Endoscope Image Guidance Using Papilla Depth Map and Summit Line
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing endoscopic procedures for bile duct treatments, such as endoscopic sphincterotomy (EST), face challenges in accurately determining the direction of the bile duct path due to the limitations of two-dimensional endoscope images, which can lead to complications like arterial damage or retroperitoneal perforation.
Innovation Solution
A processing system that estimates a depth map from endoscope images to identify the summit line of the duodenal papilla, superimposing a guide display on the image to direct the incision along the bile duct path, using machine learning to enhance accuracy without requiring a three-dimensional imaging device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If endoscopic sphincterotomy is performed without accurate guidance, then the procedure can be completed, but the risk of complications such as arterial damage or retroperitoneal perforation increases
Solution Approach 1:
The patent introduces an intermediary guidance system consisting of a guide wire and visual display apparatus that mediates between the endoscope and the duodenal papilla. The guide wire provides physical guidance along the bile duct direction, while the visual display provides optical guidance showing the summit line and incision direction, thereby reducing the risk of complications without compromising procedural completion
Solution Approach 2:
The patent replaces reliance on purely mechanical operator skill and manual manipulation with an automated image processing and display system. The system automatically acquires endoscopic images, processes them to extract the summit line and incision direction, and displays this information to guide the procedure, thereby improving safety through objective, consistent guidance rather than subjective operator judgment
2Manufacturing precision
If traditional endoscopic methods are used for incision guidance, then the device complexity remains low, but the manufacturing precision and measurement precision of incision direction are insufficient
Solution Approach 1:
The patent creates a visual copy or representation of the three-dimensional duodenal papilla structure by processing endoscopic images to generate a displayed summit line and incision direction indicators. This virtual model is superimposed on the live endoscopic view, providing precise guidance without requiring complex physical measurement devices or direct three-dimensional imaging hardware
Solution Approach 2:
The patent transforms the endoscopic image data by extracting depth information and calculating the summit line position and incision direction as new parameters. By changing from raw image data to processed geometric parameters (summit line coordinates, angle of incision), the system achieves high precision guidance while using relatively simple image processing algorithms
Data Source
AI summary
A processing system includes a processor including hardware. The processor acquires an endoscope image in which a duodenal papilla including an oral protrusion is imaged, estimates a depth map of a region including the duodenal papilla from the endoscope image, estimates a summit line of the oral protrusion from the estimated depth map, and performs display processing so as to superimpose a guide display based on the estimated summit line on the endoscope image.