In this research, we investigated how to use semi-supervised learning to overcome scarcity of training data and improve model performance in the task of detecting Knee Osteoarthritis (OA) which is a chronic degenerative disorder of joints and is the most common reason leading to total knee joint replacement (TKR).
Our semi-supervised learning approach is based on Unsupervised Data Augmentation (UDA) along with valid perturbations for radiographs to enhance the performance of supervised TKR outcome prediction model. Our results suggest that the use of semi-supervised approach provides superior results compared to the supervised approach (AUC of 0.79 ± 0.04 vs 0.74 ± 0.04).