A new segmentation technique for brain and head from high resolution MR image using unique histogram features

This paper presents a high resolution MR image acquisition protocol for better visualization of normal gray structures of brain, a unique feature of the histogram of the reconstructed images of this protocol, an automated segmentation algorithm of the head contour and the entire brain by using this feature. Using signal nulling effect we have emphasized enhancing the intensity difference between white and gray matters in the reconstructed MR image. This leads to the generation of a histogram where pixel values of different anatomical structures are distributed around separate dominant modes. An algorithm for automated multilevel thresholding for partitioning specific modes to segment the image into brain and head contour has been developed. The algorithm has been tested on a large dataset with great success and validated by a robust index with highly encouraging outcome.