End-to-end prognostication in pancreatic cancer by multimodal deep learning: a retrospective, multicenter study
Question Prognostic tools for pancreatic ductal adenocarcinoma (PDAC) remain limited, with TNM staging offering suboptimal accuracy in predicting patient survival outcomes. Findings The multimodal AI model demonstrated improved prognostic performance over TNM and unimodal models for predicting short- and long-term survival in PDAC patients. Clinical relevance Multimodal AI provides enhanced prognostic accuracy compared to current staging systems, potentially improving clinical decision-making and personalized management strategies for PDAC patients.
Authors
- John J. Hermans (ORCID: https://orcid.org/0000-0001-9207-0548)
- Sergio Sabroso‐Lasa (ORCID: https://orcid.org/0000-0001-7002-556X)
- Anindo Saha (ORCID: https://orcid.org/0000-0002-5091-9862)
- Pierpaolo Vendittelli (ORCID: https://orcid.org/0000-0001-6712-3708)
- Núria Malats (ORCID: https://orcid.org/0000-0003-2538-3784)
- Megan Schuurmans (ORCID: https://orcid.org/0000-0002-4939-6187)
- HenkJan J. Huisman (ORCID: https://orcid.org/0000-0001-6753-3221)
- Geert Litjens (ORCID: https://orcid.org/0000-0003-1554-1291)
- Derya Yakar (ORCID: https://orcid.org/0000-0002-4920-9441)
- Natália Alves (ORCID: https://orcid.org/0000-0002-7034-0137)
- Nannan Xue
Institutions
- University Medical Center Groningen (NL)
- Radboud University Nijmegen (NL)
- Radboud University Medical Center (NL)
- Spanish National Cancer Research Centre (ES)
- Radboud Institute for Molecular Life Sciences (NL)
- Centro de Investigación del Cáncer (ES)
Publication Details
- Journal
- European Radiology
- Published
- 2025-05-23
- DOI
- https://doi.org/10.1007/s00330-025-11694-y
- Citations
- 5
- Primary Topic
- Pancreatic and Hepatic Oncology Research
- Type
- article
- Field-Weighted Citation Impact
- 5.23
Funders
- Horizon 2020