The human hippocampus is a complex structure consisting of multiple anatomically and functionally distinct subfields. Obtaining subfield-specific measures from in vivo MRI is challenging, and can benefit from a detailed 3D anatomical reference. This paper builds a computational atlas of the hippocampus from high-resolution ex vivo MRI of 26 specimens using groupwise deformable registration. A surface-based approach based on the explicit segmentation and geometric modeling of hippocampal layers is used to initialize deformable registration of ex vivo MRI scans. This initialization improves of groupwise registration quality, as measured in terms of similarity metrics and qualitatively. The resulting atlas, which also includes annotations mapped from histology, is a unique resource for describing variability in hippocampal anatomy.
展开▼