Abstracto

A New Approach For an Improved Multiple Brain Lesion Segmentation

Prof. Shanthi Mahesh, Karthik Bharadwaj N, Suhas A Bhyratae ,Karthik Raju V, Karthik M N

Segmentation of human brain from MRI slices for identification of brain lesions has become one of the most active research areas in the field of medical image processing. Brain segmentation has various important applications in diagnosing a number of disorders. The main aim of this project work is to recognize lesions and its qualifications from a specific MRI scan of a brain image and compute the area of each lesion by thresholding. Thresholding approach segment scalar images by generating a binary partitioning of the image intensities. Otsu’s technique is used to automatically carry out intensity based image thresholding. The quantitative analysis of MRI brain lesions allows obtaining useful key information about the lesions. Segmentation is done on basis of threshold, due to which whole image is converted into binary image.