Magnetic resonance (MR) imaging has been playing a vital role in neuroscience research to examine brain conditions related to normal and abnormal brain structures and functions in vivo. In previous years, MRI is observed to play an important role in brain abnormalities research in determining the size and location of affected tissues. MRI Image segmentation and classification refers to a process of assigning labels to a set of pixels or multiple regions. It plays a major role in the field of biomedical applications as it is widely used by radiologists to segment the medical images input into meaningful regions. Thus, various segmentation techniques in medical imaging depending on the region of interest had been proposed. Medical image segmentation problems have been approached with several solution methods by different ranges of applicability such as Region Growing, Self-Organizing Map (SOM), and Fuzzy c-Means (FCM). Some recent progress has been made to create semi-supervised (based on user interaction) or supervised variational methods. In the last decades, many methods have been proposed to segment the brain tumor of MR images, such as neural networks, finite Gaussian mixture model, knowledge-based methods, atlas-based method, active contour model, level set methods, and outlier detection. However, the segmentation of medical imagery remains a challenging problem due to the complexity of the images. Brain tissue is a particularly complex structure and its segmentation is an important step for studies in temporal change detection of morphology. The success of MRI in the detection of brain pathologies is very encouraging. However, diagnosis and locations of abnormality are made manually by radiologists. It consumes valuable human resources, is error sensitive, and makes it prone to error.