Hepatic Alveolar Echinococcosis: Predictive Biological Activity Based on Radiomics of MRI.
Journal
BioMed research international
ISSN: 2314-6141
Titre abrégé: Biomed Res Int
Pays: United States
ID NLM: 101600173
Informations de publication
Date de publication:
2021
2021
Historique:
received:
31
12
2020
revised:
06
03
2021
accepted:
17
03
2021
entrez:
17
5
2021
pubmed:
18
5
2021
medline:
1
6
2021
Statut:
epublish
Résumé
To evaluate the role of radiomics based on magnetic resonance imaging (MRI) in the biological activity of hepatic alveolar echinococcosis (HAE). In this study, 90 active and 46 inactive cases of HAE patients were analyzed retrospectively. All the subjects underwent MRI and positron emission tomography computed tomography (PET-CT) before surgery. A total of 1409 three-dimensional radiomics features were extracted from the T2-weighted MR images (T2WI). The inactive group in the training cohort was balanced via the synthetic minority oversampling technique (SMOTE) method. The least absolute shrinkage and selection operator (LASSO) regression method was used for feature selection. The machine learning (ML) classifiers were logistic regression (LR), multilayer perceptron (MLP), and support vector machine (SVM). We used a fivefold cross-validation strategy in the training cohorts. The classification performance of the radiomics signature was evaluated using receiver operating characteristic curve (ROC) analysis in the training and test cohorts. The radiomics features were significantly associated with the biological activity, and 10 features were selected to construct the radiomics model. The best performance of the radiomics model for the biological activity prediction was obtained by MLP (AUC = 0.830 ± 0.053; accuracy = 0.817; sensitivity = 0.822; specificity = 0.811). We developed and validated a radiomics model as an adjunct tool to predict the HAE biological activity by combining T2WI images, which achieved results nearly equal to the PET-CT findings.
Sections du résumé
BACKGROUND
BACKGROUND
To evaluate the role of radiomics based on magnetic resonance imaging (MRI) in the biological activity of hepatic alveolar echinococcosis (HAE).
METHODS
METHODS
In this study, 90 active and 46 inactive cases of HAE patients were analyzed retrospectively. All the subjects underwent MRI and positron emission tomography computed tomography (PET-CT) before surgery. A total of 1409 three-dimensional radiomics features were extracted from the T2-weighted MR images (T2WI). The inactive group in the training cohort was balanced via the synthetic minority oversampling technique (SMOTE) method. The least absolute shrinkage and selection operator (LASSO) regression method was used for feature selection. The machine learning (ML) classifiers were logistic regression (LR), multilayer perceptron (MLP), and support vector machine (SVM). We used a fivefold cross-validation strategy in the training cohorts. The classification performance of the radiomics signature was evaluated using receiver operating characteristic curve (ROC) analysis in the training and test cohorts.
RESULTS
RESULTS
The radiomics features were significantly associated with the biological activity, and 10 features were selected to construct the radiomics model. The best performance of the radiomics model for the biological activity prediction was obtained by MLP (AUC = 0.830 ± 0.053; accuracy = 0.817; sensitivity = 0.822; specificity = 0.811).
CONCLUSIONS
CONCLUSIONS
We developed and validated a radiomics model as an adjunct tool to predict the HAE biological activity by combining T2WI images, which achieved results nearly equal to the PET-CT findings.
Identifiants
pubmed: 33997041
doi: 10.1155/2021/6681092
pmc: PMC8108638
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
6681092Informations de copyright
Copyright © 2021 Bo Ren et al.
Déclaration de conflit d'intérêts
The authors declare that they have no competing interests.
Références
J Helminthol. 2015 Nov;89(6):671-9
pubmed: 26271332
Radiology. 2020 May;295(2):328-338
pubmed: 32154773
J Thorac Dis. 2019 May;11(5):1809-1818
pubmed: 31285873
Korean J Radiol. 2018 Jan-Feb;19(1):40-46
pubmed: 29353998
Acta Trop. 2010 Apr;114(1):1-16
pubmed: 19931502
Trop Med Int Health. 2019 Jun;24(6):663-670
pubmed: 30851233
Clin Microbiol Rev. 2019 Feb 13;32(2):
pubmed: 30760475
Parasitol Res. 2019 Sep;118(9):2455-2466
pubmed: 31402401
PLoS One. 2016 Feb 22;11(2):e0149440
pubmed: 26901164
Food Waterborne Parasitol. 2019 May 30;16:e00057
pubmed: 32095627
Eur Radiol. 2020 Feb;30(2):1274-1284
pubmed: 31506816
Chin Med J (Engl). 2011 Sep;124(18):2824-8
pubmed: 22167824
J Natl Cancer Inst. 2020 Sep 1;112(9):869-870
pubmed: 32016420
Lancet. 2003 Oct 18;362(9392):1295-304
pubmed: 14575976
Med Sci Monit. 2017 Dec 20;23:6019-6025
pubmed: 29259149
J Hepatol. 2019 May;70(5):1030-1031
pubmed: 30718093
Food Waterborne Parasitol. 2019 Apr 05;15:e00050
pubmed: 32095621
Radiology. 2016 Feb;278(2):563-77
pubmed: 26579733
Radiology. 2003 Jul;228(1):172-7
pubmed: 12750459
Am J Surg Pathol. 2020 Jan;44(1):43-54
pubmed: 31567204
Parasitology. 2020 Aug;147(9):1026-1031
pubmed: 32338226
Cancer Med. 2020 Jul;9(14):5155-5163
pubmed: 32476295
World J Gastroenterol. 2016 Apr 7;22(13):3621-31
pubmed: 27053854
J Nucl Med. 2013 Mar;54(3):358-63
pubmed: 23303963
Sci Rep. 2020 Jul 16;10(1):11808
pubmed: 32678174
Am J Surg Pathol. 2017 Jan;41(1):94-100
pubmed: 27673549
Eur J Cancer. 2012 Mar;48(4):441-6
pubmed: 22257792
Sci Rep. 2015 Aug 05;5:11075
pubmed: 26242464
Parasite. 2014;21:70
pubmed: 25526545
Acad Radiol. 2019 Sep;26(9):1262-1268
pubmed: 30377057
BMC Public Health. 2020 Jul 14;20(1):1105
pubmed: 32664905
Nat Commun. 2014 Jun 03;5:4006
pubmed: 24892406
Exp Ther Med. 2016 Jan;11(1):43-48
pubmed: 26889215
J Magn Reson Imaging. 2019 Jan;49(1):131-140
pubmed: 30171822
Diagn Interv Radiol. 2016 May-Jun;22(3):247-56
pubmed: 27082120
Parasite. 2014;21:74
pubmed: 25531446
Cardiovasc Res. 2020 Nov 1;116(13):2040-2054
pubmed: 32090243