Benchmarking of deep learning methods for generic MRI multi-organ abdominal segmentation
We perform benchmarking of four open-source models for abdominal MR segmentation on three datasets and demonstrate that models trained on real, heterogeneous, multimodal data yield the best overall performance. We provide evaluation code and datasets for future benchmarking at https://github.com/deepakri201/AbdoBench.
Authors
- Deepa Krishnaswamy (ORCID: https://orcid.org/0000-0002-3235-1222)
- Ron Kikinis (ORCID: https://orcid.org/0000-0001-7227-7058)
- Steve Pieper (ORCID: https://orcid.org/0000-0003-4193-9578)
- Andriy Fedorov (ORCID: https://orcid.org/0000-0003-4806-9413)
- Benjamin Billot (ORCID: https://orcid.org/0000-0002-3018-1282)
- Cosmin Ciausu
Institutions
- Brigham and Women's Hospital (US)
- Institut national de recherche en sciences et technologies du numérique (FR)
- Abterra Biosciences (United States) (US)
Publication Details
- Journal
- Journal of Medical Imaging
- Published
- 2025-12-05
- DOI
- https://doi.org/10.1117/1.jmi.12.6.064503
- Primary Topic
- Advanced Neural Network Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00