Automatic Hippocampus Segmentation from Brain MRI Images

Since hippocampal volume measurement is often used in studying Alzheimer’s disease to assess disease progression, automatic hippocampus segmentation is an important task in clinical applications. However, it is a challenging task due to its small size, complex shape, fuzzy boundaries, partial volume effects, and anatomical variability. In this paper we propose a new registration method to segment the hippocampus from brain MRI images automatically. It uses a combination of local affine transformation and optical flow based non-rigid registration, which has the advantages of modifying the larger geometric deformation and intensity differences simultaneously. Meanwhile the residual subtle differences decrease due to the high degree of freedom. Quantitative evaluation with respect to manual segmentation is performed on 10 subjects with the spatial overlap (KI value) as the evaluation criterion. The average KI with the proposed method is 0.7749, while it is 0.5811 with another semi-automatic method, ITK-SNAP. It is indicated that the proposed method is more accurate and will be a good choice for hippocampus segmentation