Fully Automated and Standardized Segmentation of Adipose Tissue Compartments via Deep Learning in 3D Whole-Body MRI of Epidemiologic Cohort Studies.

Journal

Radiology. Artificial intelligence
ISSN: 2638-6100
Titre abrégé: Radiol Artif Intell
Pays: United States
ID NLM: 101746556

Informations de publication

Date de publication:
Nov 2020
Historique:
received: 30 01 2020
revised: 02 06 2020
accepted: 26 06 2020
entrez: 3 5 2021
pubmed: 4 5 2021
medline: 4 5 2021
Statut: epublish

Résumé

To enable fast and reliable assessment of subcutaneous and visceral adipose tissue compartments derived from whole-body MRI. Quantification and localization of different adipose tissue compartments derived from whole-body MR images is of high interest in research concerning metabolic conditions. For correct identification and phenotyping of individuals at increased risk for metabolic diseases, a reliable automated segmentation of adipose tissue into subcutaneous and visceral adipose tissue is required. In this work, a three-dimensional (3D) densely connected convolutional neural network (DCNet) is proposed to provide robust and objective segmentation. In this retrospective study, 1000 cases (average age, 66 years ± 13 [standard deviation]; 523 women) from the Tuebingen Family Study database and the German Center for Diabetes research database and 300 cases (average age, 53 years ± 11; 152 women) from the German National Cohort (NAKO) database were collected for model training, validation, and testing, with transfer learning between the cohorts. These datasets included variable imaging sequences, imaging contrasts, receiver coil arrangements, scanners, and imaging field strengths. The proposed DCNet was compared to a similar 3D U-Net segmentation in terms of sensitivity, specificity, precision, accuracy, and Dice overlap. Fast (range, 5-7 seconds) and reliable adipose tissue segmentation can be performed with high Dice overlap (0.94), sensitivity (96.6%), specificity (95.1%), precision (92.1%), and accuracy (98.4%) from 3D whole-body MRI datasets (field of view coverage, 450 × 450 × 2000 mm). Segmentation masks and adipose tissue profiles are automatically reported back to the referring physician. Automated adipose tissue segmentation is feasible in 3D whole-body MRI datasets and is generalizable to different epidemiologic cohort studies with the proposed DCNet.

Identifiants

DOI: 10.1148/ryai.2020200010 PMID: 33937847 PMC: PMC8082356
pubmed: 33937847
doi: 10.1148/ryai.2020200010
pmc: PMC8082356
doi:

Types de publication

Journal Article

Langues

eng

Pagination

e200010

Informations de copyright

2020 by the Radiological Society of North America, Inc.

Déclaration de conflit d'intérêts

Disclosures of Conflicts of Interest: T.K. disclosed no relevant relationships. T.H. disclosed no relevant relationships. M.F. disclosed no relevant relationships. M.S. disclosed no relevant relationships. A.F. disclosed no relevant relationships. H.U.H. disclosed no relevant relationships. K.N. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: is on the speakers bureau of Siemens, Bayer, and Bracco. Other relationships: disclosed no relevant relationships. F.B. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: institution received a research grant from Siemens Healthineers; is on the speakers bureau of Siemens Healthineers. Other relationships: disclosed no relevant relationships. B.Y. disclosed no relevant relationships. F.S. disclosed no relevant relationships. S.G. disclosed no relevant relationships. J.M. disclosed no relevant relationships.

