Peer-Reviewed Publication
NPJ Precis Oncol2025;9(1):121.April 25, 2025Journal Article
A promptable CT foundation model for solid tumor evaluation.
Léo Machado1,2, Léo Alberge1, Hélène Philippe1,2,3, Elodie Ferreres1, Julien Khlaut1,4, Julie Dupuis1, Korentin Le Floch1,4, Denis Habip Gatenyo5, Pascal Roux6, Jules Grégory2,3, Maxime Ronot7,8, Corentin Dancette1, Tom Boeken4, Daniel Tordjman1, Pierre Manceron1, Paul Hérent1,6
1Raidium, Paris Biotech Santé, Paris, France.
2AP-HP. Nord, Department of Radiology, FHU MOSAIC, Beaujon Hospital, Clichy, France.
3Université Paris Cité, Paris, France.
4Department of Vascular and Oncological Interventional Radiology, Université Paris Cité, AP-HP, Hôpital Européen Georges Pompidou, HEKA INRIA, Paris, France.
5Department of Radiology, Hôpital Cochin, AP-HP, Paris, France.
6Centre d'Imagerie du Nord, Saint-Denis, France.
7AP-HP. Nord, Department of Radiology, FHU MOSAIC, Beaujon Hospital, Clichy, France. maxime.ronot@aphp.fr.
8Université Paris Cité, Paris, France. maxime.ronot@aphp.fr.
Abstract
Carcinogenesis is inherently complex, resulting in heterogeneous tumors with variable outcomes and frequent metastatic potential. Conventional longitudinal evaluation methods like RECIST 1.1 remain labor-intensive and prone to measurement errors, while existing AI solutions face critical limitations due to tumor heterogeneity, insufficient annotations, and lack of user interaction. We developed ON…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans