HealthGPT
Unified visual medical model — 7 medical understanding + 5 generation tasks
A unified visual medical model from Zhejiang University and collaborators: 7 medical understanding and 5 medical generation tasks.
AI for biology and medicine — research tools, not medical advice.
Key features
- Medical MLLM family: HealthGPT-Pro for understanding, HealthGPT for generation
- HealthGPT-Pro built on Qwen3-VL; 14 medical modalities
- Trained on 3M alignment plus 10M SFT samples
- Covers medical text, 2D images, and 3D volumes
Good for
- Medical image and volume understanding
- Medical VQA and analysis research
Stack & tags
medicalmultimodalvlmhealthcareopen-weightsmed-vqa3d-volumes
Similar open-source projects
scientific-agent-skills
★ 49,303Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
MedGemma
★ 1,616Google's medical Gemma — incl. SignGemma sign language and DolphinGemma