Brain tissue segmentation in MR brain images using multiple Otsu's thresholding technique

摘要

In this paper a new method is devised to segment the brain tissue from Tl-weighted MR brain images. The proposed method selects optimal threshold values based on Otsu's multiple thresholding technique to segment WM, GM and CSF from MR brain images. The segmentation results obtained by the proposed method is compared with the manually segmented images and have produced best results in terms of overlapping measure. The experimental results using 20 volumes of brain images show that the proposed method accurately segmented the brain tissues than the existing methods AMAP, BMAP, FCM, MAP, ML and TKmean.