Comparison of patient stratification by computed tomography radiomics and hypoxia positron emission tomography in head-and-neck cancer radiotherapy.
CT-Imaging
Imaging biomarkers
Machine Learning
PET-Imaging
Quantitative Imaging
Radiomics
Journal
Physics and imaging in radiation oncology
ISSN: 2405-6316
Titre abrégé: Phys Imaging Radiat Oncol
Pays: Netherlands
ID NLM: 101704276
Informations de publication
Date de publication:
Jul 2020
Jul 2020
Historique:
received:
19
03
2020
revised:
21
07
2020
accepted:
21
07
2020
entrez:
12
10
2020
pubmed:
13
10
2020
medline:
13
10
2020
Statut:
ppublish
Résumé
Hypoxia Positron-Emission-Tomography (PET) as well as Computed Tomography (CT) radiomics have been shown to be prognostic for radiotherapy outcome. Here, we investigate the stratification potential of CT-radiomics in head and neck cancer (HNC) patients and test if CT-radiomics is a surrogate predictor for hypoxia as identified by PET. Two independent cohorts of HNC patients were used for model development and validation, HN1 (n = 149) and HN2 (n = 47). The training set HN1 consisted of native planning CT data whereas for the validation cohort HN2 also hypoxia PET/CT data was acquired using [ The best performing CT-radiomics signature included two features with nearest-neighbour classification (AUC = 0.76 ± 0.09), whereas AUC was 0.59 for external validation. In contrast, [ No direct correlation of patient stratification using [
Sections du résumé
BACKGROUND AND PURPOSE
OBJECTIVE
Hypoxia Positron-Emission-Tomography (PET) as well as Computed Tomography (CT) radiomics have been shown to be prognostic for radiotherapy outcome. Here, we investigate the stratification potential of CT-radiomics in head and neck cancer (HNC) patients and test if CT-radiomics is a surrogate predictor for hypoxia as identified by PET.
MATERIALS AND METHODS
METHODS
Two independent cohorts of HNC patients were used for model development and validation, HN1 (n = 149) and HN2 (n = 47). The training set HN1 consisted of native planning CT data whereas for the validation cohort HN2 also hypoxia PET/CT data was acquired using [
RESULTS
RESULTS
The best performing CT-radiomics signature included two features with nearest-neighbour classification (AUC = 0.76 ± 0.09), whereas AUC was 0.59 for external validation. In contrast, [
CONCLUSIONS
CONCLUSIONS
No direct correlation of patient stratification using [
Identifiants
pubmed: 33043157
doi: 10.1016/j.phro.2020.07.003
pii: S2405-6316(20)30037-3
pmc: PMC7536307
doi:
Types de publication
Journal Article
Langues
eng
Pagination
52-59Informations de copyright
© 2020 The Author(s).
Déclaration de conflit d'intérêts
The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: DT and DZ declare institutional collaborations including financial support with the companies Siemens Healthineers (2014–2019), Elekta AB, Philips and PTW Freiburg without any direct relation to this study. In the past 5 years, MB attended an advisory board meeting of MERCK KGaA (Darmstadt), for which the University of Dresden received a travel grant. He further received funding for his research projects and for educational grants to the University of Dresden by Teutopharma GmbH (2011–2015), IBA (2016), Bayer AG (2016–2018), Merck KGaA (2014–2030), Medipan GmbH (2014–2018). For the German Cancer Research Center (DKFZ, Heidelberg) MB is on the supervisory boards of HI-STEM gGmbH (Heidelberg). MB, as former chair of OncoRay (Dresden) and present CEO and Scientific Chair of the German Cancer Research Center (DKFZ, Heidelberg), signed/signs contracts for his institute(s) and for the staff for research funding and/or collaborations with a multitude of companies worldwide. MB confirms that none of the above funding sources were involved in the design of this study, the preparation of this paper, the materials used, or the collection, analysis, and interpretation of data.
Références
J Nucl Med. 2019 Dec;60(12):1698-1704
pubmed: 31076504
Cancer. 2013 Aug 15;119(16):3034-42
pubmed: 23696076
Strahlenther Onkol. 2019 Sep;195(9):805-818
pubmed: 31222468
Radiother Oncol. 2019 Jun;135:43-50
pubmed: 31015169
Am J Surg Pathol. 2011 Jun;35(6):853-60
pubmed: 21566513
Eur J Cancer. 2012 Mar;48(4):441-6
pubmed: 22257792
Radiother Oncol. 2018 Jun;127(3):370-373
pubmed: 29598835
Nat Commun. 2014 Jun 03;5:4006
pubmed: 24892406
Nat Rev Clin Oncol. 2012 Dec;9(12):674-87
pubmed: 23149893
Sci Rep. 2017 Oct 16;7(1):13206
pubmed: 29038455
Eur J Nucl Med Mol Imaging. 2020 May;47(5):1056-1064
pubmed: 31773233
Clin Cancer Res. 2014 Dec 15;20(24):6389-97
pubmed: 25316821
Sci Rep. 2017 Jan 31;7:41674
pubmed: 28139704
Radiology. 2014 Oct;273(1):168-74
pubmed: 24827998
Clin Cancer Res. 2016 Dec 1;22(23):5765-5771
pubmed: 27803067
Radiother Oncol. 2017 Sep;124(3):533-540
pubmed: 28843726
Int J Radiat Oncol Biol Phys. 2017 Nov 15;99(4):921-928
pubmed: 28807534
Acta Oncol. 2017 Nov;56(11):1591-1596
pubmed: 28840770
Radiology. 2020 May;295(2):328-338
pubmed: 32154773
Radiother Oncol. 2012 Oct;105(1):21-8
pubmed: 23022173
Radiother Oncol. 2010 Nov;97(2):172-5
pubmed: 20570382
Radiother Oncol. 2018 Apr;127(1):36-42
pubmed: 29273260
Radiother Oncol. 2017 Sep;124(3):526-532
pubmed: 28434798
Acta Oncol. 2017 Nov;56(11):1531-1536
pubmed: 28820287
Radiother Oncol. 2019 Jan;130:10-17
pubmed: 30087056
Acta Oncol. 2015;54(9):1364-9
pubmed: 26481464
Radiology. 2014 Feb;270(2):464-71
pubmed: 24029645
Radiology. 2016 Nov;281(2):382-391
pubmed: 27144536
Sci Rep. 2019 Oct 23;9(1):15198
pubmed: 31645603
IEEE Trans Pattern Anal Mach Intell. 2005 Aug;27(8):1226-38
pubmed: 16119262
Sci Rep. 2018 Jan 24;8(1):1524
pubmed: 29367653
Nat Rev Clin Oncol. 2017 Dec;14(12):749-762
pubmed: 28975929