TCD Waveform Categorization via Morphological Variables

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for assessing Transcranial Doppler ultrasound (TCD) waveforms for cerebrovascular pathologies, such as stroke and intracranial hypertension, rely heavily on subjective expert evaluation, limiting their utility for prehospital stroke assessment by less specialized personnel.

Innovation Solution

An automated method for categorizing TCD waveforms using morphological variables like absolute peak onset, canopy length, and auxiliary peak number/prominence, employing spectral clustering and visualization in a three-dimensional space to objectively classify waveforms into categories corresponding to specific pathologies.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated classification methods are implemented, then productivity and ease of operation improve, but measurement precision and reliability may deteriorate without proper validation

Engineering Contradiction:

Improvewaveform classification speedVSAvoidclassification accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system performs self-validation through cross-validation techniques where the algorithm validates its own classifications by testing on multiple data subsets, ensuring automated classification maintains high accuracy without requiring constant expert oversight

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system incorporates feedback mechanisms by comparing automated classifications against ground truth data and using performance metrics to continuously evaluate and refine classification accuracy, ensuring reliability while maintaining high productivity

Inventive Principle:

Principle #23Feedback

2Measurement precision

If multiple morphological variables are analyzed, then measurement precision improves, but device complexity increases

Engineering Contradiction:

Improvewaveform characterization accuracyVSAvoidanalysis system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The complex analysis is segmented into distinct morphological variables (peak onset, canopy length, auxiliary peaks) that can be independently measured and then integrated, breaking down the complex task into manageable components that improve precision without overwhelming system complexity

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Multiple morphological variables are analyzed simultaneously by treating them as different dimensions in a multi-dimensional classification space, allowing comprehensive waveform characterization while using dimensionality reduction techniques to manage computational complexity

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

3Ease of operation

If automated algorithms are used, then ease of operation improves for non-experts, but reliability deteriorates without expert validation

Engineering Contradiction:

Improveuser accessibilityVSAvoidassessment trustworthiness

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The system acts as an intermediary tool that assists rather than replaces experts, providing automated classifications that can be reviewed and validated by specialists, thereby maintaining reliability while improving ease of operation for non-expert users

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

Manual expert assessment mechanics are partially replaced with automated computational algorithms that objectively analyze waveform morphology, reducing human subjectivity while maintaining reliability through validated algorithms that experts can oversee

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

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

This approach enables objective and automated classification of TCD waveforms, providing reliable data for stroke triage and transfer decisions, improving the accuracy and efficiency of cerebrovascular pathology assessment beyond traditional Thrombolysis in Brain Ischemia (TIBI) flow grades.

Implementation Method 1

Transcranial Doppler ultrasound (TCD) is a noninvasive methodology for measuring Cerebral Blood Flow Velocity (CBFV) through the large arteries of the brain

Methodology Applied

Scientific EffectUltrasound: Ultrasound

Implementation Method 2

Transcranial Doppler ultrasound (TCD) is a noninvasive methodology for measuring Cerebral Blood Flow Velocity (CBFV)

Methodology Applied

Scientific EffectDoppler effect: Doppler Effect

Data Source

PatentUS12167932B2Categorization of ultrasound waveforms through morphological variables

Publication Date: 2024.12.17 NEURASIGNAL INC

AI summary

Arrangements described herein relate to systems, apparatuses, and methods for categorizing a waveform that includes processing a signal containing ultrasound data about the waveform, identifying one or more morphological variables of the waveform based on the ultrasound data, identifying one or more categories that correspond to a range of combinations of the morphological variables, and categorizing the waveform as belonging to one of the one or more categories. In some arrangements, the method may further include visualizing the waveforms, determining a probability that the waveform belongs to each of the one or more categories, and/or displaying the probability that the waveform falls into each of the one or more categories. Morphological variables may include quantifying absolute peak onset, number/prominence of auxiliary peaks, and systolic canopy length.