Semi-automated analysis of digital whole slides from humanized lung-cancer xenograft models for checkpoint inhibitor response prediction.

We propose a deep learning workflow for the classification of hematoxylin and eosin stained histological whole-slide images of non-small-cell lung cancer. The workflow includes automatic extraction of meta-features for the characterization of the tumor. We show that the tissue-classification produces state-of-the-art results with an average F1-score of 83%. Manual supervision indicates that experts, in practice, accept a far higher percentage of predictions. Furthermore, the extracted meta-features are validated via visualization revealing relevant biomedical relations between the different tissue classes. In a hypothetical decision-support scenario, these meta-features can be used to discriminate the tumor response with regard to available treatment options with an estimated accuracy of 84%. This workflow supports large-scale analysis of tissue obtained in preclinical animal experiments, enables reproducible quantification of tissue classes and immune system markers, and paves the way towards discovery of novel features predicting response in translational immune-oncology research.