Fiche publication
Date publication
septembre 2025
Journal
International journal of computer assisted radiology and surgery
Auteurs
Membres identifiés du Cancéropôle Est :
Pr MUTTER Didier
Tous les auteurs :
Meyer A, Murali A, Zarin F, Mutter D, Padoy N
Lien Pubmed
Résumé
Automated ultrasound (US) image analysis remains a longstanding challenge due to anatomical complexity and the scarcity of annotated data. Although large-scale pretraining has improved data efficiency in many visual domains, its impact in US is limited by a pronounced domain shift from other imaging modalities and high variability across clinical applications, such as chest, ovarian, and endoscopic imaging. To address this, we propose UltraSam, a SAM-style model trained on a heterogeneous collection of publicly available segmentation datasets, originally developed in isolation. UltraSam is trained under the prompt-conditioned segmentation paradigm, which eliminates the need for unified labels and enables generalization to a broad range of downstream tasks.
Mots clés
Foundation models, Large-scale dataset, SAM, Ultrasound
Référence
Int J Comput Assist Radiol Surg. 2025 09 11;:
