A deep learning approach for magnetization transfer contrast MR fingerprinting and chemical exchange saturation transfer imaging

Highly-accelerated CEST MRI using frequency-offset-dependent k-space sampling and deep-learning reconstruction

PURPOSE

To develop a highly accelerated CEST Z-spectral acquisition method using a specifically-designed k-space sampling pattern and corresponding deep-learning-based reconstruction.

METHODS

For k-space down-sampling, a customized pattern was proposed for CEST, with the randomized probability following a frequency-offset-dependent (FOD) function in the direction of saturation offset. For reconstruction, the convolution network (CNN) was enhanced with a Partially Separable (PS) function to optimize the spatial domain and frequency domain separately. Retrospective experiments on a self-acquired human brain dataset (13 healthy adults and 15 brain tumor patients) were conducted using k-space resampling. The prospective performance was also assessed on six healthy subjects.

RESULTS

In retrospective experiments, the combination of FOD sampling and PS network (FOD + PSN) showed the best quantitative metrics for reconstruction, outperforming three other combinations of conventional sampling with varying density and a regular CNN (nMSE and SSIM, p < 0.001 for healthy subjects). Across all acceleration factors from 4 to 14, the FOD + PSN approach consistently outperformed the comparative methods in four contrast maps including MTRasym, MTRrex, as well as the Lorentzian Difference maps of amide and nuclear Overhauser effect (NOE). In the subspace replacement experiment, the error distribution demonstrated the denoising benefits achieved in the spatial subspace. Finally, our prospective results obtained from healthy adults and brain tumor patients (14×) exhibited the initial feasibility of our method, albeit with less accurate reconstruction than retrospective ones.

CONCLUSION

The combination of FOD sampling and PSN reconstruction enabled highly accelerated CEST MRI acquisition, which may facilitate CEST metabolic MRI for brain tumor patients.

Self-supervised learning for denoising of multidimensional MRI data

PURPOSE

To develop a fast denoising framework for high-dimensional MRI data based on a self-supervised learning scheme, which does not require ground truth clean image.

THEORY AND METHODS

Quantitative MRI faces limitations in SNR, because the variation of signal amplitude in a large set of images is the key mechanism for quantification. In addition, the complex non-linear signal models make the fitting process vulnerable to noise. To address these issues, we propose a fast deep-learning framework for denoising, which efficiently exploits the redundancy in multidimensional MRI data. A self-supervised model was designed to use only noisy images for training, bypassing the challenge of clean data paucity in clinical practice. For validation, we used two different datasets of simulated magnetization transfer contrast MR fingerprinting (MTC-MRF) dataset and in vivo DWI image dataset to show the generalizability.

RESULTS

The proposed method drastically improved denoising performance in the presence of mild-to-severe noise regardless of noise distributions compared to previous methods of the BM3D, tMPPCA, and Patch2self. The improvements were even pronounced in the following quantification results from the denoised images.

CONCLUSION

The proposed MD-S2S (Multidimensional-Self2Self) denoising technique could be further applied to various multi-dimensional MRI data and improve the quantification accuracy of tissue parameter maps.

A generalized QUCESOP method with evaluating CEST peak overlap

The overlapping peaks of the target chemical exchange saturation transfer (CEST) solutes and other unknown CEST solutes affect the quantification results and accuracy of the chemical exchange parameters-the fractional concentration, f b , exchange rate, k b , and transverse relaxation rate, R 2 b -for the target solutes. However, to date, no method has been established for assessing the overlapping peaks. This study aimed to develop a method for quantifying the f b , k b , and R 2 b values of a specific CEST solute, as well as assessing the overlap between the CEST peaks of the specific solute(s) and other unknown solutes. A simplified R 1 ρ model was proposed, assuming linear approximation of the other solutes' contributions to R 1 ρ . A CEST data acquisition scheme was applied with various saturation offsets and saturation powers. In addition to fitting the f b , k b , and R 2 b values of the specific solute, the overlapping condition was evaluated based on the root mean square error (RMSE) between the trajectories of the acquired and synthesized data. Single-solute and multi-solute phantoms with various phosphocreatine (PCr) concentrations and pH values were used to calculate the f b and k b of PCr and the corresponding RMSE. The feasibility of RMSE for evaluating the overlapping condition, and the accurate fitting of f b and k b in weak overlapping conditions, were verified. Furthermore, the method was employed to quantify the nuclear Overhauser effect signal in rat brains and the PCr signal in rat skeletal muscles, providing results that were consistent with those reported in previous studies. In summary, the proposed approach can be applied to evaluate the overlapping condition of CEST peaks and quantify the f b , k b , and R 2 b values of specific solutes, if the weak overlapping condition is satisfied.

