Radiogenomic modeling predicts survival-associated prognostic groups in glioblastoma.
MRI
biomarkers
copy number alterations
glioblastoma
radiogenomics
Journal
Neuro-oncology advances
ISSN: 2632-2498
Titre abrégé: Neurooncol Adv
Pays: England
ID NLM: 101755003
Informations de publication
Date de publication:
Historique:
entrez:
22
2
2021
pubmed:
23
2
2021
medline:
23
2
2021
Statut:
epublish
Résumé
Combined whole-exome sequencing (WES) and somatic copy number alteration (SCNA) information can separate Radiologic features ( We were able to classify glioblastomas into two prognostic subgroups with a cross-validated area under the curve score of 0.80 (±0.03) using ridge logistic regression on the 15-dimensional principle component analysis (PCA) embedding of the features selected by our novel feature selection method. An interrogation of the selected features suggested that features describing contours in the T2 signal abnormality region on the T2-weighted fluid-attenuated inversion recovery (FLAIR) MRI sequence may best distinguish these two groups from one another. We successfully trained a machine learning model that allows for relevant targeted feature extraction from standard MRI to accurately predict molecularly-defined risk-stratifying
Sections du résumé
BACKGROUND
BACKGROUND
Combined whole-exome sequencing (WES) and somatic copy number alteration (SCNA) information can separate
METHODS
METHODS
Radiologic features (
RESULTS
RESULTS
We were able to classify glioblastomas into two prognostic subgroups with a cross-validated area under the curve score of 0.80 (±0.03) using ridge logistic regression on the 15-dimensional principle component analysis (PCA) embedding of the features selected by our novel feature selection method. An interrogation of the selected features suggested that features describing contours in the T2 signal abnormality region on the T2-weighted fluid-attenuated inversion recovery (FLAIR) MRI sequence may best distinguish these two groups from one another.
CONCLUSIONS
CONCLUSIONS
We successfully trained a machine learning model that allows for relevant targeted feature extraction from standard MRI to accurately predict molecularly-defined risk-stratifying
Identifiants
pubmed: 33615222
doi: 10.1093/noajnl/vdab004
pii: vdab004
pmc: PMC7883769
doi:
Types de publication
Journal Article
Langues
eng
Pagination
vdab004Subventions
Organisme : NCI NIH HHS
ID : K08 CA245037
Pays : United States
Informations de copyright
© The Author(s) 2021. Published by Oxford University Press, the Society for Neuro-Oncology and the European Association of Neuro-Oncology.
Références
Radiology. 2016 Dec;281(3):907-918
pubmed: 27636026
J Digit Imaging. 2013 Dec;26(6):1045-57
pubmed: 23884657
Genes Dev. 2013 Jul 1;27(13):1462-72
pubmed: 23796897
Neuro Oncol. 2020 Jul 24;:
pubmed: 32706862
Radiology. 2013 May;267(2):560-9
pubmed: 23392431
J Digit Imaging. 2017 Oct;30(5):622-628
pubmed: 28785873
Cancer Med. 2018 Dec;7(12):5999-6009
pubmed: 30426720
Acta Neuropathol Commun. 2017 May 22;5(1):39
pubmed: 28532485
Neuro Oncol. 2018 Sep 3;20(10):1368-1373
pubmed: 29982740
Sci Rep. 2018 Aug 6;8(1):11773
pubmed: 30082856
PLoS One. 2012;7(1):e30098
pubmed: 22291905
J Med Imaging (Bellingham). 2018 Jan;5(1):011018
pubmed: 29340286
Lancet Oncol. 2019 May;20(5):728-740
pubmed: 30952559
J Magn Reson Imaging. 2018 Oct;48(4):916-926
pubmed: 29394005
Radiology. 2016 Feb;278(2):563-77
pubmed: 26579733
Med Image Anal. 2001 Jun;5(2):143-56
pubmed: 11516708
Magn Reson Imaging. 2012 Nov;30(9):1234-48
pubmed: 22898692
Sci Data. 2017 Sep 05;4:170117
pubmed: 28872634
Acta Neuropathol. 2015 Sep;130(3):419-34
pubmed: 25931051
AJNR Am J Neuroradiol. 2018 Jul;39(7):1201-1207
pubmed: 29748206
IEEE Trans Med Imaging. 2015 Oct;34(10):1993-2024
pubmed: 25494501
Cell. 2016 Jan 28;164(3):550-63
pubmed: 26824661
Cancer Res. 2017 Nov 1;77(21):e104-e107
pubmed: 29092951
Genes Dev. 2018 Apr 1;32(7-8):512-523
pubmed: 29632085
Neuroimage. 2019 Aug 15;197:652-656
pubmed: 30296563
IEEE Trans Med Imaging. 2010 Jun;29(6):1310-20
pubmed: 20378467
Neuroimage. 2002 Oct;17(2):825-41
pubmed: 12377157
Nature. 2008 Oct 23;455(7216):1061-8
pubmed: 18772890
Proc Natl Acad Sci U S A. 2016 May 10;113(19):5394-9
pubmed: 27118839
J Neurooncol. 2020 Jan;146(2):321-327
pubmed: 31865510
Neuroimage. 2006 Jul 1;31(3):1116-28
pubmed: 16545965
Acta Neuropathol. 2016 Jun;131(6):803-20
pubmed: 27157931