Predictive models of response to neoadjuvant chemotherapy in muscle-invasive bladder cancer using nuclear morphology and tissue architecture.
Aged
Aged, 80 and over
Cell Nucleus
/ pathology
Cohort Studies
Female
Humans
Image Processing, Computer-Assisted
Machine Learning
Male
Middle Aged
Models, Biological
Muscles
/ pathology
Neoadjuvant Therapy
Neoplasm Invasiveness
Survival Analysis
Tumor Microenvironment
Urinary Bladder Neoplasms
/ drug therapy
bladder cancer
chemotherapy
digital pathology
image processing
machine learning
neoadjuvant
nucleus morphology
predictive biomarkers
tissue architecture
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:
30
01
2021
revised:
30
04
2021
accepted:
29
07
2021
entrez:
8
10
2021
pubmed:
9
10
2021
medline:
9
10
2021
Statut:
epublish
Résumé
Characterizing likelihood of response to neoadjuvant chemotherapy (NAC) in muscle-invasive bladder cancer (MIBC) is an important yet unmet challenge. In this study, a machine-learning framework is developed using imaging of biopsy pathology specimens to generate models of likelihood of NAC response. Developed using cross-validation (evaluable N = 66) and an independent validation cohort (evaluable N = 56), our models achieve promising results (65%-73% accuracy). Interestingly, one model-using features derived from hematoxylin and eosin (H&E)-stained tissues in conjunction with clinico-demographic features-is able to stratify the cohort into likely responders in cross-validation and the validation cohort (response rate of 65% for predicted responder compared with the 41% baseline response rate in the validation cohort). The results suggest that computational approaches applied to routine pathology specimens of MIBC can capture differences between responders and non-responders to NAC and should therefore be considered in the future design of precision oncology for MIBC.
Identifiants
pubmed: 34622225
doi: 10.1016/j.xcrm.2021.100382
pii: S2666-3791(21)00236-6
pmc: PMC8484511
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Langues
eng
Pagination
100382Subventions
Organisme : NCI NIH HHS
ID : R01 CA138264
Pays : United States
Organisme : NCI NIH HHS
ID : U01 CA212007
Pays : United States
Informations de copyright
© 2021 The Author(s).
Déclaration de conflit d'intérêts
The authors declare no competing interests.
Références
Front Oncol. 2019 Nov 20;9:1270
pubmed: 31824850
Am J Clin Oncol. 2009 Oct;32(5):535-9
pubmed: 19652580
Cancer Res. 2020 Mar 1;80(5):1199-1209
pubmed: 31874858
Oncoimmunology. 2016 Feb 18;5(5):e1134412
pubmed: 27467953
Nat Methods. 2020 Mar;17(3):261-272
pubmed: 32015543
J Immunother Cancer. 2020 Nov;8(2):
pubmed: 33219090
Urol Oncol. 2015 May;33(5):204.e1-7
pubmed: 25814145
PLoS One. 2015 Jul 31;10(7):e0131245
pubmed: 26230923
Sci Rep. 2017 Oct 19;7(1):13543
pubmed: 29051570
Front Oncol. 2019 Jan 07;8:649
pubmed: 30666298
Nat Commun. 2020 Apr 14;11(1):1778
pubmed: 32286325
IEEE/ACM Trans Comput Biol Bioinform. 2020 Nov-Dec;17(6):1871-1882
pubmed: 31536012
Front Physiol. 2020 Oct 19;11:583333
pubmed: 33192595
Sci Rep. 2017 Feb 16;7:42713
pubmed: 28205537
Nat Med. 2019 Aug;25(8):1301-1309
pubmed: 31308507
Cancer Cell. 2020 Apr 13;37(4):471-484
pubmed: 32289271
Sci Rep. 2017 Dec 4;7(1):16878
pubmed: 29203879
Bioinformatics. 2018 Mar 15;34(6):1024-1030
pubmed: 29136101
Lab Invest. 2015 Apr;95(4):377-84
pubmed: 25599534
Sci Rep. 2020 Jun 16;10(1):9743
pubmed: 32546765
Eur Urol Focus. 2020 Jul 15;6(4):642-649
pubmed: 31708469
Eur Urol. 2017 Oct;72(4):544-554
pubmed: 28390739
Curr Opin Oncol. 2014 May;26(3):305-20
pubmed: 24685646
Mol Biol Cell. 2016 Nov 7;27(22):3627-3636
pubmed: 27582387
Gigascience. 2018 Jun 1;7(6):
pubmed: 29860392
Cancers (Basel). 2020 Sep 21;12(9):
pubmed: 32967377
Am J Surg Pathol. 2014 Mar;38(3):325-32
pubmed: 24525502
Cell Cycle. 2011 Aug 1;10(15):2497-503
pubmed: 21775818
Nat Commun. 2020 Sep 25;11(1):4858
pubmed: 32978382
Int J Mol Sci. 2019 Feb 13;20(4):
pubmed: 30781730
Adv Radiat Oncol. 2018 Sep 07;4(1):177-185
pubmed: 30706026
Med Image Comput Comput Assist Interv. 2013;16(Pt 3):396-403
pubmed: 24505786
N Engl J Med. 2003 Aug 28;349(9):859-66
pubmed: 12944571
Eur Urol. 2005 Aug;48(2):202-5; discussion 205-6
pubmed: 15939524