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.

CEST and nuclear Overhauser enhancement imaging with deep learning-extrapolated semisolid magnetization transfer reference: Scan-rescan reproducibility and reliability studies

PURPOSE

To develop a novel MR physics-driven, deep-learning, extrapolated semisolid magnetization transfer reference (DeepEMR) framework to provide fast, reliable magnetization transfer contrast (MTC) and CEST signal estimations, and to determine the reproducibility and reliability of the estimates from the DeepEMR.

METHODS

A neural network was designed to predict a direct water saturation and MTC-dominated signal at a certain CEST frequency offset using a few high-frequency offset features in the Z-spectrum. The accuracy, scan-rescan reproducibility, and reliability of MTC, CEST, and relayed nuclear Overhauser enhancement (rNOE) signals estimated from the DeepEMR were evaluated on numerical phantoms and in heathy volunteers at 3 T. In addition, we applied the DeepEMR method to brain tumor patients and compared tissue contrast with other CEST calculation metrics.

RESULTS

The DeepEMR method demonstrated a high degree of accuracy in the estimation of reference MTC signals at ±3.5 ppm for APT and rNOE imaging, and computational efficiency (˜190-fold) compared with a conventional fitting approach. In addition, the DeepEMR method achieved high reproducibility and reliability (intraclass correlation coefficient = 0.97, intersubject coefficient of variation = 3.5%, and intrasubject coefficient of variation = 1.3%) of the estimation of MTC signals at ±3.5 ppm. In tumor patients, DeepEMR-based amide proton transfer images provided higher tumor contrast than a conventional MT ratio asymmetry image, particularly at higher B1 strengths (>1.5 μT), with a distinct delineation of the tumor core from normal tissue or peritumoral edema.

CONCLUSION

The DeepEMR approach is feasible for measuring clean APT and rNOE effects in longitudinal and cross-sectional studies with low scan-rescan variability.

Accelerating CEST imaging using a model-based deep neural network with synthetic training data

PURPOSE

To develop a model-based deep neural network for high-quality image reconstruction of undersampled multi-coil CEST data.

THEORY AND METHODS

Inspired by the variational network (VN), the CEST image reconstruction equation is unrolled into a deep neural network (CEST-VN) with a k-space data-sharing block that takes advantage of the inherent redundancy in adjacent CEST frames and 3D spatial-frequential convolution kernels that exploit correlations in the x-ω domain. Additionally, a new pipeline based on multiple-pool Bloch-McConnell simulations is devised to synthesize multi-coil CEST data from publicly available anatomical MRI data. The proposed network is trained on simulated data with a CEST-specific loss function that jointly measures the structural and CEST contrast. The performance of CEST-VN was evaluated on four healthy volunteers and five brain tumor patients using retrospectively or prospectively undersampled data with various acceleration factors, and then compared with other conventional and state-of-the-art reconstruction methods.

RESULTS

The proposed CEST-VN method generated high-quality CEST source images and amide proton transfer-weighted maps in healthy and brain tumor subjects, consistently outperforming GRAPPA, blind compressed sensing, and the original VN. With the acceleration factors increasing from 3 to 6, CEST-VN with the same hyperparameters yielded similar and accurate reconstruction without apparent loss of details or increase of artifacts. The ablation studies confirmed the effectiveness of the CEST-specific loss function and data-sharing block used.

CONCLUSIONS

The proposed CEST-VN method can offer high-quality CEST source images and amide proton transfer-weighted maps from highly undersampled multi-coil data by integrating the deep learning prior and multi-coil sensitivity encoding model.

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.

