Weakly supervised deep learning to predict recurrence in low-grade endometrial cancer from multiplexed immunofluorescence images.
Journal
NPJ digital medicine
ISSN: 2398-6352
Titre abrégé: NPJ Digit Med
Pays: England
ID NLM: 101731738
Informations de publication
Date de publication:
23 Mar 2023
23 Mar 2023
Historique:
received:
05
08
2022
accepted:
10
03
2023
entrez:
24
3
2023
pubmed:
25
3
2023
medline:
25
3
2023
Statut:
epublish
Résumé
Predicting recurrence in low-grade, early-stage endometrial cancer (EC) is both challenging and clinically relevant. We present a weakly-supervised deep learning framework, NaroNet, that can learn, without manual expert annotation, the complex tumor-immune interrelations at three levels: local phenotypes, cellular neighborhoods, and tissue areas. It uses multiplexed immunofluorescence for the simultaneous visualization and quantification of CD68 + macrophages, CD8 + T cells, FOXP3 + regulatory T cells, PD-L1/PD-1 protein expression, and tumor cells. We used 489 tumor cores from 250 patients to train a multilevel deep-learning model to predict tumor recurrence. Using a tenfold cross-validation strategy, our model achieved an area under the curve of 0.90 with a 95% confidence interval of 0.83-0.95. Our model predictions resulted in concordance for 96,8% of cases (κ = 0.88). This method could accurately assess the risk of recurrence in EC, outperforming current prognostic factors, including molecular subtyping.
Identifiants
pubmed: 36959234
doi: 10.1038/s41746-023-00795-x
pii: 10.1038/s41746-023-00795-x
pmc: PMC10036616
doi:
Types de publication
Journal Article
Langues
eng
Pagination
48Subventions
Organisme : Ministry of Economy and Competitiveness | Instituto de Salud Carlos III (Institute of Health Carlos III)
ID : PI17/01723 and PI21/00920
Informations de copyright
© 2023. The Author(s).
Références
Sci Rep. 2017 Oct 17;7(1):13380
pubmed: 29042640
J Immunother Cancer. 2021 Jul;9(7):
pubmed: 34266881
NPJ Breast Cancer. 2019 Oct 29;5:37
pubmed: 31700993
Nature. 2021 Jun;594(7861):106-110
pubmed: 33953404
Nat Rev Cancer. 2012 Mar 15;12(4):298-306
pubmed: 22419253
Cell. 2020 Sep 3;182(5):1341-1359.e19
pubmed: 32763154
J Pathol. 2020 Mar;250(3):323-335
pubmed: 31829442
J Immunother Cancer. 2020 May;8(1):
pubmed: 32414858
Nat Med. 2018 Oct;24(10):1559-1567
pubmed: 30224757
Nat Biomed Eng. 2021 Jun;5(6):555-570
pubmed: 33649564
Gynecol Oncol. 2009 Jul;114(1):105-10
pubmed: 19411095
IEEE J Biomed Health Inform. 2022 Oct 21;PP:
pubmed: 36269914
Microsyst Nanoeng. 2019 Nov 6;5:59
pubmed: 31700674
Mod Pathol. 2018 Feb;31(2):214-234
pubmed: 29192647
J Transl Med. 2017 Oct 12;15(1):206
pubmed: 29025424
Cancer Cell. 2018 Dec 10;34(6):1012-1026.e3
pubmed: 30537506
Cell Rep Med. 2021 Sep 23;2(9):100400
pubmed: 34622237
Nat Rev Dis Primers. 2021 Dec 9;7(1):88
pubmed: 34887451
Science. 2006 Sep 29;313(5795):1960-4
pubmed: 17008531
Med Image Anal. 2022 Jul;79:102474
pubmed: 35588568
Cancer Res. 2020 Mar 1;80(5):1199-1209
pubmed: 31874858
Nat Med. 2019 Mar;25(3):470-476
pubmed: 30742120
Nat Med. 2019 Aug;25(8):1301-1309
pubmed: 31308507
Br J Cancer. 2015 Sep 1;113(5):786-93
pubmed: 26217922
Cell. 2017 Aug 24;170(5):927-938.e20
pubmed: 28841418
JAMA. 2017 Dec 12;318(22):2199-2210
pubmed: 29234806
J Pathol. 2021 Oct;255(2):190-201
pubmed: 34184758
Med Image Anal. 2022 May;78:102384
pubmed: 35217454
J Pathol. 2020 Mar;250(3):336-345
pubmed: 31829441
Anticancer Res. 2005 Jan-Feb;25(1B):463-70
pubmed: 15816613
Bioinformatics. 2016 Nov 15;32(22):3532-3534
pubmed: 27412086
Cancers (Basel). 2021 Feb 14;13(4):
pubmed: 33672863
Cell. 2018 Oct 18;175(3):751-765.e16
pubmed: 30318143
Clin Cancer Res. 2022 Aug 15;28(16):3417-3424
pubmed: 35522154
Mod Pathol. 2020 Dec;33(12):2507-2519
pubmed: 32591586
N Engl J Med. 2005 Dec 22;353(25):2654-66
pubmed: 16371631
Lancet Digit Health. 2023 Feb;5(2):e71-e82
pubmed: 36496303
Nat Commun. 2021 Nov 18;12(1):6726
pubmed: 34795254
J Pathol. 2022 Dec;258(4):426-436
pubmed: 36169332
Eur J Cancer. 2016 Dec;69:51-60
pubmed: 27816832