Detection and Classification of The Osteoarthritis in Knee Joint Using Transfer Learning with Convolutional Neural Networks (CNNs)

Abstract

Osteoarthritis (OA) is a disease of human joints, especially the knee joint, due tosignificant weight of the body. This disease leads to rupture and degeneration ofparts of the cartilage in the knee joint, which causes severe pain. Diagnosis of thisdisease can be obtained through X-ray. Deep learning has become a popular solutionto medical issues due to its fast progress in recent years. This research aims todesign and build a classification system to minimize the burden on doctors and helpradiologists to assess the severity of the pain, enable them to make an optimaldiagnosis and describe the correct treatment. Deep learning-based approaches, suchas Convolution Neural Networks (CNNs), have been used to detect knee OA usingtransfer learning with fine-tuning. This paper proposed three versions of pre-trainednetworks (VGG16, VGG19, and ResNet50) for handling the classification task.According to the classification results, The proposed model ResNet50 outperformedthe other models a validation accuracy of 91.51% has been obtained.