Histopathology Based AI Model Predicts Anti-Angiogenic Therapy Response in Renal Cancer Clinical Trial.

Background: Predictive biomarkers of treatment response are lacking for metastatic clearcell renal cell carcinoma (ccRCC), a tumor type that is treated with angiogenesis inhibitors, immune checkpoint inhibitors, mTOR inhibitors and a HIF2 inhibitor. The Angioscore, an RNA-based quantification of angiogenesis, is arguably the best candidate to predict anti-angiogenic (AA) response. However, the clinical adoption of transcriptomic assays faces several challenges including standardization, time delay, and high cost. Further, ccRCC tumors are highly heterogenous, and sampling multiple areas for sequencing is impractical. Approach: Here we present a novel deep learning (DL) approach to predict the Angioscore from ubiquitous histopathology slides. In order to overcome the lack of interpretability, one of the biggest limitations of typical DL models, our model produces a visual vascular network which is the basis of the model's prediction. To test its reliability, we applied this model to multiple cohorts including a clinical trial dataset. Results: Our model accurately predicts the RNA-based Angioscore on multiple independent cohorts (spearman correlations of 0.77 and 0.73). Further, the predictions help unravel meaningful biology such as association of angiogenesis with grade, stage, and driver mutation status. Finally, we find our model is able to predict response to AA therapy, in both a real-world cohort and the IMmotion150 clinical trial. The predictive power of our model vastly exceeds that of CD31, a marker of vasculature, and nearly rivals the performance (c-index 0.66 vs 0.67) of the ground truth RNA-based Angioscore at a fraction of the cost. Conclusion: By providing a robust yet interpretable prediction of the Angioscore from histopathology slides alone, our approach offers insights into angiogenesis biology and AA treatment response.

Intratumoral Resolution of Driver Gene Mutation Heterogeneity in Renal Cancer Using Deep Learning.

Intratumoral heterogeneity arising from tumor evolution poses significant challenges biologically and clinically. Dissecting this complexity may benefit from deep learning (DL) algorithms, which can infer molecular features from ubiquitous hematoxylin and eosin (H&E)-stained tissue sections. Although DL algorithms have been developed to predict some driver mutations from H&E images, the ability of these DL algorithms to resolve intratumoral mutation heterogeneity at subclonal spatial resolution is unexplored. Here, we apply DL to a paradigm of intratumoral heterogeneity, clear cell renal cell carcinoma (ccRCC), the most common type of kidney cancer. Matched IHC and H&E images were leveraged to develop DL models for predicting intratumoral genetic heterogeneity of the three most frequently mutated ccRCC genes, BAP1, PBRM1, and SETD2. DL models were generated on a large cohort (N = 1,282) and tested on several independent cohorts, including a TCGA cohort (N = 363 patients) and two tissue microarray (TMA) cohorts (N = 118 and 365 patients). These models were also expanded to a patient-derived xenograft (PDX) TMA, affording analysis of homotopic and heterotopic interactions of tumor and stroma. The status of all three genes could be inferred by DL, with BAP1 showing the highest sensitivity and performance within and across tissue samples (AUC = 0.87-0.89 on holdout). BAP1 results were validated on independent human (AUC = 0.77-0.84) and PDX (AUC = 0.80) cohorts. Finally, BAP1 predictions correlated with clinical outputs such as disease-specific survival. Overall, these data show that DL models can resolve intratumoral heterogeneity in cancer with potential diagnostic, prognostic, and biological implications. SIGNIFICANCE: This work demonstrates the potential for deep learning analysis of histopathologic images to serve as a fast, low-cost method to assess genetic intratumoral heterogeneity. See related commentary by Song et al., p. 2672.

Deep learning reveals disease-specific signatures of white matter pathology in tauopathies.

Although pathology of tauopathies is characterized by abnormal tau protein aggregation in both gray and white matter regions of the brain, neuropathological investigations have generally focused on abnormalities in the cerebral cortex because the canonical aggregates that form the diagnostic criteria for these disorders predominate there. This corticocentric focus tends to deemphasize the relevance of the more complex white matter pathologies, which remain less well characterized and understood. We took a data-driven machine-learning approach to identify novel disease-specific morphologic signatures of white matter aggregates in three tauopathies: Alzheimer disease (AD), progressive supranuclear palsy (PSP), and corticobasal degeneration (CBD). We developed automated approaches using whole slide images of tau immunostained sections from 49 human autopsy brains (16 AD,13 CBD, 20 PSP) to identify cortex/white matter regions and individual tau aggregates, and compared tau-aggregate morphology across these diseases. Tau burden in the gray and white matter for individual subjects strongly correlated in a highly disease-specific fashion. We discovered previously unrecognized tau morphologies for AD, CBD and PSP that may be of importance in disease classification. Intriguingly, our models classified diseases equally well based on either white or gray matter tau staining. Our results suggest that tau pathology in white matter is informative, disease-specific, and linked to gray matter pathology. Machine learning has the potential to reveal latent information in histologic images that may represent previously unrecognized patterns of neuropathology, and additional studies of tau pathology in white matter could improve diagnostic accuracy.