Automated Design of Pulse Sequences for Magnetic Resonance
Fingerprinting using Physics-Inspired Optimization
- URL: http://arxiv.org/abs/2106.04740v2
- Date: Mon, 10 Jan 2022 19:50:26 GMT
- Title: Automated Design of Pulse Sequences for Magnetic Resonance
Fingerprinting using Physics-Inspired Optimization
- Authors: Stephen P. Jordan, Siyuan Hu, Ignacio Rozada, Debra F. McGivney, Rasim
Boyacioglu, Darryl C. Jacob, Sherry Huang, Michael Beverland, Helmut G.
Katzgraber, Matthias Troyer, Mark A. Griswold, and Dan Ma
- Abstract summary: Magnetic Resonance Fingerprinting (MRF) is a method to extract quantitative tissue properties such as T1 and T2 relaxation rates from arbitrary pulse sequences.
Here we perform de novo automated design of MRF pulse sequences by applying physics-inspired optimizations.
- Score: 0.8711988786121446
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Magnetic Resonance Fingerprinting (MRF) is a method to extract quantitative
tissue properties such as T1 and T2 relaxation rates from arbitrary pulse
sequences using conventional magnetic resonance imaging hardware. MRF pulse
sequences have thousands of tunable parameters which can be chosen to maximize
precision and minimize scan time. Here we perform de novo automated design of
MRF pulse sequences by applying physics-inspired optimization heuristics. Our
experimental data suggests systematic errors dominate over random errors in MRF
scans under clinically-relevant conditions of high undersampling. Thus, in
contrast to prior optimization efforts, which focused on statistical error
models, we use a cost function based on explicit first-principles simulation of
systematic errors arising from Fourier undersampling and phase variation. The
resulting pulse sequences display features qualitatively different from
previously used MRF pulse sequences and achieve fourfold shorter scan time than
prior human-designed sequences of equivalent precision in T1 and T2.
Furthermore, the optimization algorithm has discovered the existence of MRF
pulse sequences with intrinsic robustness against shading artifacts due to
phase variation.
Related papers
- qMRI Diffusor: Quantitative T1 Mapping of the Brain using a Denoising Diffusion Probabilistic Model [1.1278063431495107]
We present qMRI Diffusor, a novel approach to qMRI utilising deep generative models.
Results indicate that our method achieves improved accuracy and precision in parameter estimation, along with superior visual performance.
arXiv Detail & Related papers (2024-07-23T13:49:19Z) - SMRD: SURE-based Robust MRI Reconstruction with Diffusion Models [76.43625653814911]
Diffusion models have gained popularity for accelerated MRI reconstruction due to their high sample quality.
They can effectively serve as rich data priors while incorporating the forward model flexibly at inference time.
We introduce SURE-based MRI Reconstruction with Diffusion models (SMRD) to enhance robustness during testing.
arXiv Detail & Related papers (2023-10-03T05:05:35Z) - One-Dimensional Deep Image Prior for Curve Fitting of S-Parameters from
Electromagnetic Solvers [57.441926088870325]
Deep Image Prior (DIP) is a technique that optimized the weights of a randomly-d convolutional neural network to fit a signal from noisy or under-determined measurements.
Relative to publicly available implementations of Vector Fitting (VF), our method shows superior performance on nearly all test examples.
arXiv Detail & Related papers (2023-06-06T20:28:37Z) - Optimizing Sampling Patterns for Compressed Sensing MRI with Diffusion
Generative Models [75.52575380824051]
We present a learning method to optimize sub-sampling patterns for compressed sensing multi-coil MRI.
We use a single-step reconstruction based on the posterior mean estimate given by the diffusion model and the MRI measurement process.
Our method requires as few as five training images to learn effective sampling patterns.
arXiv Detail & Related papers (2023-06-05T22:09:06Z) - Joint MR sequence optimization beats pure neural network approaches for
spin-echo MRI super-resolution [44.52688267348063]
Current MRI super-resolution (SR) methods only use existing contrasts acquired from typical clinical sequences as input for the neural network (NN)
We propose a known-operator learning approach to perform an end-to-end optimization of MR sequence and neural net-work parameters for SR-TSE.
arXiv Detail & Related papers (2023-05-12T14:40:25Z) - High-fidelity Direct Contrast Synthesis from Magnetic Resonance
Fingerprinting [28.702553164811473]
We propose a supervised learning-based method that directly synthesizes contrast-weighted images from the MRF data without going through the quantitative mapping and spin-dynamics simulation.
In-vivo experiments demonstrate excellent image quality compared to simulation-based contrast synthesis and previous DCS methods, both visually as well as by quantitative metrics.
arXiv Detail & Related papers (2022-12-21T07:11:39Z) - Digital noise spectroscopy with a quantum sensor [57.53000001488777]
We introduce and experimentally demonstrate a quantum sensing protocol to sample and reconstruct the auto-correlation of a noise process.
Walsh noise spectroscopy method exploits simple sequences of spin-flip pulses to generate a complete basis of digital filters.
We experimentally reconstruct the auto-correlation function of the effective magnetic field produced by the nuclear-spin bath on the electronic spin of a single nitrogen-vacancy center in diamond.
arXiv Detail & Related papers (2022-12-19T02:19:35Z) - Mixed Precision Low-bit Quantization of Neural Network Language Models
for Speech Recognition [67.95996816744251]
State-of-the-art language models (LMs) represented by long-short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming increasingly complex and expensive for practical applications.
Current quantization methods are based on uniform precision and fail to account for the varying performance sensitivity at different parts of LMs to quantization errors.
Novel mixed precision neural network LM quantization methods are proposed in this paper.
arXiv Detail & Related papers (2021-11-29T12:24:02Z) - Real-Time Mapping of Tissue Properties for Magnetic Resonance
Fingerprinting [20.834829860562248]
We introduce a novel end-to-end deep learning framework to seamlessly map the tissue properties directly from spiral k-space MRF data.
Our method directly consumes the non-Cartesian k- space data, performs adaptive density compensation, and predicts multiple tissue property maps in one forward pass.
arXiv Detail & Related papers (2021-07-16T21:05:47Z) - Fast Simulation of Magnetic Field Gradients for Optimization of Pulse
Sequences [0.0]
We study how to simulate, efficiently, pulse field gradients (PFG) used in nuclear magnetic resonance (NMR)
We show that the fast simulation of PFG allow us to optimize sequences composed of PFG, radio-frequency pulses and free evolution, to implement non-unitary evolution (quantum channels)
In the second experiment, we used the fast simulation of PFG to optimize and implement a sequence to prepare pseudo pure state with better signal to noise ratio than any known procedure till now.
arXiv Detail & Related papers (2020-06-17T20:02:39Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.