THE SEGMENTATION OF HIPPOCAMPUS FROM MID-SAGITTAL T2-WEIGHTED MAGNETIC RESONANCE IMAGES OF HUMAN BRAIN USING MORPHOLOGICAL OPERATIONS AND THRESHOLDING

The segmentation of hippocampus from the human brain is a significant task in the medical field for the identification of abnormalities in the brain functions, However, the segmentation of hippocampus is a challenging task because of its complex shape, small size, fuzzy boundaries and anatomical variability. In this paper, we propose a method to segment the hippocampus from clinical magnetic resonance imaging (MRI) of human head. The proposed method uses morphological operations and k-means clustering. The connected component analysis is then used to extract the region of interest (ROI). The jaccard (J) and dice (D) indices are calculated to quantify the performance of proposed method as well as the semi-automatic method ITK-SNAP. The results show that the proposed method works better than the existing ITK-SNAP.