Integrative analysis of histopathological images and genomic data predicts clear cell renal cell carcinoma prognosis

Jun Cheng, Jie Zhang, Yatong Han, Xusheng Wang, Xiufen Ye, Yuebo Meng, Anil Parwani, Zhi Han, Qianjin Feng, Kun Huang

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

In cancer, both histopathologic images and genomic signatures are used for diagnosis, prognosis, and subtyping. However, combining histopathologic images with genomic data for predicting prognosis, as well as the relationships between them, has rarely been explored. In this study, we present an integrative genomics framework for constructing a prognostic model for clear cell renal cell carcinoma. We used patient data from The Cancer Genome Atlas (n = 410), extracting hundreds of cellular morphologic features from digitized whole-slide images and eigengenes from functional genomics data to predict patient outcome. The risk index generated by our model correlated strongly with survival, outperforming predictions based on considering morphologic features or eigengenes separately. The predicted risk index also effectively stratified patients in early-stage (stage I and stage II) tumors, whereas no significant survival difference was observed using staging alone. The prognostic value of our model was independent of other known clinical and molecular prognostic factors for patients with clear cell renal cell carcinoma. Overall, this workflow and the shared software code provide building blocks for applying similar approaches in other cancers. Cancer Res; 77(21); e91-100.

Original languageEnglish (US)
Pages (from-to)e91-e100
JournalCancer Research
Volume77
Issue number21
DOIs
StatePublished - Nov 1 2017

Fingerprint

Renal Cell Carcinoma
Neoplasms
Genomics
Survival
Workflow
Atlases
Software
Genome

ASJC Scopus subject areas

  • Oncology
  • Cancer Research

Cite this

Integrative analysis of histopathological images and genomic data predicts clear cell renal cell carcinoma prognosis. / Cheng, Jun; Zhang, Jie; Han, Yatong; Wang, Xusheng; Ye, Xiufen; Meng, Yuebo; Parwani, Anil; Han, Zhi; Feng, Qianjin; Huang, Kun.

In: Cancer Research, Vol. 77, No. 21, 01.11.2017, p. e91-e100.

Research output: Contribution to journalArticle

Cheng, J, Zhang, J, Han, Y, Wang, X, Ye, X, Meng, Y, Parwani, A, Han, Z, Feng, Q & Huang, K 2017, 'Integrative analysis of histopathological images and genomic data predicts clear cell renal cell carcinoma prognosis', Cancer Research, vol. 77, no. 21, pp. e91-e100. https://doi.org/10.1158/0008-5472.CAN-17-0313
Cheng, Jun ; Zhang, Jie ; Han, Yatong ; Wang, Xusheng ; Ye, Xiufen ; Meng, Yuebo ; Parwani, Anil ; Han, Zhi ; Feng, Qianjin ; Huang, Kun. / Integrative analysis of histopathological images and genomic data predicts clear cell renal cell carcinoma prognosis. In: Cancer Research. 2017 ; Vol. 77, No. 21. pp. e91-e100.
@article{c6bace9652d044dbbbfef85c79b8d247,
title = "Integrative analysis of histopathological images and genomic data predicts clear cell renal cell carcinoma prognosis",
abstract = "In cancer, both histopathologic images and genomic signatures are used for diagnosis, prognosis, and subtyping. However, combining histopathologic images with genomic data for predicting prognosis, as well as the relationships between them, has rarely been explored. In this study, we present an integrative genomics framework for constructing a prognostic model for clear cell renal cell carcinoma. We used patient data from The Cancer Genome Atlas (n = 410), extracting hundreds of cellular morphologic features from digitized whole-slide images and eigengenes from functional genomics data to predict patient outcome. The risk index generated by our model correlated strongly with survival, outperforming predictions based on considering morphologic features or eigengenes separately. The predicted risk index also effectively stratified patients in early-stage (stage I and stage II) tumors, whereas no significant survival difference was observed using staging alone. The prognostic value of our model was independent of other known clinical and molecular prognostic factors for patients with clear cell renal cell carcinoma. Overall, this workflow and the shared software code provide building blocks for applying similar approaches in other cancers. Cancer Res; 77(21); e91-100.",
author = "Jun Cheng and Jie Zhang and Yatong Han and Xusheng Wang and Xiufen Ye and Yuebo Meng and Anil Parwani and Zhi Han and Qianjin Feng and Kun Huang",
year = "2017",
month = "11",
day = "1",
doi = "10.1158/0008-5472.CAN-17-0313",
language = "English (US)",
volume = "77",
pages = "e91--e100",
journal = "Journal of Cancer Research",
issn = "0099-7013",
publisher = "American Association for Cancer Research Inc.",
number = "21",

}

TY - JOUR

T1 - Integrative analysis of histopathological images and genomic data predicts clear cell renal cell carcinoma prognosis

AU - Cheng, Jun

AU - Zhang, Jie

AU - Han, Yatong

AU - Wang, Xusheng

AU - Ye, Xiufen

AU - Meng, Yuebo

AU - Parwani, Anil

AU - Han, Zhi

AU - Feng, Qianjin

AU - Huang, Kun

PY - 2017/11/1

Y1 - 2017/11/1

N2 - In cancer, both histopathologic images and genomic signatures are used for diagnosis, prognosis, and subtyping. However, combining histopathologic images with genomic data for predicting prognosis, as well as the relationships between them, has rarely been explored. In this study, we present an integrative genomics framework for constructing a prognostic model for clear cell renal cell carcinoma. We used patient data from The Cancer Genome Atlas (n = 410), extracting hundreds of cellular morphologic features from digitized whole-slide images and eigengenes from functional genomics data to predict patient outcome. The risk index generated by our model correlated strongly with survival, outperforming predictions based on considering morphologic features or eigengenes separately. The predicted risk index also effectively stratified patients in early-stage (stage I and stage II) tumors, whereas no significant survival difference was observed using staging alone. The prognostic value of our model was independent of other known clinical and molecular prognostic factors for patients with clear cell renal cell carcinoma. Overall, this workflow and the shared software code provide building blocks for applying similar approaches in other cancers. Cancer Res; 77(21); e91-100.

AB - In cancer, both histopathologic images and genomic signatures are used for diagnosis, prognosis, and subtyping. However, combining histopathologic images with genomic data for predicting prognosis, as well as the relationships between them, has rarely been explored. In this study, we present an integrative genomics framework for constructing a prognostic model for clear cell renal cell carcinoma. We used patient data from The Cancer Genome Atlas (n = 410), extracting hundreds of cellular morphologic features from digitized whole-slide images and eigengenes from functional genomics data to predict patient outcome. The risk index generated by our model correlated strongly with survival, outperforming predictions based on considering morphologic features or eigengenes separately. The predicted risk index also effectively stratified patients in early-stage (stage I and stage II) tumors, whereas no significant survival difference was observed using staging alone. The prognostic value of our model was independent of other known clinical and molecular prognostic factors for patients with clear cell renal cell carcinoma. Overall, this workflow and the shared software code provide building blocks for applying similar approaches in other cancers. Cancer Res; 77(21); e91-100.

UR - http://www.scopus.com/inward/record.url?scp=85035034820&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85035034820&partnerID=8YFLogxK

U2 - 10.1158/0008-5472.CAN-17-0313

DO - 10.1158/0008-5472.CAN-17-0313

M3 - Article

C2 - 29092949

AN - SCOPUS:85035034820

VL - 77

SP - e91-e100

JO - Journal of Cancer Research

JF - Journal of Cancer Research

SN - 0099-7013

IS - 21

ER -