MR fingerprinting Deep RecOnstruction NEtwork (DRONE)

Efficient pulse sequence design framework for high-dimensional MR fingerprinting scans using systematic error index

PURPOSE

For effective optimization of MR fingerprinting (MRF) pulse sequences, estimating and minimizing errors from actual scan conditions are crucial. Although virtual-scan simulations offer an approximation to these errors, their computational demands become expensive for high-dimensional MRF frameworks, where interactions between more than two tissue properties are considered. This complexity makes sequence optimization impractical. We introduce a new mathematical model, the systematic error index (SEI), to address the scalability challenges for high-dimensional MRF sequence design.

METHODS

By eliminating the need to perform dictionary matching, the SEI model approximates quantification errors with low computational costs. The SEI model was validated in comparison with virtual-scan simulations. The SEI model was further applied to optimize three high-dimensional MRF sequences that quantify two to four tissue properties. The optimized scans were examined in simulations and healthy subjects.

RESULTS

The proposed SEI model closely approximated the virtual-scan simulation outcomes while achieving hundred- to thousand-times acceleration in the computational speed. In both simulation and in vivo experiments, the optimized MRF sequences yield higher measurement accuracy with fewer undersampling artifacts at shorter scan times than the heuristically designed sequences.

CONCLUSION

We developed an efficient method for estimating real-world errors in MRF scans with high computational efficiency. Our results illustrate that the SEI model could approximate errors both qualitatively and quantitatively. We also proved the practicality of the SEI model of optimizing sequences for high-dimensional MRF frameworks with manageable computational power. The optimized high-dimensional MRF scans exhibited enhanced robustness against undersampling and system imperfections with faster scan times.

Quantification of water exchange across the blood-brain barrier using noncontrast MR fingerprinting

PURPOSE

A method is proposed to quantify cerebral blood volume (v b $$ {v}_b $$ ) and intravascular water residence time (τ b $$ {\tau}_b $$ ) using MR fingerprinting (MRF), applied using a spoiled gradient echo sequence without the need for contrast agent.

METHODS

An in silico study optimized an acquisition protocol to maximize the sensitivity of the measurement tov b $$ {v}_b $$ andτ b $$ {\tau}_b $$ changes. Its accuracy in the presence of variations inT 1 , t $$ {\mathrm{T}}_{1,t} $$ ,T 1 , b $$ {\mathrm{T}}_{1,b} $$ , andB 1 $$ {\mathrm{B}}_1 $$ was evaluated. The optimized protocol (scan time of 19 min) was then tested in a exploratory healthy volunteer study (10 volunteers, mean age 24± $$ \pm $$ 3, six males) at 3 T with a repeat scan taken after repositioning to allow estimation of repeatability.

RESULTS

Simulations show that assuming literature values forT 1 , b $$ {\mathrm{T}}_{1,b} $$ andT 1 , t $$ {\mathrm{T}}_{1,t} $$ , no variation inB 1 $$ {\mathrm{B}}_1 $$ , while fitting onlyv b $$ {v}_b $$ andτ b $$ {\tau}_b $$ , leads to large errors in quantification ofv b $$ {v}_b $$ andτ b $$ {\tau}_b $$ , regardless of noise levels. However, simulations also show that matchingT 1 , t $$ {\mathrm{T}}_{1,t} $$ ,T 1 , b $$ {\mathrm{T}}_{1,b} $$ ,B 1 + $$ {\mathrm{B}}_1^{+} $$ ,v b $$ {v}_b $$ andτ b $$ {\tau}_b $$ , simultaneously is feasible at clinically achievable noise levels. Across the healthy volunteers, all parameter quantifications fell within the expected literature range. In addition, the maps show good agreement between hemispheres suggesting physiologically relevant information is being extracted. Expected differences between white and gray matterT 1 , t $$ {\mathrm{T}}_{1,t} $$ (p < 0.0001) andv b $$ {v}_b $$ (p < 0.0001) are observed,T 1 , b $$ {\mathrm{T}}_{1,b} $$ andτ b $$ {\tau}_b $$ show no significant differences, p = 0.4 and p = 0.6, respectively. Moderate to excellent repeatability was seen between repeat scans: mean intra-class correlation coefficient ofT 1 , t : 0 . 91 $$ {\mathrm{T}}_{1,t}:0.91 $$ ,T 1 , b : 0 . 58 $$ {\mathrm{T}}_{1,b}:0.58 $$ ,v b : 0 . 90 $$ {v}_b:0.90 $$ , andτ b : 0 . 96 $$ {\tau}_b:0.96 $$ .

CONCLUSION

We demonstrate that regional simultaneous quantification ofv b $$ {v}_b $$ ,τ b $$ {\tau}_b $$ ,T 1 , b , T 1 , t $$ {\mathrm{T}}_{1,b},{T}_{1,t} $$ , andB 1 + $$ {\mathrm{B}}_1^{+} $$ using MRF is feasible in vivo.

Bias-reduced neural networks for parameter estimation in quantitative MRI

PURPOSE

To develop neural network (NN)-based quantitative MRI parameter estimators with minimal bias and a variance close to the Cramér-Rao bound.

THEORY AND METHODS

We generalize the mean squared error loss to control the bias and variance of the NN's estimates, which involves averaging over multiple noise realizations of the same measurements during training. Bias and variance properties of the resulting NNs are studied for two neuroimaging applications.

RESULTS

In simulations, the proposed strategy reduces the estimates' bias throughout parameter space and achieves a variance close to the Cramér-Rao bound. In vivo, we observe good concordance between parameter maps estimated with the proposed NNs and traditional estimators, such as nonlinear least-squares fitting, while state-of-the-art NNs show larger deviations.

CONCLUSION

The proposed NNs have greatly reduced bias compared to those trained using the mean squared error and offer significantly improved computational efficiency over traditional estimators with comparable or better accuracy.

A joint ESTRO and AAPM guideline for development, clinical validation and reporting of artificial intelligence models in radiation therapy

BACKGROUND AND PURPOSE

Artificial Intelligence (AI) models in radiation therapy are being developed with increasing pace. Despite this, the radiation therapy community has not widely adopted these models in clinical practice. A cohesive guideline on how to develop, report and clinically validate AI algorithms might help bridge this gap.

METHODS AND MATERIALS

A Delphi process with all co-authors was followed to determine which topics should be addressed in this comprehensive guideline. Separate sections of the guideline, including Statements, were written by subgroups of the authors and discussed with the whole group at several meetings. Statements were formulated and scored as highly recommended or recommended.

RESULTS

The following topics were found most relevant: Decision making, image analysis, volume segmentation, treatment planning, patient specific quality assurance of treatment delivery, adaptive treatment, outcome prediction, training, validation and testing of AI model parameters, model availability for others to verify, model quality assurance/updates and upgrades, ethics. Key references were given together with an outlook on current hurdles and possibilities to overcome these. 19 Statements were formulated.

CONCLUSION

A cohesive guideline has been written which addresses main topics regarding AI in radiation therapy. It will help to guide development, as well as transparent and consistent reporting and validation of new AI tools and facilitate adoption.

Recurrent neural network-based simultaneous cardiac T1, T2, and T1ρ mapping

The purpose of the current study was to explore the feasibility of training a deep neural network to accelerate the process of generating T1, T2, and T1ρ maps for a recently proposed free-breathing cardiac multiparametric mapping technique, where a recurrent neural network (RNN) was utilized to exploit the temporal correlation among the multicontrast images. The RNN-based model was developed for rapid and accurate T1, T2, and T1ρ estimation. Bloch simulation was performed to simulate a dataset of more than 10 million signals and time correspondences with different noise levels for network training. The proposed RNN-based method was compared with a dictionary-matching method and a conventional mapping method to evaluate the model's effectiveness in phantom and in vivo studies at 3 T, respectively. In phantom studies, the RNN-based method and the dictionary-matching method achieved similar accuracy and precision in T1, T2, and T1ρ estimations. In in vivo studies, the estimated T1, T2, and T1ρ values obtained by the two methods achieved similar accuracy and precision for 10 healthy volunteers (T1: 1228.70 ± 53.80 vs. 1228.34 ± 52.91 ms, p > 0.1; T2: 40.70 ± 2.89 vs. 41.19 ± 2.91 ms, p > 0.1; T1ρ: 45.09 ± 4.47 vs. 45.23 ± 4.65 ms, p > 0.1). The RNN-based method can generate cardiac multiparameter quantitative maps simultaneously in just 2 s, achieving 60-fold acceleration compared with the dictionary-matching method. The RNN-accelerated method offers an almost instantaneous approach for reconstructing accurate T1, T2, and T1ρ maps, being much more efficient than the dictionary-matching method for the free-breathing multiparametric cardiac mapping technique, which may pave the way for inline mapping in clinical applications.

