New directions for deep learning in cancer research through concept explainability and virtual experimentation.

Introduction

Deep learning (DL) is rapidly transforming cancer research and oncology. DL can extract subtle visual features from preclinical and clinical image data. In my junior research group, I have developed end-to-end DL methods to predict molecular biomarkers and clinical outcomes directly from histopathology slides.

Availability of Histopathology Slides

Because histopathology slides are ubiquitously available for any patient with a solid tumor, DL is a broad tool for translational studies, enabling researchers to extract molecular information and make predictions about clinical outcomes.

Limitations of Deep Learning

However, the potential of DL in cancer research is fundamentally limited because it is purely descriptive and, in many cases, a black-box system.

Disconnection from Biological Knowledge

Also, DL is currently disjoint from the vast amount of biological mechanistic knowledge in cancer research and from the world of experimentation.

NADIR Project Goals

In NADIR, I will close this gap. My hypothesis is that DL models can not only make predictions but can be used to verify existing biological knowledge and to make new mechanistic discoveries.

Tools for Addressing the Gap

The main tools that allow me to address this are:

1. Concept explainability
2. Counterfactual virtual experimentation

For both, there exists a nonmedical proof of concept, but no systematic biomedical application yet.

Researcher Background

I approach this problem as a biomedical cancer researcher with training in programming, medical image analysis, and biomedical engineering.

Development of DL Systems

As such, I will develop DL systems that can:

• Extract biological concepts
• Elucidate biological mechanisms
• Create and answer mechanistic hypotheses

Synergy with Other Research Pipelines

NADIR’s tools will be synergistic with and can be used together with other biological high-throughput experimentation pipelines such as transgenic animal experiments or tumor organoid cultures.

Main Use Case

The main use case of NADIR is focused on tumor-immune interaction in colorectal and gastric cancer. Through the educational and outreach program in NADIR, it will be made available as a general tool for cancer researchers in biomedicine.