Deep learning-based body composition analysis from whole-body magnetic resonance imaging to predict all-cause mortality in a large western populationResearch in context

Summary: Background: Manually extracted imaging-based body composition measures from a single-slice area (A) have shown associations with clinical outcomes in patients with cardiometabolic disease and cancer. With advances in artificial intelligence, fully automated volumetric (V) segmentation appr...

Full description

Saved in:
Bibliographic Details
Main Authors: Matthias Jung, Vineet K. Raghu, Marco Reisert, Hanna Rieder, Susanne Rospleszcz, Tobias Pischon, Thoralf Niendorf, Hans-Ulrich Kauczor, Henry Völzke, Robin Bülow, Maximilian F. Russe, Christopher L. Schlett, Michael T. Lu, Fabian Bamberg, Jakob Weiss
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:EBioMedicine
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352396424005036
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850058187975163904
author Matthias Jung
Vineet K. Raghu
Marco Reisert
Hanna Rieder
Susanne Rospleszcz
Tobias Pischon
Thoralf Niendorf
Hans-Ulrich Kauczor
Henry Völzke
Robin Bülow
Maximilian F. Russe
Christopher L. Schlett
Michael T. Lu
Fabian Bamberg
Jakob Weiss
author_facet Matthias Jung
Vineet K. Raghu
Marco Reisert
Hanna Rieder
Susanne Rospleszcz
Tobias Pischon
Thoralf Niendorf
Hans-Ulrich Kauczor
Henry Völzke
Robin Bülow
Maximilian F. Russe
Christopher L. Schlett
Michael T. Lu
Fabian Bamberg
Jakob Weiss
author_sort Matthias Jung
collection DOAJ
description Summary: Background: Manually extracted imaging-based body composition measures from a single-slice area (A) have shown associations with clinical outcomes in patients with cardiometabolic disease and cancer. With advances in artificial intelligence, fully automated volumetric (V) segmentation approaches are now possible, but it is unknown whether these measures carry prognostic value to predict mortality in the general population. Here, we developed and tested a deep learning framework to automatically quantify volumetric body composition measures from whole-body magnetic resonance imaging (MRI) and investigated their prognostic value to predict mortality in a large Western population. Methods: The framework was developed using data from two large Western European population-based cohort studies, the UK Biobank (UKBB) and the German National Cohort (NAKO). Body composition was defined as (i) subcutaneous adipose tissue (SAT), (ii) visceral adipose tissue (VAT), (iii) skeletal muscle (SM), SM fat fraction (SMFF), and (iv) intramuscular adipose tissue (IMAT). The prognostic value of the body composition measures was assessed in the UKBB using Cox regression analysis. Additionally, we extracted body composition areas for every level of the thoracic and lumbar spine (i) to compare the proposed volumetric whole-body approach to the currently established single-slice area approach on the height of the L3 vertebra and (ii) to investigate the correlation between volumetric and single slice area body composition measures on the level of each vertebral body. Findings: In 36,317 UKBB participants (mean age 65.1 ± 7.8 years, age range 45–84 years; 51.7% female; 1.7% [634/36,471] all-cause deaths; median follow-up 4.8 years), Cox regression revealed an independent association between VSM (adjusted hazard ratio [aHR]: 0.88, 95% confidence interval [CI] [0.81–0.91], p = 0.00023), VSMFF (aHR: 1.06, 95% CI [1.02–1.10], p = 0.0043), and VIMAT (aHR: 1.19, 95% CI [1.05–1.35], p = 0.0056) and mortality after adjustment for demographics (age, sex, BMI, race) and cardiometabolic risk factors (alcohol consumption, smoking status, hypertension, diabetes, history of cancer, blood serum markers). This association was attenuated when using traditional single-slice area measures. Highest correlation coefficients (R) between volumetric and single-slice area body composition measures were located at vertebra L5 for SAT (R = 0.820) and SMFF (R = 0.947), at L3 for VAT (R = 0.892), SM (R = 0.944), and at L4 for IMAT (R = 0.546) (all p < 0.0001). A similar pattern was found in 23,725 NAKO participants (mean age 53.9 ± 8.3 years, age range 