Soft Tissue Surface Registration Correction Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Computer-assisted surgical procedures face challenges in reducing registration errors due to touch-induced deformation of soft tissues, especially in areas without underlying hard tissue, which can lead to increased health risks and require user expertise and additional hardware like markers.
Innovation Solution
A method that uses a correction model to shift the relative positions of points acquired by a tracked pointing device on soft tissues, based on deformation models and image data, to improve surface registration accuracy without relying on user experience or predefined locations, and reduces deformation errors by determining correction vectors oriented normal to the tissue surface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If contact-involving techniques like touching the surface with a tracked pointing device are used, then surface data can be acquired, but touch-induced deformation introduces registration errors
Solution Approach 1:
The system applies a correction model that predicts and compensates for touch-induced deformation before it affects the registration accuracy. By calculating expected deformation based on tissue properties and pointing device force, the system pre-adjusts the surface data to counteract the harmful deformation effect
Solution Approach 2:
The patent replaces direct mechanical measurement with a computational model. Instead of relying on pure mechanical contact measurement that causes deformation, the system uses a deformation model that calculates the relationship between applied force and tissue displacement, substituting physical measurement with mathematical prediction and correction
2Measurement precision
If users are trained to touch points known to be less deformable, then registration error is reduced, but cognitive load and human error increase
Solution Approach 1:
The system performs self-correction by automatically identifying and compensating for deformation effects without requiring user expertise. The correction model autonomously calculates deformation based on tissue mechanical properties and pointing device characteristics, eliminating the need for users to manually select specific touch locations or apply specialized techniques
Solution Approach 2:
The patent changes the approach from selecting specific locations (qualitative parameter) to applying quantitative correction based on tissue mechanical properties. By modeling deformation as a function of tissue stiffness, density, and applied force, the system transforms the problem from user-dependent location selection to objective parameter-based correction
3Measurement precision
If predefined locations with markers are used, then registration error due to deformation is reduced, but additional hardware and procedure duration increase
Solution Approach 1:
The patent extracts and removes the need for physical markers and predefined location systems. By using the correction model that operates on naturally acquired surface data, the system eliminates the additional hardware components (markers, predefined templates) while maintaining registration accuracy through computational correction
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
A computer-implemented technique for determining a surface registration between a first soft tissue surface defined based on mechanically acquired first surface data and a second soft tissue surface defined based on image data is provided. A method implementation of the technique comprises obtaining the first surface data, wherein the first surface data comprise a first set of points mechanically acquired by contacting the soft tissue with a pointing device. The method also comprises applying a correction model on the first surface data to obtain corrected first surface data. The correction model is configured to shift relative positions of two or more points in the first set. Further still, the method includes determining a surface registration between the first and the second soft tissue surfaces based at least in part on the corrected first surface data.