Respiration Phase Determination in MRI Using Signal Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing MRI systems face challenges in accurately determining the respiration phase of respiration signals due to inconsistent respiratory motion signals received by different coil units, leading to motion artifacts in MR images.
Innovation Solution
A method and apparatus that extract distance, score, and area characteristic values from respiration signals to train a model for determining the respiration phase, using these values to identify waveform variations and accurately determine the respiration phase by comparing aspiration and expiration curve shapes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a respiration sensor is used to detect respiratory motion state, then motion artifacts in MR images can be reduced, but different coil units receive inconsistent respiratory motion signals resulting in inaccurate respiration phase determination
Solution Approach 1:
The patent combines respiratory motion signals from multiple coil units and merges them into a single composite respiration signal. This merging process integrates the information from all coil units, allowing the system to overcome the inconsistency problem by aggregating multiple signal sources into one reliable respiration phase determination signal.
Solution Approach 2:
The patent introduces an intermediary processing step that receives inconsistent signals from different coil units and transforms them into a unified respiration phase indicator. This intermediary mechanism processes the raw signals through characteristic extraction and model training to produce a consistent respiration phase determination that can be used for triggering MRI acquisition.
2Quantity of substance
If respiratory motion signals from multiple coil units are used, then more comprehensive respiratory information can be obtained, but signal inconsistency increases making phase determination more difficult
Solution Approach 1:
The patent implements a feedback mechanism where the system continuously monitors respiratory signals from multiple coil units, compares the received signals against a trained respiration signal model, and adjusts the phase determination based on the comparison results. This feedback loop enables the system to handle signal variability and maintain accurate phase determination despite the complexity of multiple signal sources.
Solution Approach 2:
The patent transforms the raw respiratory signals into different characteristic parameters (distance characteristic value, score characteristic value, area characteristic value) that are more suitable for phase determination. By changing the parameters from raw signal amplitudes to geometric and temporal characteristics, the system simplifies the detection and measurement process while preserving the essential respiratory information.
Data Source
AI summary
The present disclosure provides techniques for determining a respiration phase by extracting a distance characteristic value, a score characteristic value, and an area characteristic value from the respiration signal, wherein the distance characteristic value, the score characteristic value and the area characteristic value are used to indicate waveform variation between two adjacent waveforms in the respiration signal. The techniques include training a respiration signal model according to the distance characteristic value, the score characteristic value, and the area characteristic value to determine the respiration phase of the respiration signal using the respiration signal model.