Capsule Endoscope Position Tracking via Intraluminal Image Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current image processing devices for analyzing time-series images from moving imaging devices, such as capsule endoscopes, face challenges in accurately estimating the movement and position of the device within in-vivo lumens, especially in organs that change shape, requiring more effective methods to determine the position of lesions relative to the lumen entrance or exit for precise medical treatment.
Innovation Solution
An image processing device and method that extracts structural areas, corresponding areas, and lumen deep portions from intraluminal images, estimating movement amounts based on these features to calculate the position of the imaging device, allowing for accurate tracking of the device's movement and position within the lumen.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If magnetic field detection by external coils is used to calculate movement amount, then position information can be obtained, but the system becomes complex and requires additional external devices
Solution Approach 1:
The patent extracts the position estimation function from external devices and implements it within the capsule endoscope itself. By detecting magnetic fields generated by body parts (heart, brain, liver) using onboard magnetic field detection means, the system eliminates the need for external coil arrays while maintaining position estimation capability.
Solution Approach 2:
The capsule endoscope performs self-positioning by using its own magnetic field detection means to detect magnetic fields generated by body parts. The processing unit calculates movement amount and position information autonomously based on these detections, making the system self-sufficient without requiring external positioning infrastructure.
2Measurement precision
If magnetic field detection by external coils is used to calculate movement amount, then position information can be obtained, but the device size increases
Solution Approach 1:
The patent removes the bulky external coil system and replaces it with compact magnetic field detection means integrated into the capsule. This extraction of the positioning function to the capsule itself enables miniaturization while maintaining position estimation accuracy.
Solution Approach 2:
Instead of using large external coils to detect magnetic fields, the patent implements a simplified magnetic field detection system within the capsule that copies the essential sensing capability in a miniaturized form, sufficient for detecting magnetic fields from body parts.
3Loss of information
If coordinate-based position information is used, then spatial location can be determined, but accuracy decreases when organs change shape
Solution Approach 1:
The patent implements a dynamic position tracking system that continuously monitors movement amount between sequential images and accumulates these changes. This dynamic approach adapts to organ shape changes by tracking relative movement from a base point rather than relying on fixed coordinate systems, maintaining accuracy throughout the examination.
Solution Approach 2:
The patent transitions from static coordinate-based positioning to a dynamic accumulation-based positioning system that tracks movement in the dimension of time and displacement. By accumulating movement amounts from sequential images, the system creates a new dimensional framework for position estimation that adapts to changing organ geometry.
Data Source
AI summary
An image processing device for processing time-series intraluminal images captured by an imaging device moving in an in-vivo lumen. The image processing device includes a structural area extracting unit that extracts a structural area from the intraluminal image; a corresponding area extracting unit that extracts a corresponding area corresponding to the structural area from the intraluminal image at a second time point different from a first time point at which the structural area is extracted; a lumen deep portion extracting unit that extracts a lumen deep portion, on which a deep portion in the lumen is captured, from the intraluminal image; and a movement amount estimating unit that estimates a movement amount of the imaging device based on positions of the structural area, the corresponding area and the lumen deep portion.