Online citations, reference lists, and bibliographies.
← Back to Search

Fully-Automated Analysis Of Body Composition From CT In Cancer Patients Using Convolutional Neural Networks

C. Bridge, M. Rosenthal, Bradley Wright, Gopal Kotecha, F. Fintelmann, Fabian M. Troschel, N. Miskin, K. Desai, W. Wrobel, A. Babic, N. Khalaf, L. Brais, M. Welch, Caitlin Zellers, Neil A. Tenenholtz, M. Michalski, B. Wolpin, K. Andriole
Published 2018 · Computer Science

Save to my Library
Download PDF
Analyze on Scholarcy
Share
The amounts of muscle and fat in a person’s body, known as body composition, are correlated with cancer risks, cancer survival, and cardiovascular risk. The current gold standard for measuring body composition requires time-consuming manual segmentation of CT images by an expert reader. In this work, we describe a two-step process to fully automate the analysis of CT body composition using a DenseNet to select the CT slice and U-Net to perform segmentation. We train and test our methods on independent cohorts. Our results show Dice scores (0.95−0.98) and correlation coefficients (R = 0.99) that are favorable compared to human readers. These results suggest that fully automated body composition analysis is feasible, which could enable both clinical use and large-scale population studies.
This paper references
10.1200/JCO.2012.45.2722
Cancer cachexia in the age of obesity: skeletal muscle depletion is a powerful prognostic factor, independent of body mass index.
L. Martin (2013)
10.1109/TMI.2015.2479252
Body Composition Assessment in Axial CT Images Using FEM-Based Automatic Segmentation of Skeletal Muscle
K. Popuri (2016)
10.1038/s41598-017-08925-8
Automated analysis of liver fat, muscle and adipose tissue distribution from CT suitable for large-scale studies
J. Kullberg (2017)
10.1016/j.jcct.2018.03.007
Computed tomography-based fat and muscle characteristics are associated with mortality after transcatheter aortic valve replacement.
B. Foldyna (2018)
10.1016/S1470-2045(08)70153-0
Prevalence and clinical implications of sarcopenic obesity in patients with solid tumours of the respiratory and gastrointestinal tracts: a population-based study.
C. Prado (2008)
10.1371/journal.pone.0183515
Development and validation of a rapid and robust method to determine visceral adipose tissue volume using computed tomography images
A. Parikh (2017)
10.1038/s41586-018-0235-7
Altered exocrine function can drive adipose wasting in early pancreatic cancer
Laura V. Danai (2018)
10.2196/medinform.4923
Computerized Automated Quantification of Subcutaneous and Visceral Adipose Tissue From Computed Tomography Scans: Development and Validation Study
Y. Kim (2016)
10.1152/JAPPLPHYSIOL.00744.2004
Total body skeletal muscle and adipose tissue volumes: estimation from a single abdominal cross-sectional image.
Wei Shen (2004)
10.1093/AJCN/80.2.271
Visceral adipose tissue: relations between single-slice areas and total volume.
Wei Shen (2004)
10.1007/978-3-319-24574-4_28
U-Net: Convolutional Networks for Biomedical Image Segmentation
O. Ronneberger (2015)
10.1109/CVPR.2017.243
Densely Connected Convolutional Networks
Gao Huang (2017)
10.1007/s10278-017-9988-z
Pixel-Level Deep Segmentation: Artificial Intelligence Quantifies Muscle on Computed Tomography for Body Morphometric Analysis
Hyunkwang Lee (2017)
Development and validation of a rapid and robust method to de termine visceral adipose tissue volume using computed tomography images
A. M. Parikh (2017)
10.1109/CVPR.2017.634
Aggregated Residual Transformations for Deep Neural Networks
Saining Xie (2017)
10.1109/3DV.2016.79
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
F. Milletari (2016)
10.1016/j.compbiomed.2017.05.018
Spotting L3 slice in CT scans using deep convolutional network and transfer learning
Soufiane Belharbi (2017)



This paper is referenced by
10.1016/j.diii.2020.04.011
Abdominal musculature segmentation and surface prediction from CT using deep learning for sarcopenia assessment.
P. Blanc-Durand (2020)
10.1159/000503996
Body Composition Analysis of Computed Tomography Scans in Clinical Populations: The Role of Deep Learning
M. Paris (2019)
10.1007/s00520-020-05730-4
FIT: Functional and imaging testing for patients with metastatic cancer
Eric J Roeland (2020)
10.1016/j.compmedimag.2020.101776
Deep learning method for localization and segmentation of abdominal CT
Setareh Dabiri (2020)
10.1097/RTI.0000000000000428
Computed Tomography–based Body Composition Analysis and Its Role in Lung Cancer Care
Amelie S Troschel (2019)
10.3348/kjr.2019.0470
Development and Validation of a Deep Learning System for Segmentation of Abdominal Muscle and Fat on Computed Tomography
H. Park (2020)
10.1002/mp.14141
ABCNet: A New Efficient 3D Dense-Structure Network for Segmentation and Analysis of Body Tissue Composition on Body-Torso-Wide CT Images.
Tiange Liu (2020)
10.1007/s11042-019-7419-5
Deep learning convolutional neural network (CNN) With Gaussian mixture model for predicting pancreatic cancer
K. Sekaran (2019)
10.1007/s00330-020-07147-3
Fully automated body composition analysis in routine CT imaging using 3D semantic segmentation convolutional neural networks
Sven Koitka (2020)
10.1016/j.bbe.2020.02.009
A fast graph-based algorithm for automated segmentation of subcutaneous and visceral adipose tissue in 3D abdominal computed tomography images
Iwona Kucybała (2020)
10.1055/s-0039-3400267
Artificial Intelligence in the Evaluation of Body Composition.
B. Wang (2020)
10.1007/s00330-019-06630-w
Prognostic value of anthropometric measures extracted from whole-body CT using deep learning in patients with non-small-cell lung cancer
P. Blanc-Durand (2020)
10.1097/RLI.0000000000000647
Fully Automated Segmentation of Connective Tissue Compartments for CT-Based Body Composition Analysis
Sebastian Nowak (2020)
10.1016/j.clnu.2020.01.008
Automated body composition analysis of clinically acquired computed tomography scans using neural networks.
M. Paris (2020)
Semantic Scholar Logo Some data provided by SemanticScholar