Neural Network Intracardiac Sensor Motion Artifact Compensation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Intracardiac sensors used in medical procedures, such as EP studies and cardiac ablation, suffer from temporal motion artifacts due to cardiac and respiratory motion, which degrade the accuracy of measurements and are not effectively addressed by conventional filtering methods that may introduce delays or exhibit unpredictable behavior.
Innovation Solution
A computer-implemented method utilizing a neural network trained to predict and compensate for temporal motion artifacts in intracardiac sensor data, where the network is trained on temporal intracardiac sensor data with ground truth motion data to adjust parameters and reduce artifacts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional filters are used to suppress temporal motion artifacts, then artifact reduction is achieved, but signal processing delay is introduced
Solution Approach 1:
The patent replaces conventional mechanical filtering systems with a neural network-based computational system. The neural network directly predicts and removes motion artifacts from sensor data without introducing the time delays associated with traditional filter-based approaches, thereby achieving artifact reduction while maintaining real-time signal processing capability.
2Measurement precision
If conventional adaptive filters such as Kalman filter are used, then artifact suppression is achieved, but unpredictable behavior occurs in response to sudden sensor position changes
Solution Approach 1:
The patent substitutes conventional adaptive filters with a neural network model that has been trained to predict motion artifacts. This neural network approach provides more reliable and predictable behavior when handling sudden sensor position changes, as it can learn from training data the appropriate responses to various motion scenarios without the instability inherent in traditional adaptive filtering algorithms.
3Device complexity
If filters with constant coefficients are used, then processing simplicity is maintained, but incomplete removal of unwanted frequencies occurs
Solution Approach 1:
The patent changes the parameters of the processing system by using a neural network that can adapt its coefficients dynamically based on the input data characteristics. This allows the system to achieve complete removal of unwanted frequencies while maintaining reasonable processing complexity, as the neural network learns optimal parameters from training data rather than using fixed constant coefficients.
Data Source
AI summary
A computer-implemented method of reducing temporal motion artifacts in temporal intracardiac sensor data, includes: inputting (S120) temporal intracardiac sensor data (110), into a neural network (130) trained to predict, from the temporal intracardiac sensor data (110), temporal motion data (140, 150) representing the temporal motion artifacts (120); and compensating (S130) for the temporal motion artifacts (120) in the received 5 temporal intracardiac sensor data (110) based on the predicted temporal motion data (140, 150).