Text2CT: Towards 3D CT Volume Generation from Free-text Descriptions Using Diffusion Model
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915278354382848 |
|---|---|
| author | Guo, Pengfei Zhao, Can Yang, Dong He, Yufan Nath, Vishwesh Xu, Ziyue Bassi, Pedro R. A. S. Zhou, Zongwei Simon, Benjamin D. Harmon, Stephanie Anne Turkbey, Baris Xu, Daguang |
| author_facet | Guo, Pengfei Zhao, Can Yang, Dong He, Yufan Nath, Vishwesh Xu, Ziyue Bassi, Pedro R. A. S. Zhou, Zongwei Simon, Benjamin D. Harmon, Stephanie Anne Turkbey, Baris Xu, Daguang |
| contents | Generating 3D CT volumes from descriptive free-text inputs presents a transformative opportunity in diagnostics and research. In this paper, we introduce Text2CT, a novel approach for synthesizing 3D CT volumes from textual descriptions using the diffusion model. Unlike previous methods that rely on fixed-format text input, Text2CT employs a novel prompt formulation that enables generation from diverse, free-text descriptions. The proposed framework encodes medical text into latent representations and decodes them into high-resolution 3D CT scans, effectively bridging the gap between semantic text inputs and detailed volumetric representations in a unified 3D framework. Our method demonstrates superior performance in preserving anatomical fidelity and capturing intricate structures as described in the input text. Extensive evaluations show that our approach achieves state-of-the-art results, offering promising potential applications in diagnostics, and data augmentation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_04522 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Text2CT: Towards 3D CT Volume Generation from Free-text Descriptions Using Diffusion Model Guo, Pengfei Zhao, Can Yang, Dong He, Yufan Nath, Vishwesh Xu, Ziyue Bassi, Pedro R. A. S. Zhou, Zongwei Simon, Benjamin D. Harmon, Stephanie Anne Turkbey, Baris Xu, Daguang Image and Video Processing Computer Vision and Pattern Recognition Generating 3D CT volumes from descriptive free-text inputs presents a transformative opportunity in diagnostics and research. In this paper, we introduce Text2CT, a novel approach for synthesizing 3D CT volumes from textual descriptions using the diffusion model. Unlike previous methods that rely on fixed-format text input, Text2CT employs a novel prompt formulation that enables generation from diverse, free-text descriptions. The proposed framework encodes medical text into latent representations and decodes them into high-resolution 3D CT scans, effectively bridging the gap between semantic text inputs and detailed volumetric representations in a unified 3D framework. Our method demonstrates superior performance in preserving anatomical fidelity and capturing intricate structures as described in the input text. Extensive evaluations show that our approach achieves state-of-the-art results, offering promising potential applications in diagnostics, and data augmentation. |
| title | Text2CT: Towards 3D CT Volume Generation from Free-text Descriptions Using Diffusion Model |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.04522 |