Association of a CT-Based Clinical and Radiomics Score of Non-Small Cell Lung Cancer (NSCLC) with Lymph Node Status and Overall Survival.
computed tomography
lung cancer
lymph nodes
overall survival
radiomics
reconstruction algorithms
Journal
Cancers
ISSN: 2072-6694
Titre abrégé: Cancers (Basel)
Pays: Switzerland
ID NLM: 101526829
Informations de publication
Date de publication:
31 May 2020
31 May 2020
Historique:
received:
28
04
2020
revised:
28
05
2020
accepted:
29
05
2020
entrez:
4
6
2020
pubmed:
4
6
2020
medline:
4
6
2020
Statut:
epublish
Résumé
To evaluate whether a model based on radiomic and clinical features may be associated with lymph node (LN) status and overall survival (OS) in lung cancer (LC) patients; to evaluate whether CT reconstruction algorithms may influence the model performance. patients operated on for LC with a pathological stage up to T3N1 were retrospectively selected and divided into training and validation sets. For the prediction of positive LNs and OS, the Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression model was used; univariable and multivariable logistic regression analysis assessed the association of clinical-radiomic variables and endpoints. All tests were repeated after dividing the groups according to the CT reconstruction algorithm. 270 patients were included and divided into training (n = 180) and validation sets (n = 90). Transfissural extension was significantly associated with positive LNs. For OS prediction, high- and low-risk groups were different according to the radiomics score, also after dividing the two groups according to reconstruction algorithms. a combined clinical-radiomics model was not superior to a single clinical or single radiomics model to predict positive LNs. A radiomics model was able to separate high-risk and low-risk patients for OS; CTs reconstructed with Iterative Reconstructions (IR) algorithm showed the best model performance.
Sections du résumé
BACKGROUND
BACKGROUND
To evaluate whether a model based on radiomic and clinical features may be associated with lymph node (LN) status and overall survival (OS) in lung cancer (LC) patients; to evaluate whether CT reconstruction algorithms may influence the model performance.
METHODS
METHODS
patients operated on for LC with a pathological stage up to T3N1 were retrospectively selected and divided into training and validation sets. For the prediction of positive LNs and OS, the Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression model was used; univariable and multivariable logistic regression analysis assessed the association of clinical-radiomic variables and endpoints. All tests were repeated after dividing the groups according to the CT reconstruction algorithm.
RESULTS
RESULTS
270 patients were included and divided into training (n = 180) and validation sets (n = 90). Transfissural extension was significantly associated with positive LNs. For OS prediction, high- and low-risk groups were different according to the radiomics score, also after dividing the two groups according to reconstruction algorithms.
CONCLUSIONS
CONCLUSIONS
a combined clinical-radiomics model was not superior to a single clinical or single radiomics model to predict positive LNs. A radiomics model was able to separate high-risk and low-risk patients for OS; CTs reconstructed with Iterative Reconstructions (IR) algorithm showed the best model performance.
Identifiants
pubmed: 32486453
pii: cancers12061432
doi: 10.3390/cancers12061432
pmc: PMC7352293
pii:
doi:
Types de publication
Journal Article
Langues
eng
Références
BMC Med Genomics. 2011 Apr 08;4:31
pubmed: 21477282
Medicine (Baltimore). 2019 Mar;98(12):e14800
pubmed: 30896623
J Thorac Cardiovasc Surg. 2011 Mar;141(3):662-70
pubmed: 21335122
CA Cancer J Clin. 2020 Jan;70(1):7-30
pubmed: 31912902
Oncol Lett. 2020 Feb;19(2):1559-1566
pubmed: 31966081
Eur J Cardiothorac Surg. 2008 Jul;34(1):187-95
pubmed: 18457958
Med Phys. 2018 Jun;45(6):2518-2526
pubmed: 29624702
Proc Natl Acad Sci U S A. 2008 Apr 1;105(13):5213-8
pubmed: 18362333
J Thorac Dis. 2018 Apr;10(Suppl 7):S807-S819
pubmed: 29780627
Surgeon. 2011 Apr;9(2):72-7
pubmed: 21342670
J Thorac Oncol. 2016 Jan;11(1):39-51
pubmed: 26762738
Radiology. 2005 Oct;237(1):309-15
pubmed: 16183939
Radiology. 2012 Aug;264(2):387-96
pubmed: 22723499
Nat Rev Clin Oncol. 2017 Dec;14(12):749-762
pubmed: 28975929
Med Phys. 2015 Mar;42(3):1341-53
pubmed: 25735289
Radiology. 2016 Feb;278(2):563-77
pubmed: 26579733
J Vasc Interv Radiol. 2007 Jul;18(7):821-31
pubmed: 17609439
Eur Radiol. 2018 Nov;28(11):4849-4859
pubmed: 29737390
Radiology. 2005 Oct;237(1):303-8
pubmed: 16183938
Eur Radiol Exp. 2018 Nov 14;2(1):36
pubmed: 30426318
Eur Radiol. 2016 Jan;26(1):32-42
pubmed: 25956936
Radiology. 2014 Feb;270(2):464-71
pubmed: 24029645
Eur Radiol. 2019 Jan;29(1):392-400
pubmed: 29922924
Nat Biotechnol. 2007 Jun;25(6):675-80
pubmed: 17515910
Biometrics. 1988 Sep;44(3):837-45
pubmed: 3203132
Radiology. 2014 Aug;272(2):568-76
pubmed: 24885982