---
license: cc-by-nc-4.0
datasets:
- ibrahimhamamci/CT-RATE
---

<p align="center">
  <h2 align="center">[MIDL 2025] Imitating Radiological Scrolling: A Global-Local Attention Model for 3D Chest CT Volumes Multi-Label Anomaly Classification 🩺👨🏻‍⚕️</h2>
</p>

✅ Official implementation of the paper "Imitating Radiological Scrolling: A Global-Local Attention Model for 3D Chest CT Volumes Multi-Label Anomaly Classification".

📄 Paper accepted for publication at MIDL 2025: [arXiv preprint](https://arxiv.org/abs/2503.20652).

⚡️ Source code available at [https://github.com/theodpzz/ct-scroll](https://github.com/theodpzz/ct-scroll).

## 🔥 Available resources

**ckpt/model_state_dict.pt**: Model trained on the CT-RATE **train** set.

**ckpt/classification_threshold.csv**: Classification thresholds optimized on our validation set, leaving the official CT-RATE test set untouched.

## 🤝🏻 Acknowledgment

We thank contributors from the CT-RATE dataset available at [https://huggingface.co/datasets/ibrahimhamamci/CT-RATE](https://huggingface.co/datasets/ibrahimhamamci/CT-RATE), and from the Rad-ChestCT dataset available at [https://zenodo.org/records/6406114](https://zenodo.org/records/6406114).

## 📎Citation

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

```bibtex
@InProceedings{dipiazza_2025_ctscroll,
        title = {Imitating Radiological Scrolling: A Global-Local Attention Model for 3D Chest CT Volumes Multi-Label Anomaly Classification},
        author = {Di Piazza, Theo and Lazarus, Carole and Nempont, Olivier and Boussel, Loic},
        booktitle = {Proceedings of The 8nd International Conference on Medical Imaging with Deep Learning -- MIDL 2025},
        year = {2025},
        publisher = {PMLR},
}
```