Ultrasonic Diagnostic Apparatus Contour Candidate Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current ultrasonic diagnostic systems require manual selection of heartbeats and manual tracing of contours for analyzing cardiac function, which can lead to inconsistencies and inaccuracies in calculating quantitative values like ejection fraction, and do not allow for easy correction of contour traces post-analysis.
Innovation Solution
An image processing apparatus that acquires ultrasonic image data, generates contour candidates based on quantitative values using machine learning and deep learning techniques, allowing operators to select desired contours and adjust them for accurate analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual selection and tracing of heartbeats is performed, then operators can directly control the analysis process, but measurement precision and consistency deteriorate due to human error and variability
Solution Approach 1:
The system performs automatic heartbeat selection and contour tracing using image processing algorithms. The processing circuitry automatically detects endocardium contours, calculates ejection fraction, and identifies optimal heartbeats without requiring manual operator intervention, thereby eliminating human variability while maintaining operational simplicity
Solution Approach 2:
The patent replaces manual mechanical tracing operations with automated image processing and pattern recognition algorithms. The system uses computer vision techniques to detect contours and calculate cardiac parameters, substituting human manual operations with computational processes that provide consistent and precise measurements
2Measurement precision
If automated pattern recognition is used for contour detection, then measurement precision improves, but reliability deteriorates when the actual heart morphology differs from registered patterns
Solution Approach 1:
The system dynamically adapts the registered heart patterns to match the actual heart morphology being analyzed. The image processing circuitry adjusts and transforms the stored reference patterns to conform to the specific anatomical variations in the patient's heart, allowing accurate contour detection even when morphology differs from standard patterns
Solution Approach 2:
The patent modifies parameters of the registered patterns (such as scaling, rotation, and deformation parameters) to better fit the actual heart structure. By changing these parameters dynamically based on the specific image being analyzed, the system maintains high detection accuracy across diverse anatomical variations
3Measurement precision
If multiple contour candidates are generated and displayed, then measurement precision and operator control improve, but loss of time increases due to additional selection steps
Solution Approach 1:
The system generates multiple contour candidates but presents only the most relevant ones to the operator for selection. By providing a limited set of high-quality candidates rather than all possible contours, the system enables accurate selection while minimizing the time required for operator review and decision-making
Data Source
AI summary
The ultrasonic diagnostic apparatus according to any of embodiments includes processing circuitry. The processing circuitry is configured to acquire ultrasonic image data by ultrasonic scanning. The processing circuitry is configured to acquire multiple contour candidates based on a quantitative value indicating a function of a tissue, and superimpose the multiple contour candidates on the acquired ultrasonic image data to display the multiple contour candidates on a display. The processing circuitry is configured to determine contour data out of the multiple contour candidates.