Références

Med Image Anal. 2009 Aug;13(4):543-63
pubmed: 19525140
J Clin Endocrinol Metab. 1982 Feb;54(2):254-60
pubmed: 7033275
Br J Radiol. 2018 Sep;91(1089):20180252
pubmed: 30004791
IEEE Trans Med Imaging. 2007 Mar;26(3):405-21
pubmed: 17354645
J Cardiometab Syndr. 2008 Summer;3(3):155-61
pubmed: 18983332
Magn Reson Med. 2019 Apr;81(4):2736-2745
pubmed: 30311704
J Magn Reson Imaging. 2012 Nov;36(5):1011-4
pubmed: 22777847
J Investig Med. 2018 Jun;66(5):1-9
pubmed: 29581385
Radiology. 1984 Oct;153(1):189-94
pubmed: 6089263
IEEE Trans Med Imaging. 2016 May;35(5):1240-1251
pubmed: 26960222
Med Image Anal. 2017 Jan;35:18-31
pubmed: 27310171
Proc Nutr Soc. 2012 Feb;71(1):181-9
pubmed: 22051112
J Clin Invest. 1983 Sep;72(3):1150-62
pubmed: 6350364
Obesity (Silver Spring). 2018 Nov;26(11):1785-1795
pubmed: 29785727
MAGMA. 2016 Apr;29(2):259-76
pubmed: 26336839
J Cardiovasc Magn Reson. 2018 Sep 14;20(1):65
pubmed: 30217194
Radiology. 2015 Oct;277(1):206-20
pubmed: 25989618
Radiology. 2010 Nov;257(2):353-63
pubmed: 20713612
Med Image Anal. 2015 Aug;24(1):205-219
pubmed: 26201875
Phys Med Biol. 2018 May 04;63(9):095017
pubmed: 29633960
Endocr J. 2002 Aug;49(4):459-64
pubmed: 12402978
J Magn Reson Imaging. 2010 Feb;31(2):430-9
pubmed: 20099357
Neural Netw. 2020 Jan;121:74-87
pubmed: 31536901
Annu Rev Biomed Eng. 2017 Jun 21;19:221-248
pubmed: 28301734
J Magn Reson Imaging. 2015 Jan;41(1):233-41
pubmed: 24431195
IEEE Trans Med Imaging. 2016 May;35(5):1252-1261
pubmed: 27046893
Magn Reson Med. 2008 Nov;60(5):1122-34
pubmed: 18956464
Magn Reson Med. 2020 Apr;83(4):1471-1483
pubmed: 31631409
Med Image Anal. 2017 Dec;42:60-88
pubmed: 28778026
Neuroimage. 2015 Mar;108:214-24
pubmed: 25562829
J Magn Reson Imaging. 2015 Jun;41(6):1558-69
pubmed: 25111561
J Magn Reson Imaging. 2005 Apr;21(4):455-62
pubmed: 15778954
Obesity (Silver Spring). 2019 Jul;27(7):1190-1199
pubmed: 31094076
Diabetes. 1985 Oct;34(10):1055-8
pubmed: 4043554

Auteurs

Thomas Küstner (T)

Department of Diagnostic and Interventional Radiology, Medical Image and Data Analysis, University Hospital Tübingen, Hoppe-Seyler-Str 3, 72076 Tübingen, Germany (T.K., T.H., M.F., K.N., S.G.); Department of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany (T.K., M.F., M.S., B.Y.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (T.K.); Department of Empirical Inference, Max-Planck Institute for Intelligent Systems, Tübingen, Germany (T.H.); Department of Diagnostic and Interventional Radiology, Section of Experimental Radiology, University Hospital Tübingen, Tübingen, Germany (M.F., M.S., F.S., J.M.); Department of Internal Medicine IV, Eberhard Karls University, Tübingen, Germany (A.F.); Institute for Diabetes Research and Metabolic Diseases of the Helmholtz Zentrum München, University of Tübingen, Tübingen, Germany (A.F., F.S., J.M.); German Center for Diabetes Research (DZD), Tübingen, Germany (A.F., H.U.H., F.S., J.M.); and Department of Diagnostic and Interventional Radiology, Medical Center-University of Freiburg, Faculty of Medicine, Freiburg, Germany (F.B.).
ORCID: 0000-0002-0353-4898

Tobias Hepp (T)

