Evaluation and failure analysis of four commercial deep learning‐based autosegmentation software for abdominal organs at risk
The causes of the segmentation outliers of the four commercial deep learning-based autocontouring solutions were summarized for each OAR. This work can help the vendors improve their autosegmentation software and also inform the users of potential modes of failure when using the tools.
Authors
- Jeffrey D. Bradley (ORCID: https://orcid.org/0000-0003-3047-3151)
- Beth Ghavidel (ORCID: https://orcid.org/0009-0003-8590-5246)
- Oluwatosin Mary Kayode (ORCID: https://orcid.org/0000-0002-7911-4443)
- Yang Lei (ORCID: https://orcid.org/0000-0002-3572-0345)
- Sean Dresser (ORCID: https://orcid.org/0000-0002-8191-0852)
- Mingdong Fan
- Richard L. J. Qiu (ORCID: https://orcid.org/0000-0002-7877-1900)
- Jun Zhou (ORCID: https://orcid.org/0000-0002-6078-9424)
- Tonghe Wang (ORCID: https://orcid.org/0000-0001-9021-1204)
- Pretesh R. Patel
- Kirk Luca (ORCID: https://orcid.org/0000-0002-3781-6666)
- Xiaofeng Yang (ORCID: https://orcid.org/0000-0001-9023-5855)
- Justin R. Roper (ORCID: https://orcid.org/0009-0004-1729-4444)
Institutions
- Memorial Sloan Kettering Cancer Center (US)
- Emory University (US)
- University of Pennsylvania (US)
- Icahn School of Medicine at Mount Sinai (US)
Publication Details
- Journal
- Journal of Applied Clinical Medical Physics
- Published
- 2025-02-13
- DOI
- https://doi.org/10.1002/acm2.70010
- Citations
- 5
- Primary Topic
- Colorectal Cancer Screening and Detection
- Type
- article
- Field-Weighted Citation Impact
- 5.23
Funders
- Emory University
- National Institutes of Health