Cargando…

Detection of diabetes from whole-body MRI using deep learning

Obesity is one of the main drivers of type 2 diabetes, but it is not uniformly associated with the disease. The location of fat accumulation is critical for metabolic health. Specific patterns of body fat distribution, such as visceral fat, are closely related to insulin resistance. There might be f...

Descripción completa

Detalles Bibliográficos
Autores principales: Dietz, Benedikt, Machann, Jürgen, Agrawal, Vaibhav, Heni, Martin, Schwab, Patrick, Dienes, Julia, Reichert, Steffen, Birkenfeld, Andreas L., Häring, Hans-Ulrich, Schick, Fritz, Stefan, Norbert, Fritsche, Andreas, Preissl, Hubert, Schölkopf, Bernhard, Bauer, Stefan, Wagner, Robert
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Society for Clinical Investigation 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8663560/
https://www.ncbi.nlm.nih.gov/pubmed/34591793
http://dx.doi.org/10.1172/jci.insight.146999
_version_ 1784613665969799168
author Dietz, Benedikt
Machann, Jürgen
Agrawal, Vaibhav
Heni, Martin
Schwab, Patrick
Dienes, Julia
Reichert, Steffen
Birkenfeld, Andreas L.
Häring, Hans-Ulrich
Schick, Fritz
Stefan, Norbert
Fritsche, Andreas
Preissl, Hubert
Schölkopf, Bernhard
Bauer, Stefan
Wagner, Robert
author_facet Dietz, Benedikt
Machann, Jürgen
Agrawal, Vaibhav
Heni, Martin
Schwab, Patrick
Dienes, Julia
Reichert, Steffen
Birkenfeld, Andreas L.
Häring, Hans-Ulrich
Schick, Fritz
Stefan, Norbert
Fritsche, Andreas
Preissl, Hubert
Schölkopf, Bernhard
Bauer, Stefan
Wagner, Robert
author_sort Dietz, Benedikt
collection PubMed
description Obesity is one of the main drivers of type 2 diabetes, but it is not uniformly associated with the disease. The location of fat accumulation is critical for metabolic health. Specific patterns of body fat distribution, such as visceral fat, are closely related to insulin resistance. There might be further, hitherto unknown, features of body fat distribution that could additionally contribute to the disease. We used machine learning with dense convolutional neural networks to detect diabetes-related variables from 2371 T1-weighted whole-body MRI data sets. MRI was performed in participants undergoing metabolic screening with oral glucose tolerance tests. Models were trained for sex, age, BMI, insulin sensitivity, HbA1c, and prediabetes or incident diabetes. The results were compared with those of conventional models. The area under the receiver operating characteristic curve was 87% for the type 2 diabetes discrimination and 68% for prediabetes, both superior to conventional models. Mean absolute regression errors were comparable to those of conventional models. Heatmaps showed that lower visceral abdominal regions were critical in diabetes classification. Subphenotyping revealed a group with high future diabetes and microalbuminuria risk.Our results show that diabetes is detectable from whole-body MRI without additional data. Our technique of heatmap visualization identifies plausible anatomical regions and highlights the leading role of fat accumulation in the lower abdomen in diabetes pathogenesis.
format Online
Article
Text
id pubmed-8663560
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher American Society for Clinical Investigation
record_format MEDLINE/PubMed
