CT-based radiomics signature of visceral adipose tissue for prediction of disease progression in patients with Crohn's disease: A multicentre cohort study.
AUC, Area under the ROC curve
BMI, Body mass index
CD, Crohn's disease
CI, Confidence interval
CRP, C-reactive protein
CT, Computed tomography
Computed tomography enterography
Crohn's disease
DCA, Decision curve analysis
ICC, Intraclass correlation coefficients
LASSO, Least absolute shrinkage and selection operator
LOOCV, Leave-one-out cross-validation
MRI, Magnetic resonance imaging
RM, Radiomics model
ROC, Receiver operating characteristic
Radiomics
SAT, Subcutaneous adipose tissue
SVM, Support vector machine
VAT, Visceral adipose tissue
VOI, Volume of interest
Visceral adipose tissue
Journal
EClinicalMedicine
ISSN: 2589-5370
Titre abrégé: EClinicalMedicine
Pays: England
ID NLM: 101733727
Informations de publication
Date de publication:
Feb 2023
Feb 2023
Historique:
received:
25
09
2022
revised:
06
12
2022
accepted:
07
12
2022
entrez:
9
1
2023
pubmed:
10
1
2023
medline:
10
1
2023
Statut:
epublish
Résumé
Visceral adipose tissue (VAT) is involved in the pathogenesis of Crohn's disease (CD). However, data describing its effects on CD progression remain scarce. We developed and validated a VAT-radiomics model (RM) using computed tomography (CT) images to predict disease progression in patients with CD and compared it with a subcutaneous adipose tissue (SAT)-RM. This retrospective study included 256 patients with CD (training, n = 156; test, n = 100) who underwent baseline CT examinations from June 19, 2015 to June 14, 2020 at three tertiary referral centres (The First Affiliated Hospital of Sun Yat-Sen University, The First Affiliated Hospital of Shantou University Medical College, and The First People's Hospital of Foshan City) in China. Disease progression referred to the development of penetrating or stricturing diseases or the requirement for CD-related surgeries during follow-up. A total of 1130 radiomics features were extracted from VAT on CT in the training cohort, and a machine-learning-based VAT-RM was developed to predict disease progression using selected reproducible features and validated in an external test cohort. Using the same modeling methodology, a SAT-RM was developed and compared with the VAT-RM. The VAT-RM exhibited satisfactory performance for predicting disease progression in total test cohort (the area under the ROC curve [AUC] = 0.850, 95% confidence Interval [CI] 0.764-0.913, Our results suggest that VAT is an important determinant of disease progression in patients with CD. Our VAT-RM allows the accurate identification of high-risk patients prone to disease progression and offers notable advantages over SAT-RM. This study was supported by the National Natural Science Foundation of China, Guangdong Basic and Applied Basic Research Foundation, Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions, Nature Science Foundation of Shenzhen, and Young S&T Talent Training Program of Guangdong Provincial Association for S&T. For the Chinese translation of the abstract see Supplementary Materials section.
Sections du résumé
Background
UNASSIGNED
Visceral adipose tissue (VAT) is involved in the pathogenesis of Crohn's disease (CD). However, data describing its effects on CD progression remain scarce. We developed and validated a VAT-radiomics model (RM) using computed tomography (CT) images to predict disease progression in patients with CD and compared it with a subcutaneous adipose tissue (SAT)-RM.
Methods
UNASSIGNED
This retrospective study included 256 patients with CD (training, n = 156; test, n = 100) who underwent baseline CT examinations from June 19, 2015 to June 14, 2020 at three tertiary referral centres (The First Affiliated Hospital of Sun Yat-Sen University, The First Affiliated Hospital of Shantou University Medical College, and The First People's Hospital of Foshan City) in China. Disease progression referred to the development of penetrating or stricturing diseases or the requirement for CD-related surgeries during follow-up. A total of 1130 radiomics features were extracted from VAT on CT in the training cohort, and a machine-learning-based VAT-RM was developed to predict disease progression using selected reproducible features and validated in an external test cohort. Using the same modeling methodology, a SAT-RM was developed and compared with the VAT-RM.
