Development of a histopathology informatics pipeline for classification and prediction of clinical outcome in subtypes of renal cell carcinoma.

Histopathology evaluation is the gold standard for diagnosing clear cell (ccRCC), papillary (pRCC), and chromophobe (chRCC) renal cell carcinoma (RCC). However, inter-rater variability has been reported, and the whole-slide histopathology images likely contain underutilized biological signals predictive of genomic profiles.

To address this knowledge gap, we obtained whole-slide histopathology images, demographic, genomic, and clinical data from The Cancer Genome Atlas, the Clinical Proteomic Tumor Analysis Consortium, and Brigham and Women's Hospital to develop computational methods for integrating data analyses. Leveraging these large and diverse datasets, we developed fully automated convolutional neural networks to diagnose renal cancers and connect quantitative pathology patterns with patients' genomic profiles and prognoses.

Our deep convolutional neural networks successfully detected malignancy (area under the receiver operating characteristic curves (AUCs) in the independent validation cohort: 0.964-0.985), diagnosed RCC histological subtypes (independent validation AUCs of the best models: 0.953-0.993), and predicted stage I ccRCC patients' survival outcomes (log-rank test p = 0.02). Our machine learning approaches further identified histopathology image features indicative of copy number alterations (AUC>0.7 in multiple genes in ccRCC patients) and tumor mutation burden.

Our results suggest that convolutional neural networks can extract histological signals predictive of patients' diagnoses, prognoses, and genomic variations of clinical importance. Our approaches can systematically identify previously unknown relations among diverse data modalities.

Clinical cancer research : an official journal of the American Association for Cancer Research. 2021 Mar 15 [Epub ahead of print]

Eliana Marostica, Rebecca Barber, Thomas Denize, Isaac S Kohane, Sabina Signoretti, Jeffrey A Golden, Kun-Hsing Yu

Department of Biomedical Informatics, Harvard Medical School., Princeton University., Pathology, Brigham and Women's Hospital., Biomedical Informatics, Harvard Medical School., Department of Pathology, Brigham and Women's Hospital., Biomedical Informatics, Harvard Medical School .