Endoscope Oxygen Saturation Calculation via ROI Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing endoscope systems face challenges in accurately calculating oxygen saturation due to issues like halation and the presence of residues or residual liquids, leading to unreliable and time-consuming data correction processes.
Innovation Solution
An endoscope system that sets multiple regions of interest in an image, determines the feasibility of data correction for each region, and corrects the oxygen saturation calculation table using regions where correction is possible, employing a processor to automate this process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If data correction is performed using the entire image, then the oxygen saturation calculation becomes more accurate, but the correction process becomes time-consuming and complex
Solution Approach 1:
The image is divided into multiple regions of interest (ROIs), and correction processing is performed independently for each ROI. This segmentation allows the system to process only relevant areas rather than the entire image, reducing overall processing time while maintaining accuracy in each segmented region.
Solution Approach 2:
Different correction methods and parameters are applied to different regions based on their specific characteristics. The system determines correction feasibility individually for each ROI and applies appropriate correction only where needed, optimizing both accuracy and processing efficiency by treating each region according to its local quality requirements.
2Measurement precision
If data correction is performed using the entire image, then the oxygen saturation calculation becomes more accurate, but the system complexity increases
Solution Approach 1:
By dividing the image into multiple manageable ROIs, the system reduces the complexity of processing the entire image at once. Each ROI can be processed independently with simpler algorithms, making the overall system more manageable and easier to implement while achieving accurate correction through the combination of regional results.
Solution Approach 2:
The system applies correction processing selectively to regions where it is feasible and beneficial, rather than uniformly across the entire image. This approach reduces system complexity by avoiding unnecessary processing in regions where correction is not possible or needed, while maintaining high accuracy in regions where correction is applied.
3Reliability
If multiple regions of interest are processed for correction, then the reliability of oxygen saturation data improves, but the processing time increases
Solution Approach 1:
The system performs preliminary determination processing for each ROI to assess correction feasibility before actually performing the correction. This preliminary action allows the system to identify and process only those regions where correction is likely to succeed, improving overall reliability while avoiding wasted time on regions where correction is not feasible.
Solution Approach 2:
The system processes multiple ROIs in parallel or selectively rather than waiting to process all regions. By performing partial processing on feasible regions while potentially skipping infeasible ones, the system achieves sufficient reliability for clinical use without incurring the full time cost of exhaustive processing of all regions.
Data Source
AI summary
The endoscope system that calculates the oxygen saturation acquires an image obtained by imaging an observation target, sets a plurality of regions of interest in the image, performs determination processing of determining, with respect to each of the plurality of regions of interest, whether or not correction of data using the region of interest is possible, and corrects the data using the region of interest for which it is determined that the correction of the data is possible.