Automated Zero-Crossing Selection for Electromechanical Wave Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current imaging techniques for cardiac conduction malfunctions, such as arrhythmias, are invasive, time-consuming, and costly, and manual selection of zero-crossing locations for electromechanical wave imaging (EWI) is particularly labor-intensive, especially with large patient populations.
Innovation Solution
An automated system using a processor configured to perform electromechanical wave imaging with a machine learning classifier, such as a Random Forest classifier, to select zero-crossing locations and generate activation maps, reducing manual intervention and increasing efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual selection of zero-crossing locations is used for EWI isochrone generation, then measurement precision can be maintained, but productivity deteriorates due to time-consuming manual analysis
Solution Approach 1:
The patent replaces the manual mechanical process of zero-crossing selection with an automated machine learning system. The Random Forest classifier automatically identifies zero-crossing locations on incremental axial strain curves, eliminating the need for manual analyst intervention while maintaining measurement precision through validated algorithms.
Solution Approach 2:
The system enables self-service automation where the machine learning model independently performs zero-crossing detection without human intervention. The automated pipeline processes echocardiographic data, generates isochrones, and produces activation maps autonomously, significantly improving productivity while preserving accuracy through rigorous validation.
2Productivity
If automated machine learning selection is used for zero-crossing locations, then productivity is improved through faster processing, but device complexity increases due to ML model implementation
Solution Approach 1:
The patent introduces a machine learning model as an intermediary component between raw echocardiographic data and isochrone generation. This intermediary layer automates the complex task of zero-crossing detection, handling the computational complexity internally while presenting a simplified interface for clinical use and significantly improving processing speed.
3Measurement precision
If manual zero-crossing selection is performed, then measurement precision can be maintained through expert judgment, but loss of time increases due to labor-intensive analysis
Solution Approach 1:
The patent applies preliminary action by pre-training the Random Forest classifier on labeled datasets of zero-crossing locations. This preliminary training phase enables the model to quickly and accurately identify zero-crossings during actual analysis, eliminating time-consuming manual selection while maintaining precision through learned patterns from extensive training data.
Data Source
AI summary
The present subject matter relates to techniques for electromechanical wave imaging. The disclosed system can include a processor that can be configured to perform an automated selection of at least one zero-crossing location using a heuristic-based baseline and/or a machine learning classifier and generate an electromechanical wave imaging isochrone based on the automated selection.