Automated Doppler Feature Extraction for Valvular Disease Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for diagnosing valvular diseases using Doppler images are prone to variability and inefficiency, as echocardiographers often miss necessary measurements, leading to inconsistent results and potential missed diagnoses.
Innovation Solution
An automated method for extracting disease-specific features from Doppler images, which involves isolating a region of interest, determining the velocity envelope, synchronizing the ECG signal, and calculating clinical features to compare with guidelines for accurate diagnosis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual tracing of velocity envelopes is performed by echocardiographers, then measurements such as decay time, pressure gradient, and velocity time integral can be extracted, but the measurements show considerable variability and are prone to human error
Solution Approach 1:
The system automatically performs velocity envelope tracing and measurement extraction without requiring manual echocardiographer intervention. The computer system independently identifies Doppler signals, traces velocity envelopes, and calculates clinical measurements, eliminating human variability while maintaining operational efficiency
Solution Approach 2:
The patent replaces the manual mechanical tracing process with an automated computer-based system that uses signal processing algorithms to detect and measure Doppler velocity signals. This substitution eliminates hand-drawn tracings and manual calculations, providing consistent, reproducible measurements across different operators
2Productivity
If a subset of measurements is performed based on anticipated diseases, then the examination process is simplified, but many necessary measurements may be missed leading to potential missed diagnoses
Solution Approach 1:
The automated system is designed to perform all 146 possible echocardiography measurements across multiple cardiac structures and disease states. By implementing a universal measurement capability that can detect any valvular abnormality regardless of initial clinical suspicion, the system ensures comprehensive disease detection while maintaining efficient automated operation
Solution Approach 2:
The system automatically compares extracted measurements against established clinical guidelines and reference ranges, providing real-time feedback on abnormal findings. This feedback mechanism ensures that no necessary measurements are missed by automatically identifying and flagging pathological conditions across the full spectrum of valvular diseases
3Measurement precision
If manual measurement and comparison with clinical guidelines is performed, then diagnosis can be determined, but the process is time-consuming and shows variability
Solution Approach 1:
The system continuously and automatically performs the complete measurement and diagnosis workflow without interruption. Velocity envelopes are traced, measurements are extracted, and results are compared with clinical guidelines in an unbroken automated sequence, eliminating the time losses and variability associated with manual transfer of data between different analysis stages
Data Source
AI summary
An automatic extraction of disease-specific features from Doppler images to help diagnose valvular diseases is provided. The method includes the steps of obtaining a raw Doppler image from a series of images of an echocardiogram, isolating a region of interest from the raw Doppler image, the region of interest including a Doppler image and an ECG signal, and depicting at least one heart cycle, determining a velocity envelope of the Doppler image in the region of interest, extracting the ECG signal to synchronize the ECG signal with the Doppler image over the at least one heart cycle, within the region of interest, calculating a value of a clinical feature based on the extracted ECG signal synchronized with the velocity envelope, and comparing the value of the clinical feature with clinical guidelines associated with the clinical feature to determine a diagnosis of a disease.