Deep Learning for Fast and Spatially Constrained Tissue Quantification From Highly Accelerated Data in Magnetic Resonance Fingerprinting

SuperMRF: deep robust reconstruction for highly accelerated magnetic resonance fingerprinting

Background

Magnetic resonance fingerprinting (MRF) is a rapid imaging technique for simultaneous mapping of multiple tissue properties such as T1 and T2 relaxation times. However, conventional pattern matching reconstruction and iterative low rank reconstruction methods may not take full advantage of the spatiotemporal content of MRF data and can require significant computational resources with long reconstruction times. Deep learning reconstruction using a three-dimensional (3D) convolutional neural network (CNN)-based method may enable high-quality, rapid MRF reconstruction. Evaluation of such proposed deep learning reconstruction methods for MRF is needed to clarify whether deep learning techniques adapted from other MR image reconstruction problems will yield benefits when employed in MRF applications. The objective of this study is to design and evaluate a novel deep learning framework (SuperMRF) that directly transforms undersampled parameter-weighted 3D Cartesian MRF data into quantitative T1 and T2 maps, bypassing traditional pattern-matching in MRF.

Methods

In contrast to conventional MRF where only the temporal evolution of each voxel is used for quantification, SuperMRF exploits both two-dimensional spatial and one-dimensional temporal information with a 3D CNN for reconstruction. Controlled simulation experiments were performed using reference parameter maps from in vivo knee scans of healthy volunteers. To evaluate the robustness to noise, we trained our network using clean data and tested it on simulated noisy data. Conventional inner product-based pattern matching and state-of-the-art iterative low rank reconstruction techniques were used for comparison. The performance of all methods was evaluated with respect to structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), and normalized mean squared error (NMSE). Prospective real-world MRF scans were performed in four volunteer subjects using the trained network from simulations and cartilage and muscle T1 and T2 values were compared between conventional pattern matching, low rank reconstruction, and SuperMRF.

Results

SuperMRF estimated accurate T1 and T2 mapping in a highly accelerated scan (15× undersampling in k-space with a 20-fold reduction in the number of acquired MRF frames) with low error (NMSE of 5%) and high resemblance (SSIM of 94%) to reference quantitative maps. SuperMRF was observed to be superior to the conventional and low rank MRF reconstruction methods in terms of NMSE, SSIM, and robustness to noise. In prospective real-world data, SuperMRF provided comparable T1 and T2 maps as compared to low rank MRF. The only significantly different cartilage and muscle values in prospective data across the three reconstruction methods were those from conventional MRF T2.

Conclusions

Our results demonstrate that the proposed SuperMRF can achieve rapid, robust reconstruction with reduced frames in addition to k-space undersampling, outperforming the conventional and state-of-the-art reconstruction methods in simulation and providing comparable results to low rank reconstruction in prospective real-world subjects.

Deep graph embedding based on Laplacian eigenmaps for MR fingerprinting reconstruction

Magnetic resonance fingerprinting (MRF) is a promising technique for fast quantitative imaging of multiple tissue parameters. However, the highly undersampled schemes utilized in MRF typically lead to noticeable aliasing artifacts in reconstructed images. Existing model-based methods can mitigate aliasing artifacts and enhance reconstruction quality but suffer from long reconstruction times. In addition, data priors used in these methods, such as low-rank and total variation, make it challenging to incorporate non-local and non-linear redundancies in MRF data. Furthermore, existing deep learning-based methods for MRF often lack interpretability and struggle with the high computational overhead caused by the high dimensionality of MRF data. To address these issues, we introduce a novel deep graph embedding framework based on the Laplacian eigenmaps for improved MRF reconstruction. Our work first models the acquired high-dimensional MRF data and the corresponding parameter maps as graph data nodes. Then, we propose an MRF reconstruction framework based on the graph embedding framework, retaining intrinsic graph structures between parameter maps and MRF data. To improve the accuracy of the estimated graph structure and the computational efficiency of the proposed framework, we unroll the iterative optimization process into a deep neural network, incorporating a learned graph embedding module to adaptively learn the Laplacian eigenmaps. By introducing the graph embedding framework into the MRF reconstruction, the proposed method can effectively exploit non-local and non-linear correlations in MRF data. Numerical experiments demonstrate that our approach can reconstruct high-quality MRF data and multiple parameter maps within a significantly reduced computational cost.

Acceleration of Simultaneous Multislice Magnetic Resonance Fingerprinting With Spatiotemporal Convolutional Neural Network

Magnetic Resonance Fingerprinting (MRF) can be accelerated with simultaneous multislice (SMS) imaging for joint T1 and T2 quantification. However, the high inter-slice and in-plane acceleration in SMS-MRF causes severe aliasing artifacts, limiting the multiband (MB) factors to typically 2 or 3. Deep learning has demonstrated superior performance compared to the conventional dictionary matching approach for single-slice MRF, but its effectiveness in SMS-MRF remains unexplored. In this paper, we introduced a new deep learning approach with decoupled spatiotemporal feature learning for SMS-MRF to achieve high MB factors for accurate and volumetric T1 and T2 quantification in neuroimaging. The proposed method leverages information from both spatial and temporal domains to mitigate the significant aliasing in SMS-MRF. Neural networks, trained using either acquired SMS-MRF data or simulated data generated from single-slice MRF acquisitions, were evaluated. The performance was further compared with both dictionary matching and a deep learning approach based on residual channel attention U-Net. Experimental results demonstrated that the proposed method, trained with acquired SMS-MRF data, achieves the best performance in brain T1 and T2 quantification, outperforming dictionary matching and residual channel attention U-Net. With a MB factor of 4, rapid T1 and T2 mapping was achieved with 1.5 s per slice for quantitative brain imaging.

Unraveling contributions to the Z-spectrum signal at 3.5 ppm of human brain tumors

PURPOSE

To evaluate the influence of the confounding factors, direct water saturation (DWS), and magnetization transfer contrast (MTC) effects on measured Z-spectra and amide proton transfer (APT) contrast in brain tumors.

METHODS

High-grade glioma patients were scanned using an RF saturation-encoded 3D MR fingerprinting (MRF) sequence at 3 T. For MRF reconstruction, a recurrent neural network was designed to learn free water and semisolid macromolecule parameter mappings of the underlying multiple tissue properties from saturation-transfer MRF signals. The DWS spectra and MTC spectra were synthesized by solving Bloch-McConnell equations and evaluated in brain tumors.

RESULTS

The dominant contribution to the saturation effect at 3.5 ppm was from DWS and MTC effects, but 25%-33% of the saturated signal in the gadolinium-enhancing tumor (13%-20% for normal tissue) was due to the APT effect. The APT# signal of the gadolinium-enhancing tumor was significantly higher than that of the normal-appearing white matter (10.1% vs. 8.3% at 1 μT and 11.2% vs. 7.8% at 1.5 μT).

CONCLUSION

The RF saturation-encoded MRF allowed us to separate contributions to the saturation signal at 3.5 ppm in the Z-spectrum. Although free water and semisolid MTC are the main contributors, significant APT contrast between tumor and normal tissues was observed.

