What question did this study set out to answer?

This research aims to improve the accuracy of axial spondyloarthritis diagnosis via automated MRI analysis.

February 21, 2026Open Access

Learning from multiple readings for axial spondyloarthritis classification of the sacroiliac joints

Key Points

This research aims to improve the accuracy of axial spondyloarthritis diagnosis via automated MRI analysis.
Developed a machine learning system for sacroiliac joint delineation and lesion classification.
Utilized a multi-reader learning framework to account for reader variability.
Evaluated model performance through patient-wise cross-validation on various clinical datasets.
Lesion detection included five types assessed using T1-weighted and STIR sequences.
Achieved AUCs from 0.85 to 0.99 for lesion classification across five types.
95% of errors in contouring were below 2.76mm in the test set.
Performance equivalent to expert inter-reader agreement, indicating high reliability in lesion detection.

Abstract

Magnetic resonance imaging (MRI) is a cornerstone in the evaluation and monitoring of axial spondyloarthritis (axSpA), a chronic inflammatory condition primarily affecting the sacroiliac joints (SIJs), spine, entheses, and peripheral joints. Accurate quantification of axSpA-related changes on MRI is critical for effective research and patient management; however, current lesion detection and grading approaches suffer from substantial intra- and inter-reader variability, limiting their consistency and reliability. To address these challenges, we propose a fully automated machine learning system for SIJ delineation and lesion classification on coronal MRI. The end-to-end pipeline automatically extracts SIJ contours using a vector-field—based open-contour model and classifies the presence or absence of five lesion types (bone marrow oedema, ankylosis, sclerosis, erosions, and fatty lesions) using both T1-weighted and STIR sequences. A multi-reader learning framework is employed to explicitly model inter- and intra-reader variability by leveraging multiple readings and consensus labels. Model performance was evaluated using patient-wise cross-validation on data from the MEASURE-1 clinical trial and further validated on other clinical datasets (PREVENT, SURPASS). Lesion classification performance was assessed using area under the receiver operating characteristic curve (AUC), balanced accuracy, sensitivity, and specificity, while contouring accuracy was quantified using root-mean-square error, where we found that 95% of the whole test set had errors below 2.76mm. The proposed approach achieved AUCs ranging from 0.85 to 0.99 across the five lesion types, with the highest performance observed when using consensus-based labels, and results were comparable to expert inter-reader agreement. These findings demonstrate that fully automated SIJ delineation and lesion scoring can achieve expert-level performance and have the potential to reduce reader burden and variability in large-scale axSpA MRI studies.

Mark Helpful

Bookmark

Relay

View Full Paper