PROPELLER MRI Reconstruction for Shorter Scan Time
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
PROPELLER magnetic resonance imaging (MRI) scans have a higher scan time compared to Cartesian techniques, which is problematic for anatomies prone to motion artifacts such as the abdomen, pelvis, and cervical spine.
Innovation Solution
A deep learning-based Cartesian-like reconstruction network is used to individually reconstruct undersampled blades of k-space data during a PROPELLER sequence, followed by a PROPELLER reconstruction algorithm to generate a complex image, reducing scan time while maintaining high resolution and minimizing motion artifacts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If PROPELLER sequence is used to provide high resolution imaging with reduced motion artifacts, then image quality is improved, but scan time increases
Solution Approach 1:
The k-space data is divided into multiple blades that are rotated around the center of k-space. Each blade can be independently undersampled and reconstructed using deep learning, allowing parallel processing and acceleration while maintaining the high resolution and motion artifact reduction characteristics of PROPELLER imaging
Solution Approach 2:
The patent applies deep learning reconstruction algorithms to change the reconstruction parameters and methods. By training neural networks to reconstruct fully sampled blades from undersampled data, the system achieves faster scan times while preserving image quality through learned reconstruction patterns
2Loss of time
If k-space data is undersampled to reduce scan time, then scan time is reduced, but image quality deteriorates
Solution Approach 1:
The patent replaces traditional mechanical reconstruction methods with deep learning-based reconstruction. Instead of using conventional Fourier transforms and iterative reconstruction algorithms, neural networks are trained to directly map undersampled k-space blades to fully sampled images, achieving both speed and quality improvements
Solution Approach 2:
The deep learning model creates a learned copy or representation of the full k-space data from the undersampled input. The neural network learns the relationship between undersampled and fully sampled blades during training, enabling it to generate accurate reconstructions that preserve image quality despite the reduced sampling density
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
The method accelerates MRI scans by undersampling k-space data and using deep learning to reconstruct fully sampled blades, resulting in faster imaging with improved image quality and increased system throughput.
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.
Implementation Method 2
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
Implementation Method 3
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
Implementation Method 4
When utilizing these signals to produce images, magnetic field gradients (Gx, Gy, and Gz) are employed. Typically, the region to be imaged is scanned by a sequence of measurement cycles in which these gradient fields vary according to the particular localization method being used
Data Source
AI summary
A system and method for reducing scan time of periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER) imaging include acquiring a plurality of blades of k-space data of a region of interest in a rotational manner around a center of k-space via a magnetic resonance imaging (MRI) scanner during a PROPELLER sequence, wherein each blade of the plurality of blades of k-space data includes a plurality of parallel phase encoding lines sampled in a phase encoding order. Each blade of the plurality of blades of k-space data is undersampled. The system and method include utilizing a deep learning-based Cartesian-like reconstruction network to individually and separately reconstruct each blade of the plurality of blades of k-space data to generate a plurality of fully sampled blades. The system and method include utilizing a PROPELLER reconstruction algorithm to generate a complex image from the plurality of fully sampled blades.