Thanks to visit codestin.com
Credit goes to www.scribd.com

Scribd
Upload
55 views4 pages

Project Work Flow: Rida Fatima (2017-BSE-058)

The document describes a project to develop an automated mammogram classification system using a probabilistic neural network. The objective is to help detect breast cancer at early stages by classifying mammogram images as benign, malignant, or normal. The methodology uses the MIAS mammogram image database, performs pre-processing including noise removal, extracts the region of interest using Gaussian mixture modeling, extracts texture features using GLCM, and then trains a probabilistic neural network to classify images as benign, malignant, or normal in order to help diagnose breast cancer.

Uploaded by

faiza
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
55 views4 pages

Project Work Flow: Rida Fatima (2017-BSE-058)

The document describes a project to develop an automated mammogram classification system using a probabilistic neural network. The objective is to help detect breast cancer at early stages by classifying mammogram images as benign, malignant, or normal. The methodology uses the MIAS mammogram image database, performs pre-processing including noise removal, extracts the region of interest using Gaussian mixture modeling, extracts texture features using GLCM, and then trains a probabilistic neural network to classify images as benign, malignant, or normal in order to help diagnose breast cancer.

Uploaded by

faiza
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 4

Fatima Jinnah Women University, Rawalpindi

Software Engineering department

Project Work Flow

Submitted to: Ma’am Mehreen Sirshar

Submitted by: Faiza Mushtaq (2017-BSE-065)

Rida Fatima (2017-BSE-058)

Course: Digital Image Processing


Title:
Mammogram classification (using Probabilistic neural network)

Objective
The classification of benign and malignant patterns in digital mammograms is one of most
important and significant processes during the diagnosis of breast cancer as it helps detecting the
disease at its early stage which saves many lives. Breast abnormalities are often embedded in and
camouflaged by various breast tissue structures. It is a very challenging and difficult task for
radiologists to correctly classify suspicious areas (benign and malignant patterns) in digital
mammograms. In the early stage, the visual clues are subtle and varied in appearance, making
diagnosis difficult; challenging even for specialists. The error rate is high because human eye
can’t recognize the patterns so easily therefore there is need for accurate diagnosis of
mammogram images. Therefore, a classifier is required which can help radiologists in classifying
suspicious areas and diagnosing breast cancer. The objective of this work is to develop an
automated system which identifies a tumor in digital mammograms images.

Flowchart:
Methodology
The images database used in this project is MIAS database that is Mammographic Image
Analysis Society that consists of total 322 mammographic images, 207 are normal images, 52
malignant and 63 benign images that has been decreased to a 200-micron pixel frame and the
images are 1024x1024.Before Classification image is preprocess using Adaptive mean filtering
for noise removal. The adaptive Median Filter classifies picture elements as noise by comparing
every pixel within the image to its close neighboring pixels. The next step is to extract ROI using
Gaussian Mixture Model (GMM). The identified region is analyzed to detect defect in
mammographic image. A feature is a noteworthy piece of information obtained from an image
which gives detailed perceptive of the image. Extracting texture features from ROI of
mammogram image using GLCM is done. It provides important texture data to classify among
masses. Probabilistic Neural network that is feed forward neural network will aid in the training
process and then the prediction can be done appropriately. The tumor is classified into the
following classes benign, malign and normal. By this classification process it can be found if the
cancer cells will spread or not.
References:

 Ranadhir G, Ghosh M, Yearwood J (2004). A Modular Framework for multi Category Feature
Selection in Digital Mammography. Proceedings of the 12th European Symposium on Artificial
Neural Networks -ESANN , pp.175-180.
 Ponti, A. et al. Cancer screening in the european union. final report on the implementation of
the council recommendation
 on cancer screening (2017).
 Bae, M. S. et al. Breast cancer detected with screening us: reasons for nondetection at
mammography. Radiol. 270,369–377 (2015).

You might also like