Plaque Burden Imaging From Tomographic Frames for Stent Positioning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing diagnostic imaging technologies for vascular treatment, such as percutaneous coronary intervention (PCI), struggle with inaccurate rule-based extraction of plaque regions from three-dimensional CT data, failing to reliably calculate stenosis rates, especially when transitioning to two-dimensional data.

Innovation Solution

An information processing device and method that utilizes a machine learning model, like a convolutional neural network (CNN), to calculate plaque burden from transverse tomographic images of blood vessels, displaying plaque burden along the axial direction with a gradation bar and determining optimal stent indwelling positions based on calculated plaque distribution.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If rule-based extraction of plaque region from three-dimensional CT data is used, then the processing method is simple, but the extraction accuracy is low

Engineering Contradiction:

Improveprocessing simplicityVSAvoidplaque region extraction accuracy

Core Design Contradiction:

Ease of manufactureVSMeasurement precision

Solution Approach 1:

The patent replaces the mechanical rule-based extraction system with a machine learning-based automated system. The learning model automatically identifies and extracts plaque regions from tomographic images without requiring manual rule设定, thereby improving extraction accuracy while maintaining processing efficiency through automation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The learning model performs self-learning from training data and automatically optimizes its extraction capabilities. The system improves its plaque region extraction accuracy through continuous learning from labeled data, eliminating the need for manual rule adjustments and achieving high-precision extraction autonomously.

Inventive Principle:

Principle #25Self-service

2Reliability

If three-dimensional CT data is used for stenosis rate calculation, then comprehensive vascular information is obtained, but the method cannot be applied to two-dimensional data

Engineering Contradiction:

Improvevascular information completenessVSAvoiddata type applicability

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent develops a learning model that can process both two-dimensional and three-dimensional tomographic image data. The model is trained on diverse data types and can adaptively process different input formats, enabling the same system to handle various data dimensions and provide consistent plaque burden calculation across different imaging modalities.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system adjusts its processing parameters based on the input data type. When receiving two-dimensional or three-dimensional data, the model automatically adapts its feature extraction and calculation parameters to appropriately process the specific data dimension, maintaining accurate plaque burden assessment across different data types.

Inventive Principle:

Principle #35Parameter changes

3Productivity

If plaque burden calculation is performed for each frame independently, then processing speed is maintained, but the overall assessment accuracy may be compromised

Engineering Contradiction:

Improveprocessing speedVSAvoidplaque burden calculation accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent segments the vascular imaging data into multiple frames and processes each frame independently through the learning model. This segmentation approach enables parallel processing of individual frames, maintaining high processing speed while the cumulative results from all frames provide comprehensive and accurate overall plaque burden assessment.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system continuously processes each frame through the learning model in sequence, maintaining uninterrupted analysis throughout the entire dataset. This continuous processing ensures that no valuable information is lost while maintaining efficient throughput, achieving both speed and accuracy in plaque burden calculation.

Inventive Principle:

Principle #20Continuity of useful action

Data Source

PatentUS12620089B2Information processing device, information processing method, and program

Publication Date: 2026.05.05 TERUMO KK

AI summary

An information processing device, an information processing method, and a non-transitory computer-readable medium are disclosed. The information processing device includes a processor configured to acquire transverse tomographic images of a plurality of frames obtained by imaging a blood vessel of a patient, and calculate plaque burden in each of the frames by inputting the acquired transverse tomographic image of each of the frames to a model that has learned to calculate plaque burden in response to the transverse tomographic image inputted, and a display unit configured to display a longitudinal tomographic image based on the transverse tomographic images of the plurality of frames and a first object that is an object displayed in correlation with the longitudinal tomographic image and represents magnitude of the plaque burden at each position of the longitudinal tomographic images along an axial direction of the blood vessel.