Related Experiment Video
Updated: Apr 19, 2026
13:44
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
Published on: August 30, 2013
43.9K
A bilateral analysis scheme for false positive reduction in mammogram mass detection.
Yanfeng Li1, Houjin Chen1, Yongyi Yang2
1School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China.
Computers in Biology and Medicine
|December 30, 2014
Summary
This study introduces a new bilateral image analysis scheme to reduce false positives (FPs) in dense mammogram mass detection. The method significantly lowers the FP rate, improving diagnostic accuracy for breast cancer screening.
Area of Science:
- Medical imaging
- Radiology
- Computer-aided diagnosis
Background:
- Dense mammograms present challenges for accurate mass detection.
- High false positive (FP) rates in mammography lead to unnecessary patient anxiety and further testing.
Purpose of the Study:
- To develop and evaluate a bilateral image analysis scheme for reducing FPs in mass detection within dense mammograms.
- To improve the specificity of mammographic screening without compromising sensitivity.
Main Methods:
- A two-step bilateral image analysis scheme was developed, including region matching and bilateral similarity analysis.
- A matching cost function was defined to assess region correspondence between bilateral mammograms.
- A similarity measurement, considering global and local image features, was introduced to differentiate masses from normal tissue.
Main Results:
- The proposed bilateral scheme demonstrated superior performance compared to existing methods on 332 mammograms.
- At 85% detection sensitivity, the scheme reduced the FP rate from 3.64 to 2.39 per image.
- This represents a significant 34% reduction in the false positive rate.
Conclusions:
- The developed bilateral image analysis scheme effectively reduces false positives in dense mammogram mass detection.
- This approach offers a promising improvement for computer-aided diagnosis in mammography, enhancing screening accuracy.