Deep learning for accelerated and robust MRI reconstruction

Deep learning (DL) has recently emerged as a pivotal technology for enhancing magnetic resonance imaging (MRI), a critical tool in diagnostic radiology. This review paper provides a comprehensive overview of recent advances in DL for MRI reconstruction, and focuses on various DL approaches and architectures designed to improve image quality, accelerate scans, and address data-related challenges. It explores end-to-end neural networks, pre-trained and generative models, and self-supervised methods, and highlights their contributions to overcoming traditional MRI limitations. It also discusses the role of DL in optimizing acquisition protocols, enhancing robustness against distribution shifts, and tackling biases. Drawing on the extensive literature and practical insights, it outlines current successes, limitations, and future directions for leveraging DL in MRI reconstruction, while emphasizing the potential of DL to significantly impact clinical imaging practices.Affiliations [3 and 6] has been split into two different affiliations. Please check if action taken is appropriate and amend if necessary.looks good.

Improved quantitative parameter estimation for prostate T2 relaxometry using convolutional neural networks

OBJECTIVE

Quantitative parameter mapping conventionally relies on curve fitting techniques to estimate parameters from magnetic resonance image series. This study compares conventional curve fitting techniques to methods using neural networks (NN) for measuring T2 in the prostate.

MATERIALS AND METHODS

Large physics-based synthetic datasets simulating T2 mapping acquisitions were generated for training NNs and for quantitative performance comparisons. Four combinations of different NN architectures and training corpora were implemented and compared with four different curve fitting strategies. All methods were compared quantitatively using synthetic data with known ground truth, and further compared on in vivo test data, with and without noise augmentation, to evaluate feasibility and noise robustness.

RESULTS

In the evaluation on synthetic data, a convolutional neural network (CNN), trained in a supervised fashion using synthetic data generated from naturalistic images, showed the highest overall accuracy and precision amongst the methods. On in vivo data, this best performing method produced low-noise T2 maps and showed the least deterioration with increasing input noise levels.

DISCUSSION

This study showed that a CNN, trained with synthetic data in a supervised manner, may provide superior T2 estimation performance compared to conventional curve fitting, especially in low signal-to-noise regions.

Deep magnetic resonance fingerprinting based on Local and Global Vision Transformer

To mitigate systematic errors in magnetic resonance fingerprinting (MRF), the precomputed dictionary is usually computed with minimal granularity across the entire range of tissue parameters. However, the dictionary grows exponentially with the number of parameters increase, posing significant challenges to the computational efficiency and matching accuracy of pattern-matching algorithms. Existing works, primarily based on convolutional neural networks (CNN), focus solely on local information to reconstruct multiple parameter maps, lacking in-depth investigations on the MRF mechanism. These methods may not exploit long-distance redundancies and the contextual information within voxel fingerprints introduced by the Bloch equation dynamics, leading to limited reconstruction speed and accuracy. To overcome these limitations, we propose a novel end-to-end neural network called the Local and Global Vision Transformer (LG-ViT) for MRF parameter reconstruction. Our proposed LG-ViT employs a multi-stage architecture that effectively reduces the computational overhead associated with the high-dimensional MRF data and the transformer model. Specifically, a local Transformer encoder is proposed to capture contextual information embedded within voxel fingerprints and local correlations introduced by the interconnected human tissues. Additionally, a global Transformer encoder is proposed to leverage long-distance dependencies arising from shared characteristics among different tissues across various spatial regions. By incorporating MRF physics-based data priors and effectively capturing local and global correlations, our proposed LG-ViT can achieve fast and accurate MRF parameter reconstruction. Experiments on both simulation and in vivo data demonstrate that the proposed method enables faster and more accurate MRF parameter reconstruction compared to state-of-the-art deep learning-based methods.

Improving quantitative MRI using self-supervised deep learning with model reinforcement: Demonstration for rapid T1 mapping

PURPOSE

This paper proposes a novel self-supervised learning framework that uses model reinforcement, REference-free LAtent map eXtraction with MOdel REinforcement (RELAX-MORE), for accelerated quantitative MRI (qMRI) reconstruction. The proposed method uses an optimization algorithm to unroll an iterative model-based qMRI reconstruction into a deep learning framework, enabling accelerated MR parameter maps that are highly accurate and robust.

METHODS

Unlike conventional deep learning methods which require large amounts of training data, RELAX-MORE is a subject-specific method that can be trained on single-subject data through self-supervised learning, making it accessible and practically applicable to many qMRI studies. Using quantitativeT 1 $$ {\mathrm{T}}_1 $$ mapping as an example, the proposed method was applied to the brain, knee and phantom data.

RESULTS

The proposed method generates high-quality MR parameter maps that correct for image artifacts, removes noise, and recovers image features in regions of imperfect image conditions. Compared with other state-of-the-art conventional and deep learning methods, RELAX-MORE significantly improves efficiency, accuracy, robustness, and generalizability for rapid MR parameter mapping.

CONCLUSION

This work demonstrates the feasibility of a new self-supervised learning method for rapid MR parameter mapping, that is readily adaptable to the clinical translation of qMRI.

Magnetic resonance relaxometry in quantitative imaging of brain gliomas: A literature review

Magnetic resonance (MR) relaxometry is a quantitative imaging method that measures tissue relaxation properties. This review discusses the state of the art of clinical proton MR relaxometry for glial brain tumors. Current MR relaxometry technology also includes MR fingerprinting and synthetic MRI, which solve the inefficiencies and challenges of earlier techniques. Despite mixed results regarding its capability for brain tumor differential diagnosis, there is growing evidence that MR relaxometry can differentiate between gliomas and metastases and between glioma grades. Studies of the peritumoral zones have demonstrated their heterogeneity and possible directions of tumor infiltration. In addition, relaxometry offers T2* mapping that can define areas of tissue hypoxia not discriminated by perfusion assessment. Studies of tumor therapy response have demonstrated an association between survival and progression terms and dynamics of native and contrast-enhanced tumor relaxometric profiles. In conclusion, MR relaxometry is a promising technique for glial tumor diagnosis, particularly in association with neuropathological studies and other imaging techniques.

High-resolution myelin-water fraction and quantitative relaxation mapping using 3D ViSTa-MR fingerprinting

PURPOSE

This study aims to develop a high-resolution whole-brain multi-parametric quantitative MRI approach for simultaneous mapping of myelin-water fraction (MWF), T1, T2, and proton-density (PD), all within a clinically feasible scan time.

METHODS

We developed 3D visualization of short transverse relaxation time component (ViSTa)-MRF, which combined ViSTa technique with MR fingerprinting (MRF), to achieve high-fidelity whole-brain MWF and T1/T2/PD mapping on a clinical 3T scanner. To achieve fast acquisition and memory-efficient reconstruction, the ViSTa-MRF sequence leverages an optimized 3D tiny-golden-angle-shuffling spiral-projection acquisition and joint spatial-temporal subspace reconstruction with optimized preconditioning algorithm. With the proposed ViSTa-MRF approach, high-fidelity direct MWF mapping was achieved without a need for multicompartment fitting that could introduce bias and/or noise from additional assumptions or priors.

RESULTS

The in vivo results demonstrate the effectiveness of the proposed acquisition and reconstruction framework to provide fast multi-parametric mapping with high SNR and good quality. The in vivo results of 1 mm- and 0.66 mm-isotropic resolution datasets indicate that the MWF values measured by the proposed method are consistent with standard ViSTa results that are 30× slower with lower SNR. Furthermore, we applied the proposed method to enable 5-min whole-brain 1 mm-iso assessment of MWF and T1/T2/PD mappings for infant brain development and for post-mortem brain samples.

CONCLUSIONS

In this work, we have developed a 3D ViSTa-MRF technique that enables the acquisition of whole-brain MWF, quantitative T1, T2, and PD maps at 1 and 0.66 mm isotropic resolution in 5 and 15 min, respectively. This advancement allows for quantitative investigations of myelination changes in the brain.

Phase-sensitive deep reconstruction method for rapid multiparametric MR fingerprinting and quantitative susceptibility mapping in the brain

INTRODUCTION

This study explores the potential of Magnetic Resonance Fingerprinting (MRF) with a novel Phase-Sensitivity Deep Reconstruction Network (PS-DRONE) for simultaneous quantification of T1, T2, Proton Density, B1+, phase and quantitative susceptibility mapping (QSM).

METHODS

Data were acquired at 3 T in vitro and in vivo using an optimized EPI-based MRF sequence. Phantom experiments were conducted using a standardized phantom for T1 and T2 maps and a custom-made agar-based gadolinium phantom for B1 and QSM maps. In vivo experiments included five healthy volunteers and one patient diagnosed with brain metastasis. PSDRONE maps were compared to reference maps obtained through standard imaging sequences.

RESULTS

Total scan time was 2 min for 32 slices and a resolution of [1 mm, 1 mm, 4.5 mm]. The reconstruction of T1, T2, Proton Density, B1+ and phase maps were reconstructed within 1 s. In the phantoms, PS-DRONE analysis presented accurate and strongly correlated T1 and T2 maps (r = 0.99) compared to the reference maps. B1 maps from PS-DRONE showed slightly higher values, though still correlated (r = 0.6) with the reference. QSM values showed a small bias but were strongly correlated (r = 0.99) with reference data. In the in vivo analysis, PS-DRONE-derived T1 and T2 values for gray and white matter matched reference values in healthy volunteers. PS-DRONE B1 and QSM maps showed strong correlations with reference values.

