Evaluating the sensitivity and reliability of hippocampal segmentation for dementia using deep learning
This study analysed the sensitivity and reliability of 5 mainstream pipelines for automated hippocampal segmentation, benchmarked against FreeSurfer, and provided a workflow to evaluate pipelines' clinical readiness. The strategy can also be applied to design/tailor pipelines that are robust to artefacts and scan variability.
Authors
- Jiongqi Qu
- Carole H. Sudre (ORCID: https://orcid.org/0000-0001-5753-428X)
- Anna Schroder (ORCID: https://orcid.org/0009-0001-0380-0674)
- Sophie Martin (ORCID: https://orcid.org/0000-0003-3819-1634)
- James H. Cole
- Matthew Grech‐Sollars
Institutions
- University College London (GB)
Publication Details
- Journal
- Alzheimer s & Dementia
- Published
- 2025-12-01
- DOI
- https://doi.org/10.1002/alz70856_102219
- Primary Topic
- Dementia and Cognitive Impairment Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00