Estimating time-to-total knee replacement on radiographs and MRI: a multimodal approach using self-supervised deep learning

• Published in: Radiology advances Vol. 1; no. 4; p. umae030
• Main Authors: Cigdem, Ozkan, Chen, Shengjia, Zhang, Chaojie, Cho, Kyunghyun, Kijowski, Richard, Deniz, Cem M
• Format: Journal Article
• Language: English
• Published: England Oxford University Press 01.01.2022
• Subjects: deep learning; self-supervised learning; multimodal learning; knee osteoarthritis; time-to-TKR prediction

Purpose Accurately predicting the expected duration of time until total knee replacement (time-to-TKR) is crucial for patient management and health care planning. Predicting when surgery may be needed, especially within shorter windows like 3 years, allows clinicians to plan timely interventions and...