Endoscope Positioning via Virtual Image Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current endoscope systems face challenges in accurately guiding the distal end of the insertion portion to the target region within complex luminal organs like bronchia, due to difficulties in acquiring precise three-dimensional images and matching endoscopic images with virtual endoscopic images, which hinders precise insertion and biopsy procedures.
Innovation Solution
An endoscope system that includes an image storage section, virtual endoscopic image generation, position registration processing, position estimation, feature region determination, and candidate information presentation to help guide the distal end of the endoscope insertion portion to the correct location within the luminal organ by comparing and matching endoscopic and virtual images, and providing candidate information for precise positioning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If image matching between endoscopic image and virtual endoscopic image is performed to guide insertion, then insertion precision is improved, but reliability deteriorates when matching fails in complex luminal organs
Solution Approach 1:
The system performs preliminary actions by storing candidate position information and candidate virtual endoscopic images in advance before insertion guidance is needed. When image matching fails, these pre-stored candidates are immediately available for presentation, avoiding delays and maintaining reliability without sacrificing insertion precision during normal operation.
Solution Approach 2:
The system prepares backup solutions (candidate positions and images) in advance to cushion against the potential failure of image matching. This ensures that even if the primary position estimation method fails in complex luminal organs, the system can fall back to pre-prepared candidate information, maintaining reliability while preserving the precision benefits of image matching when it succeeds.
2Reliability
If candidate position information is stored and presented when image matching fails, then reliability is improved, but device complexity increases
Solution Approach 1:
The position estimation section serves multiple functions: it performs image matching for precise position estimation under normal conditions, and simultaneously stores candidate position information for use when matching fails. This multi-functionality improves reliability without requiring separate dedicated systems, thereby limiting the increase in device complexity.
Solution Approach 2:
The system creates simplified copies of position information and virtual endoscopic images that can be stored and retrieved without complex processing. These candidate copies are prepared in advance and presented when needed, improving reliability through redundancy while keeping the copying and storage mechanisms relatively simple to avoid excessive complexity.
3Ease of operation
If virtual endoscopic image generation from arbitrary viewpoint is performed, then ease of operation is improved, but loss of information increases due to image matching failures
Solution Approach 1:
The system implements feedback by monitoring the success of image matching between endoscopic and virtual endoscopic images. When matching fails, the system detects this and switches to presenting pre-stored candidate position information, ensuring that position information accuracy is maintained despite the flexibility of arbitrary viewpoint generation. This feedback mechanism recovers from information loss situations.
Solution Approach 2:
Candidate position information and corresponding virtual endoscopic images are prepared in advance from multiple potential viewpoints and positions. When image matching fails during insertion guidance, these pre-prepared alternatives are immediately presented, preventing loss of position information accuracy while maintaining the ease of operation benefits of flexible viewpoint selection.
Data Source
AI summary
An endoscope system includes: an image storage section that stores image information associated with position information of a luminal organ of a subject; a virtual endoscopic image generating section that generates a virtual endoscopic image endoscopically depicted; an image pickup section that picks up an image in the luminal organ; a position registration processing section that compares the virtual endoscopic image and an endoscopic image, and extracts an virtual endoscopic image similar to the endoscopic image; a position estimation section that estimates a distal end position of an endoscope insertion portion; a feature region determination section that determines whether or not the distal end position exists in a feature region; a storage section that stores information for presentation; and a candidate information presentation control section that presents the virtual endoscopic image based on the information in the storage section, to a display section as candidate information.