and loss graphs generated during the training phase provided valuable
insights into the model's learning process, indicating its capability to generalize from the
training dataset to unseen data.
15
REFERENCES
•
https://github.com/ageitgey/face_recognition](https://github.com/ageitgey/classifi
cation)
A widely-used Python library for facial recognition with clear documentation and
code examples, helpful for implementing facial recognition in your project.
• https://www.researchgate.net/publication/366086127_Attendance_System_Using_
Facial_Recognition
1. *"Automated Attendance System Using Face Recognition with Python
OpenCV"* by Anushree K. and others (2021) - This research paper explains the
process of creating an automated attendance system using Python and OpenCV,
highlighting the steps involved in facial recognition and attendance marking.
16
THANK YOU
17
