# GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes
Welcome to the official page of GenerateCT, a pioneering project in text-conditional 3D medical image generation, with a particular focus on chest CT volumes.

Here, you will find trained models for text-to-CT generation and a large dataset of synthetic CT volumes generated by GenerateCT based on text prompts, all freely accessible to researchers.

Additionally, our codebase is openly available on [our official GitHub repository](https://github.com/ibrahimethemhamamci/GenerateCT).

<p align="center">
  <img src="https://huggingface.co/generatect/GenerateCT/resolve/main/figures/examples.gif" width="100%">
</p>


## Citing Us
When using this resource, please consider citing the following related papers:

```
1. @article{hamamci2023generatect,
  title={GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes},
  author={Hamamci, Ibrahim Ethem and Er, Sezgin and Sekuboyina, Anjany and Simsar, Enis and Tezcan, Alperen and Simsek, Ayse Gulnihan and Esirgun, Sevval Nil and Almas, Furkan and Dogan, Irem and Dasdelen, Muhammed Furkan and others},
  journal={arXiv preprint arXiv:2305.16037},
  year={2023}
}

2. @article{hamamci2024foundation,
  title={A foundation model utilizing chest CT volumes and radiology reports for supervised-level zero-shot detection of abnormalities},
  author={Hamamci, Ibrahim Ethem and Er, Sezgin and Almas, Furkan and Simsek, Ayse Gulnihan and Esirgun, Sevval Nil and Dogan, Irem and Dasdelen, Muhammed Furkan and Wittmann, Bastian and Simsar, Enis and Simsar, Mehmet and others},
  journal={arXiv preprint arXiv:2403.17834},
  year={2024}
}

3. @article{hamamci2024ct2rep,
  title={Ct2rep: Automated radiology report generation for 3d medical imaging},
  author={Hamamci, Ibrahim Ethem and Er, Sezgin and Menze, Bjoern},
  journal={arXiv preprint arXiv:2403.06801},
  year={2024}
}
```

## License
Our work, including the codes, trained models, and generated data, is released under a [Creative Commons Attribution (CC-BY) license](https://creativecommons.org/licenses/by/4.0/). This means that anyone is free to share (copy and redistribute the material in any medium or format) and adapt (remix, transform, and build upon the material) for any purpose, even commercially, as long as appropriate credit is given, a link to the license is provided, and any changes that were made are indicated. This aligns with our goal of facilitating progress in the field by providing a resource for researchers to build upon.