biostudies-literatureUnknown23(1)Schiratti JBServier<h4>Background</h4>The identification of patients with knee osteoarthritis (OA) likely to progress rapidly in terms of structure is critical to facilitate the development of disease-modifying drugs.<h4>Methods</h4>Using 9280 knee magnetic resonance (MR) images (3268 patients) from the Osteoarthritis Initiative (OAI) database , we implemented a deep learning method to predict, from MR images and clinical variables including body mass index (BMI), further cartilage degradation measured by joint space narrowing at 12 months.<h4>Results</h4>Using COR IW TSE images, our classification model achieved a ROC AUC score of 65%. On a similar task, trained radiologists obtained a ROC AUC score of 58.7% highlighting the difficulty of the classification task. Additional analyses conducted in parallel to predict pain grade evaluated by the WOMAC pain index achieved a ROC AUC score of 72%. Attention maps provided evidence for distinct specific areas as being relevant in those two predictive models, including the medial joint space for JSN progression and the intra-articular space for pain prediction.<h4>Conclusions</h4>This feasibility study demonstrates the interest of deep learning applied to OA, with a potential to support even trained radiologists in the challenging task of identifying patients with a high-risk of disease progression.Arthritis research & therapy262https://www.ebi.ac.uk/biostudies/studies/S-EPMC8521982biostudies-literatureA deep learning method for predicting knee osteoarthritis radiographic progression from MRI.PMC8521982Lalande APueyo MMoingeon PGabarroca CGuillier RDubois RWainrib GClozel THerent PSchiratti JBDachary JCahane DKeime-Guibert FfalseA deep learning method for predicting knee osteoarthritis radiographic progression from MRI.<h4>Background</h4>The identification of patients with knee osteoarthritis (OA) likely to progress rapidly in terms of structure is critical to facilitate the development of disease-modifying drugs.<h4>Methods</h4>Using 9280 knee magnetic resonance (MR) images (3268 patients) from the Osteoarthritis Initiative (OAI) database , we implemented a deep learning method to predict, from MR images and clinical variables including body mass index (BMI), further cartilage degradation measured by joint space narrowing at 12 months.<h4>Results</h4>Using COR IW TSE images, our classification model achieved a ROC AUC score of 65%. On a similar task, trained radiologists obtained a ROC AUC score of 58.7% highlighting the difficulty of the classification task. Additional analyses conducted in parallel to predict pain grade evaluated by the WOMAC pain index achieved a ROC AUC score of 72%. Attention maps provided evidence for distinct specific areas as being relevant in those two predictive models, including the medial joint space for JSN progression and the intra-articular space for pain prediction.<h4>Conclusions</h4>This feasibility study demonstrates the interest of deep learning applied to OA, with a potential to support even trained radiologists in the challenging task of identifying patients with a high-risk of disease progression.2021-01-01T00:00:00Z2021 Oct2025-04-04T19:45:11.503Z2025-04-04T19:45:11.503ZS-EPMC85219823466344010.1186/s13075-021-02634-4