A hybrid extraction-classification method for brain segmentation in MR image

In this paper, we presented a hybrid method to distinguish normal brain tissue from lesion regions based on the T1-weighted and T2-weighted MR images of the same anatomic structure. Regions of interest were extracted using an iterative Otsu's thresholding method with normal brain tissue extracted from T1-weighted MR images, and lesion regions extracted from T2-weighted MR images. Markov random field and maximum-a-posteriori approaches were used to classify areas dually identified as normal brain tissue in T1-weighted images and lesion regions in T2-weighted images. The approach was validated using synthetic and real MR images to demonstrate its ability to clearly distinguish normal brain tissue from lesion regions.