Endoscopic Lumen Matching for Accurate Branched Anatomy Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for tracking medical devices in branched anatomical structures, such as the lungs or heart, suffer from registration errors due to inaccuracies in dynamic referencing and anatomical motion, leading to challenges in maintaining proper registration and navigation accuracy.
Innovation Solution
A medical system and method that uses a computer model of the anatomical structure to determine the position of a medical device by comparing image information from its distal end with the model, employing blob detection and tracking algorithms to identify and match lumens in real-time, and self-correcting for registration errors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If electromagnetic tracking devices and dynamic referencing techniques are used to track medical devices in branched anatomical structures, then real-time position tracking is achieved, but registration errors occur due to anatomical motion and tracking inaccuracies
Solution Approach 1:
The system continuously compares actual images captured by the medical device with corresponding synthetic images generated from the computer model, calculates registration errors, and automatically corrects positioning information in real-time, creating a closed-loop feedback system that maintains accurate navigation despite anatomical motion
Solution Approach 2:
The system generates synthetic images from a computer model that replicate the appearance and characteristics of actual anatomical images, creating virtual copies that can be compared with real-time captured images to determine accurate device positioning without being affected by tracking errors
2Measurement precision
If complex image-based methods with Sequential Monte Carlo sampling are used to determine device position by comparing real and virtual images, then measurement precision is improved, but computational complexity increases making real-time application difficult
Solution Approach 1:
The system performs image comparison and registration correction only at critical moments when registration errors are detected or at scheduled intervals, rather than continuously processing all image data with complex algorithms, reducing computational burden while maintaining accuracy when needed
Solution Approach 2:
The system replaces complex computational methods like Sequential Monte Carlo sampling with a simpler image comparison approach that uses feature detection and matching algorithms, substituting heavy mathematical computations with more efficient computer vision techniques that achieve similar accuracy with lower computational cost
3Measurement precision
If traditional registration methods are used prior to medical procedures, then initial alignment is achieved, but registration errors develop during procedure performance due to anatomical structure movement
Solution Approach 1:
The system transitions from static pre-procedure registration to dynamic continuous registration by repeatedly comparing actual images with synthetic images throughout the procedure, allowing the system to adapt to anatomical motion and maintain accurate registration despite changes in tissue position and shape
Solution Approach 2:
The system implements continuous feedback by comparing real-time captured images with corresponding synthetic images from the computer model, detecting registration drift caused by anatomical motion, and automatically correcting positioning information to maintain accurate device navigation throughout the procedure
Data Source
AI summary
Information extracted from sequential images captured from the perspective of a distal end of a medical device moving through an anatomical structure are compared with corresponding information extracted from a computer model of the anatomical structure. A most likely match between the information extracted from the sequential images and the corresponding information extracted from the computer model is then determined using probabilities associated with a set of potential matches so as to register the computer model of the anatomical structure to the medical device and thereby determine the lumen of the anatomical structure which the medical device is currently in. Sensor information may be used to limit the set of potential matches. Feature attributes associated with the sequence of images and the set of potential matches may be quantitatively compared as part of the determination of the most likely match.