Validation of a Pretrained Artificial Intelligence Model for Pancreatic Cancer Detection on Diagnosis and Prediagnosis Computed Tomography Scans
PANCANAI showed high sensitivity for automatic PC detection on a large retrospective cohort of biopsy-confirmed patients. PC suspicion was detected in more than half of the CT scans that were acquired at least a year before histopathologic diagnosis.
Authors
- Rebeca Vétil
- Søren Brunak (ORCID: https://orcid.org/0000-0003-0316-5866)
- Liesbeth Degand (ORCID: https://orcid.org/0000-0003-1062-9243)
- Marc-Michel Rohé
- Alexandre Bône (ORCID: https://orcid.org/0000-0003-4442-3876)
- Piotr Jaroslaw Chmura (ORCID: https://orcid.org/0000-0002-9371-6918)
- Clément Abi Nader (ORCID: https://orcid.org/0000-0002-4542-9148)
- Federico De Masi
- Davide Placido (ORCID: https://orcid.org/0000-0002-8327-8838)
Institutions
- Novo Nordisk Foundation (DK)
- Faculty of 1000 (United States) (US)
- M4 Engineering (United States) (US)
Publication Details
- Journal
- Investigative Radiology
- Published
- 2025-06-24
- DOI
- https://doi.org/10.1097/rli.0000000000001209
- Citations
- 1
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 2.48
Funders
- Eli Lilly and Company
- European Commission
- Novo Nordisk
- Novo Nordisk Fonden
- H. Lundbeck A/S