Measuring chemical exchange saturation transfer exchange rates in the human brain using a particle swarm optimisation algorithm

The z-spectrum contains many pools with different exchange rates and T2 values, which can make it difficult to interpret in vivo data and complicates the design of experiments aimed at providing sensitivity to one pool. This work aims to characterise the main pools observable with MRI at 7T in the human brain. To achieve this, we acquired z-spectra at multiple saturation powers in the human brain at 7T. We used simulations to optimise the use of particle swarm optimisation (PSO) to fit these data, validating this approach using further simulations and creatine phantoms. We then used the PSO to fit data from grey and white matter for the pool size, exchange rate, and T2 of five proton pools (magnetisation transfer, amides, amines, nuclear Overhauser enhancement NOE-3.5ppm and NOE-1.7ppm in addition to water). We then devised an approach for using PSO to fit z-spectra while limiting the computational burden, and we investigated the sensitivity of the fit to T2 and k for three overlapping pools. We used this to measure the exchange rate of creatine and to show that it varied with temperature, as expected. In the brain we measured a significantly larger pool size in white matter than in grey matter for the magnetisation transfer pool and the NOE-3.5ppm pool. For all other parameters we found no significant difference between grey and white matter. We showed that PSO can be used to fit z-spectra acquired at a range of B1 to provide information about peak position, amplitude, exchange rate, and T2 in vivo in the human brain. These data could provide more sensitivity to change in some clinical conditions and will also provide key information for further experimental design.

Dynamic and rapid deep synthesis of chemical exchange saturation transfer and semisolid magnetization transfer MRI signals

Model-driven analysis of biophysical phenomena is gaining increased attention and utility for medical imaging applications. In magnetic resonance imaging (MRI), the availability of well-established models for describing the relations between the nuclear magnetization, tissue properties, and the externally applied magnetic fields has enabled the prediction of image contrast and served as a powerful tool for designing the imaging protocols that are now routinely used in the clinic. Recently, various advanced imaging techniques have relied on these models for image reconstruction, quantitative tissue parameter extraction, and automatic optimization of acquisition protocols. In molecular MRI, however, the increased complexity of the imaging scenario, where the signals from various chemical compounds and multiple proton pools must be accounted for, results in exceedingly long model simulation times, severely hindering the progress of this approach and its dissemination for various clinical applications. Here, we show that a deep-learning-based system can capture the nonlinear relations embedded in the molecular MRI Bloch-McConnell model, enabling a rapid and accurate generation of biologically realistic synthetic data. The applicability of this simulated data for in-silico, in-vitro, and in-vivo imaging applications is then demonstrated for chemical exchange saturation transfer (CEST) and semisolid macromolecule magnetization transfer (MT) analysis and quantification. The proposed approach yielded 63-99% acceleration in data synthesis time while retaining excellent agreement with the ground truth (Pearson's r > 0.99, p < 0.0001, normalized root mean square error < 3%).

Bloch simulator-driven deep recurrent neural network for magnetization transfer contrast MR fingerprinting and CEST imaging

PURPOSE

To develop a unified deep-learning framework by combining an ultrafast Bloch simulator and a semisolid macromolecular magnetization transfer contrast (MTC) MR fingerprinting (MRF) reconstruction for estimation of MTC effects.

METHODS

The Bloch simulator and MRF reconstruction architectures were designed with recurrent neural networks and convolutional neural networks, evaluated with numerical phantoms with known ground truths and cross-linked bovine serum albumin phantoms, and demonstrated in the brain of healthy volunteers at 3 T. In addition, the inherent magnetization-transfer ratio asymmetry effect was evaluated in MTC-MRF, CEST, and relayed nuclear Overhauser enhancement imaging. A test-retest study was performed to evaluate the repeatability of MTC parameters, CEST, and relayed nuclear Overhauser enhancement signals estimated by the unified deep-learning framework.

RESULTS

Compared with a conventional Bloch simulation, the deep Bloch simulator for generation of the MTC-MRF dictionary or a training data set reduced the computation time by 181-fold, without compromising MRF profile accuracy. The recurrent neural network-based MRF reconstruction outperformed existing methods in terms of reconstruction accuracy and noise robustness. Using the proposed MTC-MRF framework for tissue-parameter quantification, the test-retest study showed a high degree of repeatability in which the coefficients of variance were less than 7% for all tissue parameters.

CONCLUSION

Bloch simulator-driven, deep-learning MTC-MRF can provide robust and repeatable multiple-tissue parameter quantification in a clinically feasible scan time on a 3T scanner.

Validation of the presence of fast exchanging amine CEST effect at low saturation powers and its influence on the quantification of APT

PURPOSE

Accurately quantifying the amide proton transfer (APT) effect and the underlying exchange parameters is crucial for its applications, but previous studies have reported conflicting results. In these quantifications, the CEST effect from the fast exchange amine was always ignored because it was considered weak with low saturation powers. This paper aims to evaluate the influence of the fast exchange amine CEST on the quantification of APT at low saturation powers.

