Improved Deep Convolutional Neural Network to Classify Osteoarthritis from Anterior Cruciate Ligament Tear Using Magnetic Resonance Imaging

• Published in: Journal of personalized medicine Vol. 11; no. 11; p. 1163
• Main Authors: Awan, Mazhar Javed, Rahim, Mohd Shafry Mohd, Salim, Naomie, Rehman, Amjad, Nobanee, Haitham, Shabir, Hassan
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 09.11.2021; MDPI
• Subjects: Accuracy; Anterior cruciate ligament; Arthritis; Automation; Datasets; Deep learning; Diabetic retinopathy; Injuries; Knee; Ligaments; Machine learning; Magnetic resonance imaging; Meniscus; Neural networks; Osteoarthritis; Performance evaluation; Precision medicine; Support vector machines
• ISSN: 2075-4426; 2075-4426
• DOI: 10.3390/jpm11111163

Anterior cruciate ligament (ACL) tear is caused by partially or completely torn ACL ligament in the knee, especially in sportsmen. There is a need to classify the ACL tear before it fully ruptures to avoid osteoarthritis. This research aims to identify ACL tears automatically and efficiently with a deep learning approach. A dataset was gathered, consisting of 917 knee magnetic resonance images (MRI) from Clinical Hospital Centre Rijeka, Croatia. The dataset we used consists of three classes: non-injured, partial tears, and fully ruptured knee MRI. The study compares and evaluates two variants of convolutional neural networks (CNN). We first tested the standard CNN model of five layers and then a customized CNN model of eleven layers. Eight different hyper-parameters were adjusted and tested on both variants. Our customized CNN model showed good results after a 25% random split using RMSprop and a learning rate of 0.001. The average evaluations are measured by accuracy, precision, sensitivity, specificity, and F1-score in the case of the standard CNN using the Adam optimizer with a learning rate of 0.001, i.e., 96.3%, 95%, 96%, 96.9%, and 95.6%, respectively. In the case of the customized CNN model, using the same evaluation measures, the model performed at 98.6%, 98%, 98%, 98.5%, and 98%, respectively, using an RMSprop optimizer with a learning rate of 0.001. Moreover, we also present our results on the receiver operating curve and area under the curve (ROC AUC). The customized CNN model with the Adam optimizer and a learning rate of 0.001 achieved 0.99 over three classes was highest among all. The model showed good results overall, and in the future, we can improve it to apply other CNN architectures to detect and segment other ligament parts like meniscus and cartilages.