Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Akhila Krishna, Nikhil Cherian Kurian, Abhijeet Patil, Amruta Parulekar, Amit Sethi

TL;DR

PathoGen-X is a deep learning framework that leverages both genomic and imaging data during training, relying solely on imaging data at testing, and demonstrates strong survival prediction performance on TCGA-BRCA, TCGA-LUAD, and TCGA-GBM datasets.

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.

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 leverages both genomic and imaging data during training, relying solely on imaging data at testing, and demonstrates strong survival prediction performance on TCGA-BRCA, TCGA-LUAD, and TCGA-GBM datasets.

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.

Paper Structure

This paper contains 14 sections, 6 equations, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Cross-Modality Translator: Pathology to Genomics
  5. Genomic Feature Projection Network ($G_E$)
  6. Survival prediction network
  7. Cross Modal Alignment and Translation
  8. Experiment and Results
  9. Dataset
  10. Implementation details
  11. Results
  12. Discussion and Conclusion
  13. Compliance with Ethical Standards
  14. Acknowledgments

Figures (3)

  • Figure 1: The cross-modal genomic feature trans-align network (PathoGen-X) features four main components: a pathology encoder, a genomic decoder, a genomic projection matrix (PM) and a survival prediction module.
  • Figure 2: The Kaplan-Meier curves of our model on the three datasets. We used median risk to stratify patients into low and high risk groups.
  • Figure 3: Visualization of the substantial improvement in correlation between the image features with genomic features after feature translation for GBM dataset samples.