CONCLUSION

The PS-DRONE network enables concurrent acquisition of T1, T2, PD, B1+, phase and QSM maps, within 2 min of acquisition time and 1 s of reconstruction time.

DCE-Qnet: Deep Network Quantification of Dynamic Contrast Enhanced (DCE) MRI

Introduction

Quantification of dynamic contrast-enhanced (DCE)-MRI has the potential to provide valuable clinical information, but robust pharmacokinetic modeling remains a challenge for clinical adoption.

Methods

A 7-layer neural network called DCE-Qnet was trained on simulated DCE-MRI signals derived from the Extended Tofts model with the Parker arterial input function. Network training incorporated B1 inhomogeneities to estimate perfusion (Ktrans, vp, ve), tissue T1 relaxation, proton density and bolus arrival time (BAT). The accuracy was tested in a digital phantom in comparison to a conventional nonlinear least-squares fitting (NLSQ). In vivo testing was conducted in 10 healthy subjects. Regions of interest in the cervix and uterine myometrium were used to calculate the inter-subject variability. The clinical utility was demonstrated on a cervical cancer patient. Test-retest experiments were used to assess reproducibility of the parameter maps in the tumor.

Results

The DCE-Qnet reconstruction outperformed NLSQ in the phantom. The coefficient of variation (CV) in the healthy cervix varied between 5-51% depending on the parameter. Parameter values in the tumor agreed with previous studies despite differences in methodology. The CV in the tumor varied between 1-47%.

Conclusion

The proposed approach provides comprehensive DCE-MRI quantification from a single acquisition. DCE-Qnet eliminates the need for separate T1 scan or BAT processing, leading to a reduction of 10 minutes per scan and more accurate quantification.

Machine learning-based amide proton transfer imaging using partially synthetic training data

PURPOSE

Machine learning (ML) has been increasingly used to quantify CEST effect. ML models are typically trained using either measured data or fully simulated data. However, training with measured data often lacks sufficient training data, whereas training with fully simulated data may introduce bias because of limited simulations pools. This study introduces a new platform that combines simulated and measured components to generate partially synthetic CEST data, and to evaluate its feasibility for training ML models to predict amide proton transfer (APT) effect.

METHODS

Partially synthetic CEST signals were created using an inverse summation of APT effects from simulations and the other components from measurements. Training data were generated by varying APT simulation parameters and applying scaling factors to adjust the measured components, achieving a balance between simulation flexibility and fidelity. First, tissue-mimicking CEST signals along with ground truth information were created using multiple-pool model simulations to validate this method. Second, an ML model was trained individually on partially synthetic data, in vivo data, and fully simulated data, to predict APT effect in rat brains bearing 9 L tumors.

RESULTS

Experiments on tissue-mimicking data suggest that the ML method using the partially synthetic data is accurate in predicting APT. In vivo experiments suggest that our method provides more accurate and robust prediction than the training using in vivo data and fully synthetic data.

CONCLUSION

Partially synthetic CEST data can address the challenges in conventional ML methods.

Bias-Reduced Neural Networks for Parameter Estimation in Quantitative MRI

Purpose

To develop neural network (NN)-based quantitative MRI parameter estimators with minimal bias and a variance close to the Cramér-Rao bound.

Theory and Methods

We generalize the mean squared error loss to control the bias and variance of the NN's estimates, which involves averaging over multiple noise realizations of the same measurements during training. Bias and variance properties of the resulting NNs are studied for two neuroimaging applications.

Results

In simulations, the proposed strategy reduces the estimates' bias throughout parameter space and achieves a variance close to the Cramér-Rao bound. In vivo, we observe good concordance between parameter maps estimated with the proposed NNs and traditional estimators, such as non-linear least-squares fitting, while state-of-the-art NNs show larger deviations.

Conclusion

The proposed NNs have greatly reduced bias compared to those trained using the mean squared error and offer significantly improved computational efficiency over traditional estimators with comparable or better accuracy.

Rapid quantitative magnetization transfer imaging: Utilizing the hybrid state and the generalized Bloch model

PURPOSE

To explore efficient encoding schemes for quantitative magnetization transfer (qMT) imaging with few constraints on model parameters.

THEORY AND METHODS

We combine two recently proposed models in a Bloch-McConnell equation: the dynamics of the free spin pool are confined to the hybrid state, and the dynamics of the semi-solid spin pool are described by the generalized Bloch model. We numerically optimize the flip angles and durations of a train of radio frequency pulses to enhance the encoding of three qMT parameters while accounting for all eight parameters of the two-pool model. We sparsely sample each time frame along this spin dynamics with a three-dimensional radial koosh-ball trajectory, reconstruct the data with subspace modeling, and fit the qMT model with a neural network for computational efficiency.

RESULTS

We extracted qMT parameter maps of the whole brain with an effective resolution of 1.24 mm from a 12.6-min scan. In lesions of multiple sclerosis subjects, we observe a decreased size of the semi-solid spin pool and longer relaxation times, consistent with previous reports.

CONCLUSION

The encoding power of the hybrid state, combined with regularized image reconstruction, and the accuracy of the generalized Bloch model provide an excellent basis for efficient quantitative magnetization transfer imaging with few constraints on model parameters.

Nonuniform sliding-window reconstruction for accelerated dual contrast agent quantification with MR fingerprinting

OBJECTIVE

MR fingerprinting (MRF) can enable preclinical studies of cell tracking by quantifying multiple contrast agents simultaneously, but faster scan times are required for in vivo applications. Sliding window (SW)-MRF is one option for accelerating MRF, but standard implementations are not sufficient to preserve the accuracy of T2*, which is critical for tracking iron-labelled cells in vivo.

PURPOSE

To develop a SW approach to MRF which preserves the T2* accuracy required for accelerated concentration mapping of iron-labelled cells on single-channel preclinical systems.

METHODS

A nonuniform SW was applied to the MRF sequence and dictionary. Segments of the sequence most sensitive to T2* were subject to a shorter window length, preserving the T2* sensitivity. Phantoms containing iron-labelled CD8+ T cells and gadolinium were used to compare 24× undersampled uniform and nonuniform SW-MRF parameter maps. Dual concentration maps were generated for both uniform and nonuniform MRF and compared.

RESULTS

Lin's concordance correlation coefficient, compared to gold standard parameter values, was much greater for nonuniform SW-MRF than for uniform SW-MRF. A Wilcoxon signed-rank test showed no significant difference between nonuniform SW-MRF and gold standards. Nonuniform SW-MRF outperformed the uniform SW-MRF concentration maps for all parameters, providing a balance between T2* sensitivity of short window lengths, and SNR of longer window lengths.

CONCLUSIONS

Nonuniform SW-MRF improves the accuracy of matching compared to uniform SW-MRF, allowing higher accelerated concentration mapping for preclinical systems.

Unconstrained quantitative magnetization transfer imaging: disentangling T1 of the free and semi-solid spin pools

Since the inception of magnetization transfer (MT) imaging, it has been widely assumed that Henkelman's two spin pools have similar longitudinal relaxation times, which motivated many researchers to constrain them to each other. However, several recent publications reported a T 1 s of the semi-solid spin pool that is much shorter than T 1 f of the free pool. While these studies tailored experiments for robust proofs-of-concept, we here aim to quantify the disentangled relaxation processes on a voxel-by-voxel basis in a clinical imaging setting, i.e., with an effective resolution of 1.24mm isotropic and full brain coverage in 12min. To this end, we optimized a hybrid-state pulse sequence for mapping the parameters of an unconstrained MT model. We scanned four people with relapsing-remitting multiple sclerosis (MS) and four healthy controls with this pulse sequence and estimated T 1 f ≈ 1.84 s and T 1 s ≈ 0.34 s in healthy white matter. Our results confirm the reports that T 1 s ≪ T 1 f and we argue that this finding identifies MT as an inherent driver of longitudinal relaxation in brain tissue. Moreover, we estimated a fractional size of the semi-solid spin pool of m 0 s ≈ 0.212 , which is larger than previously assumed. An analysis of T 1 f in normal-appearing white matter revealed statistically significant differences between individuals with MS and controls.

SwinUNet: a multiscale feature learning approach to cardiovascular magnetic resonance parametric mapping for myocardial tissue characterization

Objective.Cardiovascular magnetic resonance (CMR) can measure T1 and T2 relaxation times for myocardial tissue characterization. However, the CMR procedure for T1/T2 parametric mapping is time-consuming, making it challenging to scan heart patients routinely in clinical practice. This study aims to accelerate CMR parametric mapping with deep learning.Approach. A deep-learning model, SwinUNet, was developed to accelerate T1/T2 mapping. SwinUNet used a convolutional UNet and a Swin transformer to form a hierarchical 3D computation structure, allowing for analyzing CMR images spatially and temporally with multiscale feature learning. A comparative study was conducted between SwinUNet and an existing deep-learning model, MyoMapNet, which only used temporal analysis for parametric mapping. The T1/T2 mapping performance was evaluated globally using mean absolute error (MAE) and structural similarity index measure (SSIM). The clinical T1/T2 indices for characterizing the left-ventricle myocardial walls were also calculated and evaluated using correlation and Bland-Altman analysis.Main results. We performed accelerated T1 mapping with ≤4 heartbeats and T2 mapping with 2 heartbeats in reference to the clinical standard, which required 11 heartbeats for T1 mapping and 3 heartbeats for T2 mapping. SwinUNet performed well in all the experiments (MAE < 50 ms, SSIM > 0.8, correlation > 0.75, and Bland-Altman agreement limits < 100 ms for T1 mapping; MAE < 1 ms, SSIM > 0.9, correlation > 0.95, and Bland-Altman agreement limits < 1.5 ms for T2 mapping). When the maximal acceleration was used (2 heartbeats), SwinUNet outperformed MyoMapNet and gave measurement accuracy similar to the clinical standard.Significance. SwinUNet offers an optimal solution to CMR parametric mapping for assessing myocardial diseases quantitatively in clinical cardiology.

