Deep learning-based identification of aberrant anterior tibial artery on knee MRI: a brazilian multicenter study
To our knowledge, this is the first study to apply artificial intelligence for automated detection of AATA on knee MRI. The proposed deep learning model performs this task with high sensitivity. Despite reduced precision in the external cohort, it demonstrates strong potential for enhancing preoperative risk assessment and surgical planning. Broader multicenter validation is warranted before clinical deployment.
Authors
- Nitamar Abdala (ORCID: https://orcid.org/0000-0002-0421-0959)
- André Yui Aihara (ORCID: https://orcid.org/0000-0002-3194-9409)
- Ana Carolina de Lima Augusto (ORCID: https://orcid.org/0000-0002-5400-3077)
- Eduardo Moreno Judice De Mattos Farina
- André César Ozawa Rodrigues
- Felipe Kitamura (ORCID: https://orcid.org/0000-0002-9992-5630)
- Lucas Ribeiro de Medeiros
- Daisy Terumi Kase (ORCID: https://orcid.org/0000-0002-6019-2580)
- Paulo de Tarso Kawakami Perez (ORCID: https://orcid.org/0000-0002-3860-4411)
- Cassiano Pereira de Barros
- Leonardo Kazunori Tsuji
- Adham do Amaral e Castro
- Ayumi Aihara
Institutions
- Aptiv (United States) (US)
- Hospital Israelita Albert Einstein (BR)
- Faculdade de Ciências Médicas da Santa Casa de São Paulo (BR)
- Palo Alto Institute (US)
- Fleury S.A. (Brazil) (BR)
- Carolina Musculoskeletal Institute (US)
- Universidade Federal de São Paulo (BR)
Publication Details
- Journal
- Skeletal Radiology
- Published
- 2026-03-23
- DOI
- https://doi.org/10.1007/s00256-026-05198-z
- Primary Topic
- Total Knee Arthroplasty Outcomes
- Type
- article
- Field-Weighted Citation Impact
- 0.00