Machine Learning Models Identify Key Histological Features of Renal Cell Carcinoma Subtypes
Clear cell (cc) RCC is the predominant subtype comprising 80% of all cases, with papillary and chromophobe carcinoma accounting for 80% of all other RCCs, but overall, 16 different RCC subtypes have been identified.1 Treatment selection and prognosis varies by subtype, and treatment response has been associated with the cell and tissue composition of the tumor microenvironment (TME), including tumorspecific mutations.1 For example, PBRM1 is commonly mutated gene in RCC that may contribute to disease prognosis and response to immunotherapy, although its role is currently unclear.3-6 Exhaustive classification and quantification of the TME by machine learning (ML) models has the potential to reveal associations between tumor histology and mutations or molecular biomarkers.7
Here, ML models quantified histologic features of the TME directly from RCC hematoxylin and eosin (H&E)-stained whole slide images (WSI). The potential for model outputs to predict clinically-relevant biomarkers was investigated.
1 Escudier et al. Ann. Oncol. 2019;30(5):706-720
2 Cimadamore et al. Transl. Androl. Urol. 2021 Mar;10(3):1506-1520
3 Liu et al. Nat Commun. 2020;11(1):2135.
4 Braun et al. JAMA Oncol. 2019;5(11):1631- 1633.
5 Dizman et al. J Immunother Cancer. 2020;8(2):e000953
6 Carneiro et al. Kidney Cancer 2021 5(2):79-92
7 Diao et al. Nat Commun. 2021;12(1):1613
*These authors contributed equally to this project.