Cardiac MR Fingerprinting: Overview, Technical Developments, and Applications

Cardiovascular magnetic resonance (CMR) is an established imaging modality with proven utility in assessing cardiovascular diseases. The ability of CMR to characterize myocardial tissue using T1- and T2-weighted imaging, parametric mapping, and late gadolinium enhancement has allowed for the non-invasive identification of specific pathologies not previously possible with modalities like echocardiography. However, CMR examinations are lengthy and technically complex, requiring multiple pulse sequences and different anatomical planes to comprehensively assess myocardial structure, function, and tissue composition. To increase the overall impact of this modality, there is a need to simplify and shorten CMR exams to improve access and efficiency, while also providing reproducible quantitative measurements. Multiparametric MRI techniques that measure multiple tissue properties offer one potential solution to this problem. This review provides an in-depth look at one such multiparametric approach, cardiac magnetic resonance fingerprinting (MRF). The article is structured as follows. First, a brief review of single-parametric and (non-Fingerprinting) multiparametric CMR mapping techniques is presented. Second, a general overview of cardiac MRF is provided covering pulse sequence implementation, dictionary generation, fast k-space sampling methods, and pattern recognition. Third, recent technical advances in cardiac MRF are covered spanning a variety of topics, including simultaneous multislice and 3D sampling, motion correction algorithms, cine MRF, synthetic multicontrast imaging, extensions to measure additional clinically important tissue properties (proton density fat fraction, T2*, and T1ρ), and deep learning methods for image reconstruction and parameter estimation. The last section will discuss potential clinical applications, concluding with a perspective on how multiparametric techniques like MRF may enable streamlined CMR protocols. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 1.

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.

Fast Whole-Brain MR Multi-Parametric Mapping with Scan-Specific Self-Supervised Networks

Quantification of tissue parameters using MRI is emerging as a powerful tool in clinical diagnosis and research studies. The need for multiple long scans with different acquisition parameters prohibits quantitative MRI from reaching widespread adoption in routine clinical and research exams. Accelerated parameter mapping techniques leverage parallel imaging, signal modelling and deep learning to offer more practical quantitative MRI acquisitions. However, the achievable acceleration and the quality of maps are often limited. Joint MAPLE is a recent state-of-the-art multi-parametric and scan-specific parameter mapping technique with promising performance at high acceleration rates. It synergistically combines parallel imaging, model-based and machine learning approaches for joint mapping ofT 1 , T 2 * , proton density and the field inhomogeneity. However, Joint MAPLE suffers from prohibitively long reconstruction time to estimate the maps from a multi-echo, multi-flip angle (MEMFA) dataset at high resolution in a scan-specific manner. In this work, we propose a faster version of Joint MAPLE which retains the mapping performance of the original version. Coil compression, random slice selection, parameter-specific learning rates and transfer learning are synergistically combined in the proposed framework. It speeds-up the reconstruction time up to 700 times than the original version and processes a whole-brain MEMFA dataset in 21 minutes on average, which originally requires ~260 hours for Joint MAPLE. The mapping performance of the proposed framework is ~2-fold better than the standard and the state-of-the-art evaluated reconstruction techniques on average in terms of the root mean squared error.

Advances in artificial intelligence for drug delivery and development: A comprehensive review

Artificial intelligence (AI) has emerged as a powerful tool to revolutionize the healthcare sector, including drug delivery and development. This review explores the current and future applications of AI in the pharmaceutical industry, focusing on drug delivery and development. It covers various aspects such as smart drug delivery networks, sensors, drug repurposing, statistical modeling, and simulation of biotechnological and biological systems. The integration of AI with nanotechnologies and nanomedicines is also examined. AI offers significant advancements in drug discovery by efficiently identifying compounds, validating drug targets, streamlining drug structures, and prioritizing response templates. Techniques like data mining, multitask learning, and high-throughput screening contribute to better drug discovery and development innovations. The review discusses AI applications in drug formulation and delivery, clinical trials, drug safety, and pharmacovigilance. It addresses regulatory considerations and challenges associated with AI in pharmaceuticals, including privacy, data security, and interpretability of AI models. The review concludes with future perspectives, highlighting emerging trends, addressing limitations and biases in AI models, and emphasizing the importance of collaboration and knowledge sharing. It provides a comprehensive overview of AI's potential to transform the pharmaceutical industry and improve patient care while identifying further research and development areas.

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.

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.

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.

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.

Improving motion robustness of 3D MR fingerprinting with a fat navigator

PURPOSE

To develop a 3D MR fingerprinting (MRF) method in combination with fat navigators to improve its motion robustness for neuroimaging.

METHODS

A rapid fat navigator was developed using the stack-of-spirals acquisition and non-Cartesian spiral GRAPPA. The fat navigator module was implemented in the 3D MRF sequence with high scan efficiency. The developed method was first validated in phantoms and five healthy subjects with intentional head motion. The method was further applied to infants with neonatal opioid withdrawal symptoms. The 3D MRF scans with fat navigators acquired with and without acceleration along the partition-encoding direction were both examined in the study.

RESULTS

Both phantom and in vivo results demonstrated that the added fat navigator modules did not influence the quantification accuracy in MRF. In combination with non-Cartesian spiral GRAPPA, a rapid fat navigator sampling with whole-brain coverage was achieved in ˜0.5 s at 3T, reducing its sensitivity to potential motion. Based on the motion waveforms extracted from fat navigators, the motion robustness of the 3D MRF was largely improved. With the proposed method, the motion-corrupted MRF datasets yielded T1 and T2 maps with significantly reduced artifacts and high correlations with measurements from the reference motion-free MRF scans.

CONCLUSION

We developed a 3D MRF method coupled with rapid fat navigators to improve its motion robustness for quantitative neuroimaging. Our results demonstrate that (1) accurate tissue quantification was preserved with the fat navigator modules and (2) the motion robustness for quantitative tissue mapping was largely improved with the developed method.

Emerging Trends in Fast MRI Using Deep-Learning Reconstruction on Undersampled k-Space Data: A Systematic Review

Magnetic Resonance Imaging (MRI) is an essential medical imaging modality that provides excellent soft-tissue contrast and high-resolution images of the human body, allowing us to understand detailed information on morphology, structural integrity, and physiologic processes. However, MRI exams usually require lengthy acquisition times. Methods such as parallel MRI and Compressive Sensing (CS) have significantly reduced the MRI acquisition time by acquiring less data through undersampling k-space. The state-of-the-art of fast MRI has recently been redefined by integrating Deep Learning (DL) models with these undersampled approaches. This Systematic Literature Review (SLR) comprehensively analyzes deep MRI reconstruction models, emphasizing the key elements of recently proposed methods and highlighting their strengths and weaknesses. This SLR involves searching and selecting relevant studies from various databases, including Web of Science and Scopus, followed by a rigorous screening and data extraction process using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. It focuses on various techniques, such as residual learning, image representation using encoders and decoders, data-consistency layers, unrolled networks, learned activations, attention modules, plug-and-play priors, diffusion models, and Bayesian methods. This SLR also discusses the use of loss functions and training with adversarial networks to enhance deep MRI reconstruction methods. Moreover, we explore various MRI reconstruction applications, including non-Cartesian reconstruction, super-resolution, dynamic MRI, joint learning of reconstruction with coil sensitivity and sampling, quantitative mapping, and MR fingerprinting. This paper also addresses research questions, provides insights for future directions, and emphasizes robust generalization and artifact handling. Therefore, this SLR serves as a valuable resource for advancing fast MRI, guiding research and development efforts of MRI reconstruction for better image quality and faster data acquisition.

