Related Experiment Video
Updated: Jul 10, 2026
13:44
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
Published on: August 30, 2013
Computer-aided mass detection on digitized mammograms using adaptive thresholding and fuzzy entropy.
F Younesi1, N Alam, R A Zoroofi
1Department of Medical Physics & Biomedical Engineering, School of Medicine, Medical Sciences / University of Tehran, Tehran-Iran. fyounesi@razi.tums.ac.ir
Summary
A new computer-aided detection (CAD) scheme effectively identifies masses in mammograms. Combining adaptive thresholding and fuzzy entropy, this method aids radiologists in mass detection during mammographic screening.
Area of Science:
- Medical Imaging
- Computer-Aided Diagnosis
- Image Processing
Background:
- Mammography is crucial for early breast cancer detection.
- Accurate segmentation of masses is essential for reliable diagnosis.
- Computer-aided detection (CAD) schemes can improve mammogram interpretation.
Purpose of the Study:
- To develop and evaluate a novel segmentation method for detecting masses in digitized mammograms.
- To combine adaptive thresholding and fuzzy entropy features for enhanced mass detection.
- To assess the performance of the proposed CAD scheme in terms of sensitivity and specificity.
Main Methods:
- The algorithm involves preprocessing, image enhancement, and feature extraction (fuzzy entropy).
- It utilizes local adaptive thresholding for mass area segmentation.
- Two parallel approaches (adaptive thresholding and fuzzy entropy) are combined for mass detection.
Main Results:
- The method was tested on 78 mammograms (30 normal, 48 cancerous).
- Sensitivity reached 90.73% and specificity reached 89.17%.
- The algorithm demonstrated effective mass detection capabilities.
Conclusions:
- The combined adaptive thresholding and fuzzy entropy method is a promising technique for mass detection in mammograms.
- This CAD scheme can serve as a valuable second reader for radiologists in mammographic screening.
- The proposed approach enhances the accuracy and efficiency of mass identification in digital mammography.
