Endoscope System Real-Time Boundary Superimposition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
During endoscopic submucosal dissection (ESD), accurately determining the boundary between abnormal and normal regions in real-time is challenging due to changing imaging conditions and the need for high-magnification observation, which complicates the identification of lesion boundaries.
Innovation Solution
A medical image processing device that acquires both reference images with defined boundary lines and real-time captured images, detects landmarks, calculates the match ratio between them, and generates a superimposition image to accurately display the boundary line in real-time, allowing for precise identification of abnormal regions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If real-time image processing is performed to display boundary lines, then the boundary line recognition speed is improved, but the accuracy of boundary line determination deteriorates due to changing imaging conditions
Solution Approach 1:
The system performs preliminary actions by capturing a reference image before the ESD procedure and determining the boundary line in advance when imaging conditions are stable. This pre-determined boundary line information is then superimposed on real-time captured images, allowing fast display without requiring real-time re-determination of the boundary, thus resolving the contradiction between speed and accuracy.
Solution Approach 2:
The system creates a copy of the reference image with the pre-determined boundary line and superimposes it on the real-time captured image. This copying approach allows the accurate boundary line information from the reference image to be transferred to the real-time view without requiring re-processing, maintaining accuracy while enabling real-time display speed.
2Measurement precision
If high-magnification observation is performed to identify lesion boundaries, then the boundary line determination accuracy is improved, but the overview of the entire lesion is lost
Solution Approach 1:
The system transitions between different magnification dimensions by capturing a reference image at high magnification for accurate boundary determination, then superimposing that boundary information onto a lower-magnification real-time image. This allows the operator to view the entire lesion area at low magnification while the accurate high-magnification boundary line is overlaid, resolving the contradiction between overview area and boundary accuracy.
3Measurement precision
If boundary lines are determined for each frame in real-time, then the real-time accuracy is improved, but the device complexity increases
Solution Approach 1:
The system performs the complex boundary line determination action in advance during reference image processing, before the ESD procedure begins. This pre-computed boundary information is then simply superimposed on real-time images without requiring complex real-time processing, reducing device complexity while maintaining real-time accuracy through the use of pre-determined boundary data.
Data Source
AI summary
A medical image processing device a reference image that is a medical image with which boundary line information related to a boundary line that is a boundary between an abnormal region and a normal region and landmark information related to a landmark that is a characteristic structure of the subject are associated and a captured image that is the medical image captured in real time, detects the landmark from the captured image, calculates a ratio of match between the landmark included in the reference image and the landmark included in the captured image, estimates a correspondence relationship between the reference image and the captured image on the basis of the ratio of match and information regarding the landmarks included in the reference image and the captured image, and generates a superimposition image in which the boundary line associated with the reference image is superimposed on the captured image on the basis of the correspondence relationship.