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.

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.

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.

Region of interest-specific loss functions improve T2 quantification with ultrafast T2 mapping MRI sequences in knee, hip and lumbar spine

MRI T2 mapping sequences quantitatively assess tissue health and depict early degenerative changes in musculoskeletal (MSK) tissues like cartilage and intervertebral discs (IVDs) but require long acquisition times. In MSK imaging, small features in cartilage and IVDs are crucial for diagnoses and must be preserved when reconstructing accelerated data. To these ends, we propose region of interest-specific postprocessing of accelerated acquisitions: a recurrent UNet deep learning architecture that provides T2 maps in knee cartilage, hip cartilage, and lumbar spine IVDs from accelerated T2-prepared snapshot gradient-echo acquisitions, optimizing for cartilage and IVD performance with a multi-component loss function that most heavily penalizes errors in those regions. Quantification errors in knee and hip cartilage were under 10% and 9% from acceleration factors R = 2 through 10, respectively, with bias for both under 3 ms for most of R = 2 through 12. In IVDs, mean quantification errors were under 12% from R = 2 through 6. A Gray Level Co-Occurrence Matrix-based scheme showed knee and hip pipelines outperformed state-of-the-art models, retaining smooth textures for most R and sharper ones through moderate R. Our methodology yields robust T2 maps while offering new approaches for optimizing and evaluating reconstruction algorithms to facilitate better preservation of small, clinically relevant features.

[Applications of Artificial Intelligence in MR Image Acquisition and Reconstruction]

Recently, artificial intelligence (AI) technology has shown potential clinical utility in a wide range of MRI fields. In particular, AI models for improving the efficiency of the image acquisition process and the quality of reconstructed images are being actively developed by the MR research community. AI is expected to further reduce acquisition times in various MRI protocols used in clinical practice when compared to current parallel imaging techniques. Additionally, AI can help with tasks such as planning, parameter optimization, artifact reduction, and quality assessment. Furthermore, AI is being actively applied to automate MR image analysis such as image registration, segmentation, and object detection. For this reason, it is important to consider the effects of protocols or devices in MR image analysis. In this review article, we briefly introduced issues related to AI application of MR image acquisition and reconstruction.

Artificial intelligence in cardiac magnetic resonance fingerprinting

Magnetic resonance fingerprinting (MRF) is a fast MRI-based technique that allows for multiparametric quantitative characterization of the tissues of interest in a single acquisition. In particular, it has gained attention in the field of cardiac imaging due to its ability to provide simultaneous and co-registered myocardial T₁ and T₂ mapping in a single breath-held cardiac MRF scan, in addition to other parameters. Initial results in small healthy subject groups and clinical studies have demonstrated the feasibility and potential of MRF imaging. Ongoing research is being conducted to improve the accuracy, efficiency, and robustness of cardiac MRF. However, these improvements usually increase the complexity of image reconstruction and dictionary generation and introduce the need for sequence optimization. Each of these steps increase the computational demand and processing time of MRF. The latest advances in artificial intelligence (AI), including progress in deep learning and the development of neural networks for MRI, now present an opportunity to efficiently address these issues. Artificial intelligence can be used to optimize candidate sequences and reduce the memory demand and computational time required for reconstruction and post-processing. Recently, proposed machine learning-based approaches have been shown to reduce dictionary generation and reconstruction times by several orders of magnitude. Such applications of AI should help to remove these bottlenecks and speed up cardiac MRF, improving its practical utility and allowing for its potential inclusion in clinical routine. This review aims to summarize the latest developments in artificial intelligence applied to cardiac MRF. Particularly, we focus on the application of machine learning at different steps of the MRF process, such as sequence optimization, dictionary generation and image reconstruction.

Artificial intelligence in multi-parametric magnetic resonance imaging: A review

Multi-parametric magnetic resonance imaging (mpMRI) is an indispensable tool in the clinical workflow for the diagnosis and treatment planning of various diseases. Machine learning-based artificial intelligence (AI) methods, especially those adopting the deep learning technique, have been extensively employed to perform mpMRI image classification, segmentation, registration, detection, reconstruction, and super-resolution. The current availability of increasing computational power and fast-improving AI algorithms have empowered numerous computer-based systems for applying mpMRI to disease diagnosis, imaging-guided radiotherapy, patient risk and overall survival time prediction, and the development of advanced quantitative imaging technology for magnetic resonance fingerprinting. However, the wide application of these developed systems in the clinic is still limited by a number of factors, including robustness, reliability, and interpretability. This survey aims to provide an overview for new researchers in the field as well as radiologists with the hope that they can understand the general concepts, main application scenarios, and remaining challenges of AI in mpMRI. This article is protected by copyright. All rights reserved.

Reduction in Acquisition Time and Improvement in Image Quality in T2-Weighted MR Imaging of Musculoskeletal Tumors of the Extremities Using a Novel Deep Learning-Based Reconstruction Technique in a Turbo Spin Echo (TSE) Sequence

Background: The aim of this study was to assess the technical feasibility and the impact on image quality and acquisition time of a deep learning-accelerated fat-saturated T2-weighted turbo spin echo sequence in musculoskeletal imaging of the extremities. Methods: Twenty-three patients who underwent MRI of the extremities were prospectively included. Standard T2w turbo inversion recovery magnitude (TIRMStd) imaging was compared to a deep learning-accelerated T2w TSE (TSEDL) sequence. Image analysis of 23 patients with a mean age of 60 years (range 30−86) was performed regarding image quality, noise, sharpness, contrast, artifacts, lesion detectability and diagnostic confidence. Pathological findings were documented measuring the maximum diameter. Results: The analysis showed a significant improvement for the T2 TSEDL with regard to image quality, noise, contrast, sharpness, lesion detectability, and diagnostic confidence, as compared to T2 TIRMStd (each p < 0.001). There were no differences in the number of detected lesions. The time of acquisition (TA) could be reduced by 52−59%. Interrater agreement was almost perfect (κ = 0.886). Conclusion: Accelerated T2 TSEDL was technically feasible and superior to conventionally applied T2 TIRMStd. Concurrently, TA could be reduced by 52−59%. Therefore, deep learning-accelerated MR imaging is a promising and applicable method in musculoskeletal imaging.

An efficient approach to optimal experimental design for magnetic resonance fingerprinting with B-splines

PURPOSE

To introduce a computationally efficient approach to optimizing the data acquisition parameters of MR Fingerprinting experiments with the Cramér-Rao bound.

METHODS

This paper presents a new approach to the optimal experimental design (OED) problem for MR Fingerprinting, which leverages an early observation that the optimized data acquisition parameters of MR Fingerprinting experiments are highly structured. Specifically, the proposed approach captures the desired structure by representing the sequences of data acquisition parameters with a special class of piecewise polynomials known as B-splines. This incorporates low-dimensional spline subspace constraints into the OED problem, which significantly reduces the search space of the problem, thereby improving the computational efficiency. With the rich B-spline representations, the proposed approach also allows for incorporating prior knowledge on the structure of different acquisition parameters, which facilitates the experimental design.

RESULTS

The effectiveness of the proposed approach was evaluated using numerical simulations, phantom experiments, and in vivo experiments. The proposed approach achieves a two-order-of-magnitude improvement of the computational efficiency over the state-of-the-art approaches, while providing a comparable signal-to-noise ratio efficiency benefit. It enables an optimal experimental design problem for MR Fingerprinting with a typical acquisition length to be solved in approximately 1 min.