Department of Diagnostic and Interventional Radiology, Medical Image and Data Analysis, University Hospital Tübingen, Hoppe-Seyler-Str 3, 72076 Tübingen, Germany (T.K., T.H., M.F., K.N., S.G.); Department of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany (T.K., M.F., M.S., B.Y.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (T.K.); Department of Empirical Inference, Max-Planck Institute for Intelligent Systems, Tübingen, Germany (T.H.); Department of Diagnostic and Interventional Radiology, Section of Experimental Radiology, University Hospital Tübingen, Tübingen, Germany (M.F., M.S., F.S., J.M.); Department of Internal Medicine IV, Eberhard Karls University, Tübingen, Germany (A.F.); Institute for Diabetes Research and Metabolic Diseases of the Helmholtz Zentrum München, University of Tübingen, Tübingen, Germany (A.F., F.S., J.M.); German Center for Diabetes Research (DZD), Tübingen, Germany (A.F., H.U.H., F.S., J.M.); and Department of Diagnostic and Interventional Radiology, Medical Center-University of Freiburg, Faculty of Medicine, Freiburg, Germany (F.B.).
ORCID: 0000-0002-5241-9642

Marc Fischer (M)

Department of Diagnostic and Interventional Radiology, Medical Image and Data Analysis, University Hospital Tübingen, Hoppe-Seyler-Str 3, 72076 Tübingen, Germany (T.K., T.H., M.F., K.N., S.G.); Department of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany (T.K., M.F., M.S., B.Y.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (T.K.); Department of Empirical Inference, Max-Planck Institute for Intelligent Systems, Tübingen, Germany (T.H.); Department of Diagnostic and Interventional Radiology, Section of Experimental Radiology, University Hospital Tübingen, Tübingen, Germany (M.F., M.S., F.S., J.M.); Department of Internal Medicine IV, Eberhard Karls University, Tübingen, Germany (A.F.); Institute for Diabetes Research and Metabolic Diseases of the Helmholtz Zentrum München, University of Tübingen, Tübingen, Germany (A.F., F.S., J.M.); German Center for Diabetes Research (DZD), Tübingen, Germany (A.F., H.U.H., F.S., J.M.); and Department of Diagnostic and Interventional Radiology, Medical Center-University of Freiburg, Faculty of Medicine, Freiburg, Germany (F.B.).
ORCID: 0000-0001-8892-0079

Martin Schwartz (M)

Department of Diagnostic and Interventional Radiology, Medical Image and Data Analysis, University Hospital Tübingen, Hoppe-Seyler-Str 3, 72076 Tübingen, Germany (T.K., T.H., M.F., K.N., S.G.); Department of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany (T.K., M.F., M.S., B.Y.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (T.K.); Department of Empirical Inference, Max-Planck Institute for Intelligent Systems, Tübingen, Germany (T.H.); Department of Diagnostic and Interventional Radiology, Section of Experimental Radiology, University Hospital Tübingen, Tübingen, Germany (M.F., M.S., F.S., J.M.); Department of Internal Medicine IV, Eberhard Karls University, Tübingen, Germany (A.F.); Institute for Diabetes Research and Metabolic Diseases of the Helmholtz Zentrum München, University of Tübingen, Tübingen, Germany (A.F., F.S., J.M.); German Center for Diabetes Research (DZD), Tübingen, Germany (A.F., H.U.H., F.S., J.M.); and Department of Diagnostic and Interventional Radiology, Medical Center-University of Freiburg, Faculty of Medicine, Freiburg, Germany (F.B.).

Andreas Fritsche (A)

Department of Diagnostic and Interventional Radiology, Medical Image and Data Analysis, University Hospital Tübingen, Hoppe-Seyler-Str 3, 72076 Tübingen, Germany (T.K., T.H., M.F., K.N., S.G.); Department of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany (T.K., M.F., M.S., B.Y.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (T.K.); Department of Empirical Inference, Max-Planck Institute for Intelligent Systems, Tübingen, Germany (T.H.); Department of Diagnostic and Interventional Radiology, Section of Experimental Radiology, University Hospital Tübingen, Tübingen, Germany (M.F., M.S., F.S., J.M.); Department of Internal Medicine IV, Eberhard Karls University, Tübingen, Germany (A.F.); Institute for Diabetes Research and Metabolic Diseases of the Helmholtz Zentrum München, University of Tübingen, Tübingen, Germany (A.F., F.S., J.M.); German Center for Diabetes Research (DZD), Tübingen, Germany (A.F., H.U.H., F.S., J.M.); and Department of Diagnostic and Interventional Radiology, Medical Center-University of Freiburg, Faculty of Medicine, Freiburg, Germany (F.B.).

