arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.01720cs.CV
收藏

腹腔手术中基于潜在证据的预手术到手术过程肝脏注册

Preoperative-to-intraoperative Liver Registration for Laparoscopic Surgery via Latent-Grounded Correspondence Constraints

The Hong Kong Polytechnic University, Hong Kong, China(香港理工大学);The Chinese University of Hong Kong, Hong Kong, China(香港中文大学)

Ruize Cui, Jialun Pei, Haiqiao Wang, Jun Zhou, Jeremy Yuen-Chun Teoh, Pheng-Ann Heng, Jing Qin

AI总结:

本文提出Land-Reg框架,通过显式学习潜在证据的2D-3D地标对应关系,提升腹腔手术中预手术到术中肝脏的跨模态注册精度与可解释性。

摘要:

在腹腔肝脏手术中,增强现实技术通过将预手术CT/MRI的3D肝脏模型叠加到腹腔2D视图上,增强了术中解剖引导。然而,现有注册方法缺乏对由潜在证据支持的可靠2D-3D几何对应关系的显式建模,导致解释性有限,并且在临床场景中可能产生不稳定对齐。在本工作中,我们引入了Land-Reg,一种基于对应关系的可变形注册框架,通过显式学习潜在证据的2D-3D地标对应关系作为可解释的中间表示,以弥合跨模态对齐。对于刚性注册,Land-Reg采用跨模态潜在对齐模块,将多模态特征映射到统一的潜在空间。进一步,我们提出了一种不确定性增强的重叠地标检测器,结合相似性匹配,以稳健地估计显式的2D-3D地标对应关系。对于非刚性注册,我们设计了一种新的形状约束监督策略,通过重投影一致性将形状变形锚定到匹配的地标上,并结合局部等距正则化以缓解固有的2D-3D深度模糊性,同时渲染掩码对齐强制全局形状一致性。在P2ILF数据集上的实验结果表明,我们的方法在刚性姿态估计和非刚性变形方面均优于现有方法。我们的代码将在https://github.com/cuiruize/Land-Reg上提供。

英文摘要:

In laparoscopic liver surgery, augmented reality technology enhances intraoperative anatomical guidance by overlaying 3D liver models from preoperative CT/MRI onto laparoscopic 2D views. However, existing registration methods lack explicit modeling of reliable 2D-3D geometric correspondences supported by latent evidence, leading to limited interpretability and potentially unstable alignment in clinical scenarios. In this work, we introduce Land-Reg, a correspondence-driven deformable registration framework that explicitly learns latent-grounded 2D-3D landmark correspondences as an interpretable intermediate representation to bridge cross-modal alignment. For rigid registration, Land-Reg embraces a Cross-modal Latent Alignment module to map multi-modal features into a unified latent space. Further, an Uncertainty-enhanced Overlap Landmark Detector with similarity matching is proposed to robustly estimate explicit 2D-3D landmark correspondences. For non-rigid registration, we design a novel shape-constrained supervision strategy that anchors shape deformation to matched landmarks through reprojection consistency and incorporates local-isometric regularization to alleviate inherent 2D-3D depth ambiguity, while a rendered-mask alignment enforces global shape consistency. Experimental results on the P2ILF dataset demonstrate the superiority of our method on both rigid pose estimation and non-rigid deformation. Our code will be available at https://github.com/cuiruize/Land-Reg.

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。

↑