Local MRI-based measures of thigh adipose tissue derived from fully automated deep convolutional neural network-based segmentation show a comparable responsiveness to bidirectional change in body weight as from quality controlled manual segmentation

Background: Thigh intermuscular (IMF) and subcutaneous (SCF) fat are associated with joint function, inflammation and knee osteoarthritis. Fully automated segmentation from MRI is important to study the above relationship in larger cohorts. However, such algorithms are not clinically evaluated for longitudinal studies. Our aim was to evaluate a fully automated U-Net segmentation approach and its ability to detect longitudinal changes in thigh IMF and SCF during weight changes compared to manual segmentation.

Methods: 103 Osteoarthritis Initiative subjects, were studied, 52 with> 10% weight loss, and 51 with> 10% weight gain over 2-years. Longitudinal change in IMF and SCF were determined from baseline and year-2 axial thigh MRIs using U-Net segmentation. The standardised response mean (SRM) was used as measure of sensitivity to change.

Results: The U-Net took substantially less time (single-slice MRI:< 1 s) and IMF and SCF showed very similar sensitivity to change as manual segmentation: With an average weight gain of + 14%, we observed an + 12% /+ 26% increase in IMF / SCF (SRM=0.99 /1.03) using the U-Net, compared with + 21% /+ 27% (SRM=0.60 /1.07) for manual segmentation. During an average weight loss of - 18%, we observed an - 14% /- 22% reduction in IMF /SCF (SRM = - 1.04 /-1.20) using the U-Net, compared with - 16% /- 22% (SRM = - 0.70 /-1.23) for manual segmentation.

Conclusion: U-Net segmentation replicates longitudinal changes of IMF and SCF associated with weight changes with a similar sensitivity to change as manual segmentation. This method is applicable to large databases for studying relationships between IMF and SCF and various disease conditions.