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

翻译：磁共振成像（MRI）修复技术支撑着众多临床与研究应用。我们提出了首个基于体素级连续肿瘤浓度条件的高保真脑肿瘤MRI合成生成模型。针对BraTS 2025修复挑战赛，我们通过将肿瘤浓度设为零，将该架构适配于健康组织修复这一互补任务。我们提出的基于组织分割与肿瘤浓度双重条件的潜在扩散模型，能够为肿瘤合成与健康组织修复生成三维空间连贯且解剖结构一致的图像。在健康组织修复任务中，我们获得了18.5的峰值信噪比（PSNR）；在肿瘤修复任务中，该指标为17.4。相关代码已开源：https://github.com/valentin-biller/ldm.git