Automated Segmentation of Visceral, Deep Subcutaneous, and Superficial Subcutaneous Adipose Tissue Volumes in MRI of
Yeshe Manuel Kway1, Kashthuri Thirumurugan1, Mya Thway Tint1
1Singapore Institute for Clinical Sciences (Y.M.K., K.T., M.T.T., N.M., L.P.C.S., Y.S.C., M.V.F., J.G.E., Y.S.L., S.S.V., S.A.S.) and Institute of Bioengineering and Bioimaging (S.S.V.), Agency for Science Technology and Research, 30 Medical Dr, Singapore 117609; Departments of Medicine (Y.M.K., J.G.E.), Obstetrics and Gynaecology (M.T.T., Y.S.C.), and Pediatrics (L.P.C.S., Y.S.L.), Yong Loo Lin School of Medicine, National University of Singapore, Singapore; Khoo Teck Puat-National University Children's Medical Institute, National University Hospital, Singapore (L.P.C.S., Y.S.L.); Departments of Pediatric Endocrinology (F.K.P.Y.), Obstetrics and Gynaecology (K.H.T.), and Diagnostic and Interventional Imaging (M.V.F.), KK Women's and Children's Hospital, Singapore; Pediatrics Academic Clinical Programme (F.K.P.Y.), Academic Medicine (K.H.T.), Duke-National University of Singapore Medical School, Singapore (F.K.P.Y., K.H.T.); Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore (F.K.P.Y.); Medical Research Council Lifecourse Epidemiology Unit and National Institute for Health Research Southampton Biomedical Research Centre, University of Southampton and University Hospital Southampton National Health Service Foundation Trust, Southampton, England (K.M.G.); School of Engineering, Pforzheim University, Pforzheim, Germany (U.C.M.); Department of General Practice and Primary Health Care, University of Helsinki and Helsinki University Hospital, Helsinki, Finland (J.G.E.); Folkhälsan Research Center, Helsinki, Finland (J.G.E.); and Saw Swee Hock School of Public Health, National University Health System and National University of Singapore, Singapore (M.F.); Institute of Data Science, National University of Singapore, Singapore (M.F.).
Purpose:
To develop and evaluate an automated segmentation method for accurate quantification of abdominal adipose tissue (AAT) depots (superficial subcutaneous adipose tissue [SSAT], deep subcutaneous adipose tissue [DSAT], and visceral adipose tissue [VAT]) in neonates and young children.
Materials And Methods:
This was a secondary analysis of prospectively collected data, which used abdominal MRI data from Growing Up in Singapore Towards healthy Outcomes, or GUSTO, a longitudinal mother-offspring cohort, to train and evaluate a convolutional neural network for volumetric AAT segmentation. The data comprised imaging volumes of 333 neonates obtained at early infancy (age ≤2 weeks, 180 male neonates) and 755 children aged either 4.5 years (n = 316, 150 male children) or 6 years (n = 439, 219 male children). The network was trained on images of 761 randomly selected volumes (neonates and children combined) and evaluated on 100 neonatal volumes and 227 child volumes by using 10-fold validation. Automated segmentations were compared with expert-generated manual segmentation. Segmentation performance was assessed using Dice scores.
Results:
When the model was tested on the test datasets across the 10 folds, the model had strong agreement with the ground truth for all testing sets, with mean Dice similarity scores for SSAT, DSAT, and VAT, respectively, of 0.960, 0.909, and 0.872 in neonates and 0.944, 0.851, and 0.960 in children. The model generalized well to different body sizes and ages and to all abdominal levels.
Conclusion:
The proposed segmentation approach provided accurate automated volumetric assessment of AAT compartments on MR images of neonates and children.Keywords Pediatrics, Deep Learning, Convolutional Neural Networks, Water-Fat MRI, Image Segmentation, Deep and Superficial Subcutaneous Adipose Tissue, Visceral Adipose TissueClinical trial registration no. NCT01174875 Supplemental material is available for this article. © RSNA, 2021.
