A Fully Automated and Elegant Method for Segmentation and Classification of Brain Mri Images Using K-means Algorithm and Ann

Computational applications are gaining significant importance in the routine life. Specially, the tradition of the computer aided systems for computational biomedical applications has been explored to a higher extent. Detection of brain tumor is the most common fatality in the current scenario of health care civilization. Automated brain disorder analysis with MR images is one of the specific medical image analysis methodologies. In this paper, segmentation is done by improved K -means algorithm with dual localization methodology. It allows the segmentation of tumour tissue with accuracy and reproducibility comparable to manual segmentation also it reduces the time for testing. At the end of the process the tumour is extracted from the MR image interms of position and shape. The proposed system uses computer based procedures to detect tumor blocks or lesions and classify the type of tumor using Artificial Neural Network in MRI images of different patients. Key wordsMagnetic Resonance Imaging(MRI), Brain tumor, Preprocessing, Thresholding, Feature extraction.