Clinical Image Relevance Detection via Hierarchical Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current image detection systems in navigation and computer-assisted surgery systems often provide updates based on the presence of new images, even if the content has not changed clinically relevantly, leading to unnecessary recalculations and delays.
Innovation Solution
A method and device that automatically detect clinical relevance by comparing images for local and global differences, using image blocks and dynamic thresholds to distinguish between significant and insignificant changes, ensuring only clinically relevant updates are processed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If image detection systems provide updates based on the presence of new images, then the system ensures all new images are processed, but unnecessary recalculations and delays occur when content has not changed clinically relevantly
Solution Approach 1:
The patent segments the image comparison process into multiple levels: first comparing global image characteristics (overall intensity, contrast, exposure), then locally comparing only specific regions of interest (anatomical structures, surgical sites). This hierarchical segmentation allows the system to quickly eliminate images that differ only globally without performing full detailed comparisons, thereby reducing unnecessary processing delays while maintaining reliable detection of clinically relevant changes.
2Loss of information
If the system processes all new images, then complete image data is provided, but computational resources are wasted on images without clinical relevance
Solution Approach 1:
The patent applies preliminary action by performing a quick global comparison of incoming images against reference images before committing to full processing. The system first checks overall image characteristics such as intensity distribution, contrast levels, and exposure parameters. Only images that show significant global differences proceed to detailed local comparison, while images with minor global variations are filtered out early. This preliminary filtering action prevents wasteful computation on clinically irrelevant images while ensuring that potentially important images receive complete processing.
3Measurement precision
If the system performs detailed local comparison of all images, then clinically relevant changes are detected, but processing speed decreases
Solution Approach 1:
The patent implements local quality by directing detailed local comparison operations only to specific regions of interest within images that have already been identified as potentially relevant through global comparison. Rather than uniformly processing all images with the same level of detail, the system applies different processing qualities: full detailed analysis only to images showing significant global differences, and simplified or skipped analysis to images with minor variations. This selective application of processing quality maintains high detection precision for clinically relevant changes while improving overall processing speed.
Data Source
Figure 1~2
Figure 3
Figure 4a~4b
AI summary
Disclosed herein are systems and methods for automatic detection of clinical relevance of images of an anatomical situation. The method includes comparing a first image and a second image and determining whether a difference between the first and second images is at least one of a local type difference and a global type difference. The local type difference is a local difference of the first image and the second image and the global type difference is a global difference between the first image and the second image. The second image is determined as having a clinical relevance if it is determined that the difference between the first image and the second image comprises a local type difference.