Skip to content
Open access

An open vision-language model for diverse medical applications

Jul 2025 · Nature Medicine · Vol 32, pp. 3695 - 3704 · 529 citations · ⚡ 84 influential · 72 references
Computer Science Medicine

TL;DR

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.

Abstract

Artificial intelligence has high potential for impact in healthcare applications, but its training and deployment are challenging due to diverse data, a complex spectrum of possible tasks and important privacy needs. High-performing foundation models that enable data-efficient fine-tuning for diverse downstream tasks can meaningfully accelerate development in this domain. We introduce MedGemma, a collection of medical vision-language foundation models based on Gemma 3. MedGemma demonstrates advanced medical understanding and reasoning across images and text and multiple medical imaging domains, exceeding the performance of similarly sized generative models while maintaining the general capabilities of the Gemma base models. For out-of-distribution tasks, MedGemma achieves improvements of 2.6–10% in medical image question answering, 15.5–18.1% in chest X-ray finding classification and 10.8% in agentic evaluations compared with the base models. Our 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. We additionally introduce MedSigLIP, a medically tuned vision encoder derived from SigLIP. MedSigLIP powers the visual understanding capabilities of MedGemma and, as an encoder, achieves performance comparable to or better than that of many specialized medical image encoders. Taken together, the MedGemma collection provides a strong foundation of medical image and text capabilities, with the potential to accelerate medical research and the development of downstream applications. MedGemma, a collection of medical vision-language foundation models based on Gemma 3, demonstrates advanced medical understanding and reasoning across images and text and multiple medical imaging domains, exceeding the performance of similarly sized generative models while maintaining the general capabilities of the Gemma base models.

Read PDF

Similar papers

Sep 2026

MedCure: Medical Data Curation for Efficient Vision–Language Pretraining

Medical foundation models (FMs) typically rely on contrastive vision-language pretraining over large-scale datasets, yet such datasets often exhibit substantial heterogeneity in data quality and demand extensive computational resources. Recent studies suggest that data quality matters more than data quantity, but how t...

Chong Wang, Feng-Bei Liu, Yu-Yuan Liu et al. · 0 citations
Review Open access Oct 2024

Large Language Model Benchmarks in Medical Tasks

A comprehensive survey of various benchmark datasets used in medical LLM tasks, focusing on various aspects of medical knowledge such as electronic health records, doctor–patient dialogues, medical question answering, and medical image captioning, is presented.

L. K. Yan, Qian Niu, Ming Li et al. · 34 citations · ⚡1
#federated learning Review Open access Oct 2026

Foundation Models and Vision-Language Models in Medical Imaging: A Review

Foundation models (FMs) and vision-language models (VLMs) have emerged as a transformative paradigm in artificial intelligence, reshaping the landscape of medical image analysis and clinical decision support. Building upon large-scale pretraining on heterogeneous datasets, these models exhibit unprecedented generalizat...

Saeed Mohsen, Leena Mahmoud Lulu, Mohamed Eassa et al. · 0 citations
Review Oct 2026

Medical Vision Foundation Models: A comprehensive review from technical evolution to clinical translation.

This review provides a structured reference to guide MVFMs from technical validation to clinically effective, reliable, and ethically sound deployment and introduces the Data-Technology-Translation Triad as a unifying conceptual framework to structure the progress, key factors, and challenges of MVFMs.

Neng-Jian Lin, Yi Ding, Zhen Qin et al. · 0 citations

How Medical VLMs Underutilize Their Vision Encoders: A Dermatology Perspective

A mechanistic analysis of the VLM model's internal attention patterns shows that a simple describe-then-decide prompting strategy increases vision attention by 30-40% during generation, and task-specific fine-tuning improves dermatology classification but reduces cross-domain medical question-answering performance in t...

Janet Wang, Yun-Bei Zhang, Xiao Wang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.