“Just Accepted” papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review ...

The KNee OsteoArthritis Prediction (KNOAP2020) challenge was organized to objectively compare methods for the prediction of incident symptomatic radiographic knee osteoarthritis within 78 months on a test set with blinded ground truth. The challenge participants were free to use any available data sources to train their models. A test set of 423 knees from the Prevention of Knee Osteoarthritis in Overweight Females (PROOF) study consisting of magnetic resonance imaging (MRI) and X-ray image data along with clinical risk factors at baseline was made available to all challenge participants. The ground truth outcomes, i.e., which knees developed incident symptomatic radiographic knee osteoarthritis (according to the combined ACR criteria) within 78 months, were not provided to the participants. To assess the performance of the submitted models, we used the area under the receiver operating characteristic curve (ROCAUC) and balanced accuracy (BACC). Seven teams submitted 23 entries in total. A majority of the algorithms were trained on data from the Osteoarthritis Initiative. The model with the highest ROCAUC (0.64 (95% confidence interval (CI): 0.57–0.70)) used deep learning to extract information from X-ray images combined with clinical variables. The model with the highest BACC (0.59 (95% CI: 0.52–0.65)) ensembled three different models that used automatically extracted X-ray and MRI features along with clinical variables. The KNOAP2020 challenge established a benchmark for predicting incident symptomatic radiographic knee osteoarthritis. Accurate prediction of incident symptomatic radiographic knee osteoarthritis is a complex and still unsolved problem requiring additional investigation.

The purpose of this proof‐of‐concept study was to develop three‐dimensional patient‐specific mechanobiological knee joint models to simulate alterations in the fixed charged density (FCD) around cartilage lesions during the stance phase of the walking gait. Two patients with anterior cruciate ligament (ACL) reconstructed knees were imaged at 1 and 3 years after surgery. The magnetic resonance imaging (MRI) data were used for segmenting the knee geometries, including the cartilage lesions. Based on these geometries, finite element (FE) models were developed. The gait of the patients was obtained using a motion capture system. Musculoskeletal modeling was utilized to calculate knee joint contact and lower extremity muscle forces for the FE models. Finally, a cartilage adaptation algorithm was implemented in both FE models. In the algorithm, it was assumed that excessive maximum shear and deviatoric strains (calculated as the combination of principal strains), and fluid velocity, are responsible for the FCD loss. Changes in the longitudinal T_1ρ and T₂ relaxation times were postulated to be related to changes in the cartilage composition and were compared with the numerical predictions. In patient 1 model, both the excessive fluid velocity and strain caused the FCD loss primarily near the cartilage lesion. T_1ρ and T₂ relaxation times increased during the follow‐up in the same location. In contrast, in patient 2 model, only the excessive fluid velocity led to a slight FCD loss near the lesion, where MRI parameters did not show evidence of alterations. Significance: This novel proof‐of‐concept study suggests mechanisms through which a local FCD loss might occur near cartilage lesions. In order to obtain statistical evidence for these findings, the method should be investigated with a larger cohort of subjects.

Automated knee cartilage segmentation for heterogeneous clinical MRI using generative adversarial networks with transfer learning Mingrui Yang, Ceylan Colak, Kishore K. Chundru, Sibaji Gaj, Andreas Nanavati, Morgan H. Jones, Carl S. Winalski, Naveen Subhas, Xiaojuan Li