Endoscopy Support Device with AI Lesion Boundary Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing endoscopic examination systems lack the capability to accurately identify the boundary area of a lesion, which is crucial for determining the depth of the lesion or performing a biopsy.

Innovation Solution

An endoscopy support device that superimposes a lesion guide on endoscopic images, segments the lesion region using a segmentation model, and outputs the boundary area for clear identification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a doctor manually identifies lesion boundaries in endoscopic images, then the process is simple and direct, but the precision and accuracy of boundary identification deteriorates

Engineering Contradiction:
Improvelesion boundary identification precisionVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces an AI model as an intermediary between the endoscopic image and the doctor's diagnosis. The AI model processes the image data and generates lesion boundary information, which then assists the doctor in making accurate diagnoses. This intermediary resolves the contradiction by providing precise measurement capabilities without requiring the doctor to manually perform complex boundary identification tasks.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the manual mechanical process of boundary identification with an automated AI-based image processing system. The AI model automatically detects and segments lesion regions from endoscopic images, substituting the doctor's manual visual inspection and manual boundary drawing with an automated computational process that provides higher precision and consistency.

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

2Adaptability or versatility

If no lesion boundary identification function is provided, then the system remains simple, but the capability to determine lesion depth and guide biopsy deteriorates

Engineering Contradiction:
Improvelesion analysis capabilityVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent performs preliminary action by automatically identifying and marking lesion boundaries before the doctor makes diagnostic decisions. The AI model pre-processes the endoscopic images to highlight potential lesion areas and their boundaries, preparing the information in advance so that the doctor can efficiently determine lesion depth and plan biopsy procedures without having to manually search for boundaries.

Inventive Principle:
Principle #10Preliminary action

3Productivity

If manual lesion boundary identification is used, then the system is easy to operate, but the time required for diagnosis and biopsy planning increases

Engineering Contradiction:
Improvediagnosis efficiencyVSAvoidtime for lesion boundary identification
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent replaces the time-consuming manual process of lesion boundary identification with an automated AI-based image processing system. The AI model rapidly analyzes endoscopic images and generates boundary information, significantly reducing the time required compared to manual visual inspection and manual boundary drawing, thereby improving diagnosis efficiency without sacrificing accuracy.

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

Data Source

PatentUS20250281022A1Endoscopy support device, endoscopy support method, and recording medium
Publication Date: 2025.09.11 NEC CORP
  • US20250281022A1 patent drawing
  • US20250281022A1 patent drawing
  • US20250281022A1 patent drawing

AI summary

In an endoscopy support device, a display control means superimposes and displays a lesion guide for specifying a lesion in an endoscopic image. An acquisition means acquires the endoscopic image. An analysis means segments a lesion region from the endoscopic image based on the endoscopic image and the lesion guide. An output means outputs the lesion region segmented. The endoscopy support device can support decision making by a user in the field of healthcare.