---
license: apache-2.0
pipeline_tag: image-to-text
---
# Model Card for Model ID

Trained on the MIMIC-CXR chest x-rays.



# Model Details

## Model Description

This model generates realistic radiology reports given an chest X-ray and a clinical indication (e.g. 'RLL crackles, eval for pneumonia').

- **Developed by:** Nathan Sutton
- **Model type:** BLIP
- **Language(s) (NLP):** English
- **License:** Apache 2.0
- **Finetuned from model [optional]:** Salesforce/blip-image-captioning-large

## Model Sources [optional]

- **Repository:** https://github.com/nathansutton/prerad
- **Paper [optional]:** https://medium.com/me/stats/post/b687a993cbb
- **Demo [optional]:** https://medium.com/me/stats/post/b687a993cbb


## Direct Use

Upload a chest x-ray in a JPG format along with a clinical indication (e.g. 'RLL crackles, eval for pneumonia').  It will generate a realistic looking radiology report.

## Out-of-Scope Use

Any medical application.

## How to Get Started with the Model

```
from PIL import Image
from transformers import BlipForConditionalGeneration, BlipProcessor

# read in the model
processor = BlipProcessor.from_pretrained("nathansutton/generate-cxr")
model = BlipForConditionalGeneration.from_pretrained("nathansutton/generate-cxr")

# your data
my_image = 'my-chest-x-ray.jpg'
my_indication = 'RLL crackles, eval for pneumonia'

# process the inputs
inputs = processor(
    images=Image.open(my_image), 
    text='indication:' + my_indication,
    return_tensors="pt"
)

# generate an entire radiology report
output = model.generate(**inputs,max_length=512)
report = processor.decode(output[0], skip_special_tokens=True)

```

# Training Details

## Training Data

This model was trained by cross-referencing the radiology reports in MIMIC-CXR with the images in the MIMIC-CXR-JPG.  None are available here and require a data usage agreement with physionet.