Computer-Aided Knee Osteoarthritis Classification System Using Artificial Neural Netwrok (ANN)

Knee osteoarthritis (OA) is a form of joint disorder caused by gradual degeneration of articular cartilage lining between knee joints. It is the leading cause of disability among elder population. In recent years, magnetic resonance imaging (MRI) technique has been widely used in the diagnosis and monitoring of knee OA. However, the conventional interpretation of MR images through visual inspection is very subjective, time consuming, inconsistent, and open to misclassification. Hence, an automated and accurate classifier is needed to enhance the diagnostic values of MRI. In this study, an artificial neural network (ANN) based classifier is proposed to classify the knee MR image. There are three stages in the design of ANN classifier including image labeling, Discrete Wavelet Transform (DWT) based feature extraction, and ANN-based classification. The proposed method obtained 98.5% classification accuracy on training images and 94.67% of classification accuracy on testing images of the selected datasets.