This is the implementation of Token Imbalance Adaptation for Radiology Report Generation at CHIL-2023.

If you use or extend our work, please cite our paper at CHIL-2023.

@misc{wu2023token,
      title={Token Imbalance Adaptation for Radiology Report Generation}, 
      author={Yuexin Wu and I-Chan Huang and Xiaolei Huang},
      year={2023},
      eprint={2304.09185},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

• torch==1.7.1
• torchvision==0.8.2
• opencv-python==4.4.0.42

You can download the models we trained for each dataset from here.

We use two datasets (IU X-Ray and MIMIC-CXR) in our paper.

For IU X-Ray, you can download the dataset from here and then put the files in data/iu_xray.

For MIMIC-CXR, you can download the dataset from here and then put the files in data/mimic_cxr.

NOTE: The IU X-Ray dataset is of small size, and thus the variance of the results is large. There have been some works using MIMIC-CXR only and treating the whole IU X-Ray dataset as an extra test set.

Run bash train_iu_xray.sh to train a model on the IU X-Ray data.

Run bash train_mimic_cxr.sh to train a model on the MIMIC-CXR data.

Run bash test_iu_xray.sh to test a model on the IU X-Ray data.

Run bash test_mimic_cxr.sh to test a model on the MIMIC-CXR data.

Because the experimental datasets are too large to share all of them. Please send any requests or questions to my email: [email protected].