Bi-component dictionary matching for MR fingerprinting for efficient quantification of fat fraction and water T1 in skeletal muscle

PURPOSE

To propose an efficient bi-component MR fingerprinting (MRF) fitting method using a Variable Projection (VARPRO) strategy, applied to the quantification of fat fraction (FF) and water T1 (T 1 H 2 0 $$ \mathrm{T}{1}_{{\mathrm{H}}_20} $$ ) in skeletal muscle tissues.

METHODS

The MRF signals were analyzed in a two-step process by comparing them to the elements of separate water and fat dictionaries (bi-component dictionary matching). First, each pair of water and fat dictionary elements was fitted to the acquired signal to determine an optimal FF that was used to merge the fingerprints in a combined water/fat dictionary. Second, standard dictionary matching was applied to the combined dictionary for determining the remaining parameters. A clustering method was implemented to further accelerate the fitting. Accuracy, precision, and matching time of this approach were evaluated on both numerical and in vivo datasets, and compared to the reference dictionary-matching approach that includes FF as a dictionary parameter.

RESULTS

In numerical phantoms, all MRF parameters showed high correlation with ground truth for the reference and the bi-component method (R2  > 0.98). In vivo, the estimated parameters from the proposed method were highly correlated with those from the reference approach (R2  > 0.997). The bi-component method achieved an acceleration factor of up to 360 compared to the reference dictionary matching.

CONCLUSION

The proposed bi-component fitting approach enables a significant acceleration of the reconstruction of MRF parameter maps for fat-water imaging, while maintaining comparable precision and accuracy to the reference on FF andT 1 H 2 0 $$ \mathrm{T}{1}_{{\mathrm{H}}_20} $$ estimation.

Deep learning-assisted preclinical MR fingerprinting for sub-millimeter T1 and T2 mapping of entire macaque brain

PURPOSE

Preclinical MR fingerprinting (MRF) suffers from long acquisition time for organ-level coverage due to demanding image resolution and limited undersampling capacity. This study aims to develop a deep learning-assisted fast MRF framework for sub-millimeter T1 and T2 mapping of entire macaque brain on a preclinical 9.4 T MR system.

METHODS

Three dimensional MRF images were reconstructed by singular value decomposition (SVD) compressed reconstruction. T1 and T2 mapping for each axial slice exploited a self-attention assisted residual U-Net to suppress aliasing-induced quantification errors, and the transmit-field (B1 + ) measurements for robustness against B1 + inhomogeneity. Supervised network training used MRF images simulated via virtual parametric maps and a desired undersampling scheme. This strategy bypassed the difficulties of acquiring fully sampled preclinical MRF data to guide network training. The proposed fast MRF framework was tested on experimental data acquired from ex vivo and in vivo macaque brains.

RESULTS

The trained network showed reasonable adaptability to experimental MRF images, enabling robust delineation of various T1 and T2 distributions in the brain tissues. Further, the proposed MRF framework outperformed several existing fast MRF methods in handling the aliasing artifacts and capturing detailed cerebral structures in the mapping results. Parametric mapping of entire macaque brain at nominal resolution of 0.35× $$ \times $$ 0.35× $$ \times $$ 1 mm3 can be realized via a 20-min 3D MRF scan, which was sixfold faster than the baseline protocol.

CONCLUSION

Introducing deep learning to MRF framework paves the way for efficient organ-level high-resolution quantitative MRI in preclinical applications.

Emerging Trends in Magnetic Resonance Fingerprinting for Quantitative Biomedical Imaging Applications: A Review

Magnetic resonance imaging (MRI) stands as a vital medical imaging technique, renowned for its ability to offer high-resolution images of the human body with remarkable soft-tissue contrast. This enables healthcare professionals to gain valuable insights into various aspects of the human body, including morphology, structural integrity, and physiological processes. Quantitative imaging provides compositional measurements of the human body, but, currently, either it takes a long scan time or is limited to low spatial resolutions. Undersampled k-space data acquisitions have significantly helped to reduce MRI scan time, while compressed sensing (CS) and deep learning (DL) reconstructions have mitigated the associated undersampling artifacts. Alternatively, magnetic resonance fingerprinting (MRF) provides an efficient and versatile framework to acquire and quantify multiple tissue properties simultaneously from a single fast MRI scan. The MRF framework involves four key aspects: (1) pulse sequence design; (2) rapid (undersampled) data acquisition; (3) encoding of tissue properties in MR signal evolutions or fingerprints; and (4) simultaneous recovery of multiple quantitative spatial maps. This paper provides an extensive literature review of the MRF framework, addressing the trends associated with these four key aspects. There are specific challenges in MRF for all ranges of magnetic field strengths and all body parts, which can present opportunities for further investigation. We aim to review the best practices in each key aspect of MRF, as well as for different applications, such as cardiac, brain, and musculoskeletal imaging, among others. A comprehensive review of these applications will enable us to assess future trends and their implications for the translation of MRF into these biomedical imaging applications.

Simultaneous perfusion, diffusion, T2 *, and T1 mapping with MR fingerprinting

PURPOSE

Quantitative mapping of brain perfusion, diffusion, T2 *, and T1 has important applications in cerebrovascular diseases. At present, these sequences are performed separately. This study aims to develop a novel MRI technique to simultaneously estimate these parameters.

METHODS

This sequence to measure perfusion, diffusion, T2 *, and T1 mapping with magnetic resonance fingerprinting (MRF) was based on a previously reported MRF-arterial spin labeling (ASL) sequence, but the acquisition module was modified to include different TEs and presence/absence of bipolar diffusion-weighting gradients. We compared parameters derived from the proposed method to those derived from reference methods (i.e., separate sequences of MRF-ASL, conventional spin-echo DWI, and T2 * mapping). Test-retest repeatability and initial clinical application in two patients with stroke were evaluated.

RESULTS

The scan time of our proposed method was 24% shorter than the sum of the reference methods. Parametric maps obtained from the proposed method revealed excellent image quality. Their quantitative values were strongly correlated with those from reference methods and were generally in agreement with values reported in the literature. Repeatability assessment revealed that ADC, T2 *, T1 , and B1 + estimation was highly reliable, with voxelwise coefficient of variation (CoV) <5%. The CoV for arterial transit time and cerebral blood flow was 16% ± 3% and 25% ± 9%, respectively. The results from the two patients with stroke demonstrated that parametric maps derived from the proposed method can detect both ischemic and hemorrhagic stroke.

CONCLUSION

The proposed method is a promising technique for multi-parametric mapping and has potential use in patients with stroke.

The future of cardiovascular magnetic resonance: All-in-one vs. real-time (Part 1)

Cardiovascular magnetic resonance (CMR) protocols can be lengthy and complex, which has driven the research community to develop new technologies to make these protocols more efficient and patient-friendly. Two different approaches to improving CMR have been proposed, specifically "all-in-one" CMR, where several contrasts and/or motion states are acquired simultaneously, and "real-time" CMR, in which the examination is accelerated to avoid the need for breathholding and/or cardiac gating. The goal of this two-part manuscript is to describe these two different types of emerging rapid CMR. To this end, the vision of each is described, along with techniques which have been devised and tested along the pathway of clinical implementation. The pros and cons of the different methods are presented, and the remaining open needs of each are detailed. Part 1 will tackle the "all-in-one" approaches, and Part 2 the "real-time" approaches along with an overall summary of these emerging methods.

Fast deep learning reconstruction techniques for preclinical magnetic resonance fingerprinting

We propose a deep learning (DL) model and a hyperparameter optimization strategy to reconstruct T1 and T2 maps acquired with the magnetic resonance fingerprinting (MRF) methodology. We applied two different MRF sequence routines to acquire images of ex vivo rat brain phantoms using a 7-T preclinical scanner. Subsequently, the DL model was trained using experimental data, completely excluding the use of any theoretical MRI signal simulator. The best combination of the DL parameters was implemented by an automatic hyperparameter optimization strategy, whose key aspect is to include all the parameters to the fit, allowing the simultaneous optimization of the neural network architecture, the structure of the DL model, and the supervised learning algorithm. By comparing the reconstruction performances of the DL technique with those achieved from the traditional dictionary-based method on an independent dataset, the DL approach was shown to reduce the mean percentage relative error by a factor of 3 for T1 and by a factor of 2 for T2 , and to improve the computational time by at least a factor of 37. Furthermore, the proposed DL method enables maintaining comparable reconstruction performance, even with a lower number of MRF images and a reduced k-space sampling percentage, with respect to the dictionary-based method. Our results suggest that the proposed DL methodology may offer an improvement in reconstruction accuracy, as well as speeding up MRF for preclinical, and in prospective clinical, investigations.