40–75; 44.9% female). Interpretation: Automated volumetric body composition assessment from whole-body MRI predicted mortality in a large Western population beyond traditional clinical risk factors. Single slice areas were highly correlated with volumetric body composition measures but their association with mortality attenuated after multivariable adjustment. As volumetric body composition measures are increasingly accessible using automated techniques, identifying high-risk individuals may help to improve personalised prevention and lifestyle interventions. Funding: This project was conducted using data from the German National Cohort (NAKO) (www.nako.de). The NAKO is funded by the Federal Ministry of Education and Research (BMBF) [project funding reference numbers: 01ER1301A/B/C, 01ER1511D, and 01ER1801A/B/C/D], federal states of Germany and the Helmholtz Association, the participating universities and the institutes of the Leibniz Association. This research has been conducted using the UK Biobank Resource under Application Number 80337. MJ was funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation)-518480401. VKR was funded by American Heart Association Career Development Award 935176 and National Heart, Lung, and Blood Institute-K01HL168231.
format Article
id doaj-art-43facf6e0c7b467a8fc3e2f7338582bc
institution DOAJ
issn 2352-3964
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series EBioMedicine
spelling doaj-art-43facf6e0c7b467a8fc3e2f7338582bc2025-08-20T02:51:14ZengElsevierEBioMedicine2352-39642024-12-0111010546710.1016/j.ebiom.2024.105467Deep learning-based body composition analysis from whole-body magnetic resonance imaging to predict all-cause mortality in a large western populationResearch in contextMatthias Jung0Vineet K. Raghu1Marco Reisert2Hanna Rieder3Susanne Rospleszcz4Tobias Pischon5Thoralf Niendorf6Hans-Ulrich Kauczor7Henry Völzke8Robin Bülow9Maximilian F. Russe10Christopher L. Schlett11Michael T. Lu12Fabian Bamberg13Jakob Weiss14Department of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany; Department of Radiology, Cardiovascular Imaging Research Center, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, USA; Corresponding author. Massachusetts General Hospital, 165 Cambridge St, Suite 400, Boston, MA, 02114, USA; Department of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Hugstetter Strasse 55, 79106 Freiburg, Germany.Department of Radiology, Cardiovascular Imaging Research Center, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, USAMedical Physics, Department of Diagnostic and Interventional Radiology, Medical Center - University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, 79106, Germany; Department of Stereotactic and Functional Neurosurgery, Medical Center - University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, 79106, GermanyDepartment of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, GermanyDepartment of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany; Institute of Epidemiology, Helmholtz Zentrum München, German Research Center for Environmental Health, Neuherberg, GermanyMolecular Epidemiology Research Group, Max Delbrück Center for Molecular Medicine in the Helmholtz Association (MDC), Berlin, 13125, GermanyBerlin Ultrahigh Field Facility, Max Delbrück Center for Molecular Medicine in the Helmholtz Association (MDC), Berlin, 13125, GermanyDepartment of Diagnostic and Interventional Radiology, Member of the German Center of Lung Research, University Hospital Heidelberg, Heidelberg, 69120, GermanyInstitute for Community Medicine, Ernst Moritz Arndt University, Greifswald, 17489, GermanyInstitute for Diagnostic Radiology and Neuroradiology, University Medicine, Ernst Moritz Arndt University Greifswald, Greifswald, 17475, GermanyDepartment of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, GermanyDepartment of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, GermanyDepartment of Radiology, Cardiovascular Imaging Research Center, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, USADepartment of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, GermanyDepartment of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, GermanySummary: