Generative AI in orthopedics: an explainable deep few-shot image augmentation pipeline for plain knee radiographs and Kellgren-Lawrence grading
Our approach demonstrates the capability to produce top-notch synthetic knee radiographs and use them for KL grading classification, even when working with a constrained training dataset. The results obtained emphasize the effectiveness of the pipeline in augmenting datasets for knee osteoarthritis research, opening doors for broader applications in orthopedics, medical image analysis, and AI-powered diagnosis.
Authors
- Soheyla Amirian (ORCID: https://orcid.org/0000-0002-7517-0739)
- Brian J. McGrory (ORCID: https://orcid.org/0000-0001-5697-964X)
- Adolph J. Yates (ORCID: https://orcid.org/0000-0002-2091-7743)
- Hooman H. Rashidi (ORCID: https://orcid.org/0000-0002-5634-8490)
- Nicole Myers (ORCID: https://orcid.org/0009-0003-5555-2005)
- Johannes F. Plate (ORCID: https://orcid.org/0000-0002-2735-2589)
- Bambang Parmanto (ORCID: https://orcid.org/0000-0002-4907-8402)
- Jacob T. Biehl (ORCID: https://orcid.org/0000-0002-3878-5208)
- Ahmad P. Tafti (ORCID: https://orcid.org/0000-0001-9650-2862)
- Thorsten M. Seyler (ORCID: https://orcid.org/0000-0003-1157-132X)
- Nickolas Littlefield (ORCID: https://orcid.org/0009-0009-2741-2981)
- Michael R. Kann (ORCID: https://orcid.org/0009-0000-6362-2083)
- Leah Reid
- Edward Andrews
Institutions
- Tufts University (US)
- Pace University (US)
- University of Pittsburgh (US)
- Duke University (US)
- Computational Diagnostics (United States) (US)
- Duke University Hospital (US)
- Neurological Surgery (US)
Publication Details
- Journal
- Journal of the American Medical Informatics Association
- Published
- 2024-09-23
- DOI
- https://doi.org/10.1093/jamia/ocae246
- Citations
- 8
- Primary Topic
- Osteoarthritis Treatment and Mechanisms
- Type
- article
- Field-Weighted Citation Impact
- 3.76
Funders
- National Institutes of Health