ACD 3D U-Net and 3D nnU-Net provided rapid and accurate automated segmentation of abdominal subcutaneous and visceral adipose tissue on longitudinal MRI, achieving median Dice scores ≥0.976 and ICC >0.997.
Observational (n=920)
Yes
Does automated abdominal SAT/VAT segmentation using 3D convolutional neural networks accurately quantify adipose tissue volume compared to reference measurements in adults with overweight/obesity?
ACD 3D U-Net and 3D nnU-Net provide rapid and accurate automated quantification of abdominal SAT and VAT volumes on longitudinal MRI in adults with overweight/obesity.
OBJECTIVE: Increased subcutaneous and visceral adipose tissue (SAT/VAT) volume is associated with risk for cardiometabolic diseases. This work aimed to develop and evaluate automated abdominal SAT/VAT segmentation on longitudinal MRI in adults with overweight/obesity using attention-based competitive dense (ACD) 3D U-Net and 3D nnU-Net with full field-of-view volumetric multi-contrast inputs. MATERIALS AND METHODS: 920 adults with overweight/obesity were scanned twice at multiple 3 T MRI scanners and institutions. The first scan was divided into training/validation/testing sets (n = 646/92/182). The second scan from the subjects in the testing set was used to evaluate the generalizability for longitudinal analysis. Segmentation performance was assessed by measuring Dice scores (DICE-SAT, DICE-VAT), false negatives (FN), and false positives (FP). Volume agreement was assessed using the intraclass correlation coefficient (ICC). RESULTS: ACD 3D U-Net achieved rapid ( 0.997) in longitudinal analysis. DISCUSSION: ACD 3D U-Net and 3D nnU-Net can be automated tools to quantify abdominal SAT/VAT volume rapidly, accurately, and longitudinally in adults with overweight/obesity.
Kafalı et al. (Thu,) conducted a observational in Overweight and obesity (n=920). ACD 3D U-Net and 3D nnU-Net vs. Manual reference segmentation and 3D U-Net was evaluated on Median DICE-SAT and DICE-VAT scores. ACD 3D U-Net and 3D nnU-Net provided rapid and accurate automated segmentation of abdominal subcutaneous and visceral adipose tissue on longitudinal MRI, achieving median Dice scores ≥0.976 and ICC >0.997.