Deep learning predicts chromosomal instability from histopathology images.
Automation in Bioinformatics
Cancer Systems Biology
Cell Biology
Neural Networks
Journal
iScience
ISSN: 2589-0042
Titre abrégé: iScience
Pays: United States
ID NLM: 101724038
Informations de publication
Date de publication:
21 May 2021
21 May 2021
Historique:
received:
14
12
2020
revised:
03
03
2021
accepted:
01
04
2021
entrez:
17
5
2021
pubmed:
18
5
2021
medline:
18
5
2021
Statut:
epublish
Résumé
Chromosomal instability (CIN) is a hallmark of human cancer yet not readily testable for patients with cancer in routine clinical setting. In this study, we sought to explore whether CIN status can be predicted using ubiquitously available hematoxylin and eosin histology through a deep learning-based model. When applied to a cohort of 1,010 patients with breast cancer (Training set: n = 858, Test set: n = 152) from The Cancer Genome Atlas where 485 patients have high CIN status, our model accurately classified CIN status, achieving an area under the curve of 0.822 with 81.2% sensitivity and 68.7% specificity in the test set. Patch-level predictions of CIN status suggested intra-tumor heterogeneity within slides. Moreover, presence of patches with high predicted CIN score within an entire slide was more predictive of clinical outcome than the average CIN score of the slide, thus underscoring the clinical importance of intra-tumor heterogeneity.
Identifiants
pubmed: 33997679
doi: 10.1016/j.isci.2021.102394
pii: S2589-0042(21)00362-X
pmc: PMC8099498
doi:
Types de publication
Journal Article
Langues
eng
Pagination
102394Subventions
Organisme : NIH HHS
ID : DP5 OD026395
Pays : United States
Organisme : NCI NIH HHS
ID : P30 CA008748
Pays : United States
Organisme : NCI NIH HHS
ID : P50 CA247749
Pays : United States
Organisme : NCI NIH HHS
ID : R01 CA256188
Pays : United States
Informations de copyright
© 2021 The Author(s).
Déclaration de conflit d'intérêts
A.V. is a full-time employee of Volastra Therapeutics. O.E. and S.B. are co-founders and hold equity in Volastra Therapeutics. Volastra Therapeutics develops therapeutic strategies to target CIN in cancer.
Références
Nat Med. 2018 Oct;24(10):1559-1567
pubmed: 30224757
Cancer Res. 2011 May 15;71(10):3447-52
pubmed: 21270108
Mol Biol Cell. 2016 Jul 1;27(13):1981-9
pubmed: 27146113
EBioMedicine. 2018 Jan;27:317-328
pubmed: 29292031
Ann Oncol. 2021 Jan;32(1):58-65
pubmed: 33098992
Med Image Anal. 2021 Jan;67:101813
pubmed: 33049577
PLoS One. 2015 Apr 20;10(4):e0123200
pubmed: 25893404
Nat Genet. 2006 Sep;38(9):1043-8
pubmed: 16921376
Elife. 2018 Sep 04;7:
pubmed: 30178746
Mol Oncol. 2010 Jun;4(3):255-66
pubmed: 20434415
In Vitro. 1978 Nov;14(11):911-5
pubmed: 730202
Mol Cytogenet. 2019 May 14;12:17
pubmed: 31114634
Nat Commun. 2020 Dec 11;11(1):6367
pubmed: 33311458
Clin Transl Med. 2020 Jun;10(2):e102
pubmed: 32536036
Gynecol Oncol. 2011 Apr;121(1):24-31
pubmed: 21251700
Nat Cancer. 2020 Aug;1(8):789-799
pubmed: 33763651
Nat Med. 2019 Jul;25(7):1054-1056
pubmed: 31160815
PLoS Genet. 2017 Apr 4;13(4):e1006707
pubmed: 28376088
Cancers (Basel). 2019 Jul 28;11(8):
pubmed: 31357676
Breast Cancer Res Treat. 2011 Jul;128(1):23-30
pubmed: 20632083
Gut. 2008 Jul;57(7):941-50
pubmed: 18364437
Cell. 2018 Sep 6;174(6):1347-1360
pubmed: 30193109
Cancer Metastasis Rev. 2013 Dec;32(3-4):341-52
pubmed: 23633034
NPJ Precis Oncol. 2020 Jun 8;4:14
pubmed: 32550270
Nature. 2018 Jan 25;553(7689):467-472
pubmed: 29342134
Proc Natl Acad Sci U S A. 2009 May 26;106(21):8671-6
pubmed: 19458043
Cancer Res. 2020 Nov 15;80(22):4892-4903
pubmed: 32816908
Oncogene. 2010 Apr 1;29(13):1897-908
pubmed: 20062086
Cancer Res. 2011 Mar 1;71(5):1858-70
pubmed: 21363922
Nature. 1998 Dec 17;396(6712):643-9
pubmed: 9872311
Ann Oncol. 2015 Jul;26(7):1340-6
pubmed: 26003169
Oral Oncol. 2017 Mar;66:14-21
pubmed: 28249643
Sci Transl Med. 2014 Mar 26;6(229):229ra43
pubmed: 24670687
BMC Cancer. 2014 Feb 22;14:121
pubmed: 24559140
Nature. 2013 Feb 28;494(7438):492-496
pubmed: 23446422
Lung Cancer. 2009 Sep;65(3):312-8
pubmed: 19168259