Endoscope System for GI Anomaly Volume Measurement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current endoscope technologies for imaging the human gastrointestinal tract are limited in accurately measuring the physical area or volume of anomalies, such as polyps, due to reliance on one-dimensional measurements and difficulty in precise alignment within the tortuous intestine, especially for lesions not on the same plane or in convoluted structures like the GI tract.
Innovation Solution
An endoscope system that estimates physical area or volume by determining distance information and using image data to calculate dimensions, incorporating techniques like image stitching, artificial intelligence for boundary outlining, and 3D mathematical models to derive accurate measurements, including the use of structured light for depth estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If one-dimensional measurement methods are used for polyp size estimation, then the measurement process is simple and quick, but the measurement precision and diagnostic accuracy are insufficient
Solution Approach 1:
The patent introduces a forceps as an intermediary object with known dimensions that is positioned near the polyp during imaging. This forceps serves as a reference scale, allowing the system to calculate the polyp's actual size by comparing its image dimensions to the forceps' known dimensions in the same image, thereby achieving accurate measurement without complex dedicated measurement devices.
Solution Approach 2:
The patent creates a digital copy or representation of the measurement process by capturing images that include both the polyp and the forceps reference object. The system then processes these image copies to extract size information, avoiding the need for direct physical measurement tools while maintaining measurement accuracy through image analysis.
2Reliability
If traditional forceps measurement method is used, then the operation is straightforward, but the measurement reliability is low due to difficulty in alignment and perspective distortion
Solution Approach 1:
The system provides visual feedback by displaying the captured image with both the polyp and forceps on a monitor. The processor automatically identifies the forceps in the image and uses its known dimensions to calculate the scaling factor, then applies this to determine the polyp size. This feedback loop ensures accurate measurement without requiring manual alignment by the operator.
Solution Approach 2:
The patent replaces the manual mechanical alignment process with an automated image processing system. Instead of requiring the operator to physically align forceps with the polyp and manually measure, the system uses computer vision to automatically detect the forceps, calculate the scaling relationship, and determine the polyp size from the captured image, eliminating mechanical alignment requirements.
3Measurement precision
If multiple images are captured to improve measurement accuracy, then the measurement precision increases, but the time consumption and processing complexity increase
Solution Approach 1:
The system performs preliminary action by automatically detecting and identifying the forceps in the captured image before proceeding to measure the polyp. The processor first locates the forceps, calculates the scaling factor based on the forceps' known dimensions, and then uses this pre-calculated scale to immediately determine the polyp size from the same image, eliminating the need for separate measurement steps or multiple images.
Data Source
AI summary
A method and apparatus for estimating or measuring a physical area or physical volume of an object of interest in one or more images captured using an endoscope are disclosed. According to the present method, an object of interest in an image or images is determined. Also, distance information associated with the object of interest with respect to an image sensor of the endoscope is received. The physical area size or physical volume size of the object of interest is then determined based on the image or images, and the distance information.