Predicting endometrial cancer subtypes and molecular features from histopathology images using multi-resolution deep learning models.
cancer genomics
cancer imaging
computational biology
computational pathology
deep learning
endometrial carcinoma
Journal
Cell reports. Medicine
ISSN: 2666-3791
Titre abrégé: Cell Rep Med
Pays: United States
ID NLM: 101766894
Informations de publication
Date de publication:
21 09 2021
21 09 2021
Historique:
received:
01
02
2021
revised:
29
05
2021
accepted:
24
08
2021
entrez:
8
10
2021
pubmed:
9
10
2021
medline:
9
10
2021
Statut:
epublish
Résumé
The determination of endometrial carcinoma histological subtypes, molecular subtypes, and mutation status is critical for the diagnostic process, and directly affects patients' prognosis and treatment. Sequencing, albeit slower and more expensive, can provide additional information on molecular subtypes and mutations that can be used to better select treatments. Here, we implement a customized multi-resolution deep convolutional neural network, Panoptes, that predicts not only the histological subtypes but also the molecular subtypes and 18 common gene mutations based on digitized H&E-stained pathological images. The model achieves high accuracy and generalizes well on independent datasets. Our results suggest that Panoptes, with further refinement, has the potential for clinical application to help pathologists determine molecular subtypes and mutations of endometrial carcinoma without sequencing.
Identifiants
pubmed: 34622237
doi: 10.1016/j.xcrm.2021.100400
pii: S2666-3791(21)00258-5
pmc: PMC8484685
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Langues
eng
Pagination
100400Subventions
Organisme : NIA NIH HHS
ID : P30 AG066512
Pays : United States
Informations de copyright
© 2021 The Author(s).
Déclaration de conflit d'intérêts
The authors declare no competing interests.
Références
Nat Med. 2018 Oct;24(10):1559-1567
pubmed: 30224757
Gynecol Oncol. 1983 Feb;15(1):10-7
pubmed: 6822361
Nat Cancer. 2020 Aug;1(8):789-799
pubmed: 33763651
Nat Med. 2019 Jul;25(7):1054-1056
pubmed: 31160815
Lancet. 2016 Mar 12;387(10023):1094-1108
pubmed: 26354523
Med Image Anal. 2016 Oct;33:170-175
pubmed: 27423409
Lancet Oncol. 2014 Jun;15(7):e268-78
pubmed: 24872110
Expert Opin Ther Targets. 2014 Jul;18(7):725-30
pubmed: 24750045
Oncotarget. 2017 Dec 31;9(5):5652-5664
pubmed: 29464025
IEEE Trans Med Imaging. 2016 Aug;35(8):1962-71
pubmed: 27164577
Gynecol Oncol. 2014 Aug;134(2):385-92
pubmed: 24905773
CA Cancer J Clin. 2016 Jan-Feb;66(1):7-30
pubmed: 26742998
Cancer Lett. 2016 Sep 28;380(1):296-303
pubmed: 26592351
Virchows Arch. 2010 Jul;457(1):27-34
pubmed: 20552366
Comput Struct Biotechnol J. 2018 Feb 09;16:34-42
pubmed: 30275936
Sci Signal. 2013 Apr 02;6(269):pl1
pubmed: 23550210
Int J Gynecol Pathol. 2019 Jan;38 Suppl 1:S40-S63
pubmed: 30550483
Gynecol Oncol. 2014 Aug;134(2):393-402
pubmed: 24929052
Cancer Cell. 2021 Apr 12;39(4):509-528.e20
pubmed: 33577785
Am J Surg Pathol. 2004 Dec;28(12):1568-78
pubmed: 15577675
Int J Surg Pathol. 2000 Oct;8(4):279-289
pubmed: 11494005
Gynecol Oncol. 2004 Dec;95(3):463-8
pubmed: 15581947
Gynecol Oncol. 2013 May;129(2):277-84
pubmed: 23485770
Cancer Discov. 2012 May;2(5):401-4
pubmed: 22588877
Cell. 2020 Feb 20;180(4):729-748.e26
pubmed: 32059776
Hum Pathol. 2008 Jan;39(1):116-25
pubmed: 17949789
Arch Pathol Lab Med. 2016 Jan;140(1):41-50
pubmed: 26098131
Nature. 2013 May 2;497(7447):67-73
pubmed: 23636398
J Pathol. 2018 Apr;244(5):512-524
pubmed: 29288495
Cell. 2020 Jul 9;182(1):200-225.e35
pubmed: 32649874
Lancet. 2005 Aug 6-12;366(9484):491-505
pubmed: 16084259