Scanner-Independent MyoMapNet for Accelerated Cardiac MRI T1 Mapping Across Vendors and Field Strengths

BACKGROUND

In cardiac T1 mapping, a series of T1 -weighted (T1 w) images are collected and numerically fitted to a two or three-parameter model of the signal recovery to estimate voxel-wise T1 values. To reduce the scan time, one can collect fewer T1 w images, albeit at the cost of precision or/and accuracy. Recently, the feasibility of using a neural network instead of conventional two- or three-parameter fit modeling has been demonstrated. However, prior studies used data from a single vendor and field strength; therefore, the generalizability of the models has not been established.

PURPOSE

To develop and evaluate an accelerated cardiac T1 mapping approach based on MyoMapNet, a convolution neural network T1 estimator that can be used across different vendors and field strengths by incorporating the relevant scanner information as additional inputs to the model.

STUDY TYPE

Retrospective, multicenter.

POPULATION

A total of 1423 patients with known or suspected cardiac disease (808 male, 57 ± 16 years), from three centers, two vendors (Siemens, Philips), and two field strengths (1.5 T, 3 T). The data were randomly split into 60% training, 20% validation, and 20% testing.

FIELD STRENGTH/SEQUENCE

A 1.5 T and 3 T, Modified Look-Locker inversion recovery (MOLLI) for native and postcontrast T1 .

ASSESSMENT

Scanner-independent MyoMapNet (SI-MyoMapNet) was developed by altering the deep learning (DL) architecture of MyoMapNet to incorporate scanner vendor and field strength as inputs. Epicardial and endocardial contours and blood pool (by manually drawing a large region of interest in the blood pool) of the left ventricle were manually delineated by three readers, with 2, 8, and 9 years of experience, and SI-MyoMapNet myocardial and blood pool T1 values (calculated from four T1 w images) were compared with conventional MOLLI T1 values (calculated from 8 to 11 T1 w images).

STATISTICAL TESTS

Equivalency test with 95% confidence interval (CI), linear regression slope, Pearson correlation coefficient (r), Bland-Altman analysis.

RESULTS

The proposed SI-MyoMapNet successfully created T1 maps. Native and postcontrast T1 values measured from SI-MyoMapNet were strongly correlated with MOLLI, despite using only four T1 w images, at both field-strengths and vendors (all r > 0.86). For native T1 , SI-MyoMapNet and MOLLI were in good agreement for myocardial and blood T1 values in institution 1 (myocardium: 5 msec, 95% CI [3, 8]; blood: -10 msec, 95%CI [-16, -4]), in institution 2 (myocardium: 6 msec, 95% CI [0, 11]; blood: 0 msec, [-18, 17]), and in institution 3 (myocardium: 7 msec, 95% CI [-8, 22]; blood: 8 msec, [-14, 30]). Similar results were observed for postcontrast T1 .

DATA CONCLUSION

Inclusion of field strength and vendor as additional inputs to the DL architecture allows generalizability of MyoMapNet across different vendors or field strength.

EVIDENCE LEVEL

2.

TECHNICAL EFFICACY

Stage 2.

High-resolution myelin-water fraction and quantitative relaxation mapping using 3D ViSTa-MR fingerprinting

Purpose

This study aims to develop a high-resolution whole-brain multi-parametric quantitative MRI approach for simultaneous mapping of myelin-water fraction (MWF), T1, T2, and proton-density (PD), all within a clinically feasible scan time.

Methods

We developed 3D ViSTa-MRF, which combined Visualization of Short Transverse relaxation time component (ViSTa) technique with MR Fingerprinting (MRF), to achieve high-fidelity whole-brain MWF and T1/T2/PD mapping on a clinical 3T scanner. To achieve fast acquisition and memory-efficient reconstruction, the ViSTa-MRF sequence leverages an optimized 3D tiny-golden-angle-shuffling spiral-projection acquisition and joint spatial-temporal subspace reconstruction with optimized preconditioning algorithm. With the proposed ViSTa-MRF approach, high-fidelity direct MWF mapping was achieved without a need for multi-compartment fitting that could introduce bias and/or noise from additional assumptions or priors.

Results

The in-vivo results demonstrate the effectiveness of the proposed acquisition and reconstruction framework to provide fast multi-parametric mapping with high SNR and good quality. The in-vivo results of 1mm- and 0.66mm-iso datasets indicate that the MWF values measured by the proposed method are consistent with standard ViSTa results that are 30x slower with lower SNR. Furthermore, we applied the proposed method to enable 5-minute whole-brain 1mm-iso assessment of MWF and T1/T2/PD mappings for infant brain development and for post-mortem brain samples.

Conclusions

In this work, we have developed a 3D ViSTa-MRF technique that enables the acquisition of whole-brain MWF, quantitative T1, T2, and PD maps at 1mm and 0.66mm isotropic resolution in 5 and 15 minutes, respectively. This advancement allows for quantitative investigations of myelination changes in the brain.

SIMPLEX: Multiple phase-cycled bSSFP quantitative magnetization transfer imaging with physic-guided simulation learning of neural network

Most quantitative magnetization transfer (qMT) imaging methods require acquiring additional quantitative maps (such as T1) for data fitting. A method based on multiple phase-cycled bSSFP was recently proposed to enable high-resolution 3D qMT imaging based on least square fitting without any extra acquisition, and thus has high potential for simplifying the qMT procedure. However, the quantification of qMT parameters with this method was suboptimal, limiting its potential for clinical application despite its simpler protocol and higher spatial resolution. To improve the fitting of qMT data obtained with multiple phase-cycled bSSFP, we propose SIMulation-based Physics-guided Learning of neural network for qMT parameters EXtraction, or SIMPLEX. In contrast to previous deep learning supervised approaches for quantitative MR that require the acquisition of input data and corresponding ground truth for training, we leveraged the MR signal model to generate training samples without expensive data curation. The network was trained exclusively with simulation data by predicting the simulation parameters. The same network was applied directly to in-vivo data without additional training. The approach was verified with both simulation and in-vivo data. SIMPLEX showed a decrease in fitting mean squared error for all simulation data compared to the existing least-square fitting method. The in-vivo experiment revealed that the network performed well with the real in vivo data unseen during training. For all experiments, we observed that SIMPLEX consistently improved the quantification quality of the qMT parameters whilst being more robust to noise compared to the prior technique. The proposed SIMPLEX will expedite the routine clinical application of qMT by providing qMT parameters (exchange rate, pool fraction) as well as T1, T2, and ΔB0 maps simultaneously with high spatial resolution, better reliability, and reduced processing time.

Amide Proton Transfer (APT) imaging in tumor with a machine learning approach using partially synthetic data

Purpose

Machine learning (ML) has been increasingly used to quantify chemical exchange saturation transfer (CEST) effect. ML models are typically trained using either measured data or fully simulated data. However, training with measured data often lacks sufficient training data, while training with fully simulated data may introduce bias due to limited simulations pools. This study introduces a new platform that combines simulated and measured components to generate partially synthetic CEST data, and to evaluate its feasibility for training ML models to predict amide proton transfer (APT) effect.

Methods

Partially synthetic CEST signals were created using an inverse summation of APT effects from simulations and the other components from measurements. Training data were generated by varying APT simulation parameters and applying scaling factors to adjust the measured components, achieving a balance between simulation flexibility and fidelity. First, tissue-mimicking CEST signals along with ground truth information were created using multiple-pool model simulations to validate this method. Second, an ML model was trained individually on partially synthetic data, in vivo data, and fully simulated data, to predict APT effect in rat brains bearing 9L tumors.

Results

Experiments on tissue-mimicking data suggest that the ML method using the partially synthetic data is accurate in predicting APT. In vivo experiments suggest that our method provides more accurate and robust prediction than the training using in vivo data and fully synthetic data.

Conclusion

Partially synthetic CEST data can address the challenges in conventional ML methods.

Physics-informed deep learning for T2-deblurred superresolution turbo spin echo MRI

PURPOSE

Deep learning superresolution (SR) is a promising approach to reduce MRI scan time without requiring custom sequences or iterative reconstruction. Previous deep learning SR approaches have generated low-resolution training images by simple k-space truncation, but this does not properly model in-plane turbo spin echo (TSE) MRI resolution degradation, which has variable T2 relaxation effects in different k-space regions. To fill this gap, we developed a T2 -deblurred deep learning SR method for the SR of 3D-TSE images.

METHODS

A SR generative adversarial network was trained using physically realistic resolution degradation (asymmetric T2 weighting of raw high-resolution k-space data). For comparison, we trained the same network structure on previous degradation models without TSE physics modeling. We tested all models for both retrospective and prospective SR with 3 × 3 acceleration factor (in the two phase-encoding directions) of genetically engineered mouse embryo model TSE-MR images.

