Estimating clear cell renal cell carcinoma transcriptomic signatures using machine learning and histopathology images.

4533 Background: Gene expression signatures derived from RNA sequencing data have been associated with treatment outcomes for renal cell carcinoma (RCC) patients. Incorporating these RNA biomarkers into clinical practice is promising, yet its real-world applicability is heavily limited as RNA profiling is expensive, time-consuming, and requires specialized expertise for data analysis. In this study, we applied a deep neural network framework to identify the correlation between standard pathology images and underlying RNA signatures using hematoxylin and eosin (H&E) stained formalin-fixed paraffin-embedded (FFPE) whole slides of clear cell kidney tumors from The Cancer Genome Atlas (TCGA). Methods: We collected 496 H&E stained FFPE clear cell RCC whole-slide images and the RNA gene signatures for 496 patients from the TCGA database. We partitioned 496 slides into training (N = 245, 50%), development (N = 49, 10%), and test (N = 202, 40%) sets. We used this dataset to train and evaluate our weakly-supervised deep learning model. The model was iteratively trained using extracted patches from a slide and processed the patches through a convolutional neural network (CNN), pre-trained for the RCC subtypes classification task, to represent features. The features were aggregated and summarized to predict angiogenesis, myeloid infiltration, and adenosine gene signature (AdenoSig) scores. Performance was assessed by computing Pearson’s correlation coefficients. 95% confident intervals (CI) are computed using the Fisher Z transformation. Results: The median angiogenesis score was 6.98 (range: 1.77-8.40), the median myeloid score was 0.54 (range: -4.59-5.96), and the median AdenoSig score was 268.31 (range: -4988.71-7621.57). A total of 202 slides were included in the test set. On this test set, the results of our weakly supervised method achieved a Pearson’s correlation of 0.65 (95% CI: 0.57-0.73), 0.10 (95% CI: -0.04-0.23), and 0.10 (95% CI: -0.04-0.23) with angiogenesis, myeloid, and AdenoSig scores from gold-standard RNA sequencing data, respectively. Conclusions: We proposed using deep learning-based AI techniques to process digitized histopathological images and estimate actionable signatures of angiogenesis, myeloid, and AdenoSig from H&E stained slides. Our model showed promising results for predicting angiogenesis scores compared to myeloid and AdenoSig scores. These results suggest the feasibility of this approach for estimating digital biomarkers from H&E histopathology images and offering a rapid and cost-effective alternative to conventional RNA sequencing.