Ultrasound Ringdown Artifact Suppression for Near-Field Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The ringdown artifact in ultrasound transducers limits the detection range of objects close to the transducer, interfering with accurate estimation of their position and characteristics, particularly in minimally invasive surgery applications.
Innovation Solution
Implementing a recurrent neural network (RNN) to suppress the ringdown artifact in ultrasound signals, combined with digital filters and machine learning-based techniques, allows for accurate estimation of time-of-flight and object characteristics by filtering out the artifact from the detected voltage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If ultrasound transducer is used for detection, then detection capability is provided, but ringdown artifact interferes with detection of objects in close proximity
Solution Approach 1:
The patent extracts and removes the ringdown artifact from the ultrasound signal using digital signal processing techniques. The system separates the harmful ringdown component from the useful echo signal, allowing accurate detection of objects in close proximity to the transducer.
Solution Approach 2:
The patent introduces digital signal processing as an intermediary between the ultrasound transducer and the detection system. This intermediary layer processes the raw signal to eliminate the ringdown artifact while preserving the useful echo information, enabling accurate near-field detection.
2Length of stationary object
If detection range is extended to include close objects, then detection coverage is improved, but ringdown artifact obscures signal from nearby objects
Solution Approach 1:
The patent converts the harmful ringdown artifact into a manageable signal component through digital processing. By characterizing and removing the artifact systematically, the system recovers signal information that would otherwise be lost, enabling detection of objects in the previously unusable near-field region.
3Measurement precision
If machine learning techniques are applied, then artifact removal accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent performs preliminary training of machine learning models using synthetic ringdown artifacts generated from measured transducer responses. This pre-training phase allows the system to learn artifact patterns offline, reducing real-time computational requirements during actual surgical procedures while maintaining high artifact removal accuracy.
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
Enables accurate detection of object position and characteristics even in close proximity to the transducer, enhancing the detection range and precision of ultrasound applications in minimally invasive surgery.
Implementation Method 1
An example ultrasound transducer includes a piezoelectric crystal that has a resonant oscillation frequency. Piezoelectric crystals can operate as both transmitters and receivers for sound waves. If a time-varying potential difference is applied across the electrodes, a piezoelectric crystal may oscillate and produce a sound wave.
Implementation Method 2
If a sound wave is applied to the piezoelectric crystal, it will generate a voltage across the electrodes.
Implementation Method 3
When an ultrasound pulse travels through the tissue, it undergoes continuous modifications, which depend on the characteristics of the sound waves as well as tissue properties.
Data Source
AI summary
An example method includes transmitting, by a single ultrasound transducer, an incident ultrasound signal and detecting, at least partially from an object within a ringdown range of the single ultrasound transducer and by the single ultrasound transducer, a received ultrasound signal. A ringdown artifact is removed from data indicative of the received ultrasound signal. Based on removing the ringdown artifact, the object is analyzed based on the data.