Endoscopic Lesion Measurement with Pre-Trained Image Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Endoscopic devices struggle with accurate lesion size measurement due to user skill level and fatigue, leading to inconsistent and inaccurate lesion detection and treatment response.

Innovation Solution

An endoscopic device equipped with a pre-trained model to identify lesions and calculate size information using image analysis and distance measurement, automatically tracking the lesion within the field of view.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a user manually measures lesion size with the naked eye, then the measurement process is simple and quick, but the measurement accuracy is low

Engineering Contradiction:
Improvelesion size measurement accuracyVSAvoidmeasurement system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces manual visual measurement with an automated image processing system that uses algorithms to detect lesions and calculate their sizes from endoscopic images, substituting human visual estimation with computational analysis to improve measurement accuracy

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an image processing algorithm as an intermediary between the endoscopic image and the final measurement result, using computational methods to bridge the gap between visual data and accurate size determination

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If a user simultaneously manipulates the scope and performs medical operation, then the operational efficiency is maintained, but the user may miss lesions due to dispersed concentration

Engineering Contradiction:
Improvelesion detection reliabilityVSAvoidoperational efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent implements a feedback mechanism where the image processing system continuously analyzes the endoscopic video stream, detects lesions, and provides real-time alerts to the operator, creating a closed-loop system that enhances detection reliability without requiring the user to divide attention

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent enables the system to automatically perform lesion detection and size measurement functions that would otherwise require manual user attention, allowing the device to serve itself in monitoring for abnormalities while the user focuses on manipulation and treatment

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4607471A1Endoscopic device and method for obtaining lesion size information
Publication Date: 2025.08.27 MEDINTECH INC
  • EP4607471A1 patent drawingFigure 1
  • EP4607471A1 patent drawingFigure 2
  • EP4607471A1 patent drawingFigure 3

AI summary

Provided are an endoscopic device for identifying a lesion based on a pre-trained model and determining size information on the identified lesion, and a method of obtaining size information on a lesion. The method of obtaining size information on a lesion includes obtaining an image inside a body from an image sensor, identifying at least one lesion from the image based on a pre-trained model, and determining size information on the lesion.