Related Experiment Video
Updated: Apr 25, 2026
13:44
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
Published on: August 30, 2013
42.6K
Comparison of enhancement methods for mammograms with performance measures
Burçin Kurt1, Vasif V Nabiyev2, Kemal Turhan1
1Medical Informatics, Karadeniz Technical University, Trabzon, Turkey.
Studies in Health Technology and Informatics
|August 28, 2014
Summary
Noise in mammograms requires image enhancement for better interpretation. A hybrid approach combining mathematical morphology, anisotropic diffusion, and CLAHE significantly improves image quality and highlights suspicious regions.
Area of Science:
- Medical Imaging
- Image Processing
Background:
- Mammograms often suffer from noise, hindering accurate interpretation.
- Identifying suspicious regions of interest (ROIs) in mammograms is crucial for early disease detection.
Purpose of the Study:
- To compare various hybrid image enhancement algorithms for mammograms.
- To evaluate the effectiveness of different enhancement techniques in improving ROI visibility.
Main Methods:
- Implementation of hybrid algorithms using mathematical morphology, contrast stretching, wavelet transform, anisotropic diffusion filter, and CLAHE.
- Performance evaluation using Enhancement Measure (EME), Absolute Mean Brightness Error (AMBE), and Peak Signal-to-Noise Ratio (PSNR).
- Utilized the MIAS database for experimental analysis.
Main Results:
- The combination of mathematical morphology, anisotropic diffusion filter, and CLAHE demonstrated superior performance.
- This hybrid approach significantly enhanced image quality compared to other methods.
- Improved visibility of suspicious regions was observed.
Conclusions:
- Hybrid enhancement techniques are effective in improving mammogram quality.
- The proposed combination of mathematical morphology, anisotropic diffusion, and CLAHE is highly recommended for mammogram enhancement.
- Enhanced mammograms facilitate more accurate detection of ROIs.