METHODS

A quantification method with low and high saturation powers was used to distinguish APT from the fast exchange amine CEST effect. Simulations were conducted to assess the method's capability to separate APT from the fast exchange amine CEST effect. Animal experiments were performed to assess the relative contributions from the fast exchange amine and amide to CEST signals at 3.5 ppm. Three APT quantification methods, each with varying degrees of contamination from the fast exchange amine, were employed to process the animal data to assess the influence of the amine on the quantification of APT effect and the exchange parameters.

RESULTS

The relative size of the fast exchange amine CEST effect to APT effect gradually increases with increasing saturation power. At 9.4 T, it increases from approximately 20% to 40% of APT effect with a saturation power increase from 0.25 to 1 μT.

CONCLUSION

The fast exchange amine CEST effect leads overestimation of APT effect, fitted amide concentration, and amide-water exchange rate, potentially contributing to the conflicting results reported in previous studies.

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.

Evaluation of contributors to amide proton transfer-weighted imaging and nuclear Overhauser enhancement-weighted imaging contrast in tumors at a high magnetic field

PURPOSE

The purpose is to evaluate the relative contribution from confounding factors (T1 weighting and magnetization transfer) to the CEST ratio (CESTR)-quantified amide proton transfer (APT) and nuclear Overhauser enhancement (NOE) (-3.5) in tumors as well as whether the CESTR can reflect the distribution of the solute concentration (fs ).

METHODS

We first provided a signal model that shows the separate dependence of CESTR on these confounding factors and the clean CEST/NOE effects quantified by an apparent exchange-dependent relaxation (AREX) method. We then measured the change in these effects in the 9-L tumor model in rats, through which we calculated the relative contribution of each confounding factor. fs was also fitted, and its correlations with the CESTR and AREX were assessed to evaluate their capabilities to reflect fs .

RESULTS

The CESTR-quantified APT shows "positive" contrast in tumors, which arises primarily from R1w at low powers and both R1w and magnetization transfer at high powers. CESTR-quantified NOE (-3.5) shows no or weak contrast in tumors, which is due to the cancelation of R1w and NOE (-3.5), which have opposite contributions. CESTR-quantified APT has a stronger correlation with APT fs than AREX-quantified APT. CESTR-quantified NOE (-3.5) has a weaker correlation with NOE (-3.5) fs than AREX-quantified NOE (-3.5).

CONCLUSION

CESTR reflects a combined effect of T1 weighting and CEST/NOE. Both factors depend on fs , which contributes positively to the dependence of CESTR on fs in APT imaging and enhances its correlation with fs . In contrast, these factors have opposite contributions to its dependence on fs in NOE (-3.5) imaging, thereby weakening the correlation.

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.

Acquisition sequences and reconstruction methods for fast chemical exchange saturation transfer imaging

Chemical exchange saturation transfer (CEST) imaging is an emerging molecular magnetic resonance imaging (MRI) technique that has been developed and employed in numerous diseases. Based on the unique saturation transfer principle, a family of CEST-detectable biomolecules in vivo have been found capable of providing valuable diagnostic information. However, CEST MRI needs a relatively long scan time due to the common long saturation labeling module and typical acquisition of multiple frequency offsets and signal averages, limiting its widespread clinical applications. So far, a plethora of imaging schemes and techniques has been developed to accelerate CEST MRI. In this review, the key acquisition and reconstruction methods for fast CEST imaging are summarized from a practical and systematic point of view. The first acquisition sequence section describes the major development of saturation schemes, readout patterns, ultrafast z-spectroscopy, and saturation-editing techniques for rapid CEST imaging. The second reconstruction method section lists the important advances of parallel imaging, compressed sensing, sparsity in the z-spectrum, and algorithms beyond the Fourier transform for speeding up CEST MRI.

