Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

DeepKneeExplainer: Explainable knee osteoarthritis diagnosis from radiographs and magnetic resonance imaging

: Karim, Rezaul; Jiao, Jiao; Döhmen, Till; Cochez, Michael; Beyan, Oya; Rebholz-Schuhmann, Dietrich; Decker, Stefan

Fulltext urn:nbn:de:0011-n-6352431 (84 KByte PDF) - Die Publikation wurde zurückgezogen und durch eine neue Version ersetzt.
MD5 Fingerprint: 861926eedcd139e5340fad426727ce42
(CC) by-nc-nd
Created on: 28.5.2021

Fulltext urn:nbn:de:0011-n-635243-12 (3.2 MByte PDF)
MD5 Fingerprint: 1041e08fdb6dec30a48284d0e5a3cac4
(CC) by-nc-nd
Created on: 3.6.2021

IEEE access 9 (2021), pp.39757-39780
ISSN: 2169-3536
Journal Article, Electronic Publication
Fraunhofer ISI ()
Fraunhofer FIT ()
knee osteoarthritis; biomedical imaging; Deep neural networks; neural ensemble; explainability; Grad-CAM++; layer-wise relevance propagation

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, artifacts, 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 artifacts that could contain unseen images for domain generalization. Then, we extract the region of interests (ROIs) by employing U-Net architecture with 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. We hope that our results will encourage medical researchers and developers to adopt explainable methods and DNN-based analytic pipelines towards an increasing acceptance and adoption of AI-assisted applications in the clinical practice for improved knee OA diagnoses.