Open access
Jul 2025
An open vision-language model for diverse medical applications
The results show that fine-tuning MedGemma can be more effective than fine-tuning the base Gemma 3 model for medical tasks, particularly in the setting of limited training data.
Andrew B. Sellergren, S. Kazemzadeh, Fereshteh Mahvar et al.
· Nature Medicine · 530 citations
· ⚡83