PathoGen-X: A Cross-Modal Genomic Feature Trans-Align Network for Enhanced Survival Prediction from Histopathology Images
This work addresses the problem of costly genomic data access for cancer prognosis by enhancing imaging-based models, though it is incremental as it builds on existing cross-modal translation methods.
The paper tackled survival prediction in cancer by developing a deep learning framework that uses genomic and imaging data during training but only imaging data at testing, achieving strong performance on TCGA datasets.
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.