Dynamic Extraction Range for Endoscope Image Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In endoscope systems, existing technologies face challenges in efficiently extracting and prioritizing images of interest, such as bleeding sites, from captured data, leading to potential missed diagnoses due to inadequate image processing and reference value management.
Innovation Solution
An image processing device and method that calculates an evaluation value for captured images, determines if it falls within a specific extraction range, extracts images of interest, and updates the extraction range based on the evaluation value, ensuring that critical images are identified and notified to medical practitioners promptly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a fixed extraction range is used to identify images of interest, then the extraction process is simple and fast, but it cannot adapt to new types of lesions or varying diagnostic standards, leading to missed diagnoses
Solution Approach 1:
The extraction range is transformed from a static fixed value to a dynamic range with upper and lower bounds. The processor dynamically adjusts the extraction range based on evaluated importance values, allowing the system to adapt to different lesion types and diagnostic requirements while maintaining efficient processing through automated range management
Solution Approach 2:
The system automatically updates the extraction range based on evaluated images without requiring manual reconfiguration. By using the evaluated importance values from processed images to automatically adjust the extraction range boundaries, the system serves itself in adapting to new diagnostic standards and lesion types
2Reliability
If all captured images are reviewed to ensure no critical information is missed, then diagnostic accuracy is maximized, but the time required for image review increases significantly
Solution Approach 1:
The system extracts only the most important images from the large set of captured images by evaluating their importance values and comparing them against the extraction range. This selective extraction approach ensures that critical diagnostic information is identified while significantly reducing the number of images that require detailed medical review
Solution Approach 2:
The system uses feedback from evaluated images to continuously refine the extraction range. By analyzing the importance values of processed images and automatically updating the extraction range boundaries, the system improves its ability to identify critical images over time, maintaining high diagnostic accuracy with efficient processing
3Adaptability or versatility
If the extraction range is updated frequently to capture new lesion types, then the system remains current with diagnostic standards, but the processing overhead and computational load increase
Solution Approach 1:
The extraction range is updated periodically based on evaluated images rather than continuously for every image. The processor determines whether to update the extraction range by comparing evaluated importance values against current boundaries, performing updates only when necessary to maintain currency with diagnostic standards while preserving processing efficiency
Data Source
AI summary
An image processing device includes: a processor comprising hardware, the processor being configured to calculate an evaluation value of a captured image that is obtained by capturing a subject, determine whether or not the evaluation value is included in a specific extraction range recorded in a memory, extract the captured image as an image of interest including a lesion when the processor has determined that the evaluation value is included in the specific extraction range, and update the specific extraction range based on the evaluation value.