BRAIN TUMOUR DETECTION USING SUPER PIXEL BASED SPECTRAL CLUSTERING

Abstract – A brain tumour or intracranial neoplasm occurs due to abnormal cell growth within the brain. It varies in different shape, size and intensity. Here method is been used for the segmentation (Magnetic Resonance Imaging) is used spectral clustering is that it suffers from dense similarity matrix construction. the drawback of dense similarity matrix construction can be overcome identification of region of interest (ROI) FCM and GMM algorithms are used to perform brain tumour segmentation. T edema and tumour core regions are calculate that the proposed method gives better result than the existing