E4D CVUS Probe Super Resolution for Sparse-Transmit Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional medical imaging systems, particularly those using electronic 4D cardiovascular ultrasound (CVUS) probes, face challenges in achieving optimal image quality at higher volume rates due to sparse transmission, leading to degraded image construction during real-time applications like ultrasound guided cardiac interventions.
Innovation Solution
Implementing super resolution techniques, specifically deep learning-based image super resolution methods, to enhance image quality by increasing volume rates without degrading image quality, using frameworks that reconstruct ultrasound images from sparse transmits and combining different reconstruction methods.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If volume rate is increased in e4D CVUS probes, then productivity is improved, but image quality deteriorates due to sparse transmission
Solution Approach 1:
A deep learning-based super resolution model is introduced as an intermediary between sparse transmission data and final image reconstruction. The model takes low-quality images from sparse transmits and transforms them into high-quality images, enabling both high volume rates and diagnostic image quality simultaneously
Solution Approach 2:
The system dynamically adjusts acquisition parameters (number of transmits per volume) based on clinical needs, and uses the super resolution model to compensate for parameter changes that would normally degrade image quality. This allows flexible operation at high volume rates while maintaining image quality through computational correction
2Productivity
If sparse transmission is used to achieve higher volume rates, then productivity is improved, but measurement precision deteriorates
Solution Approach 1:
The super resolution deep learning model serves as a mediator that processes the degraded images from sparse transmissions and restores diagnostic-quality features, ensuring that measurement precision is maintained even when productivity is increased through sparse sampling
3Device complexity
If conventional reconstruction methods are used with sparse transmits, then device complexity is reduced, but image quality deteriorates
Solution Approach 1:
The patent replaces complex hardware-based solutions (such as increasing the number of transducer elements or using mechanical scanning) with a software-based deep learning approach. The super resolution model computationally achieves image quality enhancement without requiring additional physical components, thus maintaining simplicity while improving performance
Data Source
AI summary
Systems and methods are provided for super resolution for electronic 4D (e4D) cardiovascular ultrasound (CVUS) probes. In a medical imaging system, signals associated with a medical imaging technique may be acquired and processed, with the processing including applying one or both of a first type of correction to address a first type of degradation and a second type of correction to address a second type of degradation, with the first type of degradation being based on or caused by sparse acquisition, and the second type of degradation being based on or caused by choice of beamforming/reconstruction methodology.