Catheter Image Classification Using Instrument Position Data

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing catheter systems struggle to quickly and accurately understand images acquired from complex anatomical structures, such as the intracardiac region, making it difficult to perform precise medical interventions.

Innovation Solution

An information processing device that includes an image acquisition unit, position information acquisition unit, and a trained model to classify regions in catheter images, enabling accurate identification of biological tissue, medical instrument, and non-biological tissue regions, and outputting data for enhanced image understanding.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If an image acquisition catheter is used to capture images from complex anatomical structures, then image data can be obtained, but it becomes difficult to quickly understand and interpret the images

Engineering Contradiction:

Improveimage understandingVSAvoidimage interpretation complexity

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

A trained classification model serves as an intermediary between the raw catheter image and the medical practitioner. The model automatically classifies each pixel into categories (biological tissue, non-biological tissue, medical instrument), transforming complex image data into structured, interpretable information that assists rapid understanding without requiring complex manual interpretation

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The manual interpretation process is replaced by an automated machine learning system. Instead of relying on medical practitioners to manually analyze complex catheter images, a trained classification model performs the analysis automatically, substituting mechanical human interpretation with computational processing

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If manual analysis of catheter images is performed, then detailed examination is possible, but it takes too much time for real-time intervention

Engineering Contradiction:

Improveimage analysis speedVSAvoidregion identification accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

Manual image analysis is replaced by an automated trained classification model that processes catheter images rapidly. The model achieves both high speed (enabling real-time intervention) and high precision (accurate region identification) by using machine learning algorithms to automatically classify pixels without manual intervention

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-service by automatically classifying regions in catheter images without requiring manual analysis. The trained model independently processes images, identifies biological tissue, non-biological tissue, and medical instrument regions, and provides results that assist real-time decision-making

Inventive Principle:

Principle #25Self-service

3Measurement precision

If detailed classification of image regions is performed, then accurate understanding is achieved, but the processing complexity increases

Engineering Contradiction:

Improveregion classification accuracyVSAvoidprocessing system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The image processing task is segmented into distinct classification categories (biological tissue region, non-biological tissue region, medical instrument region). This segmentation allows the system to achieve detailed and accurate region classification by breaking down the complex analysis into manageable classification tasks, each handled by the trained model

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS12567144B2Information processing device, information processing method, and program

Publication Date: 2026.03.03 TERUMO KK

AI summary

An information processing device that assists understanding of an image acquired by an image acquisition catheter. The information processing device includes: an image acquisition unit that acquires a catheter image including an inner cavity obtained by an image acquisition catheter; a position information acquisition unit that acquires position information regarding a position of a medical instrument inserted into the inner cavity included in the catheter image; and a first data output unit that inputs the acquired catheter image and the acquired position information to a first trained model that, upon receiving input of the catheter image and the position information, outputs first data in which each region of the catheter image is classified into at least three of a biological tissue region, a medical instrument region where the medical instrument exists, and a non-biological tissue region, and outputs the first data.