Frequency importance analysis for chemical exchange saturation transfer magnetic resonance imaging using permuted random forest

Chemical exchange saturation transfer magnetic resonance imaging (CEST MRI) is a promising molecular imaging tool that allows sensitive detection of endogenous metabolic changes. However, because the CEST spectrum does not display a clear peak like MR spectroscopy, its signal interpretation is challenging, especially under 3-T field strength or with a large saturation B₁ . Herein, as an alternative to conventional Z-spectral fitting approaches, a permuted random forest (PRF) method is developed to determine featured saturation frequencies for lesion identification, so-called CEST frequency importance analysis. Briefly, voxels in the CEST dataset were labeled as lesion and control according to multicontrast MR images. Then, by considering each voxel's saturation signal series as a sample, a permutation importance algorithm was employed to rank the contribution of saturation frequency offsets in the differentiation of lesion and normal tissue. Simulations demonstrated that PRF could correctly determine the frequency offsets (3.5 or -3.5 ppm) for classifying two groups of Z-spectra, under a range of B₀ , B₁ conditions and sample sizes. For ischemic rat brains, PRF only displayed high feature importance around amide frequency at 2 h postischemia, reflecting that the pH changes occurred at an early stage. By contrast, the data acquired at 24 h postischemia exhibited high feature importance at multiple frequencies (amide, water, and lipids), which suggested the complex tissue changes that occur during the later stages. Finally, PRF was assessed using 3-T CEST data from four brain tumor patients. By defining the tumor region on amide proton transfer-weighted images, PRF analysis identified different CEST frequency importance for two types of tumors (glioblastoma and metastatic tumor) (p < 0.05, with each image slice as a subject). In conclusion, the PRF method was able to rank and interpret the contribution of all acquired saturation offsets to lesion identification; this may facilitate CEST analysis in clinical applications, and open up new doors for comprehensive CEST analysis tools other than model-based approaches.

Glutamate-weighted CEST (gluCEST) imaging for mapping neurometabolism: An update on the state of the art and emerging findings from in vivo applications

Glutamate is the primary excitatory neurotransmitter in the mammalian central nervous system. As such, its proper regulation is essential to the healthy function of the human brain, and dysregulation of glutamate metabolism and compartmentalization underlies numerous neurological and neuropsychiatric pathologies. Glutamate-weighted chemical exchange saturation transfer (gluCEST) MRI is one of the only ways to non-invasively observe the relative concentration and spatial distribution of glutamate in the human brain. In the past 10 years, gluCEST has developed from a proof-of-concept experiment carried out in imaging phantoms and model systems to an increasingly sophisticated technique applied to reveal deviations from baseline neural metabolism in human beings, most notably in patients experiencing seizures of various origins or those on the psychosis spectrum. This article traces that progress, including in-depth discussion of the technical specifics of gluCEST and potential challenges to performing these experiments rigorously. We discuss the neurobiological context of glutamate, including the widely accepted hypotheses and models in the literature regarding its involvement in neurodegenerative diseases and other pathology. We then review the state of the art of in vivo glutamate detection by magnetic resonance imaging and the limitations on this front of in vivo MR spectroscopy. The gluCEST experiment is introduced and its advantages, challenges and limitations are thoroughly explored, beginning with the phantom experiment results demonstrated in the initial publication, through the latest approaches to correcting human brain images for B₁ inhomogeneity. We then give a comprehensive overview of preclinical applications demonstrated to date, including Alzheimer's disease, Parkinson's disease, Huntington's disease, Traumatic brain injury and cancer, followed by a similar discussion of human studies. Finally, we highlight emerging applications, and discuss technical improvements on the horizon that hold promise for improving the robustness and versatility of gluCEST and its increasing presence in the arena of translational and precision medicine.

Amide proton transfer imaging in stroke

Amide proton transfer (APT) imaging, a variant of chemical exchange saturation transfer MRI, has shown promise in detecting ischemic tissue acidosis following impaired aerobic metabolism in animal models and in human stroke patients due to the sensitivity of the amide proton exchange rate to changes in pH within the physiological range. Recent studies have demonstrated the possibility of using APT-MRI to detect acidosis of the ischemic penumbra, enabling the assessment of stroke severity and risk of progression, monitoring of treatment progress, and prognostication of clinical outcome. This paper reviews current APT imaging methods actively used in ischemic stroke research and explores the clinical aspects of ischemic stroke and future applications for these methods.

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.

Reassembled saturation transfer (REST) MR images at 2 B1 values for in vivo exchange-dependent imaging of amide and nuclear Overhauser enhancement

PURPOSE

Design an efficient CEST scheme for exchange-dependent images with high contrast-to-noise ratio.

THEORY

Reassembled saturation transfer (REST) signals were defined as Δ $$ \Delta $$ r.Z = r.Z_ref - r.Z_CEST and the reassembled exchange-dependen magnetization transfer ratio r.MTR_Rex  = r.1/Z_ref - r.1/Z_CEST , utilizing the averages over loosely sampled reference frequency offsets as Z_ref and over densely sampled target offsets as Z_CEST . Using r.MTR_Rex measured under 2 B_1,sat values, exchange rate could be estimated.

