Computerized segmentation of MR brain tumor: an integrated approach of multi-modal fusion and unsupervised clustering

• Published in: International journal of information technology (Singapore. Online) Vol. 16; no. 2; pp. 1155 - 1169
• Main Authors: Lavanya, K. G., Dhanalakshmi, P., Nandhini, M.
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 01.02.2024; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Brain; Clustering; Computer Imaging; Computer Science; Feature extraction; Image enhancement; Image Processing and Computer Vision; Machine Learning; Medical imaging; Original Research; Pattern Recognition and Graphics; Principal components analysis; Software Engineering; Tumors; Vision; Image segmentation; Interval valued intuitionistic fuzzy set; Gaussian kernel; Soft clustering; Multimodality image fusion
• ISSN: 2511-2104; 2511-2112
• DOI: 10.1007/s41870-023-01669-x

Tumor detection and diagnosis have become topical subjects in the current age. In this paper, an innovative technique for segmenting brain tumor is furnished. The proposed segmentation process is divided into two main phases. The initial phase focuses on fusing the multi-modal brain image, entailing enhancement and feature extraction processes. The enhancement process involves the transformation of the original crisp images into interval-valued intuitionistic fuzzy images, while feature extraction is achieved through kernel principal component analysis. These steps effectively reduce discrimination between different regions within the brain images, mitigate noise, and address variations in illumination and resolution. The subsequent phase is to accurately segment the fused images with clarity in shape and position using the proposed clustering technique. Further, the experimental analysis is done between other clustering methods and the proposed algorithm with cluster validation indices to exhibit the viability of the proposed method.