Integrative Analysis of Histopathological Images and Genomic Data in Colon Adenocarcinoma.
colon adenocarcinoma
genomic data
histopathological features
prognosis
random forest
Journal
Frontiers in oncology
ISSN: 2234-943X
Titre abrégé: Front Oncol
Pays: Switzerland
ID NLM: 101568867
Informations de publication
Date de publication:
2021
2021
Historique:
received:
01
12
2020
accepted:
31
08
2021
entrez:
14
10
2021
pubmed:
15
10
2021
medline:
15
10
2021
Statut:
epublish
Résumé
Colon adenocarcinoma (COAD) is one of the most common malignant tumors in the world. The histopathological features are crucial for the diagnosis, prognosis, and therapy of COAD. We downloaded 719 whole-slide histopathological images from TCIA, and 459 corresponding HTSeq-counts mRNA expression and clinical data were obtained from TCGA. Histopathological image features were extracted by CellProfiler. Prognostic image features were selected by the least absolute shrinkage and selection operator (LASSO) and support vector machine (SVM) algorithms. The co-expression gene module correlated with prognostic image features was identified by weighted gene co-expression network analysis (WGCNA). Random forest was employed to construct an integrative prognostic model and calculate the histopathological-genomic prognosis factor (HGPF). There were five prognostic image features and one co-expression gene module involved in the model construction. The time-dependent receiver operating curve showed that the prognostic model had a significant prognostic value. Patients were divided into high-risk group and low-risk group based on the HGPF. Kaplan-Meier analysis indicated that the overall survival of the low-risk group was significantly better than the high-risk group. These results suggested that the histopathological image features had a certain ability to predict the survival of COAD patients. The integrative prognostic model based on the histopathological images and genomic features could further improve the prognosis prediction in COAD, which may assist the clinical decision in the future.
Sections du résumé
BACKGROUND
BACKGROUND
Colon adenocarcinoma (COAD) is one of the most common malignant tumors in the world. The histopathological features are crucial for the diagnosis, prognosis, and therapy of COAD.
METHODS
METHODS
We downloaded 719 whole-slide histopathological images from TCIA, and 459 corresponding HTSeq-counts mRNA expression and clinical data were obtained from TCGA. Histopathological image features were extracted by CellProfiler. Prognostic image features were selected by the least absolute shrinkage and selection operator (LASSO) and support vector machine (SVM) algorithms. The co-expression gene module correlated with prognostic image features was identified by weighted gene co-expression network analysis (WGCNA). Random forest was employed to construct an integrative prognostic model and calculate the histopathological-genomic prognosis factor (HGPF).
RESULTS
RESULTS
There were five prognostic image features and one co-expression gene module involved in the model construction. The time-dependent receiver operating curve showed that the prognostic model had a significant prognostic value. Patients were divided into high-risk group and low-risk group based on the HGPF. Kaplan-Meier analysis indicated that the overall survival of the low-risk group was significantly better than the high-risk group.
CONCLUSIONS
CONCLUSIONS
These results suggested that the histopathological image features had a certain ability to predict the survival of COAD patients. The integrative prognostic model based on the histopathological images and genomic features could further improve the prognosis prediction in COAD, which may assist the clinical decision in the future.
Identifiants
pubmed: 34646756
doi: 10.3389/fonc.2021.636451
pmc: PMC8504715
doi:
Types de publication
Journal Article
Langues
eng
Pagination
636451Informations de copyright
Copyright © 2021 Li, Chen, Zeng, Liao, Ji and Ma.