RESULTS

The proposed method can produce high-quality 3 × 3 SR images for a typical 500-slice volume with 6-7 mouse embryos. Because 3 × 3 SR was performed, the image acquisition time can be reduced from 15 h to 1.7 h. Compared to previous SR methods without TSE modeling, the proposed method achieved the best quantitative imaging metrics for both retrospective and prospective evaluations and achieved the best imaging-quality expert scores for prospective evaluation.

CONCLUSION

The proposed T2 -deblurring method improved accuracy and image quality of deep learning-based SR of TSE MRI. This method has the potential to accelerate TSE image acquisition by a factor of up to 9.

Learned Tensor Low-CP-Rank and Bloch Response Manifold Priors for Non-Cartesian MRF Reconstruction

Magnetic resonance fingerprinting (MRF) can rapidly perform simultaneous imaging of multiple tissue parameters. However, the rapid acquisition schemes used in MRF inevitably introduce aliasing artifacts in the recovered tissue fingerprints, reducing the accuracy of the predicted parameter maps. Current regularized reconstruction methods are based on iterative procedures which are usually time-consuming. In addition, most of the current deep learning-based methods for MRF often lack interpretability owing to the black-box nature, and most deep learning-based methods are not applicable for non-Cartesian scenarios, which limits the practical applications. In this paper, we propose a joint reconstruction model incorporating MRF-physics prior and the data correlation constraint for non-Cartesian MRF reconstruction. To avoid time-consuming iterative procedures, we unroll the reconstruction model into a deep neural network. Specifically, we propose a learned CANDECOMP/PARAFAC (CP) decomposition module to exploit the tensor low-rank priors of high-dimensional MRF data, which avoids computationally burdensome singular value decomposition. Inspired by the MRF-physics, we also propose a Bloch response manifold module to learn the mapping between reconstructed MRF data and the multiple parameter maps. Numerical experiments show that the proposed network can reconstruct high-quality MRF data and multiple parameter maps within significantly reduced computational time.

Cramér-Rao Bound Optimized Subspace Reconstruction in Quantitative MRI

We extend the traditional framework for estimating subspace bases that maximize the preserved signal energy to additionally preserve the Cramér-Rao bound (CRB) of the biophysical parameters and, ultimately, improve accuracy and precision in the quantitative maps. To this end, we introduce an approximate compressed CRB based on orthogonalized versions of the signal's derivatives with respect to the model parameters. This approximation permits singular value decomposition (SVD)-based minimization of both the CRB and signal losses during compression. Compared to the traditional SVD approach, the proposed method better preserves the CRB across all biophysical parameters with negligible cost to the preserved signal energy, leading to reduced bias and variance of the parameter estimates in simulation. In vivo, improved accuracy and precision are observed in two quantitative neuroimaging applications, permitting the use of smaller basis sizes in subspace reconstruction and offering significant computational savings.

Global deep learning optimization of chemical exchange saturation transfer magnetic resonance fingerprinting acquisition schedule

Chemical exchange saturation transfer (CEST) MRI is a promising molecular imaging technique but suffers from long scan times and complicated processing. CEST was recently combined with magnetic resonance fingerprinting (MRF) to address these shortcomings. However, the CEST-MRF signal depends on multiple acquisition and tissue parameters so selecting an optimal acquisition schedule is challenging. In this work, we propose a novel dual-network deep learning framework to optimize the CEST-MRF acquisition schedule. The quality of the optimized schedule was assessed in a digital brain phantom and compared with alternate deep learning optimization approaches. The effect of schedule length on the reconstruction error was also investigated. A healthy subject was scanned with optimized and random schedules and with a conventional CEST sequence for comparison. The optimized schedule was also tested in a subject with metastatic renal cell carcinoma. Reproducibility was assessed via test-retest experiments and the concordance correlation coefficient calculated for white matter (WM) and grey matter (GM). The optimized schedule was 12% shorter but yielded equal or lower normalized root mean square error for all parameters. The proposed optimization also provided a lower error compared with alternate methodologies. Longer schedules generally yielded lower error. In vivo maps obtained with the optimized schedule showed reduced noise and improved delineation of GM and WM. CEST curves synthesized from the optimized parameters were highly correlated (r = 0.99) with measured conventional CEST. The mean concordance correlation coefficient in WM/GM for all tissue parameters was 0.990/0.978 for the optimized schedule but only 0.979/0.975 for the random schedule. The proposed schedule optimization is widely applicable to MRF pulse sequences and provides accurate and reproducible tissue maps with reduced noise at a shorter scan time than a randomly generated schedule.

Tailored magnetic resonance fingerprinting of post-operative pediatric brain tumor patients

PURPOSE

Brain and spinal cord tumors are the second most common cancer in children and account for one out of four cancers diagnosed. However, the long acquisition times associated with acquiring both data types prohibit using quantitative MR (qMR) in pediatric imaging protocols. This study aims to demonstrate the tailored magnetic resonance fingerprinting's (TMRF) ability to simultaneously provide quantitative maps (T1, T2) and multi-contrast qualitative images (T1 weighted, T1 FLAIR, T2 weighted) rapidly in pediatric brain tumor patients.

METHODS

In this work, we imaged five pediatric patients with brain tumors (resected/residual) using TMRF at 3 T. We compared the TMRF-derived T2 weighted images with those from the vendor-supplied sequence (as the gold standard, GS) for healthy and pathological tissue signal intensities. The relaxometric maps from TMRF were subjected to a region of interest (ROI) analysis to differentiate between healthy and pathological tissues. We performed the Wilcoxon rank sum test to check for significant differences between the two tissue types.

RESULTS

We found significant differences (p < 0.05) in both T1 and T2 ROI values between the two tissue types. A strong correlation was found between the TMRF-based T2 weighted and GS signal intensities for the healthy (correlation coefficient, r = 0.99) and pathological tissues (r = 0.88).

CONCLUSION

The TMRF implementation provides the two relaxometric maps and can potentially save ~2 min if it replaces the T2-weighted imaging in the current protocol.

Intravoxel incoherent motion magnetic resonance imaging reconstruction from highly under-sampled diffusion-weighted PROPELLER acquisition data via physics-informed residual feedback unrolled network

Objective. The acquisition of diffusion-weighted images for intravoxel incoherent motion (IVIM) imaging is time consuming. This work aims to accelerate the scan through a highly under-sampling diffusion-weighted turbo spin echo PROPELLER (DW-TSE-PROPELLER) scheme and to develop a reconstruction method for accurate IVIM parameter mapping from the under-sampled data.Approach.The proposed under-sampling DW-TSE-PROPELLER scheme for IVIM imaging is that a few blades perb-value are acquired and rotated along theb-value dimension to cover high-frequency information. A physics-informed residual feedback unrolled network (PIRFU-Net) is proposed to directly estimate distortion-free and artifact-free IVIM parametric maps (i.e., the perfusion-free diffusion coefficientDand the perfusion fractionf) from highly under-sampled DW-TSE-PROPELLER data. PIRFU-Net used an unrolled convolution network to explore data redundancy in the k-q space to remove under-sampling artifacts. An empirical IVIM physical constraint was incorporated into the network to ensure that the signal evolution curves along theb-value follow a bi-exponential decay. The residual between the realistic and estimated measurements was fed into the network to refine the parametric maps. Meanwhile, the use of synthetic training data eliminated the need for genuine DW-TSE-PROPELLER data.Main results.The experimental results show that the DW-TSE-PROPELLER acquisition was six times faster than full k-space coverage PROPELLER acquisition and within a clinically acceptable time. Compared with the state-of-the-art methods, the distortion-freeDandfmaps estimated by PIRFU-Net were more accurate and had better-preserved tissue boundaries on a simulated human brain and realistic phantom/rat brain/human brain data.Significance.Our proposed method greatly accelerates IVIM imaging. It is capable of directly and simultaneously reconstructing distortion-free, artifact-free, and accurateDandfmaps from six-fold under-sampled DW-TSE-PROPELLER data.

Magnetic Resonance Parameter Mapping using Self-supervised Deep Learning with Model Reinforcement

This paper proposes a novel self-supervised learning method, RELAX-MORE, for quantitative MRI (qMRI) reconstruction. The proposed method uses an optimization algorithm to unroll a model-based qMRI reconstruction into a deep learning framework, enabling the generation of highly accurate and robust MR parameter maps at imaging acceleration. Unlike conventional deep learning methods requiring a large amount of training data, RELAX-MORE is a subject-specific method that can be trained on single-subject data through self-supervised learning, making it accessible and practically applicable to many qMRI studies. Using the quantitative T 1 mapping as an example at different brain, knee and phantom experiments, the proposed method demonstrates excellent performance in reconstructing MR parameters, correcting imaging artifacts, removing noises, and recovering image features at imperfect imaging conditions. Compared with other state-of-the-art conventional and deep learning methods, RELAX-MORE significantly improves efficiency, accuracy, robustness, and generalizability for rapid MR parameter mapping. This work demonstrates the feasibility of a new self-supervised learning method for rapid MR parameter mapping, with great potential to enhance the clinical translation of qMRI.

Only-train-once MR fingerprinting for B0 and B1 inhomogeneity correction in quantitative magnetization-transfer contrast

PURPOSE

To develop a fast, deep-learning approach for quantitative magnetization-transfer contrast (MTC)-MR fingerprinting (MRF) that simultaneously estimates multiple tissue parameters and corrects the effects of B0 and B1 variations.