METHODS

The REST approach was optimized and assessed quantitatively by simulations for various exchange rates, pool concentration, and water T₁ . In vivo evaluation was performed on ischemic rat brains at 7 Tesla and human brains at 3 Tesla, in comparison with conventional asymmetrical analysis, Lorentzian difference (LD), an MTR_{Rex_} LD.

RESULTS

For a broad choice of Δ ω ref $$ \Delta {\omega}_{ref} $$ ranges and numbers, Δr.Z and r.MTR_Rex exhibited comparable quantification features with conventional LD and MTR_Rex _LD, respectively, when B_1,sat  ≤ 1 μT. The subtraction of 2 REST values under distinct B_1,sat values showed linear relationships with exchange rate and obtained immunity to field inhomogeneity and variation in MT and water T₁ . For both rat and human studies, REST images exhibited similar contrast distribution to MTR_Rex _LD, with superiority in contrast-to-noise ratio and acquisition efficiency. Compared with MTR_Rex _LD, 2-B_1,sat subtraction REST images displayed better resistance to B₁ inhomogeneity, with more specific enhanced regions. They also showed higher signals for amide than for nuclear Overhauser enhancement effect in human brain, presumably reflecting the higher increment from faster-exchanging species as B_1,sat increased.

CONCLUSION

Featuring high contrast-to-noise ratio efficiency, REST could be a practical exchange-dependent approach readily applicable to either retrospective Z-spectra analysis or perspective 6-offset acquisition.

CEST MR fingerprinting (CEST-MRF) for brain tumor quantification using EPI readout and deep learning reconstruction

PURPOSE

To develop a clinical CEST MR fingerprinting (CEST-MRF) method for brain tumor quantification using EPI acquisition and deep learning reconstruction.

METHODS

A CEST-MRF pulse sequence originally designed for animal imaging was modified to conform to hardware limits on clinical scanners while keeping scan time under 2 min. Quantitative MRF reconstruction was performed using a deep reconstruction network (DRONE) to yield the water relaxation and chemical exchange parameters. The feasibility of the six parameter DRONE reconstruction was tested in simulations using a digital brain phantom. A healthy subject was scanned with the CEST-MRF sequence, conventional MRF and CEST sequences for comparison. Reproducibility was assessed via test-retest experiments and the concordance correlation coefficient calculated for white matter and gray matter. The clinical utility of CEST-MRF was demonstrated on four patients with brain metastases in comparison to standard clinical imaging sequences. Tumors were segmented into edema, solid core, and necrotic core regions and the CEST-MRF values compared to the contra-lateral side.

RESULTS

DRONE reconstruction of the digital phantom yielded a normalized RMS error of ≤7% for all parameters. The CEST-MRF parameters were in good agreement with those from conventional MRF and CEST sequences and previous studies. The mean concordance correlation coefficient for all six parameters was 0.98 ± 0.01 in white matter and 0.98 ± 0.02 in gray matter. The CEST-MRF values in nearly all tumor regions were significantly different (P = 0.05) from each other and the contra-lateral side.

CONCLUSION

Combination of EPI readout and deep learning reconstruction enabled fast, accurate and reproducible CEST-MRF in brain tumors.

MR fingerprinting of the prostate

Multiparametric magnetic resonance imaging (mpMRI) has been adopted as the key tool for detection, localization, characterization, and risk stratification of patients suspected to have prostate cancer. Despite advantages over systematic biopsy, the interpretation of prostate mpMRI has limitations including a steep learning curve, leading to considerable interobserver variation. There is growing interest in clinical translation of quantitative imaging techniques for more objective lesion assessment. However, traditional mapping techniques are slow, precluding their use in the clinic. Magnetic resonance fingerprinting (MRF) is an efficient approach for quantitative maps of multiple tissue properties simultaneously. The T₁ and T₂ values obtained with MRF have been validated with phantom studies as well as in normal volunteers and patients. Studies have shown that MRF-derived T₁ and T₂ along with ADC values are all significant independent predictors in the differentiation between normal prostate tissue and prostate cancer, and hold promise in differentiating low and intermediate/high-grade cancers. This review seeks to introduce the basics of the prostate MRF technique, discuss the potential applications of prostate MRF for the characterization of prostate cancer, and describes ongoing areas of research.

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.

