RATING: Medical-knowledge-guided rheumatoid arthritis assessment from multimodal ultrasound images via deep learning

Abstract

AbstractUltrasound (US) examination has been commonly utilized in clinical practice for assessing the rheumatoid arthritis (RA) activity, which is hampered by low intra-observer and inter-observer agreement as well as considerable time and expense to train experienced radiologists. Here, we present the Rheumatoid ArthriTIs kNowledge Guided (RAT ING) model that scores RA activity and generates interpretable features to assist radiologists’ decision-making. The RATING model achieved an accuracy of 86.1% (95% confidence interval (CI)=82.5%–90.1%) in the clinical trial setting, and achieved an accuracy of 85.0% (95% CI=80.5%–89.1%) on the US images collected from an external medical center. An AI-assisted reader study demonstrated that the RATING model improved the average accuracy of ten radiologists from 41.4% to 64.0%. Automated AI models for the assessment of RA may facilitate US RA examination and provide support for clinical decision-making.