In-Vivo Object Size Estimation via Virtual Tool Projection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current in-vivo imaging devices face challenges in accurately estimating the size of objects within the body lumens, as existing methods are limited in providing precise three-dimensional representations and reliable size measurements, especially when dealing with complex tissues and varying distances from the imaging device.
Innovation Solution
A system and method that involves displaying a two-dimensional image of in-vivo objects, estimating depth, calculating three-dimensional coordinates, and projecting a virtual tool of known size onto the image to determine ending points, allowing for dynamic cursor creation and movement, enabling intuitive size estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a two-dimensional image is used for size estimation, then the device complexity is reduced, but the measurement precision deteriorates due to loss of depth information
Solution Approach 1:
The patent applies dimensionality change by estimating depth (z-coordinate) for each pixel in the two-dimensional image and calculating three-dimensional coordinates representation. This allows the system to recover depth information from 2D images, enabling accurate size estimation of in-vivo objects while maintaining the simplicity of two-dimensional imaging.
2Measurement precision
If professional forceps are used for size estimation, then the measurement precision is improved, but the ease of operation deteriorates due to requiring manual calibration
Solution Approach 1:
The patent creates a virtual copy of the forceps tool that is projected onto the three-dimensional representation of the imaged tissue. This virtual forceps cursor allows automated size estimation without requiring manual calibration or physical manipulation, combining the precision of professional tools with automated operation.
Solution Approach 2:
The patent replaces the mechanical forceps system with a computational approach. Instead of using physical forceps that require manual calibration and manipulation, the system uses image processing, depth estimation, and virtual tool projection to automatically determine object sizes, eliminating the need for mechanical calibration procedures.
3Measurement precision
If depth estimation is performed for all pixels, then the measurement precision is improved, but the loss of time increases due to computational complexity
Solution Approach 1:
The patent applies partial action by focusing depth estimation and three-dimensional coordinate calculation on the specific region of interest where the in-vivo object is located, rather than processing the entire image. This selective approach reduces computational time while maintaining measurement precision for the relevant area.
Data Source
AI summary
A system, method and virtual tool for size estimation of in-vivo objects includes receiving and displaying a two-dimensional image of in-vivo objects obtained by in-vivo imaging device; receiving indication of a selected area representing a point of interest from the user via a user input device; estimating depth of a plurality of image pixels around the selected area; calculating three-dimensional coordinates representation of the plurality of image points, based on the estimated depths; casting a virtual tool of a known size onto the three-dimensional representation; and projecting the virtual tool onto the two-dimensional image to create a cursor having a two-dimensional shape on the displayed image.