用分割引导配准，让解剖结构自适应变形更精准
Ideal Registration? Segmentation is All You Need
- 基于解剖分割构建局部变形场，再融合成全局配准结果
- 关键解剖结构Dice达98.23%，在三类临床图像上提升2-12%
- 配准精度高度依赖分割质量，适合有分割基础的医学影像研究者
深度学习已通过高效处理多样任务彻底改变图像配准，但现有方法多采用全局一致的平滑约束，难以适应解剖运动中复杂的区域性形变。为此，我们提出SegReg——一种由分割驱动的配准框架，通过利用区域特异性形变模式实现解剖自适应正则化。SegReg首先通过分割将移动和固定图像分解为解剖一致的子区域，再由同一配准主干网络计算优化的局部形变场，并整合为全局形变场。使用真实分割时，关键解剖结构的结构对齐精度达到98.23% Dice；即使使用自动分割，在心脏、腹部和肺部三类临床场景中仍比现有方法提升2%-12%。实验表明，配准精度与分割质量近乎线性相关，将配准问题转化为分割问题。源代码将在论文接收后发布。
原文摘要 · Abstract (English)
Deep learning has revolutionized image registration by its ability to handle diverse tasks while achieving significant speed advantages over conventional approaches. Current approaches, however, often employ globally uniform smoothness constraints that fail to accommodate the complex, regionally varying deformations characteristic of anatomical motion. To address this limitation, we propose SegReg, a Segmentation-driven Registration framework that implements anatomically adaptive regularization by exploiting region-specific deformation patterns. Our SegReg first decomposes input moving and fixed images into anatomically coherent subregions through segmentation. These localized domains are then processed by the same registration backbone to compute optimized partial deformation fields, which are subsequently integrated into a global deformation field. SegReg achieves near-perfect structural alignment (98.23% Dice on critical anatomies) using ground-truth segmentation, and outperforms existing methods by 2-12% across three clinical registration scenarios (cardiac, abdominal, and lung images) even with automatic segmentation. Our SegReg demonstrates a near-linear dependence of registration accuracy on segmentation quality, transforming the registration challenge into a segmentation problem. The source code will be released upon manuscript acceptance.
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。