Please use this identifier to cite or link to this item: https://doi.org/10.1148/ryai.2021200304
Title: Automated segmentation of visceral, deep subcutaneous, and superficial subcutaneous adipose tissue volumes in MRI of neonates and young children
Authors: Kway, YM
Thirumurugan, K
Tint, MT 
Michael, N
Shek, LPC 
Yap, FKP
Tan, KH 
Godfrey, KM
Chong, YS 
Fortier, MV
Marx, UC
Eriksson, JG 
Lee, YS 
Velan, SS
Feng, M
Sadananthan, SA 
Keywords: Convolutional Neural Networks
Deep Learning
Deep and Superficial Subcutaneous Adipose Tissue
Image Segmentation
Pediatrics
Visceral Adipose Tissue
Water-Fat MRI
Issue Date: 1-Sep-2021
Publisher: Radiological Society of North America (RSNA)
Citation: Kway, YM, Thirumurugan, K, Tint, MT, Michael, N, Shek, LPC, Yap, FKP, Tan, KH, Godfrey, KM, Chong, YS, Fortier, MV, Marx, UC, Eriksson, JG, Lee, YS, Velan, SS, Feng, M, Sadananthan, SA (2021-09-01). Automated segmentation of visceral, deep subcutaneous, and superficial subcutaneous adipose tissue volumes in MRI of neonates and young children. Radiology: Artificial Intelligence 3 (5) : e200304-. ScholarBank@NUS Repository. https://doi.org/10.1148/ryai.2021200304
Abstract: 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 chil-dren). 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. Clinical trial registration no. NCT01174875.
Source Title: Radiology: Artificial Intelligence
URI: https://scholarbank.nus.edu.sg/handle/10635/216277
ISSN: 26386100
DOI: 10.1148/ryai.2021200304
Appears in Collections:Staff Publications
Elements

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
(290)_postprint_Automated Segmentation of Visceral, Deep Subcutaneous, and Superficial....docx9.98 MBMicrosoft Word XML

OPEN

NoneView/Download

SCOPUSTM   
Citations

2
checked on Jan 26, 2023

Page view(s)

105
checked on Feb 2, 2023

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.