A Multimodal Dataset for Survival Prediction in Resected Pancreatic Ductal Adenocarcinoma

2026-09-24

AI Summary

This study addresses the scarcity of multimodal data for survival prediction in pancreatic ductal adenocarcinoma by constructing the first pancreas-specific multimodal dataset comprising 302 patients, integrating whole-slide pathological images, clinical records, and genomic information to bridge this gap. Methodologically, the work employs Ridge Cox regression and attention-based models, combined with Monte Carlo cross-validation and multimodal fusion techniques, to conduct a systematic evaluation. The research establishes an initial benchmark for this task, demonstrating that the multimodal fusion model achieves optimal performance with a concordance index of 0.619. These findings provide a critical baseline and foundational data support for subsequent precision prognostic studies in pancreatic cancer.

Abstract

Survival research in pancreatic ductal adenocarcinoma (PDAC) is limited by the scarcity of datasets linking whole-slide histology with clinical, molecular, and long-term outcome data. We present a retrospective single-centre cohort of 302 patients who underwent PDAC resection at University Medical Center Gottingen. The dataset comprises 446 H&E whole-slide images, clinicopathological variables, targeted sequencing data for 154 patients, and overall-survival outcomes. During follow-up, 253 patients died, and the median follow-up was 76 months. To establish initial reference values, we evaluated fourteen survival-prediction configurations using identical five-repetition Monte Carlo cross-validation partitions. Ridge Cox regression using numeric clinicopathological variables achieved a mean concordance of $0.649 \pm 0.042$ and $0.652 \pm 0.046$ after adding KRAS and TP53 mutation status. The image-only attention model achieved $0.603 \pm 0.030$, while multimodal fusion achieved $0.619 \pm 0.025$, the highest concordance among the neural models. These results establish promising initial benchmarks for future research using this pancreas-specific multimodal dataset, paving the way for external validation.

Problem

• Pancreatic Ductal Adenocarcinoma
• Survival Prediction
• Multimodal Dataset
• Whole-slide Histology

Innovation

• Multimodal Fusion
• Survival Prediction
• Whole-Slide Images
• Pancreatic Ductal Adenocarcinoma
• Attention Model