Local entropy based brain MR image segmentation

Magnetic Resonance Imaging (MRI) offers a lot of information for medical examination. Fast, accurate and reproducible segmentation of MRI is desirable in many applications. Brain image segmentation is important from clinical point of view for detection of tumor. Brain images mostly contain noise, inhomogeneity and sometimes deviation. Therefore, accurate segmentation of brain images is a very difficult task. In this paper we present an automatic method of brain segmentation for detection of tumor. The MR images from T1, T2 and flair sequences are used for the study along with axial, coronal and sagitial slices. The segmentation of MR images is done using textural features based on gray level co occurrence matrix. The textural feature used is the entropy of image.