Related Experiment Video
Updated: Jan 5, 2026
13:44
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
Published on: August 30, 2013
43.5K
Multi-criterion mammographic risk analysis supported with multi-label fuzzy-rough feature selection
Yanpeng Qu1, Guanli Yue2, Changjing Shang3
1Information Technology College, Dalian Maritime University, Dalian 116026, China; Department of Computer Science, Institute of Mathematics, Physics and Computer Science, Aberystwyth University, Aberystwyth, Ceredigion SY23 3DB, UK.
Artificial Intelligence in Medicine
|October 15, 2019
Summary
This study introduces a novel multi-criterion approach for breast cancer risk analysis using advanced feature selection. The method enhances classification accuracy and computational efficiency in mammographic analysis.
Area of Science:
- Medical Imaging
- Machine Learning
- Computational Biology
Background:
- Breast cancer is a leading global health threat, necessitating early and accurate risk analysis.
- Current computer-aided breast cancer risk analysis relies on mammographic features, often with redundancy and noise, impacting efficiency and accuracy.
Purpose of the Study:
- To propose an advanced feature selection mechanism for improved mammographic risk analysis.
- To enhance the accuracy and computational efficiency of breast cancer risk assessment.
Main Methods:
- Adapted a multi-label fuzzy-rough feature selection mechanism for multi-criterion mammographic risk analysis.
- Implemented a system utilizing this novel feature selection approach.
Main Results:
- The implemented system demonstrated improved classification accuracy compared to existing methods.
- The approach effectively selected informative features, mitigating redundancy and noise.
Conclusions:
- The proposed multi-criterion approach offers a robust solution for breast cancer risk analysis.
- The system shows practical efficacy and improved performance in mammographic risk assessment.
