Intraluminal Image Grouping via Dynamic Neighborhood Range
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current image processing technologies face challenges in efficiently extracting representative images from large groups of intraluminal images acquired by medical observation apparatuses, such as endoscopes, as they struggle to stabilize image capture due to the dynamic nature of the living body and varying image capturing conditions, leading to dispersed abnormal images and increased user burden during diagnosis.
Innovation Solution
An image processing apparatus and method that sets a wider time-series neighborhood range for identifying and grouping identical regions of interest, allowing for the extraction of representative images by merging overlapping neighborhood ranges and adaptively adjusting the range based on abnormal region characteristics, organ types, and display methods to ensure accurate and efficient image grouping.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a narrow time-series neighborhood range is used for grouping images, then the processing speed is fast and the algorithm is simple, but identical abnormal regions may be dispersed into different groups leading to incomplete coverage
Solution Approach 1:
The patent applies dynamics by making the neighborhood range adjustable rather than fixed. The range is dynamically determined based on the interval between continuous images, allowing it to adapt to different imaging conditions and abnormal region characteristics, thus resolving the contradiction between processing speed and grouping accuracy
Solution Approach 2:
The patent changes the parameter of neighborhood range width based on specific conditions. By setting the range wider than the interval between continuous images and adjusting it according to abnormal region characteristics and organ types, the system achieves both efficient processing and reliable grouping
2Reliability
If a wide time-series neighborhood range is used for grouping images, then the coverage of abnormal regions is improved and grouping accuracy is enhanced, but the processing time increases and computational complexity rises
Solution Approach 1:
The patent applies local quality by differentiating the neighborhood range based on local characteristics of abnormal regions and organ types. Different ranges are applied to different regions and organ types, optimizing processing time while maintaining grouping accuracy for each specific case
Solution Approach 2:
The dynamic adjustment of neighborhood range based on imaging conditions and abnormal region characteristics allows the system to use wider ranges only when necessary, thus improving grouping accuracy without consistently incurring high processing costs
3Reliability
If the neighborhood range is set wider than the interval between continuous images, then identical abnormal regions are properly grouped, but the device complexity increases due to adaptive range adjustment mechanisms
Solution Approach 1:
The patent changes the neighborhood range parameter based on detectable characteristics of abnormal regions and organ types. This parameter adaptation improves grouping reliability without requiring fundamentally complex algorithms, as it builds upon existing image analysis capabilities
Solution Approach 2:
The system performs self-service by automatically determining the appropriate neighborhood range based on the characteristics of the images being processed. This eliminates the need for manual configuration and reduces operational complexity while maintaining high grouping reliability
Data Source
AI summary
An image processing apparatus includes: a detecting unit that detects regions of interest that are estimated as an object to be detected, from a group of a series of images acquired by sequentially imaging a lumen of a living body, and to extract images of interest including the regions of interest; a neighborhood range setting unit that sets, as a time-series neighborhood range, a neighborhood range of the images of interest in the group of the series of images arranged in time series so as to be wider than an interval between images that are continuous in time series in the group of the series of images; an image-of-interest group extracting unit that extracts an image-of-interest group including identical regions of interest from the extracted images of interest, based on the time-series neighborhood range; and a representative-image extracting unit that extracts a representative image from the image-of-interest group.