Related Experiment Video
Updated: Dec 30, 2025
13:44
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
Published on: August 30, 2013
43.5K
Assessment and Classification of Mass Lesions Based on Expert Knowledge Using Mammographic Analysis
Afrooz Arzehgar1, Mohammad Mahdi Khalilzadeh1, Fatemeh Varshoei2
1Department of Biomedical Engineering, Islamic Azad University, Mashhad Branch, Mashhad, Iran.
Current Medical Imaging Reviews
|January 25, 2020
Summary
This study developed a computer-aided diagnosis (CADx) system to classify breast masses from mammograms. The system achieved high accuracy in detecting malignant tumors across various breast densities, aiding radiologists in diagnosis.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Healthcare
- Oncology
Background:
- Mammography is crucial for breast cancer detection, with mass classification (benign vs. malignant) being essential.
- Computer-Aided Diagnosis (CADx) systems enhance radiologist accuracy in interpreting mammograms.
- Accurate classification of breast masses supports early breast cancer diagnosis.
Purpose of the Study:
- To develop a human decision-making model-based method for breast mass classification.
- To create a tool for radiologists to reduce diagnostic errors and complexity.
- To assess mammographic mass classification using shape, texture, and asymmetry in MLO and CC views.
Main Methods:
- Classification of breast masses using mammography (MLO and CC views).
- Evaluation based on mass characteristics: shape, texture, and asymmetry.
- Development of a decision tree method for breast tissue density classification.
Main Results:
- The proposed system achieved high true malignant rates across different breast densities: 100% (entirely fat), 99% (scattered fibroglandular densities), 99% (heterogeneously dense), and 98% (extremely dense).
- Results were validated using a cross-validation procedure.
- The system demonstrated effective classification of breast masses.
Conclusions:
- The developed method provides a robust tool for radiologists in breast cancer diagnosis.
- The system effectively classifies breast masses, aiding in the differentiation of benign and malignant tumors.
- The approach supports accurate and efficient mammogram interpretation.
