Evaluating potential for AI automation of quantitative and semi-quantitative MRI scoring in arthritis, especially at the knee: a systematic literature review.

Objective: This systematic review explores key quantitative and semi-quantitative MRI-based scoring systems for arthritis biomarkers, focusing on their potential for automation through AI.

Methods: A systematic review of Medline, PubMed, and Scopus from 2014 to 2024. Keywords included MRI, arthritis, and quantitative/semi-quantitative. From the initial retrieval of 3321 papers, after exclusions, we evaluated the full-text for 129 studies from the past decade, 74 of which related specifically to knee osteoarthritis.

Results: Publications on MRI arthritis scoring systems peaked in 2021 and have declined in recent years, likely due to a shift toward AI-driven automation. We assessed scoring systems for biomarkers including cartilage thickness, bone marrow edema, effusion/synovitis, erosions, osteophytes, intraosseous and periarticular fat metaplasia, and connective tissue integrity (meniscus/labrum), each varying in suitability for AI. Effusion, due to its high MRI T2 contrast, appears relatively straightforward to automate, while cartilage loss remains difficult to accurately quantify and localize despite heavy research interest. AI demonstrates suitability in meniscal tear detection and the potential to automate other biomarkers like BMEs, bone erosion, and osteophyte formation.

Conclusion: AI is increasingly being used to automatically evaluate MRI for arthritis. This review identifies opportunities for AI to enhance longitudinal disease tracking and enable early intervention in arthritis by providing detailed scoring of inflammatory lesions and high-resolution evaluation of structural abnormalities.