Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.12742 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910834660212736 |
|---|---|
| author | Bongratz, Fabian Li, Yitong Elbaroudy, Sama Wachinger, Christian |
| author_facet | Bongratz, Fabian Li, Yitong Elbaroudy, Sama Wachinger, Christian |
| contents | Despite recent advances in medical image generation, existing methods struggle to produce anatomically plausible 3D structures. In synthetic brain magnetic resonance images (MRIs), characteristic fissures are often missing, and reconstructed cortical surfaces appear scattered rather than densely convoluted. To address this issue, we introduce Cor2Vox, the first diffusion model-based method that translates continuous cortical shape priors to synthetic brain MRIs. To achieve this, we leverage a Brownian bridge process which allows for direct structured mapping between shape contours and medical images. Specifically, we adapt the concept of the Brownian bridge diffusion model to 3D and extend it to embrace various complementary shape representations. Our experiments demonstrate significant improvements in the geometric accuracy of reconstructed structures compared to previous voxel-based approaches. Moreover, Cor2Vox excels in image quality and diversity, yielding high variation in non-target structures like the skull. Finally, we highlight the capability of our approach to simulate cortical atrophy at the sub-voxel level. Our code is available at https://github.com/ai-med/Cor2Vox. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12742 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | 3D Shape-to-Image Brownian Bridge Diffusion for Brain MRI Synthesis from Cortical Surfaces Bongratz, Fabian Li, Yitong Elbaroudy, Sama Wachinger, Christian Computer Vision and Pattern Recognition Despite recent advances in medical image generation, existing methods struggle to produce anatomically plausible 3D structures. In synthetic brain magnetic resonance images (MRIs), characteristic fissures are often missing, and reconstructed cortical surfaces appear scattered rather than densely convoluted. To address this issue, we introduce Cor2Vox, the first diffusion model-based method that translates continuous cortical shape priors to synthetic brain MRIs. To achieve this, we leverage a Brownian bridge process which allows for direct structured mapping between shape contours and medical images. Specifically, we adapt the concept of the Brownian bridge diffusion model to 3D and extend it to embrace various complementary shape representations. Our experiments demonstrate significant improvements in the geometric accuracy of reconstructed structures compared to previous voxel-based approaches. Moreover, Cor2Vox excels in image quality and diversity, yielding high variation in non-target structures like the skull. Finally, we highlight the capability of our approach to simulate cortical atrophy at the sub-voxel level. Our code is available at https://github.com/ai-med/Cor2Vox. |
| title | 3D Shape-to-Image Brownian Bridge Diffusion for Brain MRI Synthesis from Cortical Surfaces |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.12742 |