Motion-Robust MRI Reconstruction via Data-Consistency Weighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current motion suppression and correction approaches in MRI systems are inadequate, particularly in multi-shot MRI, as they are sensitive to subject motion, leading to artifacts and reduced image quality due to the sensitivity of deep-learning-based algorithms to motion artifacts.
Innovation Solution
The method incorporates navigator signals to detect motion occurrence and estimate motion parameters, generating a data-consistency weighting matrix to differentiate between motion-corrupted and motion-free k-space data points, which is then used in a deep-learning framework to reconstruct motion-corrected image data, accounting for the certainty level of data integrity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If multishot MRI is used to acquire high-resolution images, then image resolution is improved, but sensitivity to subject motion increases causing artifacts
Solution Approach 1:
The patent introduces navigator signals as an intermediary mechanism to detect motion between shots and generates a data-consistency weighting matrix that weights or rejects k-space data points based on detected motion. This mediator allows the system to maintain high-resolution multishot imaging while compensating for motion artifacts through the weighting mechanism.
2Reliability
If deep-learning-based algorithms are used for motion correction, then motion correction capability is improved, but sensitivity to motion artifacts in the algorithm increases
Solution Approach 1:
The patent applies preliminary action by detecting motion and generating the data-consistency weighting matrix before the deep-learning reconstruction process. By pre-weighting or rejecting motion-corrupted k-space data points based on navigator signal analysis, the system reduces the burden on the deep-learning algorithm and prevents motion artifacts from propagating through the reconstruction process.
3Manufacturing precision
If motion correction is applied to multishot MRI data, then image quality is improved, but processing complexity increases
Solution Approach 1:
The patent segments the motion correction process into distinct components: navigator signal acquisition, motion detection, data-consistency weighting matrix generation, and integration with deep-learning reconstruction. This segmentation allows each component to be optimized independently and facilitates parallel processing, reducing overall computational complexity while maintaining image quality.
Data Source
AI summary
A method for motion correction in a magnetic resonance imaging system includes receiving data collected from imaging an object by the magnetic resonance imaging system, or image data reconstructed from the collected data. The method further includes generating motion-related information with respect to a motion of the object while the collected data is being collected. The motion-related information includes a certainty level of the collected data being corrupted by the motion of the object. The method also includes generating, based on the generated motion-related information and the received data or reconstructed image data, motion-corrected image data.