Segmentation and classification of brain tumor computed tomography (CT) images using watershed segmentation for early diagnosis

S. Krishnakumar, J. Bethanney

Abstract

A computer software system is designed for segmentation and classification of benign and malignant tumor slices in brain computed tomography (CT) images. The objective of the present study is to develop software and to achieve auto-segmentation and detection of brain tumor. Therefore the algorithm has been designed and developed for analysis of medical images based on hybridization of synergistic and statistical approaches using watershed segmentation and morphological operation. This algorithm performs segmentation and classification is done in human vision system, which recognizes objects, perceives depth, identifies different textures, curved surfaces or a surface inclination by texture information and brightness. The analysis of medical image is directly based on four steps: 1) image filtering, 2) segmentation, 3) feature extraction and 4) analysis of extracted features by pattern recognition system or classifier. In proposed method an attempt has been made to present an approach for segmentation and detection of brain computed tomography images. The present approaches are threshold segmentation, color conversion, filter fft, Image enhancement, watershed segmentation and morphological operation. The algorithms itself scan the whole image and perform the segmentation and classification in unsupervised mode.