AI automated grid placement in the OMERACT knee inflammation MRI scoring system (KIMRISS) for bone marrow lesion assessment: A multi-reader exercise
Authors' conclusion
Automated grid placement is a reliable and feasible improvement to KIMRISS that could improve the ease and reproducibility of quantifying osteoarthritis in clinical trials.
Study context
- Population
- 40 knee MRI cases evaluated by eleven experts11 expert readers
- Participants
- 40 cases
- Comparison
- AI-automated vs manual grid placement for KIMRISS bone marrow lesion (BML) scoring
- Outcome
- Agreement of automated vs manual grids
Methodological detailsmulti-reader exercise, OMERACT Filter
- Multi-reader exercise
- OMERACT Filter
Main finding
As reported in the abstract
Femur spatial similarity, mean Dice Coefficient
0.78
KIMRISS BML baseline score agreement, mean ICC
0.86
KIMRISS BML change score agreement, mean ICC
0.89
Further findings
- Feasibility: System Usability Scale (SUS) for automated grid placement
- 66.1 · mean
Original publication
AI automated grid placement in the OMERACT knee inflammation MRI scoring system (KIMRISS) for bone marrow lesion assessment: A multi-reader exercise. Semin Arthritis Rheum. Published 12 June 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →