A novel hyperbolic intuitionistic fuzzy divergence measure based mammogram enhancement for visual elucidation of breast lesions. (May 2022)

• Record Type: Journal Article
• Authors: Ghosh, Swarup Kr; Ghosh, Anupam
• Is Part Of: Biomedical signal processing and control. Volume 75(2022)
• Publication Date: 2022-05
• Subjects: Mammograms -- Intuitionistic fuzzy set -- Image enhancement -- Cauchy distribution -- Mean opinion score; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.103586
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: An intuitionistic fuzzy divergent measure based contrast enhancement approach. Hesitant score metric is derived from source and complementary mammogram images. Fuzzy membership grade is modified using hyperbolic regularization and entropy. Enhanced mammogram is generated by applying Werner's AND/OR operators. The model is computationally effective. Abstract: In this article, we have proposed a novel mammogram image enhancement approach for visual interpretation of breast masses using an adaptive intuitionistic fuzzy divergent measure under hyperbolic regularization. The proposed scheme pursuits to raise the underexposed and abnormal growth of cells such as breast masses, deformity tissues, nodules, and lumps in mammogram images. In the first step, a complementary image has been generated from the source mammogram to separate object and background area. Thereafter, both source and background images are mapped into Intuitionistic Fuzzy Set (IFS) plane under Hyperbolic Regularization (HR). A novel entropy based intuitionistic fuzzy divergence measure has been designed using hyperbolic function for the membership modification in this work. In addition, fuzzy ambiguity correction distance function has been obtained from the hesitant score vectors from both source and complementary images. Werner's AND-OR has been utilized on both of them to generate modified membership function. Finally, we have achieved enhanced mammogram with visually improved breast masses through defuzzification process. It has been shown that the proposed method provides better result in comparison with the existing methods in terms of qualitative and higher score of image quantity measurement metrics such as SSIM (0.83), FQI (0.85), and IFQI (0.88).