Déclaration de conflit d'intérêts
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Références
J Clin Oncol. 2016 Jan 1;34(1):20-6
pubmed: 26578619
Oncotarget. 2017 Jan 17;8(3):5566-5577
pubmed: 27852047
Dev Cell. 2008 Jun;14(6):818-29
pubmed: 18539112
Int J Radiat Oncol Biol Phys. 2018 Nov 15;102(4):1098-1106
pubmed: 29439884
Cancer Res. 2017 Nov 1;77(21):e91-e100
pubmed: 29092949
Pac Symp Biocomput. 2020;25:355-366
pubmed: 31797610
J Digit Imaging. 2013 Dec;26(6):1045-57
pubmed: 23884657
BMC Med Inform Decis Mak. 2020 Jul 17;20(1):162
pubmed: 32680493
J Clin Oncol. 2015 Jun 1;33(16):1787-96
pubmed: 25918287
Cancer Med. 2018 Aug;7(8):3704-3712
pubmed: 29984907
Mol Med Rep. 2017 Nov;16(5):6499-6505
pubmed: 28901407
Brief Bioinform. 2015 May;16(3):461-74
pubmed: 24950687
Nat Commun. 2016 Aug 16;7:12474
pubmed: 27527408
IEEE Trans Med Imaging. 2020 Jan;39(1):99-110
pubmed: 31170067
Cancer Manag Res. 2020 Oct 27;12:10603-10613
pubmed: 33149669
J Pathol Inform. 2011;2:25
pubmed: 21773056
Biomed Res Int. 2015;2015:238757
pubmed: 26504789
IEEE J Biomed Health Inform. 2017 Jul;21(4):1027-1038
pubmed: 28113734
J Pathol Inform. 2013 Sep 27;4:27
pubmed: 24244884
Sci Transl Med. 2012 Jul 11;4(142):142ra95
pubmed: 22786680
Gene. 2017 Mar 10;604:33-40
pubmed: 27998790
Cancers (Basel). 2019 Sep 26;11(10):
pubmed: 31561604
Mol Imaging Biol. 2021 Jun;23(3):427-435
pubmed: 33108800
Gene. 2018 May 15;654:95-102
pubmed: 29408621
Cancer. 1986 May 1;57(9):1866-70
pubmed: 3485470
CA Cancer J Clin. 2019 Sep;69(5):363-385
pubmed: 31184787
Cancers (Basel). 2019 Mar 13;11(3):
pubmed: 30871256
Cancers (Basel). 2019 Apr 24;11(4):
pubmed: 31022926
Cell Adh Migr. 2014;8(6):588-94
pubmed: 25482625
Comput Methods Programs Biomed. 2018 Jul;161:45-53
pubmed: 29852967
Nat Rev Mol Cell Biol. 2014 Mar;15(3):178-96
pubmed: 24556840
Crit Rev Oncol Hematol. 2010 May;74(2):106-33
pubmed: 20138539
Cell Syst. 2017 Dec 27;5(6):620-627.e3
pubmed: 29153840
Contemp Oncol (Pozn). 2015;19(1A):A68-77
pubmed: 25691825
Front Cell Dev Biol. 2021 May 20;9:637675
pubmed: 34095111
Lab Invest. 2015 Apr;95(4):366-76
pubmed: 25599536
BMC Bioinformatics. 2008 Dec 29;9:559
pubmed: 19114008
Nat Commun. 2019 Jul 11;10(1):3071
pubmed: 31296856
Sci Transl Med. 2011 Nov 9;3(108):108ra113
pubmed: 22072638
J Thorac Oncol. 2017 Mar;12(3):501-509
pubmed: 27826035
Math Biosci Eng. 2020 Dec 18;18(1):727-744
pubmed: 33525116
Eur Radiol. 2020 Jan;30(1):547-557
pubmed: 31396730
Sci Rep. 2021 Jul 2;11(1):13729
pubmed: 34215760
Annu Int Conf IEEE Eng Med Biol Soc. 2013;2013:1282-5
pubmed: 24109929
Front Oncol. 2020 Jan 31;10:48
pubmed: 32083005
Cancer Res. 2009 Sep 15;69(18):7131-4
pubmed: 19738053
Am J Clin Pathol. 2016 Jan;145(1):6-7
pubmed: 26712865
Aging (Albany NY). 2019 Oct 15;11(19):8710-8727
pubmed: 31612869
Am J Emerg Med. 2021 Aug;46:462-468
pubmed: 33214022
Biol Proced Online. 2015 Aug 07;17:11
pubmed: 26251640
Eur J Nucl Med Mol Imaging. 2018 May;45(5):680-688
pubmed: 29344718