Background: Manually extracted imaging-based body composition measures from a single-slice area (A) have shown associations with clinical outcomes in patients with cardiometabolic disease and cancer. With advances in artificial intelligence, fully automated volumetric (V) segmentation approaches are now possible, but it is unknown whether these measures carry prognostic value to predict mortality in the general population. Here, we developed and tested a deep learning framework to automatically quantify volumetric body composition measures from whole-body magnetic resonance imaging (MRI) and investigated their prognostic value to predict mortality in a large Western population. Methods: The framework was developed using data from two large Western European population-based cohort studies, the UK Biobank (UKBB) and the German National Cohort (NAKO). Body composition was defined as (i) subcutaneous adipose tissue (SAT), (ii) visceral adipose tissue (VAT), (iii) skeletal muscle (SM), SM fat fraction (SMFF), and (iv) intramuscular adipose tissue (IMAT). The prognostic value of the body composition measures was assessed in the UKBB using Cox regression analysis. Additionally, we extracted body composition areas for every level of the thoracic and lumbar spine (i) to compare the proposed volumetric whole-body approach to the currently established single-slice area approach on the height of the L3 vertebra and (ii) to investigate the correlation between volumetric and single slice area body composition measures on the level of each vertebral body. Findings: In 36,317 UKBB participants (mean age 65.1 ± 7.8 years, age range 45–84 years; 51.7% female; 1.7% [634/36,471] all-cause deaths; median follow-up 4.8 years), Cox regression revealed an independent association between VSM (adjusted hazard ratio [aHR]: 0.88, 95% confidence interval [CI] [0.81–0.91], p = 0.00023), VSMFF (aHR: 1.06, 95% CI [1.02–1.10], p = 0.0043), and VIMAT (aHR: 1.19, 95% CI [1.05–1.35], p = 0.0056) and mortality after adjustment for demographics (age, sex, BMI, race) and cardiometabolic risk factors (alcohol consumption, smoking status, hypertension, diabetes, history of cancer, blood serum markers). This association was attenuated when using traditional single-slice area measures. Highest correlation coefficients (R) between volumetric and single-slice area body composition measures were located at vertebra L5 for SAT (R = 0.820) and SMFF (R = 0.947), at L3 for VAT (R = 0.892), SM (R = 0.944), and at L4 for IMAT (R = 0.546) (all p < 0.0001). A similar pattern was found in 23,725 NAKO participants (mean age 53.9 ± 8.3 years, age range 40–75; 44.9% female). Interpretation: Automated volumetric body composition assessment from whole-body MRI predicted mortality in a large Western population beyond traditional clinical risk factors. Single slice areas were highly correlated with volumetric body composition measures but their association with mortality attenuated after multivariable adjustment. As volumetric body composition measures are increasingly accessible using automated techniques, identifying high-risk individuals may help to improve personalised prevention and lifestyle interventions. Funding: This project was conducted using data from the German National Cohort (NAKO) (www.nako.de). The NAKO is funded by the Federal Ministry of Education and Research (BMBF) [project funding reference numbers: 01ER1301A/B/C, 01ER1511D, and 01ER1801A/B/C/D], federal states of Germany and the Helmholtz Association, the participating universities and the institutes of the Leibniz Association. This research has been conducted using the UK Biobank Resource under Application Number 80337. MJ was funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation)-518480401. VKR was funded by American Heart Association Career Development Award 935176 and National Heart, Lung, and Blood Institute-K01HL168231.http://www.sciencedirect.com/science/article/pii/S2352396424005036Magnetic resonance imagingArtificial intelligenceDeep learningBody compositionPublic healthMortality
spellingShingle Matthias Jung
Vineet K. Raghu
Marco Reisert
Hanna Rieder
