# GenerateCT: Text-Guided 3D Chest CT Generation Welcome to the official page of GenerateCT, a pioneering work in text-conditional 3D medical image generation with a particular focus on chest CT volumes. Here, you will find the code, all trained models for text-to-CT generation, and a dataset of generated CT volumes paired with text prompts, all freely accessible for researchers.
## Results Our models achieve the following performances:
Model | Resolution (px) | Dimension | Text-Guided? | FID Score (↓) | FVD Score (↓) | CLIP Score (↑) |
---|---|---|---|---|---|---|
CT-ViT | 128 | 3D | No | 73.4 | 1817.4 | N/A |
Transformer | 128 | 3D | Yes | 104.3 | 1886.8 | 25.2 |
Diffusion | 512 | 2D | Yes | 14.9 | 409.8 | 27.6 |
GenerateCT | 512 | 3D | Yes | 55.8 | 1092.3 | 27.1 |