CONCLUSIONS

The proposed approach significantly improves the computational efficiency of the optimal experimental design for MR Fingerprinting, which enhances its practical utility for a variety of quantitative MRI applications.

Improved Balanced Steady-State Free Precession Based MR Fingerprinting with Deep Autoencoders

Magnetic Resonance (MR) Fingerprinting is an emerging transient-state imaging paradigm, which enables the quantization of multiple MR tissue parameters in a single experiment. Balanced steady-state free precession (bSSFP)-based MR Fingerprinting has excellent signal-to-noise characteristics and also allows for acquiring both tissue parameter maps and field inhomogeneity maps. However, field inhomogeneity often results in complex magnetization evolutions in bSSFP-based MR Fingerprinting, which creates significant challenges in image reconstruction. In this paper, we introduce a new method to address the image reconstruction problem. The proposed method incorporates a low-dimensional nonlinear manifold learned from an ensemble of magnetization evolutions using a deep autoencoder. It provides much better representation power than a low-dimensional linear subspace in capturing complex magnetization evolutions. We formulate the image reconstruction problem with this nonlinear model and solve the resulting optimization problem using an algorithm based on variable splitting and the alternating direction method of multipliers. We evaluate the performance of the proposed method using numerical experiments and demonstrate that it significantly outperforms the state-of-art method using a linear subspace model.

Cramér-Rao bound-informed training of neural networks for quantitative MRI

PURPOSE

To improve the performance of neural networks for parameter estimation in quantitative MRI, in particular when the noise propagation varies throughout the space of biophysical parameters.

THEORY AND METHODS

A theoretically well-founded loss function is proposed that normalizes the squared error of each estimate with respective Cramér-Rao bound (CRB)-a theoretical lower bound for the variance of an unbiased estimator. This avoids a dominance of hard-to-estimate parameters and areas in parameter space, which are often of little interest. The normalization with corresponding CRB balances the large errors of fundamentally more noisy estimates and the small errors of fundamentally less noisy estimates, allowing the network to better learn to estimate the latter. Further, proposed loss function provides an absolute evaluation metric for performance: A network has an average loss of 1 if it is a maximally efficient unbiased estimator, which can be considered the ideal performance. The performance gain with proposed loss function is demonstrated at the example of an eight-parameter magnetization transfer model that is fitted to phantom and in vivo data.

RESULTS

Networks trained with proposed loss function perform close to optimal, that is, their loss converges to approximately 1, and their performance is superior to networks trained with the standard mean-squared error (MSE). The proposed loss function reduces the bias of the estimates compared to the MSE loss, and improves the match of the noise variance to the CRB. This performance gain translates to in vivo maps that align better with the literature.

CONCLUSION

Normalizing the squared error with the CRB during the training of neural networks improves their performance in estimating biophysical parameters.

A Self-Supervised Deep Learning Reconstruction for Shortening the Breathhold and Acquisition Window in Cardiac Magnetic Resonance Fingerprinting

The aim of this study is to shorten the breathhold and diastolic acquisition window in cardiac magnetic resonance fingerprinting (MRF) for simultaneous T1, T2, and proton spin density (M0) mapping to improve scan efficiency and reduce motion artifacts. To this end, a novel reconstruction was developed that combines low-rank subspace modeling with a deep image prior, termed DIP-MRF. A system of neural networks is used to generate spatial basis images and quantitative tissue property maps, with training performed using only the undersampled k-space measurements from the current scan. This approach avoids difficulties with obtaining in vivo MRF training data, as training is performed de novo for each acquisition. Calculation of the forward model during training is accelerated by using GRAPPA operator gridding to shift spiral k-space data to Cartesian grid points, and by using a neural network to rapidly generate fingerprints in place of a Bloch equation simulation. DIP-MRF was evaluated in simulations and at 1.5 T in a standardized phantom, 18 healthy subjects, and 10 patients with suspected cardiomyopathy. In addition to conventional mapping, two cardiac MRF sequences were acquired, one with a 15-heartbeat(HB) breathhold and 254 ms acquisition window, and one with a 5HB breathhold and 150 ms acquisition window. In simulations, DIP-MRF yielded decreased nRMSE compared to dictionary matching and a sparse and locally low rank (SLLR-MRF) reconstruction. Strong correlation (R2 &gt; 0.999) with T1 and T2 reference values was observed in the phantom using the 5HB/150 ms scan with DIP-MRF. DIP-MRF provided better suppression of noise and aliasing artifacts in vivo, especially for the 5HB/150 ms scan, and lower intersubject and intrasubject variability compared to dictionary matching and SLLR-MRF. Furthermore, it yielded a better agreement between myocardial T1 and T2 from 15HB/254 ms and 5HB/150 ms MRF scans, with a bias of −9 ms for T1 and 2 ms for T2. In summary, this study introduces an extension of the deep image prior framework for cardiac MRF tissue property mapping, which does not require pre-training with in vivo scans, and has the potential to reduce motion artifacts by enabling a shortened breathhold and acquisition window.

Accelerating multi-echo chemical shift encoded water-fat MRI using model-guided deep learning

PURPOSE

To accelerate chemical shift encoded (CSE) water-fat imaging by applying a model-guided deep learning water-fat separation (MGDL-WF) framework to the undersampled k-space data.

METHODS

A model-guided deep learning water-fat separation framework is proposed for the acceleration using Cartesian/radial undersampling data. The proposed MGDL-WF combines the power of CSE water-fat imaging model and data-driven deep learning by jointly using a multi-peak fat model and a modified residual U-net network. The model is used to guide the image reconstruction, and the network is used to capture the artifacts induced by the undersampling. A data consistency layer is used in MGDL-WF to ensure the output images to be consistent with the k-space measurements. A Gauss-Newton iteration algorithm is adapted for the gradient updating of the networks.

RESULTS

Compared with the compressed sensing water-fat separation (CS-WF) algorithm/2-step procedure algorithm, the MGDL-WF increased peak signal-to-noise ratio (PSNR) by 5.31/5.23, 6.11/4.54, and 4.75 dB/1.88 dB with Cartesian sampling, and by 4.13/6.53, 2.90/4.68, and 1.68 dB/3.48 dB with radial sampling, at acceleration rates (R) of 4, 6, and 8, respectively. By using MGDL-WF, radial sampling increased the PSNR by 2.07 dB at R = 8, compared with Cartesian sampling.

CONCLUSIONS

The proposed MGDL-WF enables exploiting features of the water images and fat images from the undersampled multi-echo data, leading to improved performance in the accelerated CSE water-fat imaging. By using MGDL-WF, radial sampling can further improve the image quality with comparable scan time in comparison with Cartesian sampling.

