The extraction of hippocampus from MRI of human brain using morphological and image binarization techniques

Segmentation of hippocampus (Hc) from the human brain is a significant task in the medical field for the identification of abnormalities in the brain functions. In this paper, we propose a method to segment the hippocampus from Magnetic Resonance Imaging (MRI) of human brain scans. The pipeline of the proposed method makes use of filters such as trimmed mean and top-hat to blur and highlight the hippocampal edges respectively. The K-means clustering is used to find the threshold value in order to convert the filtered image into a binary one. The jaccard (J) and dice (D) indices are used to quantify the performance of the 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.