Scribd
Upload
7 views1 page

Digital Mammography Classification System

This research presents a classification system for digital mammography aimed at detecting and diagnosing breast diseases, particularly early breast cancer. The system consists of a feature extraction phase and a classification phase, which includes selecting a region of interest and classifying images as normal or abnormal, and further as benign or malignant. The methodology utilizes MATLAB and the MIAS database for implementation.

Uploaded by

C SUBA
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
7 views1 page

Digital Mammography Classification System

This research presents a classification system for digital mammography aimed at detecting and diagnosing breast diseases, particularly early breast cancer. The system consists of a feature extraction phase and a classification phase, which includes selecting a region of interest and classifying images as normal or abnormal, and further as benign or malignant. The methodology utilizes MATLAB and the MIAS database for implementation.

Uploaded by

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

CLASSIFICATION SYSTEM FOR DIGITAL MAMMOGRAPHY BASED

ON MULTIDOMAIN FEATURES

ABSTACT

Digital mammography is the new technology for radiographic examination, which helps in
detecting, diagnosing, and managing a variety of breast diseases, especially early breast cancer,
yielding in significant improvement of breast cancer survival rate. Mammograms, an x-ray
picture of the breast which can be used to check for breast cancer in women. It also helps in
exhibiting the abnormalities or lumps which indicate early stages of breast cancer.

This research aims to develop an automatic system to classify the digital mammogram images
into Normal or Abnormal images. The Mammography techniques is an important factor which
helps in finding out the early diagnosis of cancer and also identifies the classification of medical
images which become an increased need. This demand has led to the development of several
techniques to classify the digital mammograms.

The proposed method is an approach for detecting mass and micro calcification in
mammograms. The proposed classification system mainly consists of two phases. They are
Feature extraction phase and classification phase.

1. The ROI (Region of interest) of an image is selected since 50% of an image


comprises the background with lots of noise.

2. The features are extracted from the ROI of an image.

3. Feature extraction – Texture features.

4. Texture features are classified into three major categories namely statistical, structural
and spectral.

5. Then the images are classified in two stages.

i. First stage – normal or abnormal.

ii. Second stage – benign or malignant.

REQUIREMENTS

Software: MATLAB is used

Database: MIAS database

You might also like