Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
|
@@ -8,4 +8,81 @@ pinned: false
|
|
| 8 |
license: apache-2.0
|
| 9 |
---
|
| 10 |
|
| 11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
license: apache-2.0
|
| 9 |
---
|
| 10 |
|
| 11 |
+
<div align="center">
|
| 12 |
+
<img src="https://cdn-avatars.huggingface.co/v1/production/uploads/64c0aaa4a8a2dcaa167ab5b3/tdo-7xOrIHU6DE4kCgu2N.png" width="150" alt="GMAI Logo">
|
| 13 |
+
<h1>General Medical AI (GMAI)</h1>
|
| 14 |
+
<h3>Universal AI for Healthcare Research | Shanghai AI Lab</h3>
|
| 15 |
+
|
| 16 |
+
<a href="https://github.com/uni-medical">
|
| 17 |
+
<img src="https://img.shields.io/badge/GitHub-uni--medical-181717?style=flat&logo=github" alt="GitHub">
|
| 18 |
+
</a>
|
| 19 |
+
<a href="https://www.zhihu.com/people/gmai-38/">
|
| 20 |
+
<img src="https://img.shields.io/badge/Zhihu-GMAI%20Team-0084FF?style=flat&logo=zhihu&logoColor=white" alt="Zhihu">
|
| 21 |
+
</a>
|
| 22 |
+
<a href="mailto:hejunjun@pjlab.org.cn">
|
| 23 |
+
<img src="https://img.shields.io/badge/Email-Contact%20Us-D14836?style=flat&logo=gmail&logoColor=white" alt="Email">
|
| 24 |
+
</a>
|
| 25 |
+
</div>
|
| 26 |
+
|
| 27 |
+
<br>
|
| 28 |
+
|
| 29 |
+
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.
|
| 30 |
+
|
| 31 |
+
Our research spans a wide spectrum of medical AI:
|
| 32 |
+
* General medical image segmentation
|
| 33 |
+
* General-purpose multimodal large models for medicine
|
| 34 |
+
* 2D/3D medical image generation
|
| 35 |
+
* Medical foundation models
|
| 36 |
+
* Surgical video foundation & multimodal models
|
| 37 |
+
* Surgical video generation
|
| 38 |
+
|
| 39 |
+
---
|
| 40 |
+
|
| 41 |
+
## 📊 Large-Scale Medical Data
|
| 42 |
+
We have curated massive-scale medical data resources to fuel the vision of General Medical AI.
|
| 43 |
+
|
| 44 |
+
* **Project Imaging-X**: A survey and collection of **1,000+** open-source medical imaging datasets.
|
| 45 |
+
* [](https://github.com/uni-medical/Project-Imaging-X)
|
| 46 |
+
|
| 47 |
+
**Key Statistics:**
|
| 48 |
+
* **100M+** Medical images
|
| 49 |
+
* **Hundreds of millions** of segmentation masks
|
| 50 |
+
* **20M+** Medical text dialogue records
|
| 51 |
+
* **10M+** Large-scale medical image–text pairs
|
| 52 |
+
* **20M+** Multimodal Q&A entries
|
| 53 |
+
|
| 54 |
+
---
|
| 55 |
+
|
| 56 |
+
## 🚀 Selected Achievements
|
| 57 |
+
|
| 58 |
+
### Multimodal Large Models (LVLMs)
|
| 59 |
+
* **SlideChat**: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding.
|
| 60 |
+
* [](https://github.com/uni-medical/SlideChat)
|
| 61 |
+
* **UniMedVL**: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysis.
|
| 62 |
+
* [](https://github.com/uni-medical/UniMedVL)
|
| 63 |
+
* **GMAI-VL**: A Large Vision-Language Model and Comprehensive Multimodal Dataset Towards General Medical AI.
|
| 64 |
+
* [](https://github.com/uni-medical/GMAI-VL)
|
| 65 |
+
* **OmniMedVQA**: A Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM.
|
| 66 |
+
* [](https://github.com/OpenGVLab/Multi-Modality-Arena/tree/main/MedicalEval)
|
| 67 |
+
* **GMAI-MMBench**: A Comprehensive Multimodal Benchmark for General Medical AI.
|
| 68 |
+
* [](https://github.com/uni-medical/GMAI-MMBench)
|
| 69 |
+
|
| 70 |
+
### Foundation Models & Segmentation
|
| 71 |
+
* **SAM-Med3D**: A Vision Foundation Model for General-Purpose Segmentation on Volumetric Medical Images.
|
| 72 |
+
* [](https://github.com/uni-medical/SAM-Med3D)
|
| 73 |
+
* **SAM-Med2D**: Comprehensive Segment Anything Model for 2D Medical Imaging.
|
| 74 |
+
* [](https://github.com/OpenGVLab/SAM-Med2D)
|
| 75 |
+
* **STU-Net**: Scalable and Transferable Medical Image Segmentation (1.4B parameters).
|
| 76 |
+
* [](https://github.com/uni-medical/STU-Net)
|
| 77 |
+
* **IMIS-Bench**: Interactive Medical Image Segmentation Benchmark and Baseline.
|
| 78 |
+
* [](https://github.com/uni-medical/IMIS-Bench)
|
| 79 |
+
|
| 80 |
+
---
|
| 81 |
+
|
| 82 |
+
## 🔗 Connect with Us
|
| 83 |
+
|
| 84 |
+
We welcome collaboration across academia, healthcare, and industry.
|
| 85 |
+
|
| 86 |
+
* **GitHub Organization**: [github.com/uni-medical](https://github.com/uni-medical)
|
| 87 |
+
* **Zhihu Blog**: [GMAI Team](https://www.zhihu.com/people/gmai-38/)
|
| 88 |
+
* **Contact**: [hejunjun@pjlab.org.cn](mailto:hejunjun@pjlab.org.cn)
|