Prior Knowledge Injection into Deep Learning Models Predicting Gene Expression from Whole Slide Images

TL;DR

This paper introduces a flexible framework for incorporating prior gene interaction knowledge into deep learning models to improve gene expression prediction from whole slide images, enhancing accuracy and robustness.

Contribution

It presents a model-agnostic method to inject prior knowledge into deep learning architectures for gene expression prediction from WSIs, demonstrating significant improvements in performance.

Findings

Increased significant gene predictions by an average of 983 genes across experiments

14 genes showed improved generalization on an independent dataset

High potential for knowledge injection to enhance prediction accuracy

Abstract

Cancer diagnosis and prognosis primarily depend on clinical parameters such as age and tumor grade, and are increasingly complemented by molecular data, such as gene expression, from tumor sequencing. However, sequencing is costly and delays oncology workflows. Recent advances in Deep Learning allow to predict molecular information from morphological features within Whole Slide Images (WSIs), offering a cost-effective proxy of the molecular markers. While promising, current methods lack the robustness to fully replace direct sequencing. Here we aim to improve existing methods by introducing a model-agnostic framework that allows to inject prior knowledge on gene-gene interactions into Deep Learning architectures, thereby increasing accuracy and robustness. We design the framework to be generic and flexibly adaptable to a wide range of architectures. In a case study on breast cancer, our strategy leads to an average increase of 983 significant genes (out of 25,761) across all 18 experiments, with 14 generalizing to an increase on an independent dataset. Our findings reveal a high potential for injection of prior knowledge to increase gene expression prediction performance from WSIs across a wide range of architectures.