A deep learning aided bone marrow segmentation of quantitative fat MRI for myelofibrosis patients
All four tested U-Net models effectively automated BM segmentation in pelvic MRI of MF patients. The 2D A-U-Net was found best overall for BM segmentation in both femur and ilium.
Authors
- Moshe Talpaz (ORCID: https://orcid.org/0000-0003-3361-3981)
- Thomas L. Chenevert (ORCID: https://orcid.org/0000-0003-1476-4274)
- Humera Tariq (ORCID: https://orcid.org/0000-0002-7684-9161)
- Gary D. Luker (ORCID: https://orcid.org/0000-0001-6832-2581)
- Kristen Marie Pettit (ORCID: https://orcid.org/0009-0007-3536-4137)
- Brian Dale Ross (ORCID: https://orcid.org/0000-0003-2695-9140)
- Dariya Malyarenko (ORCID: https://orcid.org/0000-0003-0403-1501)
- Lubomir M. Hadjiiski (ORCID: https://orcid.org/0000-0003-2069-8066)
Institutions
- University of Michigan (US)
- Michigan Medicine (US)
Publication Details
- Journal
- Frontiers in Oncology
- Published
- 2025-05-23
- DOI
- https://doi.org/10.3389/fonc.2025.1498832
- Citations
- 2
- Primary Topic
- Bone and Joint Diseases
- Type
- article
- Field-Weighted Citation Impact
- 3.44
Funders
- National Institutes of Health
- National Cancer Institute