MR-Based Radiomics Nomogram of Cervical Cancer in Prediction of the Lymph-Vascular Space Invasion preoperatively.
Cervix Uteri
/ diagnostic imaging
Cohort Studies
Contrast Media
Female
Humans
Image Enhancement
/ methods
Lymphatic Metastasis
/ diagnostic imaging
Magnetic Resonance Imaging
/ methods
Middle Aged
Nomograms
Reproducibility of Results
Retrospective Studies
Sensitivity and Specificity
Uterine Cervical Neoplasms
/ diagnostic imaging
MRI
cervical cancer
lymph-vascular space invasion
prediction model
radiomics nomogram
Journal
Journal of magnetic resonance imaging : JMRI
ISSN: 1522-2586
Titre abrégé: J Magn Reson Imaging
Pays: United States
ID NLM: 9105850
Informations de publication
Date de publication:
05 2019
05 2019
Historique:
received:
02
08
2018
revised:
14
09
2018
accepted:
14
09
2018
pubmed:
27
10
2018
medline:
25
8
2020
entrez:
27
10
2018
Statut:
ppublish
Résumé
Lymph-vascular space invasion (LVSI) is an unfavorable prognostic factor in cervical cancer. Unfortunately, there are no current clinical tools for the preoperative prediction of LVSI. To develop and validate an axial T Retrospective. In all, 105 patients were randomly divided into two cohorts at a 2:1 ratio. T Univariate analysis was performed on the radiomics features and clinical parameters. Multivariate analysis was performed to determine the optimal feature subset. The receiver operating characteristic (ROC) analysis was performed to evaluate the performance of prediction model and radiomics nomogram. The Mann-Whitney U-test and the chi-square test were used to evaluate the performance of clinical characteristics and LVSI status by pathology. The minimum-redundancy/maximum-relevance and recursive feature elimination methods were applied to select the features. The radiomics model was constructed using logistic regression. Three radiomics features and one clinical characteristic were selected. The radiomics nomogram showed favorable discrimination between LVSI and non-LVSI groups. The AUC was 0.754 (95% confidence interval [CI], 0.6326-0.8745) in the training cohort and 0.727 (95% CI, 0.5449-0.9097) in the validation cohort. The specificity and sensitivity were 0.756 and 0.828 in the training cohort and 0.773 and 0.692 in the validation cohort. T 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:1420-1426.
Sections du résumé
BACKGROUND
Lymph-vascular space invasion (LVSI) is an unfavorable prognostic factor in cervical cancer. Unfortunately, there are no current clinical tools for the preoperative prediction of LVSI.
PURPOSE
To develop and validate an axial T
STUDY TYPE
Retrospective.
POPULATION
In all, 105 patients were randomly divided into two cohorts at a 2:1 ratio.
FIELD STRENGTH/SEQUENCE
T
ASSESSMENT
Univariate analysis was performed on the radiomics features and clinical parameters. Multivariate analysis was performed to determine the optimal feature subset. The receiver operating characteristic (ROC) analysis was performed to evaluate the performance of prediction model and radiomics nomogram.
STATISTICAL TESTS
The Mann-Whitney U-test and the chi-square test were used to evaluate the performance of clinical characteristics and LVSI status by pathology. The minimum-redundancy/maximum-relevance and recursive feature elimination methods were applied to select the features. The radiomics model was constructed using logistic regression.
RESULTS
Three radiomics features and one clinical characteristic were selected. The radiomics nomogram showed favorable discrimination between LVSI and non-LVSI groups. The AUC was 0.754 (95% confidence interval [CI], 0.6326-0.8745) in the training cohort and 0.727 (95% CI, 0.5449-0.9097) in the validation cohort. The specificity and sensitivity were 0.756 and 0.828 in the training cohort and 0.773 and 0.692 in the validation cohort.
DATA CONCLUSION
T
LEVEL OF EVIDENCE
4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:1420-1426.
Identifiants
pubmed: 30362652
doi: 10.1002/jmri.26531
pmc: PMC6587470
doi:
Substances chimiques
Contrast Media
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1420-1426Informations de copyright
© 2018 The Authors. Journal of Magnetic Resonance Imaging published by Wiley Periodicals, Inc. on behalf of International Society for Magnetic Resonance in Medicine.
Références
Eur J Cancer. 2003 Nov;39(17):2470-86
pubmed: 14602133
J Obstet Gynaecol Res. 2006 Jun;32(3):315-23
pubmed: 16764623
Radiology. 2016 Feb;278(2):563-77
pubmed: 26579733
Gynecol Oncol. 2008 Sep;110(3):308-15
pubmed: 18606439
Anticancer Res. 2014 Oct;34(10):5703-8
pubmed: 25275077
Gynecol Oncol. 2014 May;133(2):211-5
pubmed: 24582867
Gynecol Obstet Invest. 2016;81(3):251-5
pubmed: 26584181
Zhonghua Fu Chan Ke Za Zhi. 2015 Dec;50(12):894-901
pubmed: 26887872
Cancer Res. 2017 Nov 1;77(21):e104-e107
pubmed: 29092951
Cancer. 2011 Feb 15;117(4):768-76
pubmed: 20922801
J Bioinform Comput Biol. 2005 Apr;3(2):185-205
pubmed: 15852500
Radiology. 2016 Dec;281(3):947-957
pubmed: 27347764
Science. 2002 Jun 7;296(5574):1883-6
pubmed: 11976409
Tumour Biol. 2016 Apr;37(4):5063-74
pubmed: 26546434
Conf Proc IEEE Eng Med Biol Soc. 2016 Aug;2016:1268-1271
pubmed: 28268556
J Clin Oncol. 2016 Jun 20;34(18):2157-64
pubmed: 27138577
Br J Cancer. 2013 May 28;108(10):1957-63
pubmed: 23640393
Gynecol Oncol. 2012 Feb;124(2):276-80
pubmed: 22035808
Int J Gynecol Cancer. 2016 Feb;26(2):416-21
pubmed: 26745697
Neuro Oncol. 2017 Jun 1;19(6):862-870
pubmed: 28339588
Med Oncol. 2014 Jan;31(1):795
pubmed: 24310812
Gynecol Oncol. 2014 May;133(2):180-5
pubmed: 24589412
Curr Oncol Rep. 2015;17(5):446
pubmed: 25893880
J Clin Oncol. 2009 Feb 1;27(4):612-8
pubmed: 19075275
Nat Commun. 2014 Jun 03;5:4006
pubmed: 24892406
Int J Gynecol Cancer. 2009 Jan;19(1):50-3
pubmed: 19258941
Ann Surg Oncol. 2013 Jun;20(6):2007-15
pubmed: 23224830
Tohoku J Exp Med. 2015;237(1):25-30
pubmed: 26310275
Clin Cancer Res. 2017 Aug 1;23(15):4259-4269
pubmed: 28280088
Chin J Cancer. 2011 Sep;30(9):645-54
pubmed: 21880186
Abdom Radiol (NY). 2017 Jun;42(6):1695-1704
pubmed: 28180924
J Gynecol Oncol. 2017 Nov;28(6):e86
pubmed: 29027404
Cancer Res. 2017 Jul 15;77(14):3922-3930
pubmed: 28566328
Abdom Imaging. 2015 Oct;40(7):2486-511
pubmed: 25666968
J Nucl Med. 2017 Apr;58(4):569-576
pubmed: 27688480
J Natl Compr Canc Netw. 2015 Apr;13(4):395-404; quiz 404
pubmed: 25870376