Molecular Imaging of Brain Tumors and Drug Delivery Using CEST MRI: Promises and Challenges

Chemical exchange saturation transfer (CEST) magnetic resonance imaging (MRI) detects molecules in their natural forms in a sensitive and non-invasive manner. This makes it a robust approach to assess brain tumors and related molecular alterations using endogenous molecules, such as proteins/peptides, and drugs approved for clinical use. In this review, we will discuss the promises of CEST MRI in the identification of tumors, tumor grading, detecting molecular alterations related to isocitrate dehydrogenase (IDH) and O-6-methylguanine-DNA methyltransferase (MGMT), assessment of treatment effects, and using multiple contrasts of CEST to develop theranostic approaches for cancer treatments. Promising applications include (i) using the CEST contrast of amide protons of proteins/peptides to detect brain tumors, such as glioblastoma multiforme (GBM) and low-grade gliomas; (ii) using multiple CEST contrasts for tumor stratification, and (iii) evaluation of the efficacy of drug delivery without the need of metallic or radioactive labels. These promising applications have raised enthusiasm, however, the use of CEST MRI is not trivial. CEST contrast depends on the pulse sequences, saturation parameters, methods used to analyze the CEST spectrum (i.e., Z-spectrum), and, importantly, how to interpret changes in CEST contrast and related molecular alterations in the brain. Emerging pulse sequence designs and data analysis approaches, including those assisted with deep learning, have enhanced the capability of CEST MRI in detecting molecules in brain tumors. CEST has become a specific marker for tumor grading and has the potential for prognosis and theranostics in brain tumors. With increasing understanding of the technical aspects and associated molecular alterations detected by CEST MRI, this young field is expected to have wide clinical applications in the near future.

MR fingerprinting for semisolid magnetization transfer and chemical exchange saturation transfer quantification

Chemical exchange saturation transfer (CEST) MRI has positioned itself as a promising contrast mechanism, capable of providing molecular information at sufficient resolution and amplified sensitivity. However, it has not yet become a routinely employed clinical technique, due to a variety of confounding factors affecting its contrast-weighted image interpretation and the inherently long scan time. CEST MR fingerprinting (MRF) is a novel approach for addressing these challenges, allowing simultaneous quantitation of several proton exchange parameters using rapid acquisition schemes. Recently, a number of deep-learning algorithms have been developed to further boost the performance and speed of CEST and semi-solid macromolecule magnetization transfer (MT) MRF. This review article describes the fundamental theory behind semisolid MT/CEST-MRF and its main applications. It then details supervised and unsupervised learning approaches for MRF image reconstruction and describes artificial intelligence (AI)-based pipelines for protocol optimization. Finally, practical considerations are discussed, and future perspectives are given, accompanied by basic demonstration code and data.

An end-to-end AI-based framework for automated discovery of rapid CEST/MT MRI acquisition protocols and molecular parameter quantification (AutoCEST)

Purpose

To develop an automated machine‐learning‐based method for the discovery of rapid and quantitative chemical exchange saturation transfer (CEST) MR fingerprinting acquisition and reconstruction protocols.

Methods

An MR physics‐governed AI system was trained to generate optimized acquisition schedules and the corresponding quantitative reconstruction neural network. The system (termed AutoCEST) is composed of a CEST saturation block, a spin dynamics module, and a deep reconstruction network, all differentiable and jointly connected. The method was validated using a variety of chemical exchange phantoms and in vivo mouse brains at 9.4T.

Results

The acquisition times for AutoCEST optimized schedules ranged from 35 to 71 s, with a quantitative image reconstruction time of only 29 ms. The resulting exchangeable proton concentration maps for the phantoms were in good agreement with the known solute concentrations for AutoCEST sequences (mean absolute error = 2.42 mM; Pearson’s r=0.992, p<0.0001), but not for an unoptimized sequence (mean absolute error = 65.19 mM; Pearson’s r=‐0.161, p=0.522). Similarly, improved exchange rate agreement was observed between AutoCEST and quantification of exchange using saturation power (QUESP) methods (mean absolute error: 35.8 Hz, Pearson’s r=0.971, p<0.0001) compared to an unoptimized schedule and QUESP (mean absolute error = 58.2 Hz; Pearson’s r=0.959, p<0.0001). The AutoCEST in vivo mouse brain semi‐solid proton volume fractions were lower in the cortex (12.77% ± 0.75%) compared to the white matter (19.80% ± 0.50%), as expected.

