Predicting Genetic Mutation from Whole Slide Images via Biomedical-Linguistic Knowledge Enhanced Multi-label Classification

TL;DR

This paper introduces a novel multi-label Transformer model, BPGT, that leverages biomedical knowledge and gene relationships to improve genetic mutation prediction from whole slide images, addressing inefficiencies and biological oversight in prior methods.

Contribution

The paper proposes a biological-knowledge enhanced Transformer architecture with a gene encoder and label decoder, integrating linguistic and biomedical knowledge for better mutation prediction.

Findings

BPGT outperforms state-of-the-art methods on TCGA benchmark.

The gene encoder effectively captures gene relationships and priors.

The model improves prediction accuracy by emphasizing mutation status comparisons.

Abstract

Predicting genetic mutations from whole slide images is indispensable for cancer diagnosis. However, existing work training multiple binary classification models faces two challenges: (a) Training multiple binary classifiers is inefficient and would inevitably lead to a class imbalance problem. (b) The biological relationships among genes are overlooked, which limits the prediction performance. To tackle these challenges, we innovatively design a Biological-knowledge enhanced PathGenomic multi-label Transformer to improve genetic mutation prediction performances. BPGT first establishes a novel gene encoder that constructs gene priors by two carefully designed modules: (a) A gene graph whose node features are the genes' linguistic descriptions and the cancer phenotype, with edges modeled by genes' pathway associations and mutation consistencies. (b) A knowledge association module that fuses linguistic and biomedical knowledge into gene priors by transformer-based graph representation learning, capturing the intrinsic relationships between different genes' mutations. BPGT then designs a label decoder that finally performs genetic mutation prediction by two tailored modules: (a) A modality fusion module that firstly fuses the gene priors with critical regions in WSIs and obtains gene-wise mutation logits. (b) A comparative multi-label loss that emphasizes the inherent comparisons among mutation status to enhance the discrimination capabilities. Sufficient experiments on The Cancer Genome Atlas benchmark demonstrate that BPGT outperforms the state-of-the-art.