Findings
UNASSIGNED
The VAT-RM exhibited satisfactory performance for predicting disease progression in total test cohort (the area under the ROC curve [AUC] = 0.850, 95% confidence Interval [CI] 0.764-0.913,
Interpretation
UNASSIGNED
Our results suggest that VAT is an important determinant of disease progression in patients with CD. Our VAT-RM allows the accurate identification of high-risk patients prone to disease progression and offers notable advantages over SAT-RM.
Funding
UNASSIGNED
This study was supported by the National Natural Science Foundation of China, Guangdong Basic and Applied Basic Research Foundation, Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions, Nature Science Foundation of Shenzhen, and Young S&T Talent Training Program of Guangdong Provincial Association for S&T.
Translation
UNASSIGNED
For the Chinese translation of the abstract see Supplementary Materials section.
Identifiants
pubmed: 36618894
doi: 10.1016/j.eclinm.2022.101805
pii: S2589-5370(22)00534-X
pmc: PMC9816914
doi:
Types de publication
Journal Article
Langues
eng
Pagination
101805Informations de copyright
© 2022 The Author(s).
Déclaration de conflit d'intérêts
All authors declare no competing interests.
Références
Colorectal Dis. 2015 Mar;17(3):225-34
pubmed: 25307174
J Crohns Colitis. 2021 Jul 5;15(7):1161-1173
pubmed: 33411893
Radiology. 2016 Feb;278(2):563-77
pubmed: 26579733
Inflamm Bowel Dis. 2015 Dec;21(12):2857-63
pubmed: 26241001
Gastroenterology. 2022 Feb;162(2):482-494
pubmed: 34757139
Inflamm Bowel Dis. 2014 Dec;20(12):2286-91
pubmed: 25222655
Clin Gastroenterol Hepatol. 2021 Sep;19(9):1835-1844.e6
pubmed: 32798706
Gastroenterology. 2021 Jun;160(7):2303-2316.e11
pubmed: 33609503
Aliment Pharmacol Ther. 2018 Aug;48(3):347-357
pubmed: 29920726
Inflamm Bowel Dis. 2016 Jan;22(1):114-26
pubmed: 26332309
Inflamm Bowel Dis. 2021 Aug 19;27(9):1435-1442
pubmed: 33236765
Gut. 2012 Jan;61(1):86-94
pubmed: 21930728
Eur Radiol. 2022 Feb;32(2):1256-1266
pubmed: 34435205
Lancet. 2017 Apr 29;389(10080):1741-1755
pubmed: 27914655
Lancet Gastroenterol Hepatol. 2022 Jan;7(1):96-106
pubmed: 34822760
Am J Gastroenterol. 2018 Apr;113(4):481-517
pubmed: 29610508
Nat Sci Sleep. 2021 Oct 28;13:1943-1953
pubmed: 34737662
Clin Gastroenterol Hepatol. 2018 Sep;16(9):1467-1473
pubmed: 29486253
Nutr Metab Cardiovasc Dis. 2022 Apr;32(4):973-980
pubmed: 35168828
Clin Gastroenterol Hepatol. 2011 Aug;9(8):684-687.e1
pubmed: 21642015
Gastroenterology. 2018 Mar;154(4):1172-1194
pubmed: 29329905
J Crohns Colitis. 2018 Nov 09;12(10):1139-1150
pubmed: 29309546
Front Cardiovasc Med. 2022 Mar 03;9:813085
pubmed: 35310976
Colorectal Dis. 2016 Feb;18(2):163-72
pubmed: 26391914
Aliment Pharmacol Ther. 2017 Nov;46(10):964-973
pubmed: 28949018
Cell. 2020 Oct 29;183(3):666-683.e17
pubmed: 32991841
Clin Nutr. 2020 Oct;39(10):3024-3030
pubmed: 31980183
Nat Rev Gastroenterol Hepatol. 2017 Feb;14(2):110-121
pubmed: 27899815
Nutrients. 2018 Sep 01;10(9):
pubmed: 30200405