Skip to content. | Skip to navigation

Personal tools
You are here: Home Publications DeepKneeExplainer: Explainable Knee Osteoarthritis Diagnosis from Radiographs and Magnetic Resonance Imaging


Prof. Dr. S. Decker
RWTH Aachen
Informatik 5
Ahornstr. 55
D-52056 Aachen
Tel +49/241/8021501
Fax +49/241/8022321

How to find us

Annual Reports





DeepKneeExplainer: Explainable Knee Osteoarthritis Diagnosis from Radiographs and Magnetic Resonance Imaging

Year 2021
Abstract URL view
PDF URL view
PDF File download

Osteoarthritis (OA) is a degenerative joint disease, which significantly affects middle-aged and elderly people. Although primarily identified via hyaline cartilage change based on medical images, technical bottlenecks like noise, artefacts, and modality impose an enormous challenge on high-precision, objective, and efficient early quantification of OA. Owing to recent advancements, approaches based on neural networks (DNNs) have shown outstanding success in this application domain. However, due to nested non-linear and complex structures, DNNs are mostly opaque and perceived as black-box methods, which raises numerous legal and ethical concerns. Moreover, these approaches do not have the ability to provide the reasoning behind diagnosis decisions in the way humans would do, which poses an additional risk in the clinical setting. In this paper, we propose a novel explainable method for knee OA diagnosis based on radiographs and magnetic resonance imaging (MRI), which we called DeepKneeExplainer. First, we comprehensively preprocess MRIs and radiographs through the deep-stacked transformation technique against possible noises and artefacts that could contain unseen images for domain generalization. Then, we extract the region of interest (ROIs) by employing U-Net architecture with the ResNet backbone. To classify the cohorts, we train DenseNet and VGG architectures on the extracted ROIs. Finally, we highlight class-discriminating regions using gradient-guided class activation maps (Grad-CAM++) and layer-wise relevance propagation (LRP), followed by providing human-interpretable explanations of the predictions. Comprehensive experiments based on the multicenter osteoarthritis study (MOST) cohorts, our approach yields up to 91% classification accuracy, outperforming comparable state-of-the-art approaches.


IEEE Access

Published in

IEEE Access , volume 9 , p. 39757 - 39780 .

Document Actions