Related Experiment Video
Updated: Mar 11, 2026
13:44
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
Published on: August 30, 2013
43.8K
A dual stage adaptive thresholding (DuSAT) for automatic mass detection in mammograms
J Anitha1, J Dinesh Peter2, S Immanuel Alex Pandian3
1Department of CSE, Karunya University, Coimbatore, India.
Computer Methods and Programs in Biomedicine
|November 26, 2016
Summary
This study introduces a novel computer-aided detection system for mammograms, improving early breast cancer diagnosis. The Dual Stage Adaptive Thresholding (DuSAT) method enhances abnormality detection, aiding radiologists in identifying potential masses.
Area of Science:
- Medical Imaging
- Radiology
- Computer-Aided Diagnosis
Background:
- Mammography screening significantly reduces breast cancer mortality.
- Differentiating subtle abnormalities in mammograms is challenging due to ill-defined margins.
Purpose of the Study:
- To present a new computer-aided approach for detecting abnormalities in digital mammograms.
- To improve the accuracy and efficiency of breast cancer mass detection.
Main Methods:
- A Dual Stage Adaptive Thresholding (DuSAT) method was developed.
- It utilizes global histogram analysis (Histogram Peak Analysis) and local window thresholding for precise segmentation.
- Suspicious mass regions are identified through these combined thresholding techniques.
Main Results:
- The DuSAT algorithm was validated on the DDSM (300 images) and mini-MIAS (170 images) databases.
- It achieved an average sensitivity of 92.5% (1.06 FP/image) on DDSM and 93.5% (0.62 FP/image) on mini-MIAS.
- These results demonstrate high accuracy in mass detection.
Conclusions:
- The proposed DuSAT approach outperforms existing state-of-the-art methods for mass detection.
- This technology assists radiologists in the early diagnosis of breast cancer.
- Early detection through improved mammogram analysis can lead to better patient outcomes.