Hans-Ulrich Häring (HU)

Department of Diagnostic and Interventional Radiology, Medical Image and Data Analysis, University Hospital Tübingen, Hoppe-Seyler-Str 3, 72076 Tübingen, Germany (T.K., T.H., M.F., K.N., S.G.); Department of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany (T.K., M.F., M.S., B.Y.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (T.K.); Department of Empirical Inference, Max-Planck Institute for Intelligent Systems, Tübingen, Germany (T.H.); Department of Diagnostic and Interventional Radiology, Section of Experimental Radiology, University Hospital Tübingen, Tübingen, Germany (M.F., M.S., F.S., J.M.); Department of Internal Medicine IV, Eberhard Karls University, Tübingen, Germany (A.F.); Institute for Diabetes Research and Metabolic Diseases of the Helmholtz Zentrum München, University of Tübingen, Tübingen, Germany (A.F., F.S., J.M.); German Center for Diabetes Research (DZD), Tübingen, Germany (A.F., H.U.H., F.S., J.M.); and Department of Diagnostic and Interventional Radiology, Medical Center-University of Freiburg, Faculty of Medicine, Freiburg, Germany (F.B.).
ORCID: 0000-0003-4655-9937

Konstantin Nikolaou (K)

Department of Diagnostic and Interventional Radiology, Medical Image and Data Analysis, University Hospital Tübingen, Hoppe-Seyler-Str 3, 72076 Tübingen, Germany (T.K., T.H., M.F., K.N., S.G.); Department of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany (T.K., M.F., M.S., B.Y.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (T.K.); Department of Empirical Inference, Max-Planck Institute for Intelligent Systems, Tübingen, Germany (T.H.); Department of Diagnostic and Interventional Radiology, Section of Experimental Radiology, University Hospital Tübingen, Tübingen, Germany (M.F., M.S., F.S., J.M.); Department of Internal Medicine IV, Eberhard Karls University, Tübingen, Germany (A.F.); Institute for Diabetes Research and Metabolic Diseases of the Helmholtz Zentrum München, University of Tübingen, Tübingen, Germany (A.F., F.S., J.M.); German Center for Diabetes Research (DZD), Tübingen, Germany (A.F., H.U.H., F.S., J.M.); and Department of Diagnostic and Interventional Radiology, Medical Center-University of Freiburg, Faculty of Medicine, Freiburg, Germany (F.B.).
ORCID: 0000-0003-2668-7325

Fabian Bamberg (F)

Department of Diagnostic and Interventional Radiology, Medical Image and Data Analysis, University Hospital Tübingen, Hoppe-Seyler-Str 3, 72076 Tübingen, Germany (T.K., T.H., M.F., K.N., S.G.); Department of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany (T.K., M.F., M.S., B.Y.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (T.K.); Department of Empirical Inference, Max-Planck Institute for Intelligent Systems, Tübingen, Germany (T.H.); Department of Diagnostic and Interventional Radiology, Section of Experimental Radiology, University Hospital Tübingen, Tübingen, Germany (M.F., M.S., F.S., J.M.); Department of Internal Medicine IV, Eberhard Karls University, Tübingen, Germany (A.F.); Institute for Diabetes Research and Metabolic Diseases of the Helmholtz Zentrum München, University of Tübingen, Tübingen, Germany (A.F., F.S., J.M.); German Center for Diabetes Research (DZD), Tübingen, Germany (A.F., H.U.H., F.S., J.M.); and Department of Diagnostic and Interventional Radiology, Medical Center-University of Freiburg, Faculty of Medicine, Freiburg, Germany (F.B.).

Bin Yang (B)

Department of Diagnostic and Interventional Radiology, Medical Image and Data Analysis, University Hospital Tübingen, Hoppe-Seyler-Str 3, 72076 Tübingen, Germany (T.K., T.H., M.F., K.N., S.G.); Department of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany (T.K., M.F., M.S., B.Y.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (T.K.); Department of Empirical Inference, Max-Planck Institute for Intelligent Systems, Tübingen, Germany (T.H.); Department of Diagnostic and Interventional Radiology, Section of Experimental Radiology, University Hospital Tübingen, Tübingen, Germany (M.F., M.S., F.S., J.M.); Department of Internal Medicine IV, Eberhard Karls University, Tübingen, Germany (A.F.); Institute for Diabetes Research and Metabolic Diseases of the Helmholtz Zentrum München, University of Tübingen, Tübingen, Germany (A.F., F.S., J.M.); German Center for Diabetes Research (DZD), Tübingen, Germany (A.F., H.U.H., F.S., J.M.); and Department of Diagnostic and Interventional Radiology, Medical Center-University of Freiburg, Faculty of Medicine, Freiburg, Germany (F.B.).

