Associations between deep learning-derived infrapatellar fat pad volume on MRI with knee cartilage thickness and imaging features of knee osteoarthritis: Data from the Osteoarthritis Initiative
Authors' conclusion
Larger IPFPVol was associated with greater patellofemoral cartilage thickness and less severe osteoarthritis features in the patellofemoral and lateral tibiofemoral joint.
Study context
- Population
- Baseline data from the Osteoarthritis Initiativefinal analysis
- Participants
- 4,257 participants
- Outcome
- Knee cartilage thickness (LT, medial tibia (MT), LF, medial femur (MF), patella) and WORMS scores for cartilage, BMELL and menisci by subregion, in relation to IPFPVol on MRI
- Follow-up
- Baseline
Methodological detailsdeep learning-derived MRI volumetric segmentation, linear regression with infrapatellar fat pad volume (IPFPVol) × subregion interaction, adjusted for relevant confounders
- Deep learning-derived MRI volumetric segmentation
- Linear regression with IPFPVol × subregion interaction
- Adjusted for relevant confounders
Main finding
As reported in the abstract
- Cartilage thickness, patella: β
- 0.011 mm per cm³ (95% CI 0.006-0.016)
- Cartilage thickness, lateral tibia (LT): β
- 0.015 mm per cm³ (95% CI 0.010-0.019)
- WORMS cartilage lesion score, patella: β
- −0.036 points per cm³ (95% CI −0.061 to −0.010)
- WORMS cartilage lesion score, lateral femur (LF): β
- −0.058 points per cm³ (95% CI −0.076 to −0.039)
- WORMS cartilage lesion score, LT: β
- −0.079 points per cm³ (95% CI −0.099 to −0.060)
- WORMS bone marrow edema-like lesions (BMELL) score, LT: β
- −0.027 points per cm³ (95% CI −0.036 to −0.018)
- WORMS lateral meniscus score: β
- −0.054 points per cm³ (95% CI −0.070 to −0.037)
Observational data: associations, not effects.
Original publication
Associations between deep learning-derived infrapatellar fat pad volume on MRI with knee cartilage thickness and imaging features of knee osteoarthritis: Data from the Osteoarthritis Initiative. Osteoarthritis Cartilage. Published 7 August 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →