Integrative Analysis of Histopathological Images and Genomic Data Predicts Clear Cell Renal Cell Carcinoma Prognosis.

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. ©2017 AACR.

[1]  Lorenzo Marconi,et al.  EAU guidelines on renal cell carcinoma: 2014 update. , 2010, European urology.

[2]  Mina Bissell,et al.  Reproducibility: The risks of the replication drive , 2013, Nature.

[3]  Joon-Oh Park,et al.  Somatic VHL alteration and its impact on prognosis in patients with clear cell renal cell carcinoma. , 2005, Oncology reports.

[4]  Michael I. Jordan,et al.  On Spectral Clustering: Analysis and an algorithm , 2001, NIPS.

[5]  Lawrence O. Hall,et al.  Nucleus segmentation in histology images with hierarchical multilevel thresholding , 2016, SPIE Medical Imaging.

[6]  S. Horvath,et al.  A General Framework for Weighted Gene Co-Expression Network Analysis , 2005, Statistical applications in genetics and molecular biology.

[7]  R. Figlin,et al.  Improved prognostication of renal cell carcinoma using an integrated staging system. , 2001, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[8]  Subha Madhavan,et al.  NCI Workshop Report: Clinical and Computational Requirements for Correlating Imaging Phenotypes with Genomics Signatures , 2014, Translational oncology.

[9]  Jian Xian,et al.  Combined image and genomic analysis of high-grade serous ovarian cancer reveals PTEN loss as a common driver event and prognostic classifier , 2014, Genome Biology.

[10]  S. Horvath,et al.  Using Protein Expressions to Predict Survival in Clear Cell Renal Carcinoma , 2004, Clinical Cancer Research.

[11]  Benjamin Haibe-Kains,et al.  Extensive rewiring of epithelial-stromal co-expression networks in breast cancer , 2015, Genome Biology.

[12]  H. Aburatani,et al.  Integrated molecular analysis of clear-cell renal cell carcinoma , 2013, Nature Genetics.

[13]  C. Sander,et al.  Adverse Outcomes in Clear Cell Renal Cell Carcinoma with Mutations of 3p21 Epigenetic Regulators BAP1 and SETD2: A Report by MSKCC and the KIRC TCGA Research Network , 2013, Clinical Cancer Research.

[14]  Kazuki Kobayashi,et al.  VHL tumor suppressor gene alterations associated with good prognosis in sporadic clear-cell renal carcinoma. , 2002, Journal of the National Cancer Institute.

[15]  Fang Yang,et al.  New breast cancer prognostic factors identified by computer-aided image analysis of HE stained histopathology images , 2015, Scientific Reports.

[16]  W. E. Mesker,et al.  Prognostic significance of the tumor-stroma ratio: validation study in node-negative premenopausal breast cancer patients from the EORTC perioperative chemotherapy (POP) trial (10854) , 2013, Breast Cancer Research and Treatment.

[17]  Joel H. Saltz,et al.  Research and applications: Cancer Digital Slide Archive: an informatics resource to support integrated in silico analysis of TCGA pathology data , 2013, J. Am. Medical Informatics Assoc..

[18]  Hai Su,et al.  High-throughput histopathological image analysis via robust cell segmentation and hashing , 2015, Medical Image Anal..

[19]  Benjamin J. Raphael,et al.  Mutational landscape and significance across 12 major cancer types , 2013, Nature.

[20]  Jing Chen,et al.  ToppGene Suite for gene list enrichment analysis and candidate gene prioritization , 2009, Nucleic Acids Res..

[21]  John R. Gilbertson,et al.  Computer aided diagnostic tools aim to empower rather than replace pathologists: Lessons learned from computational chess , 2011, Journal of pathology informatics.

[22]  N. Marcussen,et al.  Molecular characterization of clear cell renal cell carcinoma identifies CSNK2A1, SPP1 and DEFB1 as promising novel prognostic markers , 2016, APMIS : acta pathologica, microbiologica, et immunologica Scandinavica.

[23]  Yang Xiang,et al.  Weighted Frequent Gene Co-expression Network Mining to Identify Genes Involved in Genome Stability , 2012, PLoS Comput. Biol..

[24]  J. Hackermüller,et al.  CD31, EDNRB and TSPAN7 are promising prognostic markers in clear‐cell renal cell carcinoma revealed by genome‐wide expression analyses of primary tumors and metastases , 2012, International journal of cancer.

