MR image feature extraction using advanced statistical matrices

Computerized automatic recognition of brain tumors in magnetic resonance images (MRI) is a challenging task. Tumors are available at different location, size, shape, and texture of these lesions. Due to intensity similarities between brain lesions and normal tissues, the challenges for the researcher remain for developing progressive more algorithms in the tumor detection. Selection of single spectral or multispectral images is dependent on constraints like time, cost and some other difficulties. The proposed approach can identify tumor tissues using a single-spectral structural MR image. This paper presents an automatic system, which is able to detect slices which include tumor and features are extracted from that slice to delineate the tumor area.