A Biophysically-Conditioned Generative Framework for 3D Brain Tumor MRI Synthesis
This work addresses the need for realistic MRI synthesis in clinical and research settings, offering a novel approach for brain tumor imaging tasks.
The paper tackles the problem of generating high-fidelity 3D brain tumor MRIs by introducing a generative model that conditions on voxel-level tumor concentrations, achieving a PSNR of 18.5 for healthy tissue inpainting and 17.4 for tumor inpainting.
Magnetic resonance imaging (MRI) inpainting supports numerous clinical and research applications. We introduce the first generative model that conditions on voxel-level, continuous tumor concentrations to synthesize high-fidelity brain tumor MRIs. For the BraTS 2025 Inpainting Challenge, we adapt this architecture to the complementary task of healthy tissue restoration by setting the tumor concentrations to zero. Our latent diffusion model conditioned on both tissue segmentations and the tumor concentrations generates 3D spatially coherent and anatomically consistent images for both tumor synthesis and healthy tissue inpainting. For healthy inpainting, we achieve a PSNR of 18.5, and for tumor inpainting, we achieve 17.4. Our code is available at: https://github.com/valentin-biller/ldm.git