Deep Learning Predicts EBV Status in Gastric Cancer Based on Spatial Patterns of Lymphocyte Infiltration

SIMPLE SUMMARY: EBV infection represents a distinct subtype in gastric cancer, so determining infection status is important in guiding treatment decisions. Currently, EBV infection in gastric cancer is most often determined using PCR and in situ hybridization, which requires multiple steps and nucleic acid preservation. On the other hand, histopathology images are widely available and included in the course of diagnosis for patients. Thus, our development of an approach to determine EBV status from these histopathology images could save costs and time associated with making EBV diagnoses for gastric cancer patients or independently validate the results from traditional methods. Additionally, our model’s predictions are able to classify patients into EBV infection categories that are significantly correlated with prognosis. This may serve to better inform clinicians’ decisions in prescribing immunotherapy, as both EBV infection status and prognosis are critical factors in whether immunotherapy is effective or worth the costs and side effects. ABSTRACT: EBV infection occurs in around 10% of gastric cancer cases and represents a distinct subtype, characterized by a unique mutation profile, hypermethylation, and overexpression of PD-L1. Moreover, EBV positive gastric cancer tends to have higher immune infiltration and a better prognosis. EBV infection status in gastric cancer is most commonly determined using PCR and in situ hybridization, but such a method requires good nucleic acid preservation. Detection of EBV status with histopathology images may complement PCR and in situ hybridization as a first step of EBV infection assessment. Here, we developed a deep learning-based algorithm to directly predict EBV infection in gastric cancer from H&E stained histopathology slides. Our model can not only predict EBV infection in gastric cancers from tumor regions but also from normal regions with potential changes induced by adjacent EBV+ regions within each H&E slide. Furthermore, in cohorts with zero EBV abundances, a significant difference of immune infiltration between high and low EBV score samples was observed, consistent with the immune infiltration difference observed between EBV positive and negative samples. Therefore, we hypothesized that our model’s prediction of EBV infection is partially driven by the spatial information of immune cell composition, which was supported by mostly positive local correlations between the EBV score and immune infiltration in both tumor and normal regions across all H&E slides. Finally, EBV scores calculated from our model were found to be significantly associated with prognosis. This framework can be readily applied to develop interpretable models for prediction of virus infection across cancers.