Learning-based optimization of acquisition schedule for magnetization transfer contrast MR fingerprinting

Magnetization transfer contrast MR fingerprinting (MTC-MRF) is a novel quantitative imaging method that simultaneously quantifies free bulk water and semisolid macromolecule parameters using pseudo-randomized scan parameters. To improve acquisition efficiency and reconstruction accuracy, the optimization of MRF sequence design has been of recent interest in the MRF field, but has been challenging due to the large number of degrees of freedom to be optimized in the sequence. Herein, we propose a framework for learning-based optimization of the acquisition schedule (LOAS), which optimizes RF saturation-encoded MRF acquisitions with a minimal number of scan parameters for tissue parameter determination. In a supervised learning framework, scan parameters were subsequently updated to minimize a predefined loss function that can directly represent tissue quantification errors. We evaluated the performance of the proposed approach with a numerical phantom and in in vivo experiments. For validation, MRF images were synthesized using the tissue parameters estimated from a fully connected neural network framework and compared with references. Our results showed that LOAS outperformed existing indirect optimization methods with regard to quantification accuracy and acquisition efficiency. The proposed LOAS method could be a powerful optimization tool in the design of MRF pulse sequences.

High-Quality MR Fingerprinting Reconstruction Using Structured Low-Rank Matrix Completion and Subspace Projection

Due to the capability of fast multiparametric quantitative imaging, magnetic resonance fingerprinting (MRF) is becoming a promising quantitative magnetic resonance imaging approach. However, the artifacts caused by the highly undersampled data acquisition lead to inaccurate estimation of the tissue parameter maps. Based on the assumption that the 3-D MRF data can be modeled as a piecewise smooth signal, with the discontinuities localized to the zero sets of a bandlimited function, we exploit the low-rank property of the structured Toeplitz matrix constructed from the Fourier measurements. In addition, we adopt the subspace projection scheme to improve the accuracy of parameter estimation. In order to efficiently solve the regularized problem, we propose an iterative two-stage algorithm, which alternately updates the k -space data and projects the space-time matrix into the dictionary space. Numerical experiments demonstrate that the proposed algorithm shows significant improvement in MRF time-series images reconstruction and can provide more accurate parameter maps over the state-of-the-art algorithms.

Circumventing the curse of dimensionality in magnetic resonance fingerprinting through a deep learning approach

Magnetic resonance fingerprinting (MRF) is a rapidly developing approach for fast quantitative MRI. A typical drawback of dictionary-based MRF is an explosion of the dictionary size as a function of the number of reconstructed parameters, according to the "curse of dimensionality", which determines an explosion of resource requirements. Neural networks (NNs) have been proposed as a feasible alternative, but this approach is still in its infancy. In this work, we design a deep learning approach to MRF using a fully connected network (FCN). In the first part we investigate, by means of simulations, how the NN performance scales with the number of parameters to be retrieved in comparison with the standard dictionary approach. Four MRF sequences were considered: IR-FISP, bSSFP, IR-FISP-B₁ , and IR-bSSFP-B₁ , the latter two designed to be more specific for B1+ parameter encoding. Estimation accuracy, memory usage, and computational time required to perform the estimation task were considered to compare the scalability capabilities of the dictionary-based and the NN approaches. In the second part we study optimal training procedures by including different data augmentation and preprocessing strategies during training to achieve better accuracy and robustness to noise and undersampling artifacts. The study is conducted using the IR-FISP MRF sequence exploiting both simulations and in vivo acquisitions. Results demonstrate that the NN approach outperforms the dictionary-based approach in terms of scalability capabilities. Results also allow us to heuristically determine the optimal training strategy to make an FCN able to predict T₁ ,  T₂ , and M₀ maps that are in good agreement with those obtained with the original dictionary approach. k-SVD denoising is proposed and found to be critical as a preprocessing step to handle undersampled data.

Rapid MR relaxometry using deep learning: An overview of current techniques and emerging trends

Quantitative mapping of MR tissue parameters such as the spin-lattice relaxation time (T1 ), the spin-spin relaxation time (T2 ), and the spin-lattice relaxation in the rotating frame (T1ρ ), referred to as MR relaxometry in general, has demonstrated improved assessment in a wide range of clinical applications. Compared with conventional contrast-weighted (eg T1 -, T2 -, or T1ρ -weighted) MRI, MR relaxometry provides increased sensitivity to pathologies and delivers important information that can be more specific to tissue composition and microenvironment. The rise of deep learning in the past several years has been revolutionizing many aspects of MRI research, including image reconstruction, image analysis, and disease diagnosis and prognosis. Although deep learning has also shown great potential for MR relaxometry and quantitative MRI in general, this research direction has been much less explored to date. The goal of this paper is to discuss the applications of deep learning for rapid MR relaxometry and to review emerging deep-learning-based techniques that can be applied to improve MR relaxometry in terms of imaging speed, image quality, and quantification robustness. The paper is comprised of an introduction and four more sections. Section 2 describes a summary of the imaging models of quantitative MR relaxometry. In Section 3, we review existing "classical" methods for accelerating MR relaxometry, including state-of-the-art spatiotemporal acceleration techniques, model-based reconstruction methods, and efficient parameter generation approaches. Section 4 then presents how deep learning can be used to improve MR relaxometry and how it is linked to conventional techniques. The final section concludes the review by discussing the promise and existing challenges of deep learning for rapid MR relaxometry and potential solutions to address these challenges.

BUDA-MESMERISE: Rapid acquisition and unsupervised parameter estimation for T1 , T2 , M0 , B0 , and B1 maps

PURPOSE

Rapid acquisition scheme and parameter estimation method are proposed to acquire distortion-free spin- and stimulated-echo signals and combine the signals with a physics-driven unsupervised network to estimate T₁ , T₂ , and proton density (M₀ ) parameter maps, along with B₀ and B₁ information from the acquired signals.

THEORY AND METHODS

An imaging sequence with three 90° RF pulses is utilized to acquire spin- and stimulated-echo signals. We utilize blip-up/-down acquisition to eliminate geometric distortion incurred by the effects of B₀ inhomogeneity on rapid EPI acquisitions. For multislice imaging, echo-shifting is applied to utilize dead time between the second and third RF pulses to encode information from additional slice positions. To estimate parameter maps from the spin- and stimulated-echo signals with high fidelity, 2 estimation methods, analytic fitting and a novel unsupervised deep neural network method, are developed.

RESULTS

The proposed acquisition provided distortion-free T₁ , T₂ , relative proton density (M0), B₀ , and B₁ maps with high fidelity both in phantom and in vivo brain experiments. From the rapidly acquired spin- and stimulated-echo signals, analytic fitting and the network-based method were able to estimate T₁ , T₂ , M₀ , B₀ , and B₁ maps with high accuracy. Network estimates demonstrated noise robustness owing to the fact that the convolutional layers take information into account from spatially adjacent voxels.

CONCLUSION

The proposed acquisition/reconstruction technique enabled whole-brain acquisition of coregistered, distortion-free, T₁ , T₂ , M₀ , B₀ , and B₁ maps at 1 × 1 × 5 mm³ resolution in 50 s. The proposed unsupervised neural network provided noise-robust parameter estimates from this rapid acquisition.

Acceleration of Magnetic Resonance Fingerprinting Reconstruction Using Denoising and Self-Attention Pyramidal Convolutional Neural Network

Magnetic resonance fingerprinting (MRF) based on echo-planar imaging (EPI) enables whole-brain imaging to rapidly obtain T1 and T2* relaxation time maps. Reconstructing parametric maps from the MRF scanned baselines by the inner-product method is computationally expensive. We aimed to accelerate the reconstruction of parametric maps for MRF-EPI by using a deep learning model. The proposed approach uses a two-stage model that first eliminates noise and then regresses the parametric maps. Parametric maps obtained by dictionary matching were used as a reference and compared with the prediction results of the two-stage model. MRF-EPI scans were collected from 32 subjects. The signal-to-noise ratio increased significantly after the noise removal by the denoising model. For prediction with scans in the testing dataset, the mean absolute percentage errors between the standard and the final two-stage model were 3.1%, 3.2%, and 1.9% for T1, and 2.6%, 2.3%, and 2.8% for T2* in gray matter, white matter, and lesion locations, respectively. Our proposed two-stage deep learning model can effectively remove noise and accurately reconstruct MRF-EPI parametric maps, increasing the speed of reconstruction and reducing the storage space required by dictionaries.

