# Pathomics Signature for Prognosis and CA19‐9 Interception in Pancreatic Ductal Adenocarcinoma: A Real‐Life, Multi‐Center Study

## TL;DR

A deep learning model using H&E slides predicts pancreatic cancer prognosis and identifies patients who benefit from chemotherapy.

## Contribution

A novel pathomics model using CrossFormer architecture for PDAC prognosis and treatment guidance.

## Key findings

- The CrossFormer model outperformed other architectures in predicting survival outcomes.
- High-risk patients benefited from chemotherapy, while low-risk patients did not.
- CA19-9 was prognostic only in low-risk patients.

## Abstract

Histopathological hematoxylin and eosin (H&E) slides contain valuable prognostic information for pancreatic ductal adenocarcinoma (PDAC), yet systematic feature extraction remains challenging. This multi‐center study developed and validated an automated prognostic model using deep learning on digitized whole‐slide images from 873 PDAC patients with surgical resection across three academic centers. The CrossFormer architecture achieved superior performance in external validation (area under the curve [AUC] = 0.774), significantly outperforming ResNet‐18 (AUC = 0.716), ResNet‐50 (AUC = 0.737), and DenseNet‐121 (AUC = 0.729). Gradient‐weighted Class Activation Mapping identified key prognostic features including desmoplastic stroma, high nuclear‐to‐cytoplasmic ratio, tumor necrosis, and immune cell infiltration. The pathomics signature effectively stratified patients into low‐risk and high‐risk groups with significant survival differences (p < 0.001). Critically, carbohydrate antigen 19‐9 (CA19‐9) retained prognostic value only in low‐risk patients (hazard ratio [HR] = 2.70, p < 0.001) but not in high‐risk patients (HR = 0.998, p = 0.990). High‐risk patients derived substantial benefit from adjuvant chemotherapy (HR = 0.56, p = 0.038), whereas low‐risk patients showed no significant benefit (HR = 0.83, p = 0.562). These findings provide actionable clinical insights: treatment intensification for high‐risk patients and CA19‐9‐guided monitoring for low‐risk patients. This validated, interpretable model transforms routine H&E slides into quantitative prognostic tools, enabling personalized treatment strategies without additional testing costs.

This study develops a deep learning‐based pathomics model to predict survival outcomes in pancreatic cancer patients. The CrossFormer architecture analyzes routine H&E‐stained tissue slides, identifying key prognostic features including stromal patterns, cellular characteristics, and immune infiltration. The model successfully stratifies patients into high‐ and low‐risk groups, enabling personalized treatment decisions and demonstrating robust performance across multiple independent clinical cohorts.