用对称先验和注意力约束，精准修复脑MRI健康组织。
Now You Have My Healthy Attention: A U-DiT for Brain-MRI Inpainting
- 基于脑部对称性设计先验，引导修复区域只参考健康部分。
- 在BraTS-2026上实现0.864的SSIM、24.7dB PSNR、4.6×10⁻³ MSE。
- 适合医学影像修复、需要结构真实性的研究者使用。
ASNR-MICCAI BraTS局部合成（修复）任务要求在T1加权MRI的掩蔽区域中完成健康脑组织的解剖合理重建，为下游分析提供无肿瘤的解剖参考。由于评分基于失真指标（SSIM、PSNR、MSE），我们构建了一个确定性回归模型，并引入针对修复任务的归纳偏置。网络遵循U-DiT架构，在下采样标记网格上执行自注意力：三维体素编码器-解码器通过下采样全局自注意力块引入长程上下文，结合三维旋转位置编码；卷积与跳跃连接保留高频细节。两个关键设计提升性能：第一，限制注意力机制，使被遮挡（“空洞”）标记仅关注同体积的已知健康标记，并学习查询与其对侧同源区域的偏置，确保修复仅基于观测解剖结构而非未知区域；第二，加入对侧对称性输入，提供镜像的健康半球作为患者特异性先验；由于大脑近似双侧对称且病灶通常单侧，该先验显著提升结构相似性。在官方BraTS-2026验证榜单上，我们的提交在219例数据上达到平均健康区域SSIM 0.864、PSNR 24.7 dB、MSE 4.6×10⁻³。我们进一步分析了失真最优回归固有的残差平滑性，并讨论其对解剖真实性的意义。
原文摘要 · Abstract (English)
The ASNR-MICCAI BraTS Local Synthesis (Inpainting) task asks for the anatomically plausible completion of healthy brain tissue within a masked region of a T1-weighted MRI, providing a tumor-free anatomical reference for downstream analysis. As the task is scored by distortion metrics (SSIM, PSNR, MSE), we build a deterministic regression model and focus on giving it inductive biases tailored to inpainting. Our network follows the U-DiT principle of performing self-attention on a downsampled token grid: a volumetric encoder-decoder imports long-range context through a downsampled global self-attention block with three-dimensional rotary position embeddings, while convolutions and skip connections preserve high-frequency detail. Two ideas drive our results. First, we constrain the attention so that occluded ("void") tokens attend only to known-healthy tokens of the same volume, with a learned bias toward each query's contralateral homologue, forcing the completion to be inferred from observed anatomy rather than from other unknown regions. Second, we add a contralateral-symmetry input that supplies the mirrored healthy hemisphere as a patient-specific prior; since the brain is approximately bilaterally symmetric and lesions are typically unilateral, this prior improves the distortion metrics at matched structural similarity. On the official BraTS-2026 validation leaderboard our submission reaches a mean healthy-region SSIM of $0.864$, PSNR of $24.7$\,dB and MSE of $4.6{\times}10^{-3}$ over $219$ cases. We further analyse the residual smoothness inherent to distortion-optimal regression and discuss its implications for anatomical realism.
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。