This paper deals with the automatic segmentation of tumor in brain MRI. Tumors are uncontrolled growth of tissues in any part of the
body. Tumors may be of different types and they have different Characteristics and different treatment. Being in brain, tumor is
inherently serious and life-threatening because of its limited space of the intracranial cavity (space formed inside the skull). Most
Researches show that the number of people who have brain tumors were died due to the fact of inaccurate detection. Generally, CT
scan or MRI are directed into intracranial cavity produces a complete image of brain, which is visually examined by the physician for
detection & diagnosis of brain tumor. To avoid inaccurate determination, this paper uses a method in the detection (segmentation) of
brain tumor based on Hessian analysis. Hessian analysis is used for Multi-scale blob detection, that corresponds to detection of
tumors. This method detects every tumor, in addition some non tumors also were detected. The tumor likelihoods for the remaining
tumor candidates were estimated using a logistic regression model based on blobness, and morphology features. It also reduces the
time for analysis in addition. At the end of the process the tumor is extracted from the MRI and classified as normal and abnormal.