Conclusion

AutoCEST can automatically generate optimized CEST/MT acquisition protocols that can be rapidly reconstructed into quantitative exchange parameter maps.

A Fully Convolutional Network (FCN) based Automated Ischemic Stroke Segment Method using Chemical Exchange Saturation Transfer Imaging

BACKGROUND

Chemical exchange saturation transfer (CEST) MRI is a promising imaging modality in ischemic stroke detection for its sensitivity in sensing post-ischemic pH alteration. However, the accurate segmentation of pH-altered regions remains difficult due to the complicated sources in water signal changes of CEST MRI. Meanwhile, manual localization and quantification of stroke lesions are laborious and time-consuming, which cannot meet the urgent need for timely therapeutic interventions.

PURPOSE

The goal of this study was to develop an automatic lesion segmentation approach of ischemic region based on CEST MR images. A novel segmentation framework based on fully convolutional neural network was investigated for our task.

METHODS

Z-spectra from 10 rats were manually labeled as ground truth and split into two datasets, where the training dataset including 3 rats was used to generate a segmentation model, and the remaining rats were used as test datasets to evaluate the model's performance. Then a 1-D fully convolutional neural network equipped with bottleneck structures was set up, and a Grad-CAM approach was used to produce a coarse localization map, which can reflect the relevancy to the 'ischemia' class of each pixel.

RESULTS

As compared with the ground truth, the proposed network model achieved satisfying segmentation results with high values of evaluation metrics including specificity (SPE), sensitivity (SEN), accuracy (ACC), and Dice similarity coefficient (DSC), especially in some intractable situations where conventional MRI modalities and CEST quantitative method failed to distinguish between ischemic and normal tissues, and the model with augmentation was robust to input perturbations. The Grad-CAM maps performed clear tissue change distributions and interpreted the segmentations, and showed a strong correlation with the quantitative method, gave extended thinking to the function of networks.

CONCLUSIONS

The proposed method can segment ischemia region from CEST images, with the Grad-CAM maps give access to interpretative information about the segmentations, which demonstrates great potential in clinical routines. This article is protected by copyright. All rights reserved.

PEAKIT: A Gaussian Process regression analysis tool for chemical exchange saturation transfer spectra

Chemical Exchange Saturation Transfer (CEST) is a powerful technique for metabolic imaging, capable of exploring concentrations in the μM to mM range. However, extracting quantitative information from Z-spectra can be challenging due to the non-CEST contributions present and the limited knowledge about the exchanging pools. The PEAKIT tool is proposed as an alternative approach to quantifying CEST peaks, which requires no prior assumptions about the frequency offset or the underlying shape of the baseline. Specifically, the tool takes as input an experimental Z-spectrum and proceeds to identify peak candidates. After a baseline estimation based on Gaussian Process regression, PEAKIT outputs the chemical shift offsets, the areas, the heights and the statistical significance of the detected peaks. The performance and limitations of the PEAKIT tool are discussed for in vitro and in vivo applications.

An MR fingerprinting approach for quantitative inhomogeneous magnetization transfer imaging

PURPOSE

Magnetization transfer (MT) and inhomogeneous MT (ihMT) contrasts are used in MRI to provide information about macromolecular tissue content. In particular, MT is sensitive to macromolecules, and ihMT appears to be specific to myelinated tissue. This study proposes a technique to characterize MT and ihMT properties from a single acquisition, producing both semiquantitative contrast ratios and quantitative parameter maps.

THEORY AND METHODS

Building on previous work that uses multiband RF pulses to efficiently generate ihMT contrast, we propose a cyclic steady-state approach that cycles between multiband and single-band pulses to boost the achieved contrast. Resultant time-variable signals are reminiscent of an MR fingerprinting acquisition, except that the signal fluctuations are entirely mediated by MT effects. A dictionary-based low-rank inversion method is used to reconstruct the resulting images and to produce both semiquantitative MT ratio and ihMT ratio maps, as well as quantitative parameter estimates corresponding to an ihMT tissue model.

RESULTS

Phantom and in vivo brain data acquired at 1.5 Tesla demonstrate the expected contrast trends, with ihMT ratio maps showing contrast more specific to white matter, as has been reported by others. Quantitative estimation of semisolid fraction and dipolar T₁ was also possible and yielded measurements consistent with literature values in the brain.

CONCLUSION

By cycling between multiband and single-band pulses, an entirely MT-mediated fingerprinting method was demonstrated. This proof-of-concept approach can be used