Title: Effective statistical texture features for segmenting mammogram images based on M-ARKFCM with multi-ROI segmentation method
Authors: Ramayanam Suresh; A. Nagaraja Rao; B. Eswara Reddy
Addresses: Department of Computer Science and Engineering, Jawaharlal Nehru Technological University Anantapur (JNTUA), Anantapur, Andhra Pradesh 515002, India; Department of CSE, Chadalawada Ramanamma Enginering College, Tirupati, AP, India ' School of Computer Science and Engineering (SCOPE), VIT, Vellore-632014, Tamilnadu, India ' Department of Computer Science and Engineering, Jawaharlal Nehru Technological University Anantapur College of Engineering (JNTUACE), Kalikiri-517234, Chittoor Dist., Andhra Pradesh, India
Abstract: Mammogram segmentation using multi-region of interest is one of the most emerging research areas in the field of medical image analysis. In recent decades, mammogram segmentation is well-developed, but still the feature extraction algorithms are facing problems like poor outcome in severe lighting variations, illuminance, etc. To address these difficulties, an effective methodology is proposed in this research paper. Initially, the mammogram images were collected from mammographic image analysis society (MIAS) dataset, which was enhanced by using Laplacian filtering. Then, the pre-processed mammogram images were used for segmentation by applying modified adaptively regularised kernel based fuzzy C means (M-ARKFCM). After segmentation, feature extraction was performed by using statistical features for distinguishing the patterns of cancer and non-cancer regions in mammogram images. The experimental outcome shows that the M-ARKFCM improves the segmentation performance by means of area under curve (AUC), dice coefficient and Jaccard coefficient.
Keywords: image segmentation; mammographic image analysis society; modified adaptively regularised kernel-based fuzzy c means; texture features.
DOI: 10.1504/IJAIP.2024.140092
International Journal of Advanced Intelligence Paradigms, 2024 Vol.28 No.3/4, pp.300 - 315
Received: 20 Jun 2018
Accepted: 17 Nov 2018
Published online: 24 Jul 2024 *