Endoscope Lens Washing Control for AI-Guided Tool Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Endoscope lens contamination or fogging during medical procedures reduces visibility, necessitating manual intervention for cleaning, which disrupts autonomous control and can lead to inaccurate image recognition.
Innovation Solution
An autonomous medical system using AI to detect treatment tools from endoscopic images, determining a confidence level for recognition accuracy, and autonomously executing water supply to clean the lens when recognition falls below a threshold.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual cleaning intervention is performed when lens contamination is detected, then visibility is restored, but autonomous control is disrupted and operation time is lost
Solution Approach 1:
The system automatically detects lens contamination through AI-based image analysis and triggers water supply cleaning without operator intervention. The processor continuously monitors endoscopic images, detects contamination patterns, and autonomously activates the water supply device to clean the objective lens, enabling the system to service itself during operation.
Solution Approach 2:
The system implements a closed-loop feedback mechanism where the processor continuously analyzes endoscopic images for contamination, compares detected patterns against threshold values, and automatically adjusts water supply activation. This real-time feedback loop ensures timely cleaning responses while maintaining autonomous operation without disrupting the overall procedure.
2Extent of automation
If AI-based automatic contamination detection is implemented, then manual intervention is reduced, but system complexity increases
Solution Approach 1:
The existing image processing pipeline is extended to serve dual purposes: maintaining autonomous navigation/control functions and detecting lens contamination. The processor leverages the same endoscopic image input and AI model infrastructure for both primary navigation tasks and contamination detection, eliminating the need for separate dedicated detection hardware and reducing overall system complexity.
Solution Approach 2:
The contamination detection functionality is merged with the existing autonomous control system rather than being implemented as a separate subsystem. The AI model processes endoscopic images for both navigation guidance and contamination identification, and the water supply control is integrated into the same processor that handles autonomous manipulation, consolidating multiple functions into unified system architecture.
Data Source
AI summary
A medical system includes an endoscope configured to be electrically driven to move and to capture an endoscopic image, a treatment tool configured to be electrically driven to move, a processor configured to perform autonomous control of electrically-driven motions of the endoscope and the treatment tool and to control a water supply motion, and a memory configured to store a trained model trained so as to detect the treatment tool from the endoscopic image showing the treatment tool. The processor inputs the endoscopic image to the trained model to allow the trained model to detect the treatment tool from the endoscopic image, and acquires, from the trained model, a confidence level as to whether a detected target is the treatment tool. When the confidence level is equal to or smaller than a predetermined threshold, the processor executes the water supply motion of washing an objective lens of the endoscope.