Artery Width Detection Using Kernel-Based Ultrasound Pattern Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for determining the diameter of an artery from ultrasound measurements require manual analysis by a professional operator, making them time-consuming and resource-intensive.

Innovation Solution

An automated method using a machine learning model to analyze time sequences of ultrasound data, identifying a region of interest within the data using kernels that represent the pattern of an artery, and determining the cross-sectional width of the artery based on this analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual analysis by a professional operator is used to determine artery diameter from ultrasound measurements, then measurement precision is improved, but productivity deteriorates (time-consuming and resource-intensive)

Engineering Contradiction:
Improveartery diameter measurement accuracyVSAvoidanalysis speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The system performs automated self-analysis of ultrasound data using machine learning models and kernel-based pattern recognition, eliminating the need for manual operator intervention. The algorithm automatically identifies artery structures, determines cross-sectional width, and generates measurements independently, thereby resolving the contradiction between maintaining measurement precision and improving productivity.

Inventive Principle:
Principle #25Self-service

2Measurement precision

If full ultrasound data is processed to determine artery diameter, then measurement precision is improved, but use of energy deteriorates (high processing resource requirements)

Engineering Contradiction:
Improvediameter determination accuracyVSAvoidprocessing resource consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system extracts only the relevant region of interest containing the artery from the full ultrasound dataset using kernel-based pattern recognition. By identifying and isolating the specific arterial structure through characteristic wall-lumen-wall patterns, the system processes only the necessary portion of the data, thereby maintaining measurement precision while significantly reducing energy consumption and processing resource requirements.

Inventive Principle:
Principle #2Taking out (Extraction)

3Productivity

If automated determination is implemented, then productivity is improved, but device complexity deteriorates (requires machine learning models and processing resources)

Engineering Contradiction:
Improveautomated analysis capabilityVSAvoidprocessing system complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system employs lightweight, computationally efficient kernel-based algorithms that can be implemented in resource-constrained wearable devices. Instead of requiring complex deep learning models, the invention uses simplified pattern recognition approaches with pre-defined kernels that represent arterial wall-lumen-wall structures, enabling automated determination with minimal processing power and memory requirements.

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The method enables accurate and efficient determination of the cross-sectional width of an artery with low processing resource requirements, allowing for potential implementation in wearable devices for real-time monitoring.

Implementation Method 1

receiving a time sequence of sets of ultrasound data, each set representing reflection of ultrasound along a line extending through tissue including the artery

Methodology Applied
Scientific EffectUltrasound reflection: Reflection

Data Source

PatentEP4537765A1A method, a computer program product, and a device for determining a cross-sectional width of an artery
Publication Date: 2025.04.16 STICHTING IMEC NEDERLAND
  • EP4537765A1 patent drawingFigure 1
  • EP4537765A1 patent drawingFigure 2~3
  • EP4537765A1 patent drawingFigure 4~5

AI summary

A method for determining a cross-sectional width of an artery comprises: receiving (202) a time sequence of sets of ultrasound data, each set representing reflection of ultrasound along a line extending through tissue including the artery at a single point in time in the time sequence; and for each set of ultrasound data: determining (204), using a machine learning model (300), a region of interest within the ultrasound data, wherein the region of interest is determined using one or more kernels being compared to the ultrasound data, wherein each kernel represents a first wall portion at a first side of a cross-section of the artery, a second wall portion at a second side of the cross-section of the artery, and a lumen in-between; and determining (206) the cross-sectional width of the artery based on analysis of the region of interest of the ultrasound data.