Automatic Segmentation of brain MRI is used as a diagnostic tool in neuro medicine. Abnormal growth of brain tissues can be detected. Changes in volumetric growth of brain tissues such as white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF) can help in the early detection of neural disorders like epilepsy, Alzhemeirpsilas disease etc. Automatic segmentation of brain is a challenging problem. We have developed a hybrid method using threshold and neural network model. In this paper we have discussed preprocessing filters and skull stripping.