Preoperative liver model non-rigid deformation correction method and device for intraoperative navigation

By employing a coupling strategy of implicit neural networks and linear elastic finite element biomechanical models, the problem of registration for non-rigid deformation of the liver was solved, achieving high-precision intraoperative navigation, reducing surgical risks and improving surgical efficiency.

CN122391033APending Publication Date: 2026-07-14SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI +1
0 Cites 0 Cited by

Patent Information

Application Number
CN202610234856.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-02-27
Publication Date
2026-07-14

AI Technical Summary

Technical Problem

In existing image-guided laparoscopic liver resection surgery, the preoperative 3D model and the real-time liver soft tissue surface cannot be accurately registered due to non-rigid deformation, resulting in large errors in the location of blood vessels and tumors, which increases surgical risks.

Method used

A local-guided global coupling strategy is adopted, using an implicit neural network model to predict the local deformation field of the liver, and combined with a linear elastic finite element biomechanical model. By iteratively updating the force and displacement of the nodes and solving the mechanical equilibrium equations, the global deformation field is determined.

Benefits of technology

It achieves high-precision, physically reasonable, and rapid non-rigid registration of all organs, reducing surgical risks and improving surgical efficiency and safety.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a pre-operative liver model non-rigid deformation correction method and device for intra-operative navigation. The method comprises the following steps: extracting a potential overlapping region with intra-operative liver reconstruction point cloud from the surface of a pre-operative liver model after initial registration; using an implicit neural network model to predict a liver local deformation field from the overlapping region to the intraoperative liver reconstruction point cloud as a determined physical boundary condition; according to the corresponding relation between physical boundary conditions and preoperative liver model grids, a mechanical equilibrium equation is solved by iteratively updating node stress and displacement, and a liver global deformation field is determined; the node stress and displacement solving mechanical equilibrium equation is an equation pre-established by introducing a diagonal loading strategy to assemble a global stiffness matrix on the basis of a linear elastic finite element liver biomechanical model. According to the method, high-precision, physically reasonable and rapid all-organ non-rigid registration is realized on the premise that time-consuming iteration corresponding relation search in a traditional method is not needed through a local guiding global coupling strategy.
Need to check novelty before this filing date? Find Prior Art