Semantic Segmentation of Hippocampal Subregions With U-Net Architecture

The automatic semantic segmentation of the hippocampus is an important area of research in which several convolutional neural networks (CNN) models have been used to detect the hippocampus from the whole cerebral MRI. In this paper, the authors present two convolutional neural networks. The first network (hippocampus segmentation single entity [HSSE]) segmented the hippocampus as a single entity, and the second was used to detect the hippocampal sub-regions (hippocampus segmentation multi-class [HSMC]), these two networks inspire their architecture of the U-net model. Two cohorts were used as training data from NITRC (neuroimaging tools and resources collaboratory) annotated by ITK-SNAP software. The authors analyze this network alongside other recent methods that do hippocampal segmentation. The results obtained are encouraging and reach dice scores greater than 0.84.