Evaluating Traditional, Deep Learning and Subfield Methods for Automatically Segmenting the Hippocampus From <scp>MRI</scp>

Given the relationship between hippocampal atrophy and cognitive impairment in various pathological conditions, hippocampus segmentation from MRI is an important task in neuroimaging. Manual segmentation, though considered the gold standard, is time-consuming and error-prone, leading to the development of numerous automatic segmentation methods. However, no study has yet independently compared the performance of traditional, deep learning-based and hippocampal subfield segmentation methods within a single investigation. We evaluated 10 automatic hippocampal segmentation methods (FreeSurfer, SynthSeg, FastSurfer, FIRST, e2dhipseg, Hippmapper, Hippodeep, FreeSurfer-Subfields, HippUnfold and HSF) across 3 datasets with manually segmented hippocampus labels. Performance metrics included overlap with manual labels, correlations between manual and automatic volumes, volume similarity, diagnostic group differentiation and systematically located false positives and negatives. Most methods, especially deep learning-based ones that were trained on manual labels, performed well on public datasets but showed more error and variability on clinical data. Many methods tended to over-segment, particularly at the anterior hippocampus border, but were able to distinguish between healthy controls, MCI, and dementia patients based on hippocampal volume. Our findings highlight the challenges in hippocampal segmentation from MRI and the need for more publicly accessible datasets with manual labels across diverse ages and pathological conditions.