Three-dimensional high-resolution T1 and T2 mapping of whole macaque brain at 9.4 T using magnetic resonance fingerprinting

PURPOSE

Quantitative T₁ and T₂ mapping in non-human primates with whole-brain coverage is challenged by the requirement of sub-millimeter resolution and the inhomogeneity of the transmit magnetic field (B₁ ⁺ ) covering a large field of view. The goal of the current study is to develop a magnetic resonance fingerprinting (MRF) method for simultaneous T₁ and T₂ mapping of the entire macaque brain within feasible scan time.

METHODS

A three-dimensional (3D) MRF sequence with both inversion- and T₂ -preparation modules was developed and evaluated on a 9.4 T preclinical scanner. Data acquisition used a 3D stack-of-spirals trajectory, with undersampling along both the in-plane and the through-plane directions. The effect of B₁ ⁺ inhomogeneity was accounted for by matching the acquired fingerprint to a dictionary simulated with the B₁ ⁺ factors measured from a separate scan. In vitro and ex vivo studies were performed to evaluate the accuracy and the undersampling capacity of the MRF method. The application of the MRF method for in vivo, brain-wide T₁ and T₂ mapping was demonstrated on macaques at 4, 6, and 12 years of age.

RESULTS

The MRF method enabled highly repeatable T₁ and T₂ mapping at high spatial resolution (0.35 × 0.35 × 1 mm³ ) with an acceleration factor of 24. In vivo studies showed significant age-related T₂ reduction in deep gray nuclei including the globus pallidus, the putamen, and the caudate nucleus.

CONCLUSIONS

This study demonstrates the first MRF study for brain-wide, multi-parametric quantification in non-human primates with sub-millimeter resolution.

Tailored Magnetic Resonance Fingerprinting for simultaneous non-synthetic and quantitative imaging: A repeatability study

PURPOSE

The goals of this study include: (a) generating tailored magnetic resonance fingerprinting (TMRF) based non-synthetic imaging; (b) assessing the repeatability of TMRF and deep learning-based mapping of in vitro ISMRM/NIST phantom and in vivo brain data of healthy human subjects.

METHODS

We have acquired qualitative images obtained from the vendor-supplied gold standard, MRF (synthetic), and TMRF (non-synthetic) on one representative healthy human brain. We also acquired thirty datasets on the ISMRM/NIST phantom for the in vitro repeatability study on a GE Discovery 3T MR750w scanner using the TMRF sequence. We compared T₁ and T₂ maps generated from thirty ISMRM/NIST phantom datasets to the spin-echo (SE) based gold standard (GS) method as part of the in vitro repeatability study. R-squared coefficient of determination in a simple linear regression and Bland-Altman analysis were computed for thirty datasets of ISMRM/NIST phantom to assess the accuracy of in vitro quantitative TMRF data. The repeatability of T₁ and T₂ estimates by TMRF was evaluated by calculating the standard deviation (SD) divided by the average of thirty datasets for each sphere, respectively. We acquired ten volunteers for the in vivo repeatability study on the same scanner using the same TMRF sequence. These volunteers were imaged five times with two runs per repetition, resulting in one hundred in vivo datasets. Five contrasts, T₁ and T₂ maps of ten human volunteers acquired over five repetitions, were evaluated in the in vivo repeatability study. We computed the intraclass correlation coefficient (ICC) of the signal-to-noise ratio (SNR), signal intensities, T₁ and T₂ relaxation times in white matter (WM) and gray matter (GM).

RESULTS

The synthetic images generated from MRF show partial volume and flow artifacts compared to non-synthetic images obtained from TMRF images and the gold standard. in vitro studies show that TMRF estimates have less than 5% variations except sphere 14 in the T₂ array (6.36%). TMRF and spin-echo relaxometry measurements were strongly correlated; R² values were 0.9958 and 0.9789 for T₁ and T₂ estimates, respectively. Based on the ICC values, SNR, mean intensity values, and relaxation times of WM and GM for the in vivo studies were consistent. T₁ and T₂ values of WM and GM were similar to previously published values. The mean ± SD of T₁ and T₂ for WM for ten subjects and five repeats are 992 ± 41 ms and 99 ± 6 ms, while the corresponding values for T₁ and T₂ for GM are 1598 ± 73 ms and 152 ± 14 ms.

CONCLUSION

TMRF and deep learning-based reconstruction produce repeatable, non-synthetic multi-contrast images and parametric maps simultaneously. This article is protected by copyright. All rights reserved.

Magnetic Resonance Fingerprinting of the Pediatric Brain

Magnetic resonance fingerprinting (MRF) is increasingly being used to evaluate brain development and differentiate normal and pathologic tissues in children. MRF can provide reliable and accurate intrinsic tissue properties, such as T1 and T2 relaxation times. MRF is a powerful tool in evaluating brain disease in pediatric population. MRF is a new quantitative MR imaging technique for rapid and simultaneous quantification of multiple tissue properties.

Channel Attention Networks for Robust MR Fingerprint Matching

Magnetic Resonance Fingerprinting (MRF) enables simultaneous mapping of multiple tissue parameters such as T1 and T2 relaxation times. The working principle of MRF relies on varying acquisition parameters pseudo-randomly, so that each tissue generates its unique signal evolution during scanning. Even though MRF provides faster scanning, it has disadvantages such as erroneous and slow generation of the corresponding parametric maps, which needs to be improved. Moreover, there is a need for explainable architectures for understanding the guiding signals to generate accurate parametric maps. In this paper, we addressed both of these shortcomings by proposing a novel neural network architecture (CONV-ICA) consisting of a channel-wise attention module and a fully convolutional network. The proposed approach, evaluated over 3 simulated MRF signals, reduces error in the reconstruction of tissue parameters by 8.88% for T1 and 75.44% for T2 with respect to state-of-the-art methods. Another contribution of this study is a new channel selection method: attention-based channel selection. Furthermore, the effect of patch size and temporal frames of MRF signal on channel reduction are analyzed by employing a channel-wise attention.

Real-Time Mapping of Tissue Properties for Magnetic Resonance Fingerprinting

Magnetic resonance fingerprinting (MRF) is a relatively new multi-parametric quantitative imaging method that involves a two-step process: (i) reconstructing a series of time frames from highly-undersampled non-Cartesian spiral k-space data and (ii) pattern matching using the time frames to infer tissue properties (e.g., T 1 and T 2 relaxation times). In this paper, we introduce a novel end-to-end deep learning framework to seamlessly map the tissue properties directly from spiral k-space MRF data, thereby avoiding time-consuming processing such as the non-uniform fast Fourier transform (NUFFT) and the dictionary-based fingerprint matching. Our method directly consumes the non-Cartesian k -space data, performs adaptive density compensation, and predicts multiple tissue property maps in one forward pass. Experiments on both 2D and 3D MRF data demonstrate that quantification accuracy comparable to state-of-the-art methods can be accomplished within 0.5 s, which is 1,100 to 7,700 times faster than the original MRF framework. The proposed method is thus promising for facilitating the adoption of MRF in clinical settings.

