https://github.com/Stanford-AIMI/CheXagent

[Arxiv-2024] CheXagent: Towards a Foundation Model for Chest X-Ray Interpretation
https://github.com/Stanford-AIMI/CheXagent

Last synced: about 2 months ago
JSON representation

[Arxiv-2024] CheXagent: Towards a Foundation Model for Chest X-Ray Interpretation

• Host: GitHub
• URL: https://github.com/Stanford-AIMI/CheXagent
• Owner: Stanford-AIMI
• Created: 2023-12-14T17:44:21.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-02-07T01:01:40.000Z (11 months ago)
• Last Synced: 2024-08-01T02:26:43.057Z (5 months ago)
• Language: Python
• Homepage: https://stanford-aimi.github.io/chexagent.html
• Size: 4.88 KB
• Stars: 104
• Watchers: 6
• Forks: 7
• Open Issues: 6
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• Awesome-Reasoning-Foundation-Models - [code

README

        






  CheXagent







📝 Paper • 🤗 Hugging Face • 🧩 Github • 🪄 Project







## ✨ Latest News

- [12/15/2023]: Model released in [Hugging Face](https://huggingface.co/StanfordAIMI/CheXagent-8b/).

## 🎬 Get Started

```python

import io

import requests

import torch

from PIL import Image

from transformers import AutoModelForCausalLM, AutoProcessor, GenerationConfig

# step 1: Setup constant

device = "cuda"

dtype = torch.float16

# step 2: Load Processor and Model

processor = AutoProcessor.from_pretrained("StanfordAIMI/CheXagent-8b", trust_remote_code=True)

generation_config = GenerationConfig.from_pretrained("StanfordAIMI/CheXagent-8b")

model = AutoModelForCausalLM.from_pretrained("StanfordAIMI/CheXagent-8b", torch_dtype=dtype, trust_remote_code=True)

# step 3: Fetch the images

image_path = "https://upload.wikimedia.org/wikipedia/commons/3/3b/Pleural_effusion-Metastatic_breast_carcinoma_Case_166_%285477628658%29.jpg"

images = [Image.open(io.BytesIO(requests.get(image_path).content)).convert("RGB")]

# step 4: Generate the Findings section

prompt = f'Describe "Airway"'

inputs = processor(images=images, text=f" USER: {prompt} ASSISTANT: ", return_tensors="pt").to(device=device, dtype=dtype)

output = model.generate(**inputs, generation_config=generation_config)[0]

response = processor.tokenizer.decode(output, skip_special_tokens=True)

```

## ✏️ Citation

```

@article{chexagent-2024,

  title={CheXagent: Towards a Foundation Model for Chest X-Ray Interpretation},

  author={Chen, Zhihong and Varma, Maya and Delbrouck, Jean-Benoit and Paschali, Magdalini and Blankemeier, Louis and Veen, Dave Van and Valanarasu, Jeya Maria Jose and Youssef, Alaa and Cohen, Joseph Paul and Reis, Eduardo Pontes and Tsai, Emily B. and Johnston, Andrew and Olsen, Cameron and Abraham, Tanishq Mathew and Gatidis, Sergios and Chaudhari, Akshay S and Langlotz, Curtis},

  journal={arXiv preprint arXiv:2401.12208},

  url={https://arxiv.org/abs/2401.12208},

  year={2024}

}

```