Susanne Rospleszcz
Tobias Pischon
Thoralf Niendorf
Hans-Ulrich Kauczor
Henry Völzke
Robin Bülow
Maximilian F. Russe
Christopher L. Schlett
Michael T. Lu
Fabian Bamberg
Jakob Weiss
Deep learning-based body composition analysis from whole-body magnetic resonance imaging to predict all-cause mortality in a large western populationResearch in context
EBioMedicine
Magnetic resonance imaging
Artificial intelligence
Deep learning
Body composition
Public health
Mortality
title Deep learning-based body composition analysis from whole-body magnetic resonance imaging to predict all-cause mortality in a large western populationResearch in context
title_full Deep learning-based body composition analysis from whole-body magnetic resonance imaging to predict all-cause mortality in a large western populationResearch in context
title_fullStr Deep learning-based body composition analysis from whole-body magnetic resonance imaging to predict all-cause mortality in a large western populationResearch in context
title_full_unstemmed Deep learning-based body composition analysis from whole-body magnetic resonance imaging to predict all-cause mortality in a large western populationResearch in context
title_short Deep learning-based body composition analysis from whole-body magnetic resonance imaging to predict all-cause mortality in a large western populationResearch in context
title_sort deep learning based body composition analysis from whole body magnetic resonance imaging to predict all cause mortality in a large western populationresearch in context
topic Magnetic resonance imaging
Artificial intelligence
Deep learning
Body composition
Public health
Mortality
url http://www.sciencedirect.com/science/article/pii/S2352396424005036
work_keys_str_mv AT matthiasjung deeplearningbasedbodycompositionanalysisfromwholebodymagneticresonanceimagingtopredictallcausemortalityinalargewesternpopulationresearchincontext
AT vineetkraghu deeplearningbasedbodycompositionanalysisfromwholebodymagneticresonanceimagingtopredictallcausemortalityinalargewesternpopulationresearchincontext
AT marcoreisert deeplearningbasedbodycompositionanalysisfromwholebodymagneticresonanceimagingtopredictallcausemortalityinalargewesternpopulationresearchincontext
AT hannarieder deeplearningbasedbodycompositionanalysisfromwholebodymagneticresonanceimagingtopredictallcausemortalityinalargewesternpopulationresearchincontext
AT susannerospleszcz deeplearningbasedbodycompositionanalysisfromwholebodymagneticresonanceimagingtopredictallcausemortalityinalargewesternpopulationresearchincontext
AT tobiaspischon deeplearningbasedbodycompositionanalysisfromwholebodymagneticresonanceimagingtopredictallcausemortalityinalargewesternpopulationresearchincontext
AT thoralfniendorf deeplearningbasedbodycompositionanalysisfromwholebodymagneticresonanceimagingtopredictallcausemortalityinalargewesternpopulationresearchincontext
AT hansulrichkauczor deeplearningbasedbodycompositionanalysisfromwholebodymagneticresonanceimagingtopredictallcausemortalityinalargewesternpopulationresearchincontext
AT henryvolzke deeplearningbasedbodycompositionanalysisfromwholebodymagneticresonanceimagingtopredictallcausemortalityinalargewesternpopulationresearchincontext
AT robinbulow deeplearningbasedbodycompositionanalysisfromwholebodymagneticresonanceimagingtopredictallcausemortalityinalargewesternpopulationresearchincontext
AT maximilianfrusse deeplearningbasedbodycompositionanalysisfromwholebodymagneticresonanceimagingtopredictallcausemortalityinalargewesternpopulationresearchincontext
AT christopherlschlett deeplearningbasedbodycompositionanalysisfromwholebodymagneticresonanceimagingtopredictallcausemortalityinalargewesternpopulationresearchincontext
AT michaeltlu deeplearningbasedbodycompositionanalysisfromwholebodymagneticresonanceimagingtopredictallcausemortalityinalargewesternpopulationresearchincontext
AT fabianbamberg deeplearningbasedbodycompositionanalysisfromwholebodymagneticresonanceimagingtopredictallcausemortalityinalargewesternpopulationresearchincontext
AT jakobweiss deeplearningbasedbodycompositionanalysisfromwholebodymagneticresonanceimagingtopredictallcausemortalityinalargewesternpopulationresearchincontext