[25]  J Kulka,et al.  The prognostic significance of tumour–stroma ratio in oestrogen receptor-positive breast cancer , 2014, British Journal of Cancer.

[26]  Peter Langfelder,et al.  Eigengene networks for studying the relationships between co-expression modules , 2007, BMC Systems Biology.

[27]  J. Gutkind,et al.  G-protein-coupled receptors and cancer , 2007, Nature Reviews Cancer.

[28]  P. Tang,et al.  Clinical and molecular prognostic factors in renal cell carcinoma: what we know so far. , 2011, Hematology/oncology clinics of North America.

[29]  Steve Horvath,et al.  WGCNA: an R package for weighted correlation network analysis , 2008, BMC Bioinformatics.

[30]  Paul K Crane,et al.  lordif: An R Package for Detecting Differential Item Functioning Using Iterative Hybrid Ordinal Logistic Regression/Item Response Theory and Monte Carlo Simulations. , 2011, Journal of statistical software.

[31]  B. Rini,et al.  Molecular Biomarkers in Advanced Renal Cell Carcinoma , 2014, Clinical Cancer Research.

[32]  Chao Wang,et al.  Identifying survival associated morphological features of triple negative breast cancer using multiple datasets , 2013, Journal of the American Medical Informatics Association : JAMIA.

[33]  The Cancer Genome Atlas Research Network.  COMPREHENSIVE MOLECULAR CHARACTERIZATION OF CLEAR CELL RENAL CELL CARCINOMA , 2013, Nature.

[34]  Zoltan Szallasi,et al.  Systematic Evaluation of the Prognostic Impact and Intratumour Heterogeneity of Clear Cell Renal Cell Carcinoma Biomarkers , 2014, European urology.

[35]  M Mazumdar,et al.  Survival and prognostic stratification of 670 patients with advanced renal cell carcinoma. , 1999, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[36]  Joel H. Saltz,et al.  Machine-Based Morphologic Analysis of Glioblastoma Using Whole-Slide Pathology Images Uncovers Clinically Relevant Molecular Correlates , 2013, PloS one.

[37]  Steven J. M. Jones,et al.  Comprehensive molecular characterization of clear cell renal cell carcinoma , 2013, Nature.

[38]  Bin Wang,et al.  Deconvolution Estimation in Measurement Error Models: The R Package decon. , 2011, Journal of statistical software.

[39]  C. Demir,et al.  Two-Tier Tissue Decomposition for Histopathological Image Representation and Classification , 2015, IEEE Transactions on Medical Imaging.

[40]  Andrew H. Beck,et al.  Systematic Analysis of Breast Cancer Morphology Uncovers Stromal Features Associated with Survival , 2011, Science Translational Medicine.

[41]  Stephen T. C. Wong,et al.  Differential diagnosis of breast cancer using quantitative, label-free and molecular vibrational imaging , 2011, Biomedical optics express.

[42]  Chao Wang,et al.  iGPSe: A visual analytic system for integrative genomic based cancer patient stratification , 2014, BMC Bioinformatics.

[43]  H. Endou,et al.  Molecular physiology of renal organic anion transporters. , 2006, American journal of physiology. Renal physiology.

[44]  F. Markowetz,et al.  Quantitative Image Analysis of Cellular Heterogeneity in Breast Tumors Complements Genomic Profiling , 2012, Science Translational Medicine.

[45]  P. Kapur,et al.  Effects on survival of BAP1 and PBRM1 mutations in sporadic clear-cell renal-cell carcinoma: a retrospective analysis with independent validation. , 2013, The Lancet. Oncology.

[46]  Ce Zhang,et al.  Predicting non-small cell lung cancer prognosis by fully automated microscopic pathology image features , 2016, Nature Communications.

[47]  Tony Pan,et al.  An imaging workflow for characterizing phenotypical change in large histological mouse model datasets , 2008, J. Biomed. Informatics.

[48]  Holger Moch,et al.  The Heidelberg classification of renal cell tumours , 1997, The Journal of pathology.

[49]  Chao Wang,et al.  GRAPHIE: graph based histology image explorer , 2015, BMC Bioinformatics.

[50]  Daniel J. Brat,et al.  Novel genotype-phenotype associations in human cancers enabled by advanced molecular platforms and computational analysis of whole slide images , 2014, Laboratory Investigation.

[51]  Trevor Hastie,et al.  Regularization Paths for Cox's Proportional Hazards Model via Coordinate Descent. , 2011, Journal of statistical software.