METHODS

An only-train-once recurrent neural network was designed to perform the fast tissue-parameter quantification for a large range of different MRF acquisition schedules. It enabled a dynamic scan-wise linear calibration of the scan parameters using the measured B0 and B1 maps, which allowed accurate, multiple-tissue parameter mapping. MRF images were acquired from 8 healthy volunteers at 3 T. Estimated parameter maps from the MRF images were used to synthesize the MTC reference signal (Zref ) through Bloch equations at multiple saturation power levels.

RESULTS

The B0 and B1 errors in MR fingerprints, if not corrected, would impair the tissue quantification and subsequently corrupt the synthesized MTC reference images. Bloch equation-based numerical phantom studies and synthetic MRI analysis demonstrated that the proposed approach could correctly estimate water and semisolid macromolecule parameters, even with severe B0 and B1 inhomogeneities.

CONCLUSION

The only-train-once deep-learning framework can improve the reconstruction accuracy of brain-tissue parameter maps and be further combined with any conventional MRF or CEST-MRF method.

Assessment of MRF for simultaneous T1 and T2 quantification and water-fat separation in the liver at 0.55 T

OBJECTIVE

The goal of this work was to assess the feasibility of performing MRF in the liver on a 0.55 T scanner and to examine the feasibility of water-fat separation using rosette MRF at 0.55 T.

MATERIALS AND METHODS

Spiral and rosette MRF sequences were implemented on a commercial 0.55 T scanner. The accuracy of both sequences in T1 and T2 quantification was validated in the ISMRM/NIST system phantom. The efficacy of rosette MRF in water-fat separation was evaluated in simulations and water/oil phantoms. Both spiral and rosette MRF were performed in the liver of healthy subjects.

RESULTS

In the ISMRM/NIST phantom, both spiral and rosette MRF achieved good agreement with reference values in T1 and T2 measurements. In addition, rosette MRF enables water-fat separation and can generate water- and fat- specific T1 maps, T2 maps, and proton density images from the same dataset for a spatial resolution of 1.56 × 1.56 × 5mm3 within the acquisition time of 15 s.

CONCLUSION

It is feasible to measure T1 and T2 simultaneously in the liver using MRF on a 0.55 T system with lower performance gradients compared to state-of-the-art 1.5 T and 3 T systems within an acquisition time of 15 s. In addition, rosette MRF enables water-fat separation along with T1 and T2 quantification with no time penalty.

Tailored magnetic resonance fingerprinting

Neuroimaging of certain pathologies requires both multi-parametric qualitative and quantitative imaging. The role of the quantitative MRI (qMRI) is well accepted but suffers from long acquisition times leading to patient discomfort, especially in geriatric and pediatric patients. Previous studies show that synthetic MRI can be used in order to reduce the scan time and provide qMRI as well as multi-contrast data. However, this approach suffers from artifacts such as partial volume and flow. In order to increase the scan efficiency (the number of contrasts and quantitative maps acquired per unit time), we designed, simulated, and demonstrated rapid, simultaneous, multi-contrast qualitative (T₁ weighted, T₁ fluid attenuated inversion recovery (FLAIR), T₂ weighted, water, and fat), and quantitative imaging (T₁ and T₂ maps) through the approach of tailored MR fingerprinting (TMRF) to cover whole-brain in approximately four minutes. We performed TMRF on in vivo four healthy human brains and in vitro ISMRM/NIST phantom and compared with vendor supplied gold standard (GS) and MRF sequences. All scans were performed on a 3 T GE Premier system and images were reconstructed offline using MATLAB. The reconstructed qualitative images were then subjected to custom DL denoising and gradient anisotropic diffusion denoising. The quantitative tissue parametric maps were reconstructed using a dense neural network to gain computational speed compared to dictionary matching. The grey matter and white matter tissues in qualitative and quantitative data for the in vivo datasets were segmented semi-automatically. The SNR and mean contrasts were plotted and compared across all three methods. The GS images show better SNR in all four subjects compared to MRF and TMRF (GS > TMRF>MRF). The T₁ and T₂ values of MRF are relatively overestimated as compared to GS and TMRF. The scan efficiency for TMRF is 1.72 min^-1 which is higher compared to GS (0.32 min^-1) and MRF (0.90 min^-1).

Adaptive model-based Magnetic Resonance

PURPOSE

Conventional sequences are static in nature, fixing measurement parameters in advance in anticipation of a wide range of expected tissue parameter values. We set out to design and benchmark a new, personalized approach-termed adaptive MR-in which incoming subject data is used to update and fine-tune the pulse sequence parameters in real time.

METHODS

We implemented an adaptive, real-time multi-echo (MTE) experiment for estimating T₂ s. Our approach combined a Bayesian framework with model-based reconstruction. It maintained and continuously updated a prior distribution of the desired tissue parameters, including T₂ , which was used to guide the selection of sequence parameters in real time.

RESULTS

Computer simulations predicted accelerations between 1.7- and 3.3-fold for adaptive multi-echo sequences relative to static ones. These predictions were corroborated in phantom experiments. In healthy volunteers, our adaptive framework accelerated the measurement of T₂ for n-acetyl-aspartate by a factor of 2.5.

CONCLUSION

Adaptive pulse sequences that alter their excitations in real time could provide substantial reductions in acquisition times. Given the generality of our proposed framework, our results motivate further research into other adaptive model-based approaches to MRI and MRS.

Accelerated and quantitative three-dimensional molecular MRI using a generative adversarial network

PURPOSE

To substantially shorten the acquisition time required for quantitative three-dimensional (3D) chemical exchange saturation transfer (CEST) and semisolid magnetization transfer (MT) imaging and allow for rapid chemical exchange parameter map reconstruction.

METHODS

Three-dimensional CEST and MT magnetic resonance fingerprinting (MRF) datasets of L-arginine phantoms, whole-brains, and calf muscles from healthy volunteers, cancer patients, and cardiac patients were acquired using 3T clinical scanners at three different sites, using three different scanner models and coils. A saturation transfer-oriented generative adversarial network (GAN-ST) supervised framework was then designed and trained to learn the mapping from a reduced input data space to the quantitative exchange parameter space, while preserving perceptual and quantitative content.

RESULTS

The GAN-ST 3D acquisition time was 42-52 s, 70% shorter than CEST-MRF. The quantitative reconstruction of the entire brain took 0.8 s. An excellent agreement was observed between the ground truth and GAN-based L-arginine concentration and pH values (Pearson's r > 0.95, ICC > 0.88, NRMSE < 3%). GAN-ST images from a brain-tumor subject yielded a semi-solid volume fraction and exchange rate NRMSE of3 . 8 ± 1 . 3 % $$ 3.8\pm 1.3\% $$ and4 . 6 ± 1 . 3 % $$ 4.6\pm 1.3\% $$ , respectively, and SSIM of96 . 3 ± 1 . 6 % $$ 96.3\pm 1.6\% $$ and95 . 0 ± 2 . 4 % $$ 95.0\pm 2.4\% $$ , respectively. The mapping of the calf-muscle exchange parameters in a cardiac patient, yielded NRMSE < 7% and SSIM > 94% for the semi-solid exchange parameters. In regions with large susceptibility artifacts, GAN-ST has demonstrated improved performance and reduced noise compared to MRF.

CONCLUSION

GAN-ST can substantially reduce the acquisition time for quantitative semi-solid MT/CEST mapping, while retaining performance even when facing pathologies and scanner models that were not available during training.

A fast MR fingerprinting simulator for direct error estimation and sequence optimization

Magnetic resonance fingerprinting (MRF) is a novel quantitative MR technique that simultaneously provides multiple tissue property maps. When optimizing MRF scans, modeling undersampling errors and field imperfections in cost functions for direct measurement of quantitative errors will make the optimization results more practical and robust. However, optimizing such cost function is computationally expensive and impractical for MRF optimization with tens of thousands of iterations. Here, we introduce a fast MRF simulator to simulate aliased images from actual scan scenarios including undersampling and system imperfections, which substantially reduces computational time and allows for direct error estimation of the quantitative maps and efficient sequence optimization. We evaluate the performance and computational speed of the proposed approach by simulations and in vivo experiments. The simulations from the proposed method closely approximate the signals and MRF maps from in vivo scans, with 158 times shorter processing time than the conventional simulation method using Non-uniform Fourier transform. We also demonstrate the power of applying the fast MRF simulator in MRF sequence optimization. The optimized sequences are validated with in vivo scans to assess the image quality and accuracy. The optimized sequences produce artifact-free T1 and T2 maps in 2D and 3D scans with equivalent mapping accuracy as the human-designed sequence but at shorter scan times. Incorporating the proposed simulator in the MRF optimization framework makes direct estimation of undersampling errors during the optimization process feasible, and provide optimized MRF sequences that are robust against undersampling artifacts and field inhomogeneity.

Latent signal models: Learning compact representations of signal evolution for improved time-resolved, multi-contrast MRI

PURPOSE

To improve time-resolved reconstructions by training auto-encoders to learn compact representations of Bloch-simulated signal evolution and inserting the decoder into the forward model.

