Endoscope Image Processing for Phantom Model Navigation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Medical personnel face challenges in accurately navigating endoscopes during procedures due to similarities in human cavity structures, leading to potential mistakes and inconsistent training, especially when using phantom models for training.

Innovation Solution

An image processing device that connects to the endoscope's image capturing device, continuously processes images to determine if a predetermined reference position has been reached, allowing for accurate estimation and updating of the endoscope's location within a phantom model, which can include visual markers and machine learning architectures for robust recognition.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If medical personnel rely on training and experience to navigate the endoscope through the human cavity, then they can perform endoscopic procedures, but it is difficult to determine the location of the endoscope due to similar appearance of cavity parts

Engineering Contradiction:
Improvelocation determination accuracyVSAvoidnavigation difficulty
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent introduces a location determination device as an intermediary system that includes a database of reference images and processing units. This mediator compares real-time endoscope images with stored reference images to automatically determine and display the current location within the cavity, eliminating the need for medical personnel to manually judge location based on visual inspection alone.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system provides continuous feedback by displaying the determined location on the screen alongside the real-time images. This feedback loop allows medical personnel to immediately see where the endoscope is positioned, enabling them to adjust navigation accordingly and ensuring complete examination of all required areas.

Inventive Principle:
Principle #23Feedback

2Reliability

If medical personnel use phantom models for training, then they can practice endoscope navigation, but the training is inconsistent and insufficient due to reliance on best practice of experienced persons

Engineering Contradiction:
Improvetraining consistencyVSAvoidtraining system simplicity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent creates a virtual copy of the human cavity using a database of reference images that represents the anatomical structure. During training with phantom models, the location determination device processes images from the training endoscope and compares them against this virtual model, providing automated location feedback that ensures consistent and accurate training without relying on individual instructor expertise.

Inventive Principle:
Principle #26Copying

3Measurement precision

If navigation systems are provided to aid medical personnel, then location determination is improved, but the systems require additional training for correct use

Engineering Contradiction:
Improvelocation determination accuracyVSAvoidadditional training time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The location determination device is designed to automatically perform location determination without requiring manual intervention or complex operation by the medical personnel. The system autonomously processes images, compares them with the database, and displays results, making the technology self-sufficient and minimizing the learning curve for users.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4191565A1Endoscope image processing device
Publication Date: 2023.06.07 AMBU AS
  • EP4191565A1 patent drawingFigure 1a~1b
  • EP4191565A1 patent drawingFigure 2
  • EP4191565A1 patent drawingFigure 3~4

AI summary

Disclosed is an image processing device for determining the location of an endoscope in a phantom model. The phantom model is a physical model of a cavity of a human body. The image processing device comprises a processing unit operationally connectable to an image capturing device of an endoscope. The image processing device is configured to obtain a stream of images from the image capturing device of the endoscope. The image processing device is further configured to continuously process images of the stream of images to determine if a predetermined reference position has been reached. The image processing device is further configured to, in response to determining that the predetermined reference position has been reached, updating an estimated location of the endoscope. Further disclosed is a method for determining the location of an endoscope in a phantom model, a display unit connectable to the processing unit, an endoscope system comprising an endoscope and the image processing device, and a computer program product.