Diff-RRG: Longitudinal Disease-wise Patch Difference as Guidance for LLM-based Radiology Report Generation (MICCAI25')

Getting Started

Installation

1. Prepare the code and the environment

1. Git clone our repository and creat a new conda environment.

cd Diff-RRG
conda create -n diffrrg python=3.9 -y
conda activate diffrrg

2. Install the requirements.

pip install -r requirements.txt

2. Prepare the training dataset

Longitudinal-MIMIC: you can download this dataset from Here and download the images from Official website

We prvoide the annotation file for disease progression of Longitudinal-MIMIC dataset. You can download the dataset from Here.

After downloading the data and the annotation, place them in the ./data folder.

Training

bash scripts/1-1.mimic_train.sh

Testing

You can download our pretrained Delta checkpoints for Here

bash scripts/1-2.mimic_test.sh

Acknowledgement

• R2GenGPT
• BiomedCLIP
• BioMistral

License

This repository is under BSD 3-Clause License.