Scoring magnetic resonance imaging (MRI) inflammation and structural lesions in sacroiliac joints of patients with axial spondyloarthritis: assessment of all MRI slices of the cartilaginous compartment versus standardized six or five slices

Research on automatic recognition radiomics algorithm for early sacroiliac arthritis based on sacroiliac MRI imaging

OBJECTIVE

To create an automated machine learning model using sacroiliac joint MRI imaging for early sacroiliac arthritis detection, aiming to enhance diagnostic accuracy.

METHODS

We conducted a retrospective analysis involving 71 patients with early sacroiliac arthritis and 85 patients with normal sacroiliac joint MRI scans. Transverse T1WI and T2WI sequences were collected and subjected to radiomics analysis by two physicians. Patients were randomly divided into training and test groups at a 7:3 ratio. Initially, we extracted the region of interest on the sacroiliac joint surface using ITK-SNAP 3.6.0 software and extracted radiomic features. We retained features with an Intraclass Correlation Coefficient > 0.80, followed by filtering using max-relevance and min-redundancy (mRMR) and LASSO algorithms to establish an automatic identification model for sacroiliac joint surface injury. Receiver operating characteristic (ROC) curves were plotted, and the area under the ROC curve (AUC) was calculated. Model performance was assessed by accuracy, sensitivity, and specificity.

RESULTS

We evaluated model performance, achieving an AUC of 0.943 for the SVM-T1WI training group, with accuracy, sensitivity, and specificity values of 0.878, 0.836, and 0.943, respectively. The SVM-T1WI test group exhibited an AUC of 0.875, with corresponding accuracy, sensitivity, and specificity values of 0.909, 0.929, and 0.875, respectively. For the SVM-T2WI training group, the AUC was 0.975, with accuracy, sensitivity, and specificity values of 0.933, 0.889, and 0.750. The SVM-T2WI test group produced an AUC of 0.902, with accuracy, sensitivity, and specificity values of 0.864, 0.889, and 0.800. In the SVM-bimodal training group, we achieved an AUC of 0.974, with accuracy, sensitivity, and specificity values of 0.921, 0.889, and 0.971, respectively. The SVM-bimodal test group exhibited an AUC of 0.964, with accuracy, sensitivity, and specificity values of 0.955, 1.000, and 0.875, respectively.

CONCLUSION

The radiomics-based detection model demonstrates excellent automatic identification performance for early sacroiliitis.

Quantification of Bone Marrow Edema by MRI of the Sacroiliac Joints in Patients Diagnosed with Axial Spondyloarthritis: Results from the ESPeranza Cohort

Objective: To evaluate whether the quantification of bone marrow edema (BMO) of the sacroiliac (SI) joints by magnetic resonance imaging (MRI) improves capacity for axial spondyloarthritis (axSpA) classification in comparison with the assessment of sacroiliitis by Assessment of SpondyloArthritis international Society (ASAS) classification criteria.Method: This prospective study from the ESPeranza cohort involved 66 subjects with an available MRI of the SI joints at baseline. This subgroup includes patients with axSpA (n = 28), peripheral spondyloarthritis (n = 10), and other diagnoses that were not spondyloarthritis (n = 28). Measures of diagnostic usefulness [area under the curve (AUC), sensitivity, specificity, Youden's J statistic, positive and negative likelihood ratios (LR+ and LR-)] were calculated for MRI of the SI joints according to ASAS criteria and for MRI quantified by means of SCAISS (Spanish tool for semi-automatic quantification of sacroiliac inflammation by MRI in spondyloarthritis). This analysis was stratified in patients who were human leucocyte antigen (HLA)-B27 positive and negative.Results: The AUC value with BMO quantification was 0.919 [95% confidence interval (CI) 0.799-1] for HLA-B27-positive patients and 0.884 (95% CI 0.764-1) for HLA-B27-negative patients. A SCAISS cut-off point of 80 units obtained a specificity of 94.4% and LR+ 7.5, while assessment by ASAS criteria showed a specificity value of 90% and LR+ 6.4.Conclusion: For patients with suspected axSpA, quantification of BMO improves the predictive capacity of MRI of the SI joints, for both HLA-B27-positive and HLA-B27-negative patients.Axial spondyloarthritis (axSpA) has a dramatic impact on physical function and quality of life (1). Despite its significant impact, patients with axSpA are normally diagnosed several years after presenting symptoms (2). In this respect, magnetic resonance imaging (MRI) of the sacroiliac (SI) joints has gained significance over the past decade, particularly in the early stages of the disease. Nowadays, imaging tests and human leucocyte antigen (HLA)-B27 testing are among the most important diagnostic procedures for patients with suspected axSpA.