CheXagent-8b Open-source AI Model - Free to Assist in Professional Interpretation of Chest X-ray Images in the Medical Field

Chexagent 8b

Developed by StanfordAIMI

CheXagent is a foundational model for chest X-ray interpretation, which can assist the medical field in professionally interpreting chest X-ray images.

Image-to-Text

Transformers

#Chest X-ray interpretation #Medical image analysis #Multimodal generation

Downloads 1,020

Release Time : 12/15/2023

Model Overview

CheXagent is a foundational model specifically designed for chest X-ray image analysis. Professional interpretation and description generation of images can be achieved through code calls.

Model Features

Professional medical image interpretation

Specifically designed for chest X-ray images, it can generate professional medical interpretations and descriptions.

Multimodal processing ability

Combining visual and language processing capabilities, it can understand images and generate text descriptions.

Optimized for the medical field

Optimized for the specific needs of the medical field, it can handle professional medical terms and concepts.

Model Capabilities

Chest X-ray image analysis

Medical image description generation

Specific anatomical structure recognition

Medical abnormality detection

Use Cases

Medical diagnosis assistance

Pleural effusion detection

Analyze chest X-ray images to identify and describe abnormal conditions such as pleural effusion.

It can accurately identify and describe the pleural effusion in the example images.

Airway analysis

Analyze and describe the airway structure in the images.

Professional airway descriptions can be generated according to the prompts.

Medical education

Image teaching assistance

Provide professional interpretations and explanations of X-ray images for medical students.

🚀 CheXagent

CheXagent is a model for chest X - ray interpretation. It provides an effective solution for analyzing chest X - ray images through advanced techniques.

🚀 Quick Start

✨ Features

Model Release: The model was released on Hugging Face on 12/15/2023.
Multiple Resources: It has associated resources including a paper on arXiv, a Hugging Face repository, a GitHub project, and a project website.

📦 Installation

No specific installation steps are provided in the original README.

💻 Usage Examples

Basic Usage

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: <s>{prompt} ASSISTANT: <s>", 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)

📚 Documentation

Latest News:
- [12/15/2023]: Model released in Hugging Face.

📄 License

No license information is provided in the original README.

📚 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}
}

🌟 Paper • 💾 Hugging Face • 💻 Github • 🌐 Project

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご