Related Experiment Video
Updated: Jul 7, 2026
13:44
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
Published on: August 30, 2013
On techniques for detecting circumscribed masses in mammograms
1Dept. of Comput. Sci., Alberta Univ., Edmonton, Alta.
IEEE Transactions on Medical Imaging
|January 1, 1989
Summary
This study presents a new mammogram analysis method to detect circumscribed breast masses. The technique uses image enhancement and template matching, showing promising results for identifying tumors.
Area of Science:
- Medical imaging
- Radiology
- Computer-aided diagnosis
Background:
- Mammography is crucial for breast cancer screening.
- Accurate detection of circumscribed masses is essential for diagnosis.
- Automated methods can aid radiologists in mass detection.
Purpose of the Study:
- To develop and evaluate an automated method for detecting circumscribed breast masses in mammograms.
- To replicate expert criteria for mass detection using computational techniques.
Main Methods:
- Modified median filtering for image enhancement.
- Template matching with cross-correlation for suspicious area identification.
- Percentile-based thresholding and false alarm reduction tests.
Main Results:
- The method successfully identified suspicious areas indicative of circumscribed masses.
- Post-processing steps effectively reduced false positives.
- Initial results on test images were encouraging.
Conclusions:
- The proposed method shows potential for assisting in the detection of circumscribed masses on mammograms.
- Further validation is warranted to confirm clinical utility.
