Spondyloarthritis & psoriatic arthritis
Assessment of axial spondyloarthritis activity using a magnetic resonance imaging-based multi-region-of-interest fusion model
Authors' conclusion
The multi-ROI fusion radiomics model developed in this study differentiated between active and non-active axSpA using sacroiliac FS T2w-MRI.
Study context
- Population
- Patients diagnosed with axial spondyloarthritis (axSpA); Fat-suppressed (FS) T2-weighted (T2w) magnetic resonance imaging (MRI) of sacroiliac joints
- Participants
- 109 patients
- Comparison
- MRI radiomics fusion model for active vs non-active axSpA
- Non-active axSpAn = 68
- Active axSpAn = 41
- Outcome
- Differentiation of active from non-active axSpA by radiomics model (accuracy, sensitivity, specificity)
Methodological detailsradiomics, training and testing cohorts (8:2), 3.0 T sacroiliac MRI, multi-ROI fusion model
- Radiomics
- Training and testing cohorts (8:2)
- 3.0 T sacroiliac MRI
- multi-ROI fusion model
Performance
As reported in the abstract
Fusion ROI model performance, training vs testing cohort
Accuracy (training vs testing)
0.90 vs.0.81
Sensitivity (training vs testing)
0.90 vs. 0.75
Specificity (training vs testing)
0.90 vs. 0.85
Further findings
Radiomics features extracted (Circle- and Facet-based models)
- Features extracted
- 2284
Original publication
Assessment of axial spondyloarthritis activity using a magnetic resonance imaging-based multi-region-of-interest fusion model. Arthritis Res Ther. Published 24 November 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →