PMID- 32800693
OWN - NLM
STAT- MEDLINE
DCOM- 20211123
LR  - 20211123
IS  - 1878-4046 (Electronic)
IS  - 1076-6332 (Linking)
VI  - 28 Suppl 1
DP  - 2021 Nov
TI  - MRI-Derived Radiomics Features of Hepatic Fat Predict Metabolic States in 
      Individuals without Cardiovascular Disease.
PG  - S1-S10
LID - S1076-6332(20)30408-6 [pii]
LID - 10.1016/j.acra.2020.06.030 [doi]
AB  - RATIONALE AND OBJECTIVES: To investigate radiomics features of hepatic fat as 
      potential biomarkers of type 2 diabetes mellitus (T2DM) and metabolic syndrome 
      (MetS) in individuals without overt cardiovascular disease, and benchmarking 
      against hepatic proton density fat fraction (PDFF) and the body mass index (BMI). 
      MATERIALS AND METHODS: This study collected liver radiomics features of 310 
      individuals that were part of a case-controlled imaging substudy embedded in a 
      prospective cohort. Individuals had known T2DM (n = 39; 12.6 %) and MetS 
      (n = 107; 34.5 %) status, and were divided into stratified training (n = 232; 75 
      %) and validation (n = 78; 25 %) sets. Six hundred eighty-four MRI radiomics 
      features were extracted for each liver volume of interest (VOI) on T(1)-weighted 
      dual-echo Dixon relative fat water content (rfwc) maps. Test-retest and 
      inter-rater variance was simulated by additionally extracting radiomics features 
      using noise augmented rfwc maps and deformed volume of interests. One hundred and 
      seventy-one features with test-retest reliability (ICC(1,1)) and inter-rater 
      agreement (ICC(3,k)) of >/=0.85 on the training set were considered stable. To 
      construct predictive random forest (RF) models, stable features were filtered 
      using univariate RF analysis followed by sequential forward aggregation. The 
      predictive performance was evaluated on the independent validation set with area 
      under the curve of the receiver operating characteristic (AUROC) and balanced 
      accuracy (Accuracy(B)). RESULTS: On the validation set, the radiomics RF models 
      predicted T2DM with AUROC of 0.835 and Accuracy(B) of 0.822 and MetS with AUROC 
      of 0.838 and Accuracy(B) of 0.787, outperforming the RF models trained on the 
      benchmark parameters PDFF and BMI. CONCLUSION: Hepatic radiomics features may 
      serve as potential imaging biomarkers for T2DM and MetS.
CI  - Copyright (c) 2020 The Association of University Radiologists. Published by 
      Elsevier Inc. All rights reserved.
FAU - Gutmann, Daniel A P
AU  - Gutmann DAP
AD  - Department of Diagnostic and Interventional Radiology, University Hospital, 
      University of Tubingen, Tubingen, Germany.
FAU - Rospleszcz, Susanne
AU  - Rospleszcz S
AD  - Institute of Epidemiology, Helmholtz Zentrum Munchen, German Research Center for 
      Environmental Health, Neuherberg, Germany.
FAU - Rathmann, Wolfgang
AU  - Rathmann W
AD  - Institute for Biometrics and Epidemiology, German Diabetes Center, Duesseldorf, 
      Germany; German Center for Diabetes Research (DZD), Neuherberg, Germany.
FAU - Schlett, Christopher L
AU  - Schlett CL
AD  - Department of Diagnostic and Interventional Radiology, Medical Center - Faculty 
      of Medicine, Hugstetter Strasse 55 79106, Freiburg, Germany.
FAU - Peters, Annette
AU  - Peters A
AD  - Institute of Epidemiology, Helmholtz Zentrum Munchen, German Research Center for 
      Environmental Health, Neuherberg, Germany; Chair of Epidemiology, Faculty of 
      Medicine, Ludwig-Maximilians-University, Munich, Germany; German Center for 
      Diabetes Research (DZD), Neuherberg, Germany; German Center for Cardiovascular 
      Research (DZHK e.V.), Munich, Germany.
FAU - Wachinger, Christian
AU  - Wachinger C
AD  - Artificial Intelligence in Medical Imaging (AI-Med), Department of Child and 
      Adolescent Psychiatry, Psychosomatic and Psychotherapy, University Hospital, 
      Ludwig-Maximilians-University, Munich, Germany.
FAU - Gatidis, Sergios
AU  - Gatidis S
AD  - Department of Diagnostic and Interventional Radiology, University Hospital, 
      University of Tubingen, Tubingen, Germany.
FAU - Bamberg, Fabian
AU  - Bamberg F
AD  - Department of Diagnostic and Interventional Radiology, Medical Center - Faculty 
      of Medicine, Hugstetter Strasse 55 79106, Freiburg, Germany. Electronic address: 
      fabian.bamberg@uniklinik-freiburg.de.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20200814
PL  - United States
TA  - Acad Radiol
JT  - Academic radiology
JID - 9440159
SB  - IM
MH  - *Cardiovascular Diseases
MH  - *Diabetes Mellitus, Type 2/complications/diagnostic imaging
MH  - Humans
MH  - Liver/diagnostic imaging
MH  - Magnetic Resonance Imaging
MH  - Prospective Studies
MH  - Reproducibility of Results
MH  - Retrospective Studies
OTO - NOTNLM
OT  - Diabetes mellitus
OT  - Fatty liver
OT  - Magnetic resonance Imaging
OT  - Metabolic syndrome
EDAT- 2020/08/18 06:00
MHDA- 2021/11/24 06:00
CRDT- 2020/08/18 06:00
PHST- 2020/03/11 00:00 [received]
PHST- 2020/06/23 00:00 [revised]
PHST- 2020/06/25 00:00 [accepted]
PHST- 2020/08/18 06:00 [pubmed]
PHST- 2021/11/24 06:00 [medline]
PHST- 2020/08/18 06:00 [entrez]
AID - S1076-6332(20)30408-6 [pii]
AID - 10.1016/j.acra.2020.06.030 [doi]
PST - ppublish
SO  - Acad Radiol. 2021 Nov;28 Suppl 1:S1-S10. doi: 10.1016/j.acra.2020.06.030. Epub 
      2020 Aug 14.