Lesion probability mapping in MS patients using a regression network on MR fingerprinting

BACKGROUND

To develop a regression neural network for the reconstruction of lesion probability maps on Magnetic Resonance Fingerprinting using echo-planar imaging (MRF-EPI) in addition to [Formula: see text], [Formula: see text], NAWM, and GM- probability maps.

METHODS

We performed MRF-EPI measurements in 42 patients with multiple sclerosis and 6 healthy volunteers along two sites. A U-net was trained to reconstruct the denoised and distortion corrected [Formula: see text] and [Formula: see text] maps, and to additionally generate NAWM-, GM-, and WM lesion probability maps.

RESULTS

WM lesions were predicted with a dice coefficient of [Formula: see text] and a lesion detection rate of [Formula: see text] for a threshold of 33%. The network jointly enabled accurate [Formula: see text] and [Formula: see text] times with relative deviations of 5.2% and 5.1% and average dice coefficients of [Formula: see text] and [Formula: see text] for NAWM and GM after binarizing with a threshold of 80%.

CONCLUSION

DL is a promising tool for the prediction of lesion probability maps in a fraction of time. These might be of clinical interest for the WM lesion analysis in MS patients.

Synergistic multi-contrast cardiac magnetic resonance image reconstruction

Cardiac magnetic resonance imaging (CMR) is an important tool for the non-invasive diagnosis of a variety of cardiovascular diseases. Parametric mapping with multi-contrast CMR is able to quantify tissue alterations in myocardial disease and promises to improve patient care. However, magnetic resonance imaging is an inherently slow imaging modality, resulting in long acquisition times for parametric mapping which acquires a series of cardiac images with different contrasts for signal fitting or dictionary matching. Furthermore, extra efforts to deal with respiratory and cardiac motion by triggering and gating further increase the scan time. Several techniques have been developed to speed up CMR acquisitions, which usually acquire less data than that required by the Nyquist-Shannon sampling theorem, followed by regularized reconstruction to mitigate undersampling artefacts. Recent advances in CMR parametric mapping speed up CMR by synergistically exploiting spatial-temporal and contrast redundancies. In this article, we will review the recent developments in multi-contrast CMR image reconstruction for parametric mapping with special focus on low-rank and model-based reconstructions. Deep learning-based multi-contrast reconstruction has recently been proposed in other magnetic resonance applications. These developments will be covered to introduce the general methodology. Current technical limitations and potential future directions are discussed. This article is part of the theme issue 'Synergistic tomographic image reconstruction: part 1'.

A parallel spatial and Bloch manifold regularized iterative reconstruction method for MR Fingerprinting

Magnetic Resonance Fingerprinting (MRF) reconstructs tissue maps based on a sequence of very highly undersampled images. In order to be able to perform MRF reconstruction, state-of-the-art MRF methods rely on priors such as the MR physics (Bloch equations) and might also use some additional low-rank or spatial regularization. However to our knowledge these three regularizations are not applied together in a joint reconstruction. The reason is that it is indeed challenging to incorporate effectively multiple regularizations in a single MRF optimization algorithm. As a result most of these methods are not robust to noise especially when the sequence length is short. In this paper, we propose a family of new methods where spatial and low-rank regularizations, in addition to the Bloch manifold regularization, are applied on the images. We show on digital phantom and NIST phantom scans, as well as volunteer scans that the proposed methods bring significant improvement in the quality of the estimated tissue maps.

Streamlined magnetic resonance fingerprinting: Fast whole-brain coverage with deep-learning based parameter estimation

Magnetic resonance fingerprinting (MRF) is a quantitative MRI (qMRI) framework that provides simultaneous estimates of multiple relaxation parameters as well as metrics of field inhomogeneity in a single acquisition. However, current challenges exist in the forms of (1) scan time; (2) need for custom image reconstruction; (3) large dictionary sizes; (4) long dictionary-matching time. This study aims to introduce a novel streamlined magnetic-resonance fingerprinting (sMRF) framework based on a single-shot echo-planar imaging (EPI) sequence to simultaneously estimate tissue T1, T2, and T2* with integrated B1⁺ correction. Encouraged by recent work on EPI-based MRF, we developed a method that combines spin-echo EPI with gradient-echo EPI to achieve T2 in addition to T1 and T2* quantification. To this design, we add simultaneous multi-slice (SMS) acceleration to enable full-brain coverage in a few minutes. Moreover, in the parameter-estimation step, we use deep learning to train a deep neural network (DNN) to accelerate the estimation process by orders of magnitude. Notably, due to the high image quality of the EPI scans, the training process can rely simply on Bloch-simulated data. The DNN also removes the need for storing large dictionaries. Phantom scans along with in-vivo multi-slice scans from seven healthy volunteers were acquired with resolutions of 1.1×1.1×3 mm³ and 1.7×1.7×3 mm³, and the results were validated against ground truth measurements. Excellent correspondence was found between our T1, T2, and T2* estimates and results obtained from standard approaches. In the phantom scan, a strong linear relationship (R = 1-1.04, R²>0.96) was found for all parameter estimates, with a particularly high agreement for T2 estimation (R²>0.99). Similar findings are reported for the in-vivo human data for all of our parameter estimates. Incorporation of DNN results in a reduction of parameter estimation time on the order of 1000 x and a reduction in storage requirements on the order of 2500 x while achieving highly similar results as conventional dictionary matching (%differences of 7.4 ± 0.4%, 3.6 ± 0.3% and 6.0 ± 0.4% error in T1, T2, and T2* estimation). Thus, sMRF has the potential to be the method of choice for future MRF studies by providing ease of implementation, fast whole-brain coverage, and ultra-fast T1/T2/T2* estimation.

Magnetic resonance parameter mapping using model-guided self-supervised deep learning

PURPOSE

To develop a model-guided self-supervised deep learning MRI reconstruction framework called reference-free latent map extraction (RELAX) for rapid quantitative MR parameter mapping.

METHODS

Two physical models are incorporated for network training in RELAX, including the inherent MR imaging model and a quantitative model that is used to fit parameters in quantitative MRI. By enforcing these physical model constraints, RELAX eliminates the need for full sampled reference data sets that are required in standard supervised learning. Meanwhile, RELAX also enables direct reconstruction of corresponding MR parameter maps from undersampled k-space. Generic sparsity constraints used in conventional iterative reconstruction, such as the total variation constraint, can be additionally included in the RELAX framework to improve reconstruction quality. The performance of RELAX was tested for accelerated T1 and T2 mapping in both simulated and actually acquired MRI data sets and was compared with supervised learning and conventional constrained reconstruction for suppressing noise and/or undersampling-induced artifacts.

RESULTS

In the simulated data sets, RELAX generated good T1 /T2 maps in the presence of noise and/or undersampling artifacts, comparable to artifact/noise-free ground truth. The inclusion of a spatial total variation constraint helps improve image quality. For the in vivo T1 /T2 mapping data sets, RELAX achieved superior reconstruction quality compared with conventional iterative reconstruction, and similar reconstruction performance to supervised deep learning reconstruction.

