PathoGen-X: A Cross-Modal Genomic Feature Trans-Align Network for Enhanced Survival Prediction from Histopathology Images

TL;DR

PathoGen-X is a deep learning framework that enhances survival prediction from histopathology images by translating and aligning features with genomic data, improving accuracy while only requiring imaging data at test time.

Contribution

It introduces a novel cross-modal feature translation and alignment network that leverages genomic data during training to improve imaging-based survival prediction without needing genomic data at inference.

Findings

Outperforms existing methods on TCGA datasets

Requires fewer paired samples for training

Demonstrates strong survival prediction accuracy

Abstract

Accurate survival prediction is essential for personalized cancer treatment. However, genomic data - often a more powerful predictor than pathology data - is costly and inaccessible. We present the cross-modal genomic feature translation and alignment network for enhanced survival prediction from histopathology images (PathoGen-X). It is a deep learning framework that leverages both genomic and imaging data during training, relying solely on imaging data at testing. PathoGen-X employs transformer-based networks to align and translate image features into the genomic feature space, enhancing weaker imaging signals with stronger genomic signals. Unlike other methods, PathoGen-X translates and aligns features without projecting them to a shared latent space and requires fewer paired samples. Evaluated on TCGA-BRCA, TCGA-LUAD, and TCGA-GBM datasets, PathoGen-X demonstrates strong survival prediction performance, emphasizing the potential of enriched imaging models for accessible cancer prognosis.