MRI Rigid Motion Correction via Neural Network K-Space Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Motion artifacts in MRI acquisitions due to subject movement degrade image quality and can lead to misdiagnosis, with existing prospective motion correction strategies either prolonging scans or requiring clinical workflow changes, while retrospective methods without additional motion measurements are limited in correcting large datasets.
Innovation Solution
A system and method for rigid motion correction in MRI using a motion parameter estimation module and a motion correction neural network to generate motion-corrected k-space data and images from corrupted data, without requiring auxiliary measurements or external hardware, employing a deep learning approach for retrospective correction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If prospective motion correction strategies are used, then motion artifacts are reduced, but scan duration is prolonged and clinical workflows are altered
Solution Approach 1:
The system performs motion correction retrospectively after the scan is complete, using the acquired k-space data and motion parameters to correct images without requiring real-time intervention during the scan, thus avoiding prolonged scan duration while still achieving motion artifact reduction
Solution Approach 2:
The patent introduces motion parameters as an intermediary that captures motion information separately, allowing the correction process to occur independently after acquisition without interfering with the original scan workflow or extending scan time
2Reliability
If prospective motion correction strategies are used, then motion artifacts are reduced, but clinical workflow complexity increases
Solution Approach 1:
The system automatically estimates motion parameters and applies corrections using the acquired k-space data without requiring manual intervention or complex workflow changes, allowing the correction process to serve itself independently after standard acquisition
Solution Approach 2:
Instead of correcting motion during acquisition as prospective methods do, the system inverts the approach by correcting motion after acquisition using the already-collected data, thereby simplifying the workflow while maintaining image quality
3Device complexity
If retrospective motion correction without additional motion measurements is used, then hardware requirements are reduced, but correction accuracy for large datasets is limited
Solution Approach 1:
The system extracts motion information directly from the acquired k-space data itself, removing the need for external motion measurement hardware while achieving accurate motion parameter estimation through signal processing of the existing data
Solution Approach 2:
The k-space data serves multiple functions: it is used both for the primary image reconstruction and for estimating motion parameters, eliminating the need for separate motion sensing hardware while maximizing the utility of the acquired data
Data Source
AI summary
A system for rigid motion correction for magnetic resonance imaging (MRI) of a subject includes an input for receiving motion corrupted k-space data for the subject acquired using an MRI system, a motion parameter estimation module coupled to the input and configured to estimate motion parameters based on the motion corrupted k-space data, a motion correction neural network coupled to the input and the motion parameter estimation module and configured to generate motion corrected k-space data based on the motion corrupted k-space data and the estimated motion parameters, and a reconstruction module coupled to the motion correction neural network and configured to generate a motion corrected image from the motion corrected k-space data.