Computer-Assisted Image Analysis Demonstrates Superior Results in MRI for Inflammatory Arthritis

Computer-aided image quantification technology demonstrated superior reliability and precision in quantifying magnetic resonance imaging (MRI) among patients with inflammatory arthritis, according to results from a systematic review and meta-analysis published in ACR Open Rheumatology.

“Early diagnosis of inflammatory arthritis and accurate monitoring of disease progression are central for optimizing management of patients with rheumatoid arthritis and other types of arthritis,” the investigators stated in the report. Despite the diagnostic value of MRI, there are still some limitations in terms of time and reliability. The use of computer-aided image quantification technology has “the advantage of better reproducibility and time efficiency,” they said.

The study included 1342 MRIs of patients with inflammatory arthritis and arthritis-related structural damage in peripheral joints. The average age of participants was 54.8 years, the duration of arthritis was 3.6 years, and 66.7% of the participants were women. The damage in the peripheral joints was assessed using 3 methods: noncontrast-enhanced method, contrast-enhanced (CE) method, and dynamic CE (DCE)-MRI using (semi)automated method.

The intra- and inter-reader reliability for computer-aided quantification were generally superior compared to conventional methods. “Meta-regression showed that computer-aided and manual methods provide comparable reliability (P > 0.05), the authors stated. “Computer-aided measurement of bone erosion volume (r = 0.92), SV (r = 0.82), and DCE-MRI biomarkers (r = 0.72 N-total; r = 0.74 N-plateau; r = 0.64 N-washout) were significantly correlated with the Rheumatoid Arthritis Magnetic Resonance Imaging Score (RAMRIS; P < 0.01), allowing for earlier assessment of drug efficacy.”

Analyses revealed that computer-aided image quantification technologies scored excellent on reliability, validity, and feasibility.

“Computer-aided evaluation of inflammatory arthritis is an emerging field and should be considered as a viable complement to conventional observer-based scoring methods for clinical trials application,” the researchers insisted.

—Priyam Vora

Reference:
Haj-Mirzajan A, Kubassova O, Boesen M, Carrino J and Bird P. Computer-assisted image analysis in assessment of peripheral joint MRI in inflammatory arthritis: A systematic review and meta-analysis. ACR Open Rheum. 2022; 4: 721-734. DOI: https://doi.org/10.1002/acr2.11450