Cardiac Ultrasound Strain Quantification Using Motion Vector Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual strain measurement in cardiovascular diagnosis is time-consuming and subjective, leading to unreliable results due to expert dependence and multiple error-prone steps, with existing AI-based methods limited to left ventricle analysis.
Innovation Solution
An artificial neural network-based prediction model for cardiac ultrasound images that segments heart structures, estimates motion vectors, and determines strain quantification parameters, incorporating global structural features and regional similarities to automate the process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual strain measurement is performed by experts, then diagnostic accuracy can be maintained through experience, but the process becomes time-consuming and subject to inter-observer variability
Solution Approach 1:
The system enables automated strain quantification where the ultrasound imaging system itself performs the measurement without requiring expert intervention. The processor automatically calculates strain parameters from captured images, making the system self-sufficient and eliminating dependency on expert operators while maintaining measurement accuracy
Solution Approach 2:
The patent replaces the manual mechanical measurement process with an automated computational system. Instead of experts manually tracing and measuring strain, a processor-based system automatically performs image analysis and strain calculation, substituting human mechanical operations with automated digital processing
2Measurement precision
If manual strain measurement is performed, then detailed analysis can be conducted, but multiple error-prone steps increase the likelihood of measurement errors
Solution Approach 1:
The patent combines multiple separate measurement steps into a single integrated automated process. The processor simultaneously performs image capture, region identification, and strain calculation in one unified operation, eliminating the multiple discrete steps that previously increased error risk while reducing overall process complexity
Solution Approach 2:
The imaging system is designed to perform multiple functions automatically: it captures ultrasound images, identifies relevant anatomical regions, calculates strain parameters, and generates diagnostic reports. This multi-functional capability eliminates the need for separate specialized tools and steps for each measurement task
3Extent of automation
If existing AI-based strain analysis is used, then automation is achieved for left ventricle analysis, but the scope is limited and cannot analyze other heart areas
Solution Approach 1:
The system is designed with universal capability to analyze multiple heart structures including left ventricle, right ventricle, left atrium, and right atrium. The same automated processing pipeline and strain calculation algorithms are applied across all heart areas, enabling the system to perform diverse anatomical analyses without requiring separate specialized methods for each structure
Solution Approach 2:
The system segments different heart areas independently within the automated analysis framework. Each heart structure is identified and processed as a distinct region, allowing the automated system to maintain specificity for each anatomical area while preserving overall versatility across multiple heart structures
Data Source
AI summary
The present disclosure provides a method for providing information on strain quantification implemented by a processor, the method includes receiving a cardiac ultrasound image including a target heart area of an subject, determining a motion vector field for the target heart area in the received cardiac ultrasound image using a prediction model trained to segment the target heart area using the cardiac ultrasound image as an input and determine a motion vector field based on the segmented target heart area, and determining a strain quantification parameter based on the motion vector field, and the present disclosure provides a device and system using the method for providing information on strain quantification.