Ultrasonic Imaging Device Deep Learning Shape Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional ultrasonic imaging devices require repeated calculations to estimate the shape of a deformable pedestal, making real-time imaging challenging due to the time-consuming process of iteratively adjusting hypothetical shapes until a shape index meets an allowable value.
Innovation Solution
The ultrasonic imaging device employs deep learning to establish a relationship between ultrasonic reception data and shape data, allowing for quick estimation of the pedestal's shape by applying learning results to ultrasonic reception data, enabling near real-time image construction using estimated shape data and ultrasonic reception data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If iterative shape adjustment and shape index calculation are used to estimate pedestal shape, then measurement precision is improved, but productivity deteriorates due to repeated calculations
Solution Approach 1:
The patent pre-calculates shape indices for multiple candidate shapes and stores them in advance. During actual imaging, the system only needs to compare the measured shape index against these pre-stored values to identify the matching shape, eliminating the need for repeated iterative calculations and enabling rapid real-time imaging while maintaining accurate shape estimation.
2Measurement precision
If iterative shape adjustment is performed until shape index meets allowable value, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The system pre-computes and stores the relationship between candidate shapes and their corresponding shape indices in a lookup table before actual use. When imaging is performed, the measured shape index is directly compared against this pre-established database to quickly identify the corresponding shape, completely avoiding time-consuming iterative adjustments and repeated calculations while ensuring accurate shape estimation.
Solution Approach 2:
The patent creates a simplified copy of the shape-index relationship in the form of a lookup table or database during the preparation phase. This copy contains pre-calculated shape index values for various candidate shapes, allowing the system to perform rapid shape estimation by simple comparison during imaging without needing to recalculate shape indices iteratively, thus dramatically reducing computation time while maintaining precision.
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 significantly reduces the time required for shape estimation, allowing for real-time imaging by leveraging pre-learned relationships between ultrasonic reception and shape data, resulting in accurate and timely image output.
Implementation Method 1
a probe having a plurality of element capable of transmitting and receiving ultrasonic signals
Data Source
AI summary
An ultrasonic imaging device has a learning result as a relationship between the ultrasonic reception data and the shape data obtained by deep learning using the ultrasonic reception data of an imaging target obtained by transmitting and receiving ultrasonic signals by the plurality of element and the shape data of the pedestal (arrangement of multiple elements). Then the ultrasonic imaging device obtains the estimated shape data as the estimated shape data of the pedestal (estimated arrangement of multiple elements) by applying the learning result to the ultrasonic reception data, and constructs an image of the imaging target based on the estimated shape data and the ultrasonic reception data.