Coronary Flow Assessment Using Trained Classifier on Angiography

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for measuring coronary blood flow-related parameters, such as Coronary Flow Reserve (CFR), are complex and lack robustness, making them unsuitable for clinical practice.

Innovation Solution

An apparatus and method using a trained classifier device to derive quantitative fluid dynamics parameters from a time series of diagnostic images and boundary parameters, allowing for accurate and simple determination of flow-related indices by tracking contrast agent progression through the vasculature.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If direct flow measurement techniques are used to determine coronary blood flow parameters, then measurement accuracy is improved, but device complexity and operational difficulty increase significantly

Engineering Contradiction:

Improveflow measurement accuracyVSAvoidmeasurement technique complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces direct mechanical/physical flow measurement systems with an image processing-based system. A trained classifier device processes standard angiographic images to derive flow parameters indirectly, substituting complex flow measurement hardware with software-based image analysis that leverages contrast agent dynamics visible in routine angiography sequences.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces contrast agent dynamics as an intermediary parameter. Instead of measuring flow directly, the system tracks how contrast agents move through vessels in sequential images, using this intermediate information to infer flow velocity and other hemodynamic parameters through trained classification algorithms.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Device complexity

If indirect derivation of flow parameters from contrast agent dynamics is used, then device complexity is reduced, but measurement accuracy and reliability deteriorate

Engineering Contradiction:

Improvemeasurement technique simplicityVSAvoidflow parameter accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent applies preliminary action through extensive training of the classifier device before actual use. The system is pre-trained on large datasets of angiographic images with known flow parameters, enabling it to accurately predict flow characteristics from routine images without requiring complex real-time measurements during clinical procedures.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system incorporates feedback mechanisms where the classifier device continuously refines its predictions based on the temporal dynamics of contrast agent progression across multiple sequential images. By analyzing how contrast concentration changes over time in different vessel segments, the system feedback-adjusts flow parameter estimates to improve accuracy.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20220175332A1Angiography derived coronary flow

Publication Date: 2022.06.09 KONINKLIJKE PHILIPS NV

AI summary

An apparatus and a method for assessing a vasculature is provided in which a time series of diagnostic images is used in combination with at least one boundary parameter associated with said time series to determine a quantitative fluid dynamics parameter indicative of the fluid flow through the vasculature using a trained classifier. By providing both, the time series of diagnostic images and the at least one boundary parameter to the determination, it is ensured that the classifier is provided with consistent data allowing for a more accurate determination of the quantitative fluid dynamics parameter.