CONCLUSION

This work has demonstrated the initial feasibility of rapid quantitative MR parameter mapping based on self-supervised deep learning. The RELAX framework may also be further extended to other quantitative MRI applications by incorporating corresponding quantitative imaging models.

Investigation of the effect of acquisition schemes on time-resolved magnetic resonance fingerprinting

Purpose.This study aims to investigate the feasibility of different acquisition methods for time-resolved magnetic resonance fingerprinting (TR-MRF) in computer simulation.Methods.An extended cardiac-torso (XCAT) phantom is used to generate abdominal T1, T2, and proton density maps for MRF simulation. The simulated MRF technique consists of an IR-FISP MRF sequence with spiral trajectory acquisition. MRF maps were simulated with different numbers of repetitions from 1 to 15. Three different methods were used to generate TR-MRF maps: (1) continuous acquisition without delay between MRF repetitions; (2) continuous acquisition with 5 s delay between MRF repetitions; (3) triggered acquisition with variable delay between MRF repetitions to allow the next acquisition to start at different respiration phase. After the generation of TR-MRF maps, the image quality indexes including the absolute T1 and T2 values, signal-to-noise-ratio (SNR), tumor-to-liver contrast-to-noise ratio, error in the amplitude of diaphragm motion and tumor volume error were used to evaluate the reconstructed parameter maps. Three volunteers were recruited to test the feasibility of the selected acquisition method.Results.Dynamic MR parametric maps using three different acquisition methods were estimated. The overall and liver T1 value error, liver SNR in T1 and T2 maps, and tumor SNR from T1 maps from triggered method is statistically significantly better than the other two methods (p-value < 0.05). The other image quality indexes have no significant difference between the triggered method and the other two continuous acquisition methods. All image quality indexes exhibit no significant difference between the acquisition methods with 0 s and 5 s delay. The triggered method was successfully performed in three healthy volunteers.Conclusion.TR-MRF technique was investigated using three different acquisition methods in computer simulation where the triggered method showed better performance than the other two methods. The triggered method has been tested successfully in healthy volunteers.

Bayesian uncertainty quantification for magnetic resonance fingerprinting

Magnetic Resonance Fingerprinting (MRF) is a promising technique for fast quantitative imaging of human tissue. In general, MRF is based on a sequence of highly undersampled MR images which are analyzed with a pre-computed dictionary. MRF provides valuable diagnostic parameters such as the $T_1$ and $T_2$ MR relaxation times. However, uncertainty characterization of dictionary-based MRF estimates for $T_1$ and $T_2$ has not been achieved so far, which makes it challenging to assess if observed differences in these estimates are significant and may indicate pathological changes of the underlying tissue. We propose a Bayesian approach for the uncertainty quantification of dictionary-based MRF which leads to probability distributions for $T_1$ and $T_2$ in every voxel. The distributions can be used to make probability statements about the relaxation times, and to assign uncertainties to their dictionary-based MRF estimates. All uncertainty calculations are based on the pre-computed dictionary and the observed sequence of undersampled MR images, and they can be calculated in short time. The approach is explored by analyzing MRF measurements of a phantom consisting of several tubes across which MR relaxation times are constant. The proposed uncertainty quantification is quantitatively consistent with the observed within-tube variability of estimated relaxation times. Furthermore, calculated uncertainties are shown to characterize well observed differences between the MRF estimates and the results obtained from high-accurate reference measurements. These findings indicate that a reliable uncertainty quantification is achieved. We also present results for simulated MRF data and an uncertainty quantification for an in vivo MRF measurement. MATLAB$^{\scriptsize \text{\textregistered}}$ source code implementing the proposed approach is made available.

Accelerated white matter lesion analysis based on simultaneous T 1 and T 2 ∗ quantification using magnetic resonance fingerprinting and deep learning

PURPOSE

To develop an accelerated postprocessing pipeline for reproducible and efficient assessment of white matter lesions using quantitative magnetic resonance fingerprinting (MRF) and deep learning.

METHODS

MRF using echo-planar imaging (EPI) scans with varying repetition and echo times were acquired for whole brain quantification of T 1 and T 2 ∗ in 50 subjects with multiple sclerosis (MS) and 10 healthy volunteers along 2 centers. MRF T 1 and T 2 ∗ parametric maps were distortion corrected and denoised. A CNN was trained to reconstruct the T 1 and T 2 ∗ parametric maps, and the WM and GM probability maps.

RESULTS

Deep learning-based postprocessing reduced reconstruction and image processing times from hours to a few seconds while maintaining high accuracy, reliability, and precision. Mean absolute error performed the best for T 1 (deviations 5.6%) and the logarithmic hyperbolic cosinus loss the best for T 2 ∗ (deviations 6.0%).

CONCLUSIONS

MRF is a fast and robust tool for quantitative T 1 and T 2 ∗ mapping. Its long reconstruction and several postprocessing steps can be facilitated and accelerated using deep learning.

Compressive MRI quantification using convex spatiotemporal priors and deep encoder-decoder networks

We propose a dictionary-matching-free pipeline for multi-parametric quantitative MRI image computing. Our approach has two stages based on compressed sensing reconstruction and deep learned quantitative inference. The reconstruction phase is convex and incorporates efficient spatiotemporal regularisations within an accelerated iterative shrinkage algorithm. This minimises the under-sampling (aliasing) artefacts from aggressively short scan times. The learned quantitative inference phase is purely trained on physical simulations (Bloch equations) that are flexible for producing rich training samples. We propose a deep and compact encoder-decoder network with residual blocks in order to embed Bloch manifold projections through multi-scale piecewise affine approximations, and to replace the non-scalable dictionary-matching baseline. Tested on a number of datasets we demonstrate effectiveness of the proposed scheme for recovering accurate and consistent quantitative information from novel and aggressively subsampled 2D/3D quantitative MRI acquisition protocols.

Magnetic resonance fingerprinting: from evolution to clinical applications

In 2013, Magnetic Resonance Fingerprinting (MRF) emerged as a method for fast, quantitative Magnetic Resonance Imaging. This paper reviews the current status of MRF up to early 2020 and aims to highlight the advantages MRF can offer medical imaging professionals. By acquiring scan data as pseudorandom samples, MRF elicits a unique signal evolution, or 'fingerprint', from each tissue type. It matches 'randomised' free induction decay acquisitions against pre-computed simulated tissue responses to generate a set of quantitative images of T1 , T2 and proton density (PD) with co-registered voxels, rather than as traditional relative T1 - and T2 -weighted images. MRF numeric pixel values retain accuracy and reproducibility between 2% and 8%. MRF acquisition is robust to strong undersampling of k-space. Scan sequences have been optimised to suppress sub-sampling artefacts, while artificial intelligence and machine learning techniques have been employed to increase matching speed and precision. MRF promises improved patient comfort with reduced scan times and fewer image artefacts. Quantitative MRF data could be used to define population-wide numeric biomarkers that classify normal versus diseased tissue. Certification of clinical centres for MRF scan repeatability would permit numeric comparison of sequential images for any individual patient and the pooling of multiple patient images across large, cross-site imaging studies. MRF has to date shown promising results in early clinical trials, demonstrating reliable differentiation between malignant and benign prostate conditions, and normal and sclerotic hippocampal tissue. MRF is now undergoing small-scale trials at several sites across the world; moving it closer to routine clinical application.