spelling pubmed-86635602021-12-15 Detection of diabetes from whole-body MRI using deep learning Dietz, Benedikt Machann, Jürgen Agrawal, Vaibhav Heni, Martin Schwab, Patrick Dienes, Julia Reichert, Steffen Birkenfeld, Andreas L. Häring, Hans-Ulrich Schick, Fritz Stefan, Norbert Fritsche, Andreas Preissl, Hubert Schölkopf, Bernhard Bauer, Stefan Wagner, Robert JCI Insight Research Article Obesity is one of the main drivers of type 2 diabetes, but it is not uniformly associated with the disease. The location of fat accumulation is critical for metabolic health. Specific patterns of body fat distribution, such as visceral fat, are closely related to insulin resistance. There might be further, hitherto unknown, features of body fat distribution that could additionally contribute to the disease. We used machine learning with dense convolutional neural networks to detect diabetes-related variables from 2371 T1-weighted whole-body MRI data sets. MRI was performed in participants undergoing metabolic screening with oral glucose tolerance tests. Models were trained for sex, age, BMI, insulin sensitivity, HbA1c, and prediabetes or incident diabetes. The results were compared with those of conventional models. The area under the receiver operating characteristic curve was 87% for the type 2 diabetes discrimination and 68% for prediabetes, both superior to conventional models. Mean absolute regression errors were comparable to those of conventional models. Heatmaps showed that lower visceral abdominal regions were critical in diabetes classification. Subphenotyping revealed a group with high future diabetes and microalbuminuria risk.Our results show that diabetes is detectable from whole-body MRI without additional data. Our technique of heatmap visualization identifies plausible anatomical regions and highlights the leading role of fat accumulation in the lower abdomen in diabetes pathogenesis. American Society for Clinical Investigation 2021-11-08 /pmc/articles/PMC8663560/ /pubmed/34591793 http://dx.doi.org/10.1172/jci.insight.146999 Text en © 2021 Dietz et al. https://creativecommons.org/licenses/by/4.0/This work is licensed under the Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Research Article
Dietz, Benedikt
Machann, Jürgen
Agrawal, Vaibhav
Heni, Martin
Schwab, Patrick
Dienes, Julia
Reichert, Steffen
Birkenfeld, Andreas L.
Häring, Hans-Ulrich
Schick, Fritz
Stefan, Norbert
Fritsche, Andreas
Preissl, Hubert
Schölkopf, Bernhard
Bauer, Stefan
Wagner, Robert
Detection of diabetes from whole-body MRI using deep learning
title Detection of diabetes from whole-body MRI using deep learning
title_full Detection of diabetes from whole-body MRI using deep learning
title_fullStr Detection of diabetes from whole-body MRI using deep learning
title_full_unstemmed Detection of diabetes from whole-body MRI using deep learning
title_short Detection of diabetes from whole-body MRI using deep learning
title_sort detection of diabetes from whole-body mri using deep learning
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8663560/
https://www.ncbi.nlm.nih.gov/pubmed/34591793
http://dx.doi.org/10.1172/jci.insight.146999
work_keys_str_mv AT dietzbenedikt detectionofdiabetesfromwholebodymriusingdeeplearning
AT machannjurgen detectionofdiabetesfromwholebodymriusingdeeplearning
AT agrawalvaibhav detectionofdiabetesfromwholebodymriusingdeeplearning
AT henimartin detectionofdiabetesfromwholebodymriusingdeeplearning
AT schwabpatrick detectionofdiabetesfromwholebodymriusingdeeplearning
AT dienesjulia detectionofdiabetesfromwholebodymriusingdeeplearning
AT reichertsteffen detectionofdiabetesfromwholebodymriusingdeeplearning
AT birkenfeldandreasl detectionofdiabetesfromwholebodymriusingdeeplearning
AT haringhansulrich detectionofdiabetesfromwholebodymriusingdeeplearning
AT schickfritz detectionofdiabetesfromwholebodymriusingdeeplearning
AT stefannorbert detectionofdiabetesfromwholebodymriusingdeeplearning
AT fritscheandreas detectionofdiabetesfromwholebodymriusingdeeplearning
AT preisslhubert detectionofdiabetesfromwholebodymriusingdeeplearning
AT scholkopfbernhard detectionofdiabetesfromwholebodymriusingdeeplearning
AT bauerstefan detectionofdiabetesfromwholebodymriusingdeeplearning
AT wagnerrobert detectionofdiabetesfromwholebodymriusingdeeplearning