Neural Network MR Coil Sensitivity Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for mapping the sensitivity of radio frequency (RF) coils in magnetic resonance imaging (MRI) systems require multiple data acquisitions at different flip angles, leading to increased scan time and reduced patient throughput, particularly in applications like parallel imaging where time efficiency is crucial.
Innovation Solution
The use of neural networks to generate normalization or weighting functions for rapid coil sensitivity mapping, allowing for the construction of coil sensitivity profiles with minimal input data and reducing the number of required mapping acquisitions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple data acquisitions at different flip angles are used to map coil sensitivity, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The system performs preliminary calibration to determine actual flip angles, then uses these pre-determined values to guide subsequent sensitivity mapping acquisitions. This preliminary characterization of the system allows for optimized scanning strategies that reduce total acquisition time while maintaining precision.
Solution Approach 2:
The system varies flip angle parameters across multiple acquisitions to map coil sensitivity profiles. By systematically changing this key parameter and analyzing the resulting signal variations, the system achieves precise sensitivity mapping. The method optimizes the selection of flip angle values to balance precision requirements with time constraints.
2Measurement precision
If the number of flip angles or transmit powers is increased for each coil, then measurement precision is improved, but productivity decreases
Solution Approach 1:
The system performs preliminary calibration scans to characterize actual flip angles achieved by each coil. This advance knowledge allows for optimized planning of subsequent sensitivity mapping acquisitions, reducing the total number of required scans while maintaining measurement precision, thereby improving patient throughput.
Solution Approach 2:
The system uses the measured signal intensities from calibration scans to self-determine actual flip angles for each coil. This self-characterization eliminates the need for separate calibration procedures and enables the system to automatically optimize its own operating parameters for subsequent imaging, improving overall efficiency.
3Measurement precision
If multiple acquisitions are performed to determine coil sensitivity profiles, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The system acquires multiple data sets with varying flip angle parameters to map coil sensitivity profiles. By optimizing the selection and number of flip angle values used in these acquisitions, the system achieves accurate sensitivity profiles with minimized scan time, directly addressing the time-precision tradeoff.
Solution Approach 2:
The system replaces traditional iterative calibration methods with a streamlined approach that uses measured signal intensities directly to calculate actual flip angles. This substitution of the calibration mechanism reduces the number of required acquisitions and accelerates the sensitivity mapping process while maintaining accuracy.
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
This approach enables faster production of coil sensitivity maps, significantly reducing the time needed for sensitivity mapping and improving patient throughput while maintaining image quality and accuracy in MRI procedures.
Implementation Method 1
The use of neural networks to generate normalization or weighting functions for rapid coil sensitivity mapping, allowing for the construction of coil sensitivity profiles with minimal input data
Implementation Method 2
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 3
When utilizing these signals to produce images, magnetic field gradients (Gx, Gy, and Gz) are employed
Data Source
AI summary
A system and method for mapping the sensitivity of MR coils includes a neural network or other computer intelligence trained from sample MR data to determine coil sensitivity profiles or sensitivity normalizations. Once the network is trained, subsequent coil mapping determinations may include fewer mapping acquisitions per coil. The resulting sensitivity map can be used in compensating for B1 inhomogeneities, parallel imaging reconstruction, generating tailored excitation currents for each individual coil, RF shimming, or other processes.