MRI Motion-Corrupted Shot Detection With Deep Learning Reconstruction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Magnetic resonance imaging (MRI) scans are prone to motion artifacts due to patient movement during long acquisition times, leading to non-diagnostic images.
Innovation Solution
A system and method utilizing deep learning-based reconstruction to correct for motion artifacts by identifying and rejecting motion-corrupted shots in multi-shot acquisitions, employing additional navigator echoes to detect consistent poses, and applying unrolled deep learning-based reconstruction to generate artifact-free images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multi-shot acquisitions are used to reduce scan time, then productivity is improved, but motion artifacts increase because patient movement occurs during the scan
Solution Approach 1:
The patent segments the k-space data into multiple shots and identifies motion-corrupted shots by comparing navigator echoes between shots. By segmenting the data acquisition process and analyzing each shot individually, the system can reject motion-corrupted shots and retain only motion-free shots for reconstruction, thereby maintaining short scan times while eliminating motion artifacts.
Solution Approach 2:
The patent employs navigator echoes as feedback signals to monitor patient position during each shot. By comparing navigator echoes across shots, the system provides feedback about motion occurrence and uses this information to identify and reject motion-corrupted shots. This feedback mechanism enables the system to maintain high productivity while ensuring image quality through motion rejection.
2Measurement precision
If motion-corrupted shots are rejected to improve image quality, then measurement precision is improved, but loss of information increases due to missing k-space data
Solution Approach 1:
The patent changes the reconstruction approach by using deep learning models that can infer missing k-space data based on patterns from motion-free shots. Instead of traditional reconstruction methods that fail when data is missing, the system uses parameter changes in the reconstruction algorithm (switching to AI-based reconstruction) to fill in gaps from rejected shots, thereby maintaining measurement precision while minimizing information loss.
Solution Approach 2:
The patent creates a copy of the k-space data from motion-free shots and uses this copy to reconstruct the image. By copying only the reliable data from shots without motion artifacts, the system can generate high-quality images while discarding corrupted data. The deep learning model then uses this clean copied data to produce the final reconstruction, effectively replacing lost information with accurate alternatives.
3Reliability
If additional navigator echoes are acquired to detect motion, then reliability is improved, but device complexity increases
Solution Approach 1:
The patent makes the navigator echoes serve multiple functions: they are used both for motion detection and for guiding the reconstruction process. By making these additional signals multi-functional, the system improves reliability through better motion monitoring while avoiding the need for separate complex systems. The same navigator data supports both detection and reconstruction guidance, reducing overall device complexity.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Improves image quality by reducing patient rescans and enhancing comfort, particularly for uncompliant patients, while correcting for various types of motion in MRI data without increasing scan time.
Implementation Method 1
During magnetic resonance imaging (MRI), when a substance such as human tissue is subjected to a uniform magnetic field (polarizing field B0), the individual magnetic moments of the spins in the tissue attempt to align with this polarizing field, but precess about it in random order at their characteristic Larmor frequency. If the substance, or tissue, is subjected to a magnetic field (excitation field B1) which is in the x-y plane and which is near the Larmor frequency, the net aligned moment, or 'longitudinal magnetization', Mz, may be rotated, or 'tipped', into the x-y plane to produce a net transverse magnetic moment, Mt. A signal is emitted by the excited spins after the excitation signal B1 is terminated and this signal may be received and processed to form an image.
Data Source
AI summary
A method includes obtaining k-space data, wherein a plurality of navigator like echoes of the k-space data including an additional navigator like echo are acquired for each shot or a group of shots. The k-space data is motion corrupted. The method includes identifying any shots where a subject moved during acquisition based on the respective additional navigator like echoes. The method includes generating dominant pose k-space data based on identification of any shots where the subject moved during acquisition, the dominant pose k-space data includes only shots not affected by movement, wherein the dominant pose k-space data is missing k-space data due to rejecting the shots where the subject moved. The method includes utilizing a deep learning-based reconstruction model on the motion-corrupted k-space data to modify motion-corrupted k-space data with k-space data that is consistent with the dominant pose k-space data to generate a reconstructed image.