Using an Ensemble of Segmentation Methods to Detect Vertebral Bodies on Radiographs.
An ensemble model combining predictions from U-Net and Mask-RCNN resulted in the best performance in detecting VBs on lateral radiographs and generalized well to an external data set. This model could be a key component of a pipeline to detect fractures on all vertebrae in a radiograph in an automated, opportunistic screening tool under development.
Authors
- Nathan Cross (ORCID: https://orcid.org/0000-0002-5040-4340)
- Jessica Perry
- Nancy E. Lane (ORCID: https://orcid.org/0000-0002-0177-2198)
- Jeffrey G. Jarvik (ORCID: https://orcid.org/0000-0002-0528-3455)
- Gang Luo (ORCID: https://orcid.org/0000-0001-7217-4008)
- Qifei Dong (ORCID: https://orcid.org/0000-0002-5751-3208)
- David R. Haynor (ORCID: https://orcid.org/0000-0002-8940-7426)
- Jonathan Renslo
- Sandra K. Johnston (ORCID: https://orcid.org/0000-0003-4106-3924)
- Brian C. Chang (ORCID: https://orcid.org/0000-0001-8327-2084)
Institutions
- University of Southern California (US)
- University of Washington (US)
- University of Washington Medical Center (US)
- University of California, Davis (US)
Publication Details
- Journal
- PubMed
- Published
- 2024-10-03
- DOI
- https://doi.org/10.3174/ajnr.a8343
- Primary Topic
- Medical Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- University of Washington
- Association of University Radiologists
- National Institutes of Health
- National Institute on Aging
- National Heart, Lung, and Blood Institute
- National Institute of Arthritis and Musculoskeletal and Skin Diseases
- U.S. National Library of Medicine
- National Center for Advancing Translational Sciences