Oncotarget

Research Papers:

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

Daniel Bug _, Friedrich Feuerhake, Eva Oswald, Julia Schüler and Dorit Merhof

PDF  |  Full Text  |  Supplementary Files  |  How to cite

Oncotarget. 2019; 10:4587-4597. https://doi.org/10.18632/oncotarget.27069

Metrics: PDF 1146 views  |   Full Text 1734 views  |   ?  


Abstract

Daniel Bug1, Friedrich Feuerhake2,3, Eva Oswald4, Julia Schüler4 and Dorit Merhof1

1 Institute of Imaging and Computer Vision, RWTH-Aachen University, D-52074 Aachen, Germany

2 Institute for Pathology, Hannover Medical School, D-30625 Hannover, Germany

3 Institute for Neuropathology, University Clinic Freiburg, D-79106 Freiburg im Breisgau, Germany

4 Charles River Discovery, Research Services Germany GmbH, D-79108 Freiburg im Breisgau, Germany

Correspondence to:

Daniel Bug,email: daniel.bug@lfb.rwth-aachen.de

Keywords: deep learning; digital pathology; histology; non small cell lung cancer; xenograft

Received: February 19, 2019     Accepted: June 21, 2019     Published: July 16, 2019

ABSTRACT

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.


Creative Commons License All site content, except where otherwise noted, is licensed under a Creative Commons Attribution 4.0 License.
PII: 27069