Deep learning for automatic detection of hepatocellular carcinoma in dynamic contrast-enhanced MRI
Both patient-level and lesion-level achieved 80% HCC detection sensitivity by using a deep learning segmentation neural network pre-trained from large open datasets. This performance highlights the translational potential of such tools in the clinical workup of patients at risk of HCC.
Authors
- Mario Jreige (ORCID: https://orcid.org/0000-0003-3918-150X)
- Naïk Vietti Violi (ORCID: https://orcid.org/0000-0002-1412-857X)
- Raphaël Girardet (ORCID: https://orcid.org/0000-0002-6843-4169)
- Jonas Richiardi (ORCID: https://orcid.org/0000-0002-6975-5634)
- Clarisse Dromain (ORCID: https://orcid.org/0000-0002-2999-1958)
- Montserrat Fraga Christinet
- Marianna Gulizia (ORCID: https://orcid.org/0000-0001-5494-2691)
- Killian Monnin
- Patrick Jeltsch
- Lucia Fernandes-Mendes
- Vasco Cazzagon
Institutions
- Centre Hospitalier Universitaire Vaudois (CH)
- North Metropolitan Health Service (AU)
- South Metropolitan Health Service (AU)
- University of Lausanne (CH)
Publication Details
- Journal
- Abdominal Radiology
- Published
- 2025-11-11
- DOI
- https://doi.org/10.1007/s00261-025-05249-4
- Primary Topic
- Hepatocellular Carcinoma Treatment and Prognosis
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Science Foundation
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung