Automated abdominal adipose tissue segmentation and volume quantification on longitudinal MRI using 3D convolutional neural networks with multi-contrast inputs

• Published in: Magma (New York, N.Y.) Vol. 37; no. 3; pp. 491 - 506
• Main Authors: Kafali, Sevgi Gokce, Shih, Shu-Fu, Li, Xinzhou, Kim, Grace Hyun J., Kelly, Tristan, Chowdhury, Shilpy, Loong, Spencer, Moretz, Jeremy, Barnes, Samuel R., Li, Zhaoping, Wu, Holden H.
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.07.2024
• Subjects: Abdominal Fat - diagnostic imaging; Adult; Aged; Algorithms; Basic Science - Image analysis; Biomedical Engineering and Bioengineering; Computer Appl. in Life Sciences; Contrast Media; Female; Health Informatics; Humans; Image Interpretation, Computer-Assisted - methods; Imaging; Imaging, Three-Dimensional - methods; Intra-Abdominal Fat - diagnostic imaging; Longitudinal Studies; Magnetic Resonance Imaging - methods; Male; Medicine; Medicine & Public Health; Middle Aged; Neural Networks, Computer; Obesity - diagnostic imaging; Overweight - diagnostic imaging; Radiology; Reproducibility of Results; Research Article; Solid State Physics; Obesity; Adipose tissue; Magnetic resonance imaging; Neural networks; Automated segmentation; Body composition; Overweight
• ISSN: 1352-8661; 0968-5243; 1352-8661
• DOI: 10.1007/s10334-023-01146-3

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 (< 4.8 s/subject) segmentation with high DICE-SAT (median ≥ 0.994) and DICE-VAT (median ≥ 0.976), small FN (median ≤ 0.7%), and FP (median ≤ 1.1%). 3D nnU-Net yielded rapid (< 2.5 s/subject) segmentation with similar DICE-SAT (median ≥ 0.992), DICE-VAT (median ≥ 0.979), FN (median ≤ 1.1%) and FP (median ≤ 1.2%). Both models yielded excellent agreement in SAT/VAT volume versus reference measurements (ICC > 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.