Knee Adjacent Obesity

Diagram illustrating an automated deep learning pipeline for detecting knee adjacent subchondral cystic formations from MRI, showing steps from image input and slice selection to knee localization and lateral and medial prediction, with example bounding boxes and final MRI output highlighting detected regions.

Knee-adjacent subcutaneous fat (kaSCF) has emerged as a potential biomarker and risk factor for osteoarthritis (OA) progression. We developed an artificial intelligence-based tool for the automatic segmentation of kaSCF thickness and evaluated the cross-sectional associations between kaSCF, cartilage thickness, magnetic resonance imaging-based cartilage T2 relaxation time, knee pain, and muscle strength independent of body mass index (BMI). We found that greater kaSCF was associated with thinner cartilage in men, higher T2 in women, reduced knee strength, and greater knee pain, independent of BMI. These findings suggest a potential role of kaSCF as a predictor for knee osteoarthritis-related structural, functional, and clinical outcomes independent of the effects of BMI.