Related Experiment Video
Updated: Jul 8, 2026
13:44
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
Published on: August 30, 2013
Application of shape analysis to mammographic calcifications
L Shen1, R M Rangayyan, J L Desautels
1Dept. of Electr. & Comput. Eng., Calgary Univ., Alta.
IEEE Transactions on Medical Imaging
|January 1, 1994
Summary
Researchers developed shape factors to classify mammogram calcifications. This method achieved 100% accuracy in distinguishing benign from malignant cases using contour analysis.
Area of Science:
- Medical imaging analysis
- Biomedical engineering
- Radiology
Background:
- Mammography is crucial for breast cancer detection.
- Accurate classification of calcifications as benign or malignant is essential.
- Automated analysis can improve diagnostic efficiency.
Purpose of the Study:
- To develop and evaluate shape factors for mammogram calcification analysis.
- To assess the efficacy of these factors in classifying calcifications.
- To improve the accuracy of distinguishing malignant from benign calcifications.
Main Methods:
- Region growing technique to extract calcification contours.
- Computation of shape features: compactness, moments, and Fourier descriptors.
- Classification using nearest-neighbor method with computed shape features.
Main Results:
- Shape factors effectively measure calcification contour roughness.
- A feature vector combining compactness, moments, and Fourier descriptors was created.
- 100% accurate classification of 143 calcifications from 18 biopsy-proven cases.
Conclusions:
- The developed shape factors are highly effective for calcification classification.
- This automated approach shows promise for improving mammogram analysis.
- The method offers a potential tool for enhanced breast cancer diagnosis.
