Scholarlink

Purpose: <p>In image-guided liver surgery (IGLS), the preoperative information can be overlaid onto the intraoperative scene by registering the 3D preoperative model with the intraoperative surface reconstructed from the laparoscopic image. It enables doctors to accurately locate tumors and perform precise resections. However, accurate registration remains challenging due to significant tissue deformation and partial overlaps caused by the limited laparoscopic view. To address these challenges, we propose a coarse-to-fine non-rigid registration framework using point cloud completion, i.e., point cloud completion-based non-rigid registration (PCReg) framework to achieve accurate registration between the preoperative and intraoperative data.</p> Methods: <p>PCReg consists of three consecutive stages: intraoperative point cloud completion, coarse registration, and fine registration. More specifically, we firstly utilize the point cloud completion network (PCN)-based method to complete the intraoperative point set. Then, we also develop an improved optimal transport (OT)-based coarse registration method that takes the preoperative and completed intraoperative point set as inputs and predicts the initial displacement field. Finally, a fine registration step is introduced to further refine the coarse alignment result.</p> Results: <p>Experimental results on simulated and real-world datasets demonstrate that PCReg achieves state-of-the-art performance, significantly outperforming existing methods in handling complex tissue deformations and varying overlap ratios.</p> Conclusions: <p>This work introduces PCReg, a novel point cloud registration framework for image-guided liver surgery. It achieves superior registration accuracy in low-overlapping scenarios and offers a promising solution for registration in image-guided liver surgery.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

PCReg: a coarse-to-fine registration framework using point cloud completion for intraoperative liver deformation correction

  • 期刊论文

  • 发表日期：

    2026年5月17日

查看全文
  • Mingyang Liu,
  • Xinzhe Du,
  • Peng Liu,
  • Shixing Ma,
  • Rui Song,
  • Yibin Li,
  • Max Q. -H. Meng,
  • Zhaoru Dong,
  • Zhe Min

摘要

Purpose:

In image-guided liver surgery (IGLS), the preoperative information can be overlaid onto the intraoperative scene by registering the 3D preoperative model with the intraoperative surface reconstructed from the laparoscopic image. It enables doctors to accurately locate tumors and perform precise resections. However, accurate registration remains challenging due to significant tissue deformation and partial overlaps caused by the limited laparoscopic view. To address these challenges, we propose a coarse-to-fine non-rigid registration framework using point cloud completion, i.e., point cloud completion-based non-rigid registration (PCReg) framework to achieve accurate registration between the preoperative and intraoperative data.

Methods:

PCReg consists of three consecutive stages: intraoperative point cloud completion, coarse registration, and fine registration. More specifically, we firstly utilize the point cloud completion network (PCN)-based method to complete the intraoperative point set. Then, we also develop an improved optimal transport (OT)-based coarse registration method that takes the preoperative and completed intraoperative point set as inputs and predicts the initial displacement field. Finally, a fine registration step is introduced to further refine the coarse alignment result.

Results:

Experimental results on simulated and real-world datasets demonstrate that PCReg achieves state-of-the-art performance, significantly outperforming existing methods in handling complex tissue deformations and varying overlap ratios.

Conclusions:

This work introduces PCReg, a novel point cloud registration framework for image-guided liver surgery. It achieves superior registration accuracy in low-overlapping scenarios and offers a promising solution for registration in image-guided liver surgery.