3D Shape-to-Image Brownian Bridge Diffusion for Brain MRI Synthesis from Cortical Surfaces

TL;DR

Cor2Vox is a novel diffusion model that translates cortical shape priors into realistic 3D brain MRIs, improving anatomical accuracy and diversity, and enabling detailed simulation of cortical atrophy.

Contribution

We introduce Cor2Vox, the first diffusion-based method for converting cortical shape priors into synthetic brain MRIs using a Brownian bridge process.

Findings

Enhanced geometric accuracy of reconstructed brain structures

High image quality and structural diversity

Ability to simulate cortical atrophy at sub-voxel resolution

Abstract

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.