用肿瘤浓度控制生成高保真脑瘤MRI，支持病灶合成与健康组织修复。
A Biophysically-Conditioned Generative Framework for 3D Brain Tumor MRI Synthesis
- 基于体素级肿瘤浓度的潜空间扩散模型，实现3D脑影像生成。
- 健康组织修复PSNR达18.5，肿瘤区域修复达17.4，保持解剖一致性。
- 适用于脑瘤生成与病灶缺失修复，适合医学影像研究者使用。
磁共振成像（MRI）修复支持众多临床与科研应用。我们提出首个基于体素级连续肿瘤浓度条件的生成模型，用于合成高保真脑瘤MRI。针对BraTS 2025 Inpainting Challenge，我们将该架构拓展至健康组织恢复任务，将肿瘤浓度设为零。该潜空间扩散模型同时结合组织分割图与肿瘤浓度信息，生成具有三维空间一致性和解剖合理性的图像，适用于肿瘤合成与健康组织修复。在健康组织修复任务中，达到18.5的PSNR；在肿瘤修复任务中，达到17.4的PSNR。代码已开源：https://github.com/valentin-biller/ldm.git。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。