Endoscope Image Recognition Gating by Inner-Region Sharpness

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing medical imaging systems struggle with erroneous recognition of feature regions due to low sharpness levels, leading to inaccurate feature recognition in medical images.

Innovation Solution

A medical support device and method that controls image recognition processing based on the sharpness level of inner regions within feature regions, executing recognition and output processing only when the sharpness meets certain threshold criteria, and utilizing a segmentation mask with reduced resolution for enhanced accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If image recognition processing is performed on medical images with low sharpness levels, then productivity is improved by continuous processing, but measurement precision deteriorates leading to erroneous recognition of feature regions

Engineering Contradiction:
Improveimage recognition processing efficiencyVSAvoidsharpness level accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The system performs preliminary sharpness evaluation on the medical image before executing image recognition processing. By assessing the sharpness level of the feature region in advance, the system determines whether the image quality is sufficient for accurate recognition, thereby preventing erroneous results from low-quality images while maintaining efficient processing of suitable images

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements a feedback mechanism where the sharpness evaluation result directly controls the execution of image recognition processing. When the sharpness level meets the threshold, recognition processing is performed and results are output; when the sharpness level is insufficient, the system notifies the user and prevents erroneous recognition, creating a closed-loop quality control system

Inventive Principle:
Principle #23Feedback

2Reliability

If image recognition processing is controlled based on sharpness level thresholds, then reliability is improved by preventing erroneous recognition, but device complexity increases due to additional processing steps

Engineering Contradiction:
Improverecognition accuracyVSAvoidprocessing control complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system segments the medical image into a feature region and other regions, then performs sharpness evaluation specifically on the feature region. This targeted approach allows the system to assess only the critical area for recognition accuracy, reducing unnecessary processing complexity while maintaining high reliability

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system uses a threshold-based parameter change approach where the sharpness level value determines the processing outcome. By comparing the measured sharpness parameter against a predetermined threshold, the system simplifies the control logic into clear decision branches (process or notify), reducing overall system complexity while ensuring reliable operation

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS20260051394A1Medical support device, endoscope system, medical support method, and program
Publication Date: 2026.02.19 FUJIFILM CORP
  • US20260051394A1 patent drawing
  • US20260051394A1 patent drawing
  • US20260051394A1 patent drawing

AI summary

A medical support device includes a processor. A processor is configured to: acquire a medical image obtained by imaging a portion including a feature region; and perform first processing in accordance with a sharpness level of an inner region, which is a region inside an outer edge of the feature region included in the medical image, or second processing in accordance with the sharpness level, in which the first processing is processing of controlling image recognition processing that is executable on the medical image and that recognizes a feature of the feature region, and the second processing is processing of controlling output of information based on a processing result of the image recognition processing.