Endoscope Navigation via 3D-Fluoroscopy Image Registration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing endoscope navigation methods require sensors to accurately determine the position of the endoscope within a subject, which is challenging due to the lack of depth information in fluoroscopic images, making precise navigation difficult.
Innovation Solution
An image processing device that acquires a three-dimensional image of the subject, derives a virtual viewpoint using real endoscopic and three-dimensional images, registers the radiation image with the three-dimensional image, and superimposes the lumen structure onto the radiation image for navigation without using sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a sensor is provided in the endoscope to detect the position of the endoscope, then the position detection accuracy is improved, but the device complexity increases
Solution Approach 1:
The patent creates a virtual copy of the endoscope's visual appearance from the three-dimensional image data. This virtual endoscopic image serves as a representation of the endoscope's position and orientation without requiring physical sensors. The virtual image is generated by rendering the three-dimensional anatomical structure from the viewpoint corresponding to the endoscope's position, allowing position detection through image processing rather than sensor-based measurement.
Solution Approach 2:
The patent replaces the mechanical sensor-based position detection system with an optical/image-based system. Instead of using physical sensors to detect position, the system uses the visual information from the endoscopic image and corresponding three-dimensional image data to computationally determine position. This substitution eliminates the need for sensors while maintaining position detection capability through computational methods.
2Device complexity
If the position of the endoscope is detected from the fluoroscopic image without a sensor, then the device complexity is reduced, but the measurement precision deteriorates due to lack of depth information
Solution Approach 1:
The patent transitions from two-dimensional fluoroscopic imaging to three-dimensional image data. By utilizing three-dimensional anatomical structures and volumetric rendering, the system gains depth information that is absent in conventional fluoroscopic images. This dimensional transition enables accurate three-dimensional position detection by correlating the virtual endoscopic viewpoint with the three-dimensional space, resolving the depth information deficiency of planar imaging.
Solution Approach 2:
The patent introduces a virtual endoscopic image as an intermediary between the physical endoscope position and the three-dimensional anatomical structure. This virtual image serves as a mediator that bridges the gap between two-dimensional fluoroscopic projection and three-dimensional space. By processing the virtual endoscopic image and correlating it with three-dimensional image data, the system can accurately determine three-dimensional position without direct sensor input.
3Measurement precision
If a three-dimensional image is acquired and processed to derive virtual viewpoint, then the navigation accuracy is improved, but the processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary processing by pre-acquiring and storing three-dimensional image data of the anatomical structure before the actual navigation procedure. The three-dimensional images are processed in advance to create a database of anatomical information and virtual endoscopic views. This preliminary preparation allows the system to quickly retrieve and process relevant three-dimensional data during the actual navigation, reducing real-time computational burden while maintaining high navigation accuracy.
Data Source
AI summary
A processor acquires a three-dimensional image of a subject, acquires a real endoscopic image in a lumen structure of the subject, which is picked up by an endoscope inserted into the lumen structure of the subject, derives a virtual viewpoint in the three-dimensional image of the endoscope using the real endoscopic image and the three-dimensional image, acquires a radiation image of the subject in which the endoscope is inserted into the lumen structure, performs registration between the radiation image and the three-dimensional image, and superimposes and displays at least a part of the lumen structure included in the three-dimensional image, on the radiation image, based on the virtual viewpoint and a result of the registration.