高斯基元优化的可变形视网膜图像配准
Gaussian Primitive Optimized Deformable Retinal Image Registration
AI总结：
本文提出高斯基元优化（GPO）框架，通过在关键血管处构建可训练高斯基元控制节点并进行KNN高斯插值，解决可变形视网膜图像配准中梯度信号不足的问题，在FIRE数据集上显著降低配准误差并提升AUC。
摘要：
可变形视网膜图像配准因存在大面积同质区域以及稀疏但关键的血管特征而极为困难，这些特征导致标准基于学习的框架中梯度信号有限。本文提出高斯基元优化（GPO），一种执行结构化消息传递的新型迭代框架，以克服这些挑战。在初始粗对齐之后，我们在显著解剖结构（例如主要血管）处提取关键点，作为一组最小的基于描述符的控制节点（DCN）。每个节点被建模为一个具有可训练位置、位移和半径的高斯基元，从而使其空间影响适应局部变形尺度。随后，K最近邻（KNN）高斯插值混合并传播来自这些信息丰富节点的位移信号，以构建全局一致的位移场；将插值聚焦于前K个邻居可降低计算开销，同时保留局部细节。通过将节点策略性地锚定在高梯度区域，GPO确保稳健的梯度流动，缓解无纹理区域中梯度信号消失的问题。该框架通过多项损失进行端到端优化，该损失同时约束关键点一致性和强度对齐。在FIRE数据集上的实验表明，GPO将目标配准误差从6.2像素降低至约2.4像素，并将25像素处的AUC从0.770提高到0.938，显著优于现有方法。源代码可通过https://github.com/xintian-99/GPOreg获取。
英文摘要：
Deformable retinal image registration is notoriously difficult due to large homogeneous regions and sparse but critical vascular features, which cause limited gradient signals in standard learning-based frameworks. In this paper, we introduce Gaussian Primitive Optimization (GPO), a novel iterative framework that performs structured message passing to overcome these challenges. After an initial coarse alignment, we extract keypoints at salient anatomical structures (e.g., major vessels) to serve as a minimal set of descriptor-based control nodes (DCN). Each node is modelled as a Gaussian primitive with trainable position, displacement, and radius, thus adapting its spatial influence to local deformation scales. A K-Nearest Neighbors (KNN) Gaussian interpolation then blends and propagates displacement signals from these information-rich nodes to construct a globally coherent displacement field; focusing interpolation on the top (K) neighbors reduces computational overhead while preserving local detail. By strategically anchoring nodes in high-gradient regions, GPO ensures robust gradient flow, mitigating vanishing gradient signal in textureless areas. The framework is optimized end-to-end via a multi-term loss that enforces both keypoint consistency and intensity alignment. Experiments on the FIRE dataset show that GPO reduces the target registration error from 6.2\,px to ~2.4\,px and increases the AUC at 25\,px from 0.770 to 0.938, substantially outperforming existing methods. The source code can be accessed via https://github.com/xintian-99/GPOreg.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
