Classification and risk estimation of osteoarthritis using deep learning methods

The classification of knee osteoarthritis is solely based on contextual factors, with image processing algorithms playing a significant role in computer-aided diagnosis (CAD) systems. The inconsistent real-time pre-processing, on the other hand, has a significant impact on the diagnosing process. In this work, a Densely Connected Fully Convolutional Network (DFCN) for knee osteoarthritis classifier based on multiple learning (ML) strategies effectively classify knee osteoarthritis on the basis of risk estimation. Spatial osteoarthritis contextual vectors extracted by identifying the relationship between contextual variables using a machine learning approach. The hidden convolutional layers are used to compute edge interpretation, contextual cues, and input correction. The fused layer, which is simply a concentration of derived features, supports automatic learning of contextual features of osteoarthritis classification. The standard datasets from the Osteoarthritis Initiative (OAI) and the Multicentre Osteoarthritis Study (MOST) are used for experimental purposes to validate the proposed method. The results shows that the proposed DFCN is significantly improves the feature recognition for accurate classification around 94 % which is significantly higher than existing CNN results and flexibility to real-time implementation in the CAD system. It can also be used to automatically detect osteoarthritis types using a lightweight CNN architecture.