Related Experiment Video
Updated: May 26, 2026
13:44
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
Published on: August 30, 2013
Automatic diagnosis of mammographic abnormalities based on hybrid features with learning classifier
1Department of Master of Computer Applications, Park College of Engineering and Technology, Coimbatore Tamil Nadu India. jaisingh_w@yahoo.com
Computer Methods in Biomechanics and Biomedical Engineering
|January 10, 2012
Summary
This study introduces a novel computer-aided detection (CAD) system using hybrid features and a learning classifier for mammograms. The CAD system achieved 94.5% sensitivity in detecting breast cancer lesions, aiding radiologists.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Mammography is the standard for breast cancer screening but faces limitations.
- Dense breast tissue and overlying anatomy can obscure lesions.
- Computer-aided detection (CAD) systems can enhance radiologist performance.
Purpose of the Study:
- To develop and evaluate a novel CAD system for segmenting and classifying suspicious regions in mammograms.
- To improve the accuracy of breast cancer detection using hybrid features and a learning classifier.
Main Methods:
- A supervised learning approach was used to differentiate lesions from normal tissue.
- A classification algorithm was developed utilizing hybrid features.
- The algorithm was validated on 164 mammograms from the mini-Mammographic Image Analysis Society database.
Main Results:
- The developed CAD method achieved a sensitivity of 94.5%.
- The system demonstrated a low false positive rate of 0.26 per image.
- Efficiency was assessed using free-response receiver operating characteristic (FROC) curves.
Conclusions:
- The CAD technology with a learning classifier shows significant potential in assisting radiologists.
- This approach can improve the discrimination between malignant lesions and normal tissue in mammography.