Endoscope Controller Registration for Invisible Bifurcations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In minimally invasive coronary artery bypass grafting (CABG) surgeries, the challenge lies in registering pre-operative 3D vessel tree images with intra-operative endoscopic images, particularly when bifurcations are obscured by fatty tissue, and in coordinating the endoscope's position relative to the surgeon's frame of reference, leading to potential misidentification and prolonged surgery due to spatial constraints and lack of tactile feedback.
Innovation Solution
A robotic guiding system that employs an endoscope and endoscope controller to register intra-operative endoscopic images of vessel trees with pre-operative 3D images by delineating polygonal areas around invisible bifurcations and using image processing to match graphical representations, enabling accurate localization and orientation of the endoscope within the anatomical region.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If surface-based matching is used to register endoscopic images with pre-operative CT data, then the registration can be performed without palpation, but the method fails when the endoscope view is too small and operates in suboptimal local maximum due to the smooth heart surface without specific features
Solution Approach 1:
The patent segments the heart surface into multiple patches and performs matching iteratively. Instead of attempting to match the entire smooth surface at once (which leads to local maximum problems), the algorithm divides the surface into smaller manageable patches, matches them individually, and progressively refines the registration. This segmentation approach allows the system to overcome the lack of global surface features by creating local features through patch-based analysis.
2Measurement precision
If an optically tracked pointer is used to digitalize artery positions in open heart setting, then the arteries can be registered to pre-operative tree, but the technique is impractical for minimally invasive CABG due to spatial constraints of small port access
Solution Approach 1:
The patent replaces the mechanical optically tracked pointer system with an endoscope-based visual system. Instead of using a physical pointer that requires manual manipulation and spatial access, the system uses an endoscope to capture images of the heart surface and automatically identifies artery positions through image processing and pattern recognition algorithms. This substitution eliminates the need for physical access constraints while maintaining measurement precision.
3Productivity
If the endoscope is held by an assistant while the surgeon holds two instruments, then the surgeon can perform the procedure, but hand-eye coordination is hindered due to multiple coordinate systems and translation errors
Solution Approach 1:
The patent implements a real-time feedback system that provides the surgeon with visual information about endoscope position and orientation overlaid on the surgical field. The system continuously tracks the endoscope's location, transforms coordinates automatically, and displays guidance information that directly correlates with the surgeon's view. This feedback loop eliminates the need for the surgeon to mentally translate between multiple coordinate systems, as the system handles the coordinate transformation and presents information in the surgeon's native frame of reference.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
An image registration system an endoscope (12) and an endoscope controller (22). In operation, the endoscope (12) generates an intra-operative endoscopic image (14) of a vessel tree within an anatomical region including a plurality of branches of the vessel tree visible within the intra-operative endoscopic image (14) as an indication of a furcation of the vessel tree invisible within the intra-operative endoscopic image (14). The endoscope controller (22) image registers the intra-operative operative endoscopic image (14) of the vessel tree to a pre-operative three- dimensional image (44) of the vessel tree. The image registration includes an image matching of a graphical representation of the furcation of the vessel tree as indicated by the branches of the vessel tree visible within the intra-operative endoscopic image (14) of the vessel tree to a graphical representation of the furcation of the vessel tree visible within the pre-operative three- dimensional image (44) of the vessel tree.