Lower Gastrointestinal Endoscope Steering with AI Image Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Endoscopic procedures for capturing images of the lower gastrointestinal tract are challenging due to the reliance on manual manipulation, which is skill-dependent and prone to inaccuracies, making it difficult to obtain precise images of curved body parts.
Innovation Solution
An endoscopic device controlled by an AI neural network that acquires images, detects body parts, calculates relative position and pose information, and generates control signals to steer the endoscope's front-end portion for accurate image capture.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual manipulation by a medical specialist is used to adjust the endoscope, then the endoscope can be positioned and oriented, but the precision and accuracy of image acquisition deteriorates due to skill dependency and unnecessary motion
Solution Approach 1:
The endoscope system performs self-positioning and self-orientation by automatically detecting body parts in captured images and calculating required adjustment angles, eliminating the need for manual manipulation by medical specialists
Solution Approach 2:
The patent replaces manual mechanical manipulation with an automated control system that uses image processing algorithms and computational geometry to determine endoscope positioning and orientation adjustments
2Manufacturing precision
If manual manipulation is used to adjust the front end of the endoscope, then the scope can be steered, but the accuracy of positioning and angling deteriorates making it difficult to acquire images of curved body parts
Solution Approach 1:
The system continuously captures images, detects body part positions, calculates positioning errors, and generates corrective control signals to adjust the endoscope's front end position and orientation, forming a closed-loop feedback control system
Solution Approach 2:
The patent introduces an automated control unit as an intermediary between the image capture system and the endoscope actuation system, which processes visual information and translates it into precise mechanical adjustments
3Measurement precision
If AI-based automated control is implemented to steer the endoscope, then image acquisition precision is improved, but device complexity increases
Solution Approach 1:
The automated control unit performs multiple functions including image processing, body part detection, position calculation, and control signal generation, consolidating these capabilities into a single multi-functional system
Data Source
AI summary
Provided are a medical image device and an automated control technique, particularly, an endoscopic device for capturing an image of a lower gastrointestinal tract using an endoscope and a method of controlling the endoscopic device. The method of controlling an endoscopic device includes acquiring an image of a lower gastrointestinal tract from an image sensor, acquiring environment information with respect to a front-end portion of the endoscopic device, detecting at least one first body part from the image, based on a pre-trained model, calculating relative position information between the at least one first body part and the front-end portion of the endoscopic device, generating, based on the environment information and the relative position information, a first control signal for steering the front-end portion to correspond to the at least one first body part, and transmitting the first control signal to a driver.