---
title: README
emoji: ๐
colorFrom: green
colorTo: indigo
sdk: static
pinned: false
license: apache-2.0
---
General Medical AI (GMAI)
Universal AI for Healthcare Research | Shanghai AI Lab
The **General Medical AI (GMAI)** team at **Shanghai AI Lab** is dedicated to building general-purpose AI for healthcare. We aim to make healthcare AI more efficient and accessible through cutting-edge research and open-source contributions.
Our research spans a wide spectrum of medical AI:
* General medical image segmentation
* General-purpose multimodal large models for medicine
* 2D/3D medical image generation
* Medical foundation models
* Surgical video foundation & multimodal models
* Surgical video generation
---
## ๐ Large-Scale Medical Data
We have curated massive-scale medical data resources to fuel the vision of General Medical AI.
* **Project Imaging-X**: A survey and collection of **1,000+** open-source medical imaging datasets.
* [](https://github.com/uni-medical/Project-Imaging-X)
**Key Statistics:**
* **100M+** Medical images
* **Hundreds of millions** of segmentation masks
* **20M+** Medical text dialogue records
* **10M+** Large-scale medical imageโtext pairs
* **20M+** Multimodal Q&A entries
---
## ๐ Selected Achievements
### Multimodal Large Models (LVLMs)
* **SlideChat**: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding.
* [](https://github.com/uni-medical/SlideChat)
* **UniMedVL**: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysis.
* [](https://github.com/uni-medical/UniMedVL)
* **GMAI-VL**: A Large Vision-Language Model and Comprehensive Multimodal Dataset Towards General Medical AI.
* [](https://github.com/uni-medical/GMAI-VL)
* **OmniMedVQA**: A Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM.
* [](https://github.com/OpenGVLab/Multi-Modality-Arena/tree/main/MedicalEval)
* **GMAI-MMBench**: A Comprehensive Multimodal Benchmark for General Medical AI.
* [](https://github.com/uni-medical/GMAI-MMBench)
### Foundation Models & Segmentation
* **SAM-Med3D**: A Vision Foundation Model for General-Purpose Segmentation on Volumetric Medical Images.
* [](https://github.com/uni-medical/SAM-Med3D)
* **SAM-Med2D**: Comprehensive Segment Anything Model for 2D Medical Imaging.
* [](https://github.com/OpenGVLab/SAM-Med2D)
* **STU-Net**: Scalable and Transferable Medical Image Segmentation (1.4B parameters).
* [](https://github.com/uni-medical/STU-Net)
* **IMIS-Bench**: Interactive Medical Image Segmentation Benchmark and Baseline.
* [](https://github.com/uni-medical/IMIS-Bench)
---
## ๐ Connect with Us
We welcome collaboration across academia, healthcare, and industry.
* **GitHub Organization**: [github.com/uni-medical](https://github.com/uni-medical)
* **Zhihu Blog**: [GMAI Team](https://www.zhihu.com/people/gmai-38/)
* **Contact**: [hejunjun@pjlab.org.cn](mailto:hejunjun@pjlab.org.cn)