A novel machine learning approach reveals latent vascular phenotypes predictive of renal cancer outcome

• Published in: Scientific reports 2017-10, Vol.7 (1), p.13190-10, Article 13190
• Main Authors: Ing, Nathan, Huang, Fangjin, Conley, Andrew, You, Sungyong, Ma, Zhaoxuan, Klimov, Sergey, Ohe, Chisato, Yuan, Xiaopu, Amin, Mahul B., Figlin, Robert, Gertych, Arkadiusz, Knudsen, Beatrice S.
• Format: Article
• Language: English
• Subjects: 13/105; 13/51; 38; 45; 631/114/1564; 631/67/2328; 639/166/985; 692/53/2422; Algorithms; Artificial intelligence; Biomarkers, Tumor - genetics; Carcinoma, Renal Cell; Clear cell-type renal cell carcinoma; Correlation analysis; Endothelial cells; Gene expression; Gene Expression Profiling; Gene Expression Regulation, Neoplastic - genetics; Generalized linear models; Genomes; Humanities and Social Sciences; Humans; Image processing; Kaplan-Meier Estimate; Kidney cancer; Kidney Neoplasms - genetics; Kidney Neoplasms - pathology; Learning algorithms; Machine Learning; multidisciplinary; Prognosis; Science; Science (multidisciplinary)
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-017-13196-4

Gene expression signatures are commonly used as predictive biomarkers, but do not capture structural features within the tissue architecture. Here we apply a 2-step machine learning framework for quantitative imaging of tumor vasculature to derive a spatially informed, prognostic gene signature. The trained algorithms classify endothelial cells and generate a vascular area mask (VAM) in H&E micrographs of clear cell renal cell carcinoma (ccRCC) cases from The Cancer Genome Atlas (TCGA). Quantification of VAMs led to the discovery of 9 vascular features (9VF) that predicted disease-free-survival in a discovery cohort (n = 64, HR = 2.3). Correlation analysis and information gain identified a 14 gene expression signature related to the 9VF’s. Two generalized linear models with elastic net regularization (14VF and 14GT), based on the 14 genes, separated independent cohorts of up to 301 cases into good and poor disease-free survival groups (14VF HR = 2.4, 14GT HR = 3.33). For the first time, we successfully applied digital image analysis and targeted machine learning to develop prognostic, morphology-based, gene expression signatures from the vascular architecture. This novel morphogenomic approach has the potential to improve previous methods for biomarker development.