arXiv 2506.108132025-06-12cs.CVeess.IVeess.SP

带结构非参数平滑的无监督可变形图像配准

Unsupervised Deformable Image Registration with Structural Nonparametric Smoothing

Cornell University（康奈尔大学）；Hunan University（湖南大学）；University of Pennsylvania（宾夕法尼亚大学）；Johns Hopkins University（约翰霍普金斯大学）；Shanghai Jiao Tong University（上海交通大学）；University of Birmingham（伯明翰大学）；University of Manchester（曼彻斯特大学）

Hang Zhang, Xiang Chen, Renjiu Hu, Rongguang Wang, Jinwei Zhang, Min Liu, Yaonan Wang, Gaolei Li, Xinxing Cheng, Jinming Duan

备注：: Accepted for publication at Information Processing in Medical Imaging (IPMI) 2025

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对无监督可变形图像配准在稀疏特征大位移场景下的精度瓶颈，提出即插即用模块SmoothProper，通过对偶优化层实现前向传播中的平滑约束，在视网膜血管数据集上取得最优效果。

摘要：

基于学习的可变形图像配准（DIR）通过神经网络分摊传统优化过程，加快了配准速度。标签监督可进一步提升精度，实现对未见过扫描图像的高效精准非线性配准。但视网膜血管这类存在大片平滑区域、特征稀疏的图像，会带来孔径问题和大位移挑战，这是无监督DIR方法难以应对的。该局限的成因是神经网络仅通过单次前向传播预测形变场，训练后形变场不受约束，正则化负担完全落在网络权重上。为解决这些问题，我们提出SmoothProper，这是一种即插即用的神经模块，可在网络前向传播过程中施加平滑约束并促进消息传递。通过整合带定制交互项的基于对偶的优化层，SmoothProper能高效地在空间位置间传播光流信号，施加平滑约束并保持结构一致性。它具有模型无关性，可无缝集成到现有配准框架中，参数开销极小，且无需调整正则化超参数。在存在孔径和大位移挑战的视网膜血管数据集上的初步结果表明，我们的方法在2912×2912图像上将配准误差降至1.88像素，是首个有效解决这两类挑战的无监督DIR方法。源代码将发布于https://github.com/tinymilky/SmoothProper。

英文摘要：

Learning-based deformable image registration (DIR) accelerates alignment by amortizing traditional optimization via neural networks. Label supervision further enhances accuracy, enabling efficient and precise nonlinear alignment of unseen scans. However, images with sparse features amid large smooth regions, such as retinal vessels, introduce aperture and large-displacement challenges that unsupervised DIR methods struggle to address. This limitation occurs because neural networks predict deformation fields in a single forward pass, leaving fields unconstrained post-training and shifting the regularization burden entirely to network weights. To address these issues, we introduce SmoothProper, a plug-and-play neural module enforcing smoothness and promoting message passing within the network's forward pass. By integrating a duality-based optimization layer with tailored interaction terms, SmoothProper efficiently propagates flow signals across spatial locations, enforces smoothness, and preserves structural consistency. It is model-agnostic, seamlessly integrates into existing registration frameworks with minimal parameter overhead, and eliminates regularizer hyperparameter tuning. Preliminary results on a retinal vessel dataset exhibiting aperture and large-displacement challenges demonstrate our method reduces registration error to 1.88 pixels on 2912x2912 images, marking the first unsupervised DIR approach to effectively address both challenges. The source code will be available at https://github.com/tinymilky/SmoothProper.

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。