Catheter Medical Image Defect Diagnosis by Generation Time Point

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing medical diagnostic imaging systems struggle with accurately detecting and addressing image defects caused by apparatus failures or improper use, leading to suboptimal diagnostic outcomes.

Innovation Solution

A non-transitory computer-readable program and information processing apparatus that utilize machine learning models, such as convolutional neural networks, to analyze medical images generated by catheters for intravascular examinations, estimating the presence and cause of image defects and providing countermeasures for removal.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If pattern matching with typical images is used to detect abnormalities, then the detection process is simple, but the detection accuracy is not necessarily accurate

Engineering Contradiction:

Improvedetection process complexityVSAvoidabnormality detection accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent transforms the detection approach from simple pattern matching to a comprehensive analysis that incorporates multiple parameters including generation time point information, image quality metrics, and defect characteristics. This parameter expansion enables more accurate abnormality detection while maintaining systematic processing.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent introduces an information processing apparatus as an intermediary between the medical imaging apparatus and the user. This intermediary performs automated image defect detection and cause estimation, bridging the gap between simple pattern matching and accurate diagnostic interpretation.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If automated image defect detection is implemented, then diagnostic accuracy is improved, but system complexity increases

Engineering Contradiction:

Improvediagnostic accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The information processing apparatus performs self-service by automatically detecting image defects and estimating their causes without requiring manual intervention. The system uses machine learning models trained on defect data to autonomously identify and characterize abnormalities, reducing the need for complex manual analysis protocols.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent implements preliminary action by pre-training machine learning models with defect data before actual diagnostic use. The system prepares detection algorithms and cause-estimation models in advance, so that during actual operation, the complex analysis is already optimized and ready to execute efficiently on incoming images.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12475554B2Removing an image defect occuring in a medical image before examination based on the generation time point

Publication Date: 2025.11.18 TERUMO KK

AI summary

A non-transitory computer-readable medium storing computer program code executed by a computer processor that executes an imaging process comprising: acquiring a medical image generated based on a signal detected by a catheter insertable into a body lumen; estimating a cause of an image defect by inputting the acquired medical image to a model learned to output the cause of the image defect when the medical image in which the image defect occurs is input; and outputting introduction information for introducing a countermeasure for removing the estimated cause of the image defect.