Schneider, D.* ; Eggebrecht, T.* ; Linder, A.* ; Linder, N.* ; Schaudinn, A.* ; Blüher, M. ; Denecke, T.* ; Busse, H.*
Abdominal fat quantification using convolutional networks.
Eur. Radiol. 33, 8957-8964 (2023)
OBJECTIVES: To present software for automated adipose tissue quantification of abdominal magnetic resonance imaging (MRI) data using fully convolutional networks (FCN) and to evaluate its overall performance-accuracy, reliability, processing effort, and time-in comparison with an interactive reference method. MATERIALS AND METHODS: Single-center data of patients with obesity were analyzed retrospectively with institutional review board approval. Ground truth for subcutaneous (SAT) and visceral adipose tissue (VAT) segmentation was provided by semiautomated region-of-interest (ROI) histogram thresholding of 331 full abdominal image series. Automated analyses were implemented using UNet-based FCN architectures and data augmentation techniques. Cross-validation was performed on hold-out data using standard similarity and error measures. RESULTS: The FCN models reached Dice coefficients of up to 0.954 for SAT and 0.889 for VAT segmentation during cross-validation. Volumetric SAT (VAT) assessment resulted in a Pearson correlation coefficient of 0.999 (0.997), relative bias of 0.7% (0.8%), and standard deviation of 1.2% (3.1%). Intraclass correlation (coefficient of variation) within the same cohort was 0.999 (1.4%) for SAT and 0.996 (3.1%) for VAT. CONCLUSION: The presented methods for automated adipose-tissue quantification showed substantial improvements over common semiautomated approaches (no reader dependence, less effort) and thus provide a promising option for adipose tissue quantification. CLINICAL RELEVANCE STATEMENT: Deep learning techniques will likely enable image-based body composition analyses on a routine basis. The presented fully convolutional network models are well suited for full abdominopelvic adipose tissue quantification in patients with obesity. KEY POINTS: • This work compared the performance of different deep-learning approaches for adipose tissue quantification in patients with obesity. • Supervised deep learning-based methods using fully convolutional networks were suited best. • Measures of accuracy were equal to or better than the operator-driven approach.
Altmetric
Additional Metrics?
Publication type
Article: Journal article
Document type
Scientific Article
Thesis type
Editors
Corresponding Author
Keywords
Adipose Tissue ; Deep Learning ; Image Processing, Computer-assisted ; Magnetic Resonance Imaging ; Obesity; Subcutaneous Adipose-tissue; Unsupervised Assessment; Segmentation; Software; Compartments
Keywords plus
ISSN (print) / ISBN
0938-7994
e-ISSN
1432-1084
ISBN
Book Volume Title
Conference Title
Conference Date
Conference Location
Proceedings Title
Quellenangaben
Volume: 33,
Issue: 12,
Pages: 8957-8964
Article Number: ,
Supplement: ,
Series
Publisher
Springer
Publishing Place
One New York Plaza, Suite 4600, New York, Ny, United States
University
University place
Faculty
Publication date
0000-00-00
Application date
0000-00-00
Patent owner
Further owners
Application country
Patent priority
Reviewing status
Peer reviewed
Institute(s)
Helmholtz Institute for Metabolism, Obesity and Vascular Research (HI-MAG)
Grants
German Federal Ministry of Education and Research - BMBF