Segmentation and classification of brain images using firefly and hybrid kernel-based support vector machine. Issue 3 (4th May 2017)

• Record Type: Journal Article
• Authors: Selva Bhuvaneswari, K.; Geetha, P.
• Is Part Of: Journal of experimental & theoretical artificial intelligence. Volume 29:Issue 3(2017)
• Page Start: 663
• Page End: 678
• Publication Date: 2017-05-04
• Subjects: Tumour -- segmentation -- kernel -- MRI -- SVM -- threshold generation -- region merging; Artificial intelligence -- Periodicals; 006.3
• DOI: 10.1080/0952813X.2016.1212106
• Languages: English
• ISSNs: 0952-813X

Abstract

Abstract: Magnetic resonance imaging segmentation refers to a process of assigning labels to set of pixels or multiple regions. It plays a major role in the field of biomedical applications as it is widely used by the radiologists to segment the medical images input into meaningful regions. In recent years, various brain tumour detection techniques are presented in the literature. The entire segmentation process of our proposed work comprises three phases: threshold generation with dynamic modified region growing phase, texture feature generation phase and region merging phase. by dynamically changing two thresholds in the modified region growing approach, the first phase of the given input image can be performed as dynamic modified region growing process, in which the optimisation algorithm, firefly algorithm help to optimise the two thresholds in modified region growing. After obtaining the region growth segmented image using modified region growing, the edges can be detected with edge detection algorithm. In the second phase, the texture feature can be extracted using entropy-based operation from the input image. In region merging phase, the results obtained from the texture feature-generation phase are combined with the results of dynamic modified region growing phase and similar regions are merged using a distance comparison between regions. After identifying the abnormal tissues, the classification can be done by hybrid kernel-based SVM (Support Vector Machine). The performance analysis of the proposed method will be carried by K-cross fold validation method. The proposed method will be implemented in MATLAB with various images.