Fritz Schick (F)

Department of Diagnostic and Interventional Radiology, Medical Image and Data Analysis, University Hospital Tübingen, Hoppe-Seyler-Str 3, 72076 Tübingen, Germany (T.K., T.H., M.F., K.N., S.G.); Department of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany (T.K., M.F., M.S., B.Y.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (T.K.); Department of Empirical Inference, Max-Planck Institute for Intelligent Systems, Tübingen, Germany (T.H.); Department of Diagnostic and Interventional Radiology, Section of Experimental Radiology, University Hospital Tübingen, Tübingen, Germany (M.F., M.S., F.S., J.M.); Department of Internal Medicine IV, Eberhard Karls University, Tübingen, Germany (A.F.); Institute for Diabetes Research and Metabolic Diseases of the Helmholtz Zentrum München, University of Tübingen, Tübingen, Germany (A.F., F.S., J.M.); German Center for Diabetes Research (DZD), Tübingen, Germany (A.F., H.U.H., F.S., J.M.); and Department of Diagnostic and Interventional Radiology, Medical Center-University of Freiburg, Faculty of Medicine, Freiburg, Germany (F.B.).

Sergios Gatidis (S)

Department of Diagnostic and Interventional Radiology, Medical Image and Data Analysis, University Hospital Tübingen, Hoppe-Seyler-Str 3, 72076 Tübingen, Germany (T.K., T.H., M.F., K.N., S.G.); Department of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany (T.K., M.F., M.S., B.Y.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (T.K.); Department of Empirical Inference, Max-Planck Institute for Intelligent Systems, Tübingen, Germany (T.H.); Department of Diagnostic and Interventional Radiology, Section of Experimental Radiology, University Hospital Tübingen, Tübingen, Germany (M.F., M.S., F.S., J.M.); Department of Internal Medicine IV, Eberhard Karls University, Tübingen, Germany (A.F.); Institute for Diabetes Research and Metabolic Diseases of the Helmholtz Zentrum München, University of Tübingen, Tübingen, Germany (A.F., F.S., J.M.); German Center for Diabetes Research (DZD), Tübingen, Germany (A.F., H.U.H., F.S., J.M.); and Department of Diagnostic and Interventional Radiology, Medical Center-University of Freiburg, Faculty of Medicine, Freiburg, Germany (F.B.).
ORCID: 0000-0002-6928-4967

Jürgen Machann (J)

Department of Diagnostic and Interventional Radiology, Medical Image and Data Analysis, University Hospital Tübingen, Hoppe-Seyler-Str 3, 72076 Tübingen, Germany (T.K., T.H., M.F., K.N., S.G.); Department of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany (T.K., M.F., M.S., B.Y.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (T.K.); Department of Empirical Inference, Max-Planck Institute for Intelligent Systems, Tübingen, Germany (T.H.); Department of Diagnostic and Interventional Radiology, Section of Experimental Radiology, University Hospital Tübingen, Tübingen, Germany (M.F., M.S., F.S., J.M.); Department of Internal Medicine IV, Eberhard Karls University, Tübingen, Germany (A.F.); Institute for Diabetes Research and Metabolic Diseases of the Helmholtz Zentrum München, University of Tübingen, Tübingen, Germany (A.F., F.S., J.M.); German Center for Diabetes Research (DZD), Tübingen, Germany (A.F., H.U.H., F.S., J.M.); and Department of Diagnostic and Interventional Radiology, Medical Center-University of Freiburg, Faculty of Medicine, Freiburg, Germany (F.B.).
ORCID: 0000-0002-4458-5886

Classifications MeSH