theodpzz/ct-agrg

[ISBI 2025] CT-AGRG: Automated Abnormality-Guided Report Generation for CT Scans 👨🏻‍⚕️📝

✅ PyTorch pretrained model weights of "CT-AGRG: Automated Abnormality-Guided Report Generation for CT Scans".

📄 Accepted at ISBI 2025: arXiv preprint.

🔥 PyTorch implementation available at https://github.com/theodpzz/ct-agrg.

🚀 Available resources

./model_state_dict.pt: Model weights for CT-AGRG trained on the CT-RATE training set.

./thresholds.json: Per-abnormality classification thresholds optimized on our internal CT-RATE validation set. The official CT-RATE test set was not used during threshold optimization to preserve unbiased evaluation.

🤝🏻 Acknowledgment

We thank contributors from the CT-RATE dataset available at https://huggingface.co/datasets/ibrahimhamamci/CT-RATE.

📎Citation

If you use this repository in your work, we would appreciate the following citation:

@InProceedings{dipiazza_2025_ctagrg,
        title = {CT-AGRG: Automated Abnormality-Guided Report Generation for CT Scans},
          author = {Di Piazza, Theo and Lazarus, Carole and Nempont, Olivier and Boussel, Loic},
          booktitle = {2025 {IEEE} 22nd {International} {Symposium} on {Biomedical} {Imaging} ({ISBI})},
          year = {2025},
}