METHODS

Building on model-based nonlinear and linear subspace techniques, we train auto-encoders on dictionaries of simulated signal evolution to learn compact, nonlinear, latent representations. The proposed latent signal model framework inserts the decoder portion of the auto-encoder into the forward model and directly reconstructs the latent representation. Latent signal models essentially serve as a proxy for fast and feasible differentiation through the Bloch equations used to simulate signal. This work performs experiments in the context of T₂ -shuffling, gradient echo EPTI, and MPRAGE-shuffling. We compare how efficiently auto-encoders represent signal evolution in comparison to linear subspaces. Simulation and in vivo experiments then evaluate if reducing degrees of freedom by incorporating our proxy for the Bloch equations, the decoder portion of the auto-encoder, into the forward model improves reconstructions in comparison to subspace constraints.

RESULTS

An auto-encoder with 1 real latent variable represents single-tissue fast spin echo, EPTI, and MPRAGE signal evolution to within 0.15% normalized RMS error, enabling reconstruction problems with 3 degrees of freedom per voxel (real latent variable + complex scaling) in comparison to linear models with 4-8 degrees of freedom per voxel. In simulated/in vivo T₂ -shuffling and in vivo EPTI experiments, the proposed framework achieves consistent quantitative normalized RMS error improvement over linear approaches. From qualitative evaluation, the proposed approach yields images with reduced blurring and noise amplification in MPRAGE-shuffling experiments.

CONCLUSION

Directly solving for nonlinear latent representations of signal evolution improves time-resolved MRI reconstructions.

AI in MRI: Computational Frameworks for a Faster, Optimized, and Automated Imaging Workflow

Over the last decade, artificial intelligence (AI) has made an enormous impact on a wide range of fields, including science, engineering, informatics, finance, and transportation [...].

Improved Quantitative Parameter Estimation for Prostate T2 Relaxometry using Convolutional Neural Networks

This work seeks to evaluate multiple methods for quantitative parameter estimation from standard T2 mapping acquisitions in the prostate. The T2 estimation performance of methods based on neural networks (NN) was quantitatively compared to that of conventional curve fitting techniques. Large physics-based synthetic datasets simulating T2 mapping acquisitions were generated for training NNs and for quantitative performance comparisons. Ten combinations of different NN architectures, training strategies, and training corpora were implemented and compared with four different curve fitting strategies. All methods were compared quantitatively using synthetic data with known ground truth, and further compared on in vivo test data, with and without noise augmentation, to evaluate feasibility and noise robustness. In the evaluation on synthetic data, a convolutional neural network (CNN), trained in a supervised fashion using synthetic data generated from naturalistic images, showed the highest overall accuracy and precision amongst all the methods. On in vivo data, this best-performing method produced low-noise T2 maps and showed the least deterioration with increasing input noise levels. This study showed that a CNN, trained with synthetic data in a supervised manner, may provide superior T2 estimation performance compared to conventional curve fitting, especially in low signal-to-noise regions.

Three-dimensional multi-parameter brain mapping using MR fingerprinting

The purpose of this study was to develop and test a 3D multi-parameter MR fingerprinting (MRF) method for brain imaging applications. The subject cohort included 5 healthy volunteers, repeatability tests done on 2 healthy volunteers and tested on two multiple sclerosis (MS) patients. A 3D-MRF imaging technique capable of quantifying T1, T2 and T1ρ was used. The imaging sequence was tested in standardized phantoms and 3D-MRF brain imaging with multiple shots (1, 2 and 4) in healthy human volunteers and MS patients. Quantitative parametric maps for T1, T2, T1ρ, were generated. Mean gray matter (GM) and white matter (WM) ROIs were compared for each mapping technique, Bland-Altman plots and intra-class correlation coefficient (ICC) were used to assess repeatability and Student T-tests were used to compare results in MS patients. Standardized phantom studies demonstrated excellent agreement with reference T1/T2/T1ρ mapping techniques. This study demonstrates that the 3D-MRF technique is able to simultaneously quantify T1, T2 and T1ρ for tissue property characterization in a clinically feasible scan time. This multi-parametric approach offers increased potential to detect and differentiate brain lesions and to better test imaging biomarker hypotheses for several neurological diseases, including MS.

High-Resolution 3D Magnetic Resonance Fingerprinting With a Graph Convolutional Network

Magnetic resonance fingerprinting (MRF) is a novel quantitative imaging framework for rapid and simultaneous quantification of multiple tissue properties. 3D MRF allows higher through-plane resolution, but the acquisition process is slow when whole-brain coverage is needed. Existing methods for acceleration mainly rely on GRAPPA for k-space interpolation in the partition-encoding direction, limiting the acceleration factor to 2 or 3. In this work, we replace GRAPPA with a deep learning approach for accurate tissue quantification with greater acceleration. Specifically, a graph convolution network (GCN) is developed to cater to the non-Cartesian spiral sampling trajectories typical in MRF acquisition. The GCN maintains high quantification accuracy with up to 6-fold acceleration and allows 1mm isotropic resolution whole-brain 3D MRF data to be acquired in 3min and submillimeter 3D MRF (0.8mm) in 5min, greatly improving the feasibility of MRF in clinical settings.

Deep Learning Staging of Liver Iron Content From Multiecho MR Images

BACKGROUND

MRI represents the most established liver iron content (LIC) evaluation approach by estimation of liver T2* value, but it is dependent on the choice of the measurement region and the software used for image analysis.

PURPOSE

To develop a deep-learning method for unsupervised classification of LIC from magnitude T2* multiecho MR images.

STUDY TYPE

Retrospective.

POPULATION/SUBJECTS

A total of 1069 thalassemia major patients enrolled in the core laboratory of the Myocardial Iron Overload in Thalassemia (MIOT) network, which were included in the training (80%) and test (20%) sets. Twenty patients from different MRI vendors included in the external test set.

FIELD STRENGTH/SEQUENCE

A5 T, T2* multiecho magnitude images.

ASSESSMENT

Four deep-learning convolutional neural networks (HippoNet-2D, HippoNet-3D, HippoNet-LSTM, and an ensemble network HippoNet-Ensemble) were used to achieve unsupervised staging of LIC using five classes (normal, borderline, middle, moderate, severe). The training set was employed to construct the deep-learning model. The performance of the LIC staging model was evaluated in the test set and in the external test set. The model's performances were assessed by evaluating the accuracy, sensitivity, and specificity with respect to the ground truth labels obtained by T2* measurements and by comparison with operator-induced variability originating from different region of interest (ROI) placements.

STATISTICAL TESTS

The network's performances were evaluated by single-class accuracy, specificity, and sensitivity and compared by one-way repeated measures analysis of variance (ANOVA) and one-way ANOVA.

RESULTS

HippoNet-Ensemble reached an accuracy significantly higher than the other networks, and a sensitivity and specificity higher than HippoNet-LSTM. Accuracy, sensitivity, and specificity values for the LIC stages were: normal: 0.96/0.93/0.97, borderline: 0.95/0.85/0.98, mild: 0.96/0.88/0.98, moderate: 0.95/0.89/0.97, severe: 0.97/0.95/0.98. Correctly staging of cases was in the range of 85%-95%, depending on the LIC class. Multiclass accuracy was 0.90 against 0.92 for the interobserver variability.

DATA CONCLUSION

The proposed HippoNet-Ensemble network can perform unsupervised LIC staging and achieves good prognostic performance.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 2.

Quantitative MRI in cardiometabolic disease: From conventional cardiac and liver tissue mapping techniques to multi-parametric approaches

Cardiometabolic disease refers to the spectrum of chronic conditions that include diabetes, hypertension, atheromatosis, non-alcoholic fatty liver disease, and their long-term impact on cardiovascular health. Histological studies have confirmed several modifications at the tissue level in cardiometabolic disease. Recently, quantitative MR methods have enabled non-invasive myocardial and liver tissue characterization. MR relaxation mapping techniques such as T₁, T_1ρ, T₂ and T₂* provide a pixel-by-pixel representation of the corresponding tissue specific relaxation times, which have been shown to correlate with fibrosis, altered tissue perfusion, oedema and iron levels. Proton density fat fraction mapping approaches allow measurement of lipid tissue in the organ of interest. Several studies have demonstrated their utility as early diagnostic biomarkers and their potential to bear prognostic implications. Conventionally, the quantification of these parameters by MRI relies on the acquisition of sequential scans, encoding and mapping only one parameter per scan. However, this methodology is time inefficient and suffers from the confounding effects of the relaxation parameters in each single map, limiting wider clinical and research applications. To address these limitations, several novel approaches have been proposed that encode multiple tissue parameters simultaneously, providing co-registered multiparametric information of the tissues of interest. This review aims to describe the multi-faceted myocardial and hepatic tissue alterations in cardiometabolic disease and to motivate the application of relaxometry and proton-density cardiac and liver tissue mapping techniques. Current approaches in myocardial and liver tissue characterization as well as latest technical developments in multiparametric quantitative MRI are included. Limitations and challenges of these novel approaches, and recommendations to facilitate clinical validation are also discussed.