Automating classification of osteoarthritis according to Kellgren-Lawrence in the knee using deep learning in an unfiltered adult population

Abstract

Background Prevalence for knee osteoarthritis is rising in both Sweden and globally due to increased age and obesity in the population. This has subsequently led to an increasing demand for knee arthroplasties. Correct diagnosis and classification of a knee osteoarthritis (OA) are therefore of a great interest in following-up and planning for either conservative or operative management. Most orthopedic surgeons rely on standard weight bearing radiographs of the knee. Improving the reliability and reproducibility of these interpretations could thus be hugely beneficial. Recently, deep learning which is a form of artificial intelligence (AI), has been showing promising results in interpreting radiographic images. In this study, we aim to evaluate how well an AI can classify the severity of knee OA, using entire image series and not excluding common visual disturbances such as an implant, cast and non-degenerative pathologies. Methods We selected 6103 radiographic exams of the knee taken at Danderyd University Hospital between the years 2002-2016 and manually categorized them according to the Kellgren & Lawrence grading scale (KL). We then trained a convolutional neural network (CNN) of ResNet architecture using PyTorch. We evaluated the results against a test set of 300 exams that had been reviewed independently by two senior orthopedic surgeons who settled eventual interobserver disagreements through consensus sessions. Results The CNN yielded an overall AUC of more than 0.87 for all KL grades except KL grade 2, which yielded an AUC of 0.8 and a mean AUC of 0.92. When merging adjacent KL grades, all but one group showed near perfect results with AUC > 0.95 indicating excellent performance. Conclusion We have found that we could teach a CNN to correctly diagnose and classify the severity of knee OA using the KL grading system without cleaning the input data from major visual disturbances such as implants and other pathologies.

Proximal fibular osteotomy versus high tibial osteotomy for treating knee osteoarthritis: a systematic review and meta-analysis

“…PFO is a simple, trauma-minimized and effective procedure that enables patients to perform rehabilitation exercises and bear weight at earlier postoperative stage, which is widely used in recent decades [ 43 ]. PFO is based on the “non-uniform settlement” theory proposed by Zhang et al [ 10 , 11 ].…”

Stem cell-based therapy for human diseases

“…There are two types of OA: (1) primary OA or idiopathic OA and secondary OA caused by causative factors such as trauma, surgery, and abnormal joint development at birth. 66 As conventional treatments for OA are not consistent in their effectiveness and might cause unbearable pain as well as long-term rehabilitation (in the case of joint replacement), there is a need for a more reliable, less painful, and curative therapy targeting the root of OA. 67 Thus, stem cell therapy has recently emerged as an alternative approach for OA and has drawn great attention in the regenerative field.…”

Deep learning-assisted knee osteoarthritis automatic grading on plain radiographs: the value of multiview X-ray images and prior knowledge

“…The lowest accuracy in our study was 0.87, but this only occurred when anteroposterior images were used. In addition, many researchers found using the ResNet network framework for grading knee OA to be highly effective, with the overall AUC value reaching more than 90% and the highest accuracy rate reaching 98.90% ( 41 - 43 ). These results are in good agreement with our experimental results, as we obtained an overall accuracy of 0.94 using the ResNet-50 network on the anteroposterior images.…”