Fully automated body composition analysis in routine CT imaging using 3D semantic segmentation convolutional neural netw
- PDF / 4,079,574 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 16 Downloads / 230 Views
IMAGING INFORMATICS AND ARTIFICIAL INTELLIGENCE
Fully automated body composition analysis in routine CT imaging using 3D semantic segmentation convolutional neural networks Sven Koitka 1
&
Lennard Kroll 1
&
Eugen Malamutmann 2
&
Arzu Oezcelik 2
&
Felix Nensa 1
Received: 26 February 2020 / Revised: 18 June 2020 / Accepted: 4 August 2020 # The Author(s) 2020
Abstract Objectives Body tissue composition is a long-known biomarker with high diagnostic and prognostic value not only in cardiovascular, oncological, and orthopedic diseases but also in rehabilitation medicine or drug dosage. In this study, the aim was to develop a fully automated, reproducible, and quantitative 3D volumetry of body tissue composition from standard CT examinations of the abdomen in order to be able to offer such valuable biomarkers as part of routine clinical imaging. Methods Therefore, an in-house dataset of 40 CTs for training and 10 CTs for testing were fully annotated on every fifth axial slice with five different semantic body regions: abdominal cavity, bones, muscle, subcutaneous tissue, and thoracic cavity. Multiresolution U-Net 3D neural networks were employed for segmenting these body regions, followed by subclassifying adipose tissue and muscle using known Hounsfield unit limits. Results The Sørensen Dice scores averaged over all semantic regions was 0.9553 and the intra-class correlation coefficients for subclassified tissues were above 0.99. Conclusions Our results show that fully automated body composition analysis on routine CT imaging can provide stable biomarkers across the whole abdomen and not just on L3 slices, which is historically the reference location for analyzing body composition in the clinical routine. Key Points • Our study enables fully automated body composition analysis on routine abdomen CT scans. • The best segmentation models for semantic body region segmentation achieved an averaged Sørensen Dice score of 0.9553. • Subclassified tissue volumes achieved intra-class correlation coefficients over 0.99. Keywords Abdomen . Body composition . Computer-assisted image analysis . Deep learning
Abbreviations 2D Two-dimensional 3D Three-dimensional CT Computer tomography GPU Graphics processing unit HU Hounsfield units Electronic supplementary material The online version of this article (https://doi.org/10.1007/s00330-020-07147-3) contains supplementary material, which is available to authorized users. * Sven Koitka [email protected] 1
Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Essen, Germany
2
Department of General, Visceral and Transplantation Surgery, University Hospital Essen, Essen, Germany
L3 PDF SAT TAT VAT
Third vertebra of the lumbar spine Portable document format Subcutaneous adipose tissue Total adipose tissue Visceral adipose tissue
Introduction Thanks to advances in computer-aided image analysis, radiological image data are now increasingly considered a valuable source of quantitative biomarkers [1–6]. Body tissue composition i
Data Loading...
