Author : Mr. Amol N. Khirade and Prof. Vilas.S.Gaikwad

This work deals with the implementation of Simple Algorithm for detection of range and shape of tumor in brain MR images and identifies stage of tumor from the given area of tumor. Tumor is an uncontrolled development of tissues in any piece of the body. Tumors are of various sorts and they have various Characteristics and diverse treatment.As it is known, brain tumor is characteristically genuine and dangerous attributable to its person in the constrained space of the intracranial cavity (area shaped inside the skull). Most Research in developed countries show that the number of people who have brain tumors were died because of the reality of inaccurate detection. Generally, CT test or MRI that is directed into intracranial hollow space produces a complete photocopy of brain. After researching a lot statistical analysis which is primarily based on those human beings whose are affected in brain tumor some general Risk factors and Symptoms had been discovered. The improvement of technology in science day night tries to develop new methods of treatment. This image is visually examined by the physician for detection diagnosis of brain tumor. However this method accurate determines the accurate of stage size of tumor and also predicts the disease details from the area of tumor. This work uses segmentation of brain tumor based on the Expectation maximization and fuzzy c-means algorithms. This method allows the segmentation of tumor tissue with accuracy and reproducibility comparable to manual segmentation. In addition, it additionally reduces the time for analysis and predicts the disease details from the given area of tumor.

Keywords: Deep Learning, Machine Learning, Medical image segmentation, Expectation Maximization, fuzzy c means clustering;