MRI Neural Network Motion Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Patient motion during MRI scans leads to inefficiencies, requiring re-scans or second visits, as existing methods for motion correction often rely on external tracking hardware or time-consuming navigator sequences, resulting in significant annual losses due to reduced throughput.
Innovation Solution
A magnetic resonance imaging (MRI) method using a trained neural network to detect and correct for patient motion by generating predictions from sub-images, allowing for adaptive motion correction without external monitoring devices, enabling real-time detection and adjustment of scan parameters to compensate for motion-related inconsistencies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If external tracking hardware or navigator sequences are used for motion correction, then motion detection capability is improved, but device complexity and time consumption increase
Solution Approach 1:
The patent extracts the motion detection function from external hardware and navigator sequences, implementing it directly within the MRI reconstruction process using neural networks that analyze k-space data patterns to identify motion artifacts without requiring separate monitoring devices
Solution Approach 2:
The MRI system performs self-diagnosis by using the neural network to automatically detect motion artifacts in the acquired data and trigger re-acquisition of affected k-space lines, eliminating the need for external monitoring systems
2Measurement precision
If navigator sequences are used for motion correction, then motion detection capability is improved, but scan time increases
Solution Approach 1:
The patent merges motion detection with the MRI reconstruction process by integrating neural network-based artifact detection into the standard imaging sequence, allowing simultaneous acquisition of imaging data and motion information without separate navigator pulses
Solution Approach 2:
The system performs preliminary motion assessment by analyzing k-space data patterns during the scan to predict motion artifacts before they fully develop, enabling proactive adjustment of scan parameters or triggering of re-acquisition only when necessary
3Manufacturing precision
If motion correction methods are applied, then image quality is improved, but productivity decreases due to re-scans
Solution Approach 1:
The patent implements a feedback mechanism where the neural network continuously monitors image quality during acquisition and provides real-time feedback to the reconstruction system, automatically adjusting parameters or triggering targeted re-acquisition only when motion artifacts are detected, thereby maintaining high throughput while ensuring image quality
Data Source
AI summary
A magnetic resonance imaging (MRI) system includes control and analysis circuitry having programming to acquire magnetic resonance (MR) data using coil elements of the MRI system, analyze the MR data, and reconstruct the MR data into MR sub-images. The system also includes a trained neural network associated with the control and analysis circuitry to transform the MR sub-images into a prediction relating to a presence and extent of motion corruption in the MR sub-images. The programming of the control and analysis circuitry includes instructions to control operations of the MRI system based at least in part on the prediction of the trained neural network.