Merge branch 'main' of github.com:bowang-lab/MedRAX
Browse files
README.md
CHANGED
|
@@ -1,8 +1,14 @@
|
|
| 1 |
<h1 align="center">
|
| 2 |
🤖 MedRAX: Medical Reasoning Agent for Chest X-ray
|
| 3 |
</h1>
|
|
|
|
|
|
|
| 4 |
<br>
|
| 5 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
## Abstract
|
| 7 |
Chest X-rays (CXRs) play an integral role in driving critical decisions in disease management and patient care. While recent innovations have led to specialized models for various CXR interpretation tasks, these solutions often operate in isolation, limiting their practical utility in clinical practice. We present MedRAX, the first versatile AI agent that seamlessly integrates state-of-the-art CXR analysis tools and multimodal large language models into a unified framework. MedRAX dynamically leverages these models to address complex medical queries without requiring additional training. To rigorously evaluate its capabilities, we introduce ChestAgentBench, a comprehensive benchmark containing 2,500 complex medical queries across 7 diverse categories. Our experiments demonstrate that MedRAX achieves state-of-the-art performance compared to both open-source and proprietary models, representing a significant step toward the practical deployment of automated CXR interpretation systems.
|
| 8 |
<br><br>
|
|
@@ -25,6 +31,7 @@ MedRAX is built on a robust technical foundation:
|
|
| 25 |
- **X-ray Generation**: Utilizes RoentGen for synthetic CXR generation
|
| 26 |
- **Utilities**: Includes DICOM processing, visualization tools, and custom plotting capabilities
|
| 27 |
|
|
|
|
| 28 |
<br>
|
| 29 |
|
| 30 |
## ChestAgentBench
|
|
@@ -62,7 +69,12 @@ pip install -e .
|
|
| 62 |
# Start the Gradio interface
|
| 63 |
python main.py
|
| 64 |
```
|
| 65 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
Make sure to setup your OpenAI API key in `.env` file!
|
| 67 |
<br><br>
|
| 68 |
|
|
|
|
| 1 |
<h1 align="center">
|
| 2 |
🤖 MedRAX: Medical Reasoning Agent for Chest X-ray
|
| 3 |
</h1>
|
| 4 |
+
<p align="center"> <a href="https://arxiv.org/abs/2502.02673" target="_blank"><img src="https://img.shields.io/badge/arXiv-Paper-FF6B6B?style=for-the-badge&logo=arxiv&logoColor=white" alt="arXiv"></a> <a href="https://github.com/bowang-lab/MedRAX"><img src="https://img.shields.io/badge/GitHub-Code-4A90E2?style=for-the-badge&logo=github&logoColor=white" alt="GitHub"></a> <a href="https://huggingface.co/datasets/wanglab/chest-agent-bench"><img src="https://img.shields.io/badge/HuggingFace-Dataset-FFBF00?style=for-the-badge&logo=huggingface&logoColor=white" alt="HuggingFace Dataset"></a> </p>
|
| 5 |
+
|
| 6 |
<br>
|
| 7 |
|
| 8 |
+
[](https://github.com/bowang-lab/MedRAX/raw/main/assets/demo_fast.mp4)
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
## Abstract
|
| 13 |
Chest X-rays (CXRs) play an integral role in driving critical decisions in disease management and patient care. While recent innovations have led to specialized models for various CXR interpretation tasks, these solutions often operate in isolation, limiting their practical utility in clinical practice. We present MedRAX, the first versatile AI agent that seamlessly integrates state-of-the-art CXR analysis tools and multimodal large language models into a unified framework. MedRAX dynamically leverages these models to address complex medical queries without requiring additional training. To rigorously evaluate its capabilities, we introduce ChestAgentBench, a comprehensive benchmark containing 2,500 complex medical queries across 7 diverse categories. Our experiments demonstrate that MedRAX achieves state-of-the-art performance compared to both open-source and proprietary models, representing a significant step toward the practical deployment of automated CXR interpretation systems.
|
| 14 |
<br><br>
|
|
|
|
| 31 |
- **X-ray Generation**: Utilizes RoentGen for synthetic CXR generation
|
| 32 |
- **Utilities**: Includes DICOM processing, visualization tools, and custom plotting capabilities
|
| 33 |
|
| 34 |
+
Note the current version of MedRAX is experimentally released and does not support vision for GPT-4o and MedSAM. We will be integrating these shortly.
|
| 35 |
<br>
|
| 36 |
|
| 37 |
## ChestAgentBench
|
|
|
|
| 69 |
# Start the Gradio interface
|
| 70 |
python main.py
|
| 71 |
```
|
| 72 |
+
or if you run into permission issues
|
| 73 |
+
```bash
|
| 74 |
+
sudo -E env "PATH=$PATH" python main.py
|
| 75 |
+
```
|
| 76 |
+
You need to setup the `model_dir` to directory where you want to download or already have the weights of above tools from Hugging Face.
|
| 77 |
+
Comment out the tools that you do not have access to.
|
| 78 |
Make sure to setup your OpenAI API key in `.env` file!
|
| 79 |
<br><br>
|
| 80 |
|