Comparison of Vendor-Pretrained and Custom-Trained Deep Learning Segmentation Models for Head-and-Neck, Breast, and Prostate Cancers
These findings underscore the substantial impact of institutional preferences and clinical practices on the implementation of vendor-pretrained models. We also found that a relatively small amount of institutional data was sufficient to train customized segmentation models with sufficient accuracy.
Authors
- Jack Phan (ORCID: https://orcid.org/0000-0001-5977-6004)
- Sanjay Shete (ORCID: https://orcid.org/0000-0001-7622-376X)
- Fredrik Löfman
- Mohammad D. El Basha
- Xinru Chen (ORCID: https://orcid.org/0000-0002-9989-8943)
- Hana Baroudi (ORCID: https://orcid.org/0000-0001-9921-4663)
- Laurence E. Court (ORCID: https://orcid.org/0000-0002-3241-6145)
- Yao Zhao (ORCID: https://orcid.org/0000-0001-8863-841X)
- Chelain R. Goodman
- Peter Balter (ORCID: https://orcid.org/0000-0003-4806-8920)
- Skylar Gay (ORCID: https://orcid.org/0000-0003-4659-0766)
- Jinzhong Yang (ORCID: https://orcid.org/0000-0002-9254-4501)
- Joshua S. Niedzielski (ORCID: https://orcid.org/0000-0002-7666-5039)
- Cenji Yu (ORCID: https://orcid.org/0000-0002-4350-9910)
- Zhongxing Liao (ORCID: https://orcid.org/0000-0002-2224-9478)
- He Wang (ORCID: https://orcid.org/0000-0002-2053-9439)
- Xiaodong Zhang (ORCID: https://orcid.org/0000-0001-8350-0411)
- Seungtaek Choi (ORCID: https://orcid.org/0000-0003-3570-0907)
- Aji Daniel
Institutions
- The University of Texas MD Anderson Cancer Center (US)
- RaySearch Laboratories (Sweden) (SE)
- The University of Texas Health Science Center at Houston (US)
Publication Details
- Journal
- Diagnostics
- Published
- 2024-12-18
- DOI
- https://doi.org/10.3390/diagnostics14242851
- Citations
- 1
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 0.35
Funders
- Radiation Oncology Institute
- National Institutes of Health
- University of Texas MD Anderson Cancer Center