Discriminative Deep Neural Network for Predicting Knee OsteoArthritis in Early Stage

Knee osteoarthritis (OA) is a degenerative joint disease that causes physical disability worldwide and has a significant impact on public health. The diagnosis of OA is often made from X-ray images, however, this diagnosis suffers from subjectivity as it is achieved visually by evaluating symptoms according to the radiologist experience/expertise. In this article, we introduce a new deep convolutional neural network based on the standard DenseNet model to automatically score early knee OA from X-ray images. Our method consists of two main ideas: improving network texture analysis to better identify early signs of OA, and combining prediction loss with a novel discriminative loss to address the problem of the high similarity shown between knee joint radiographs of OA and non-OA subjects. Comprehensive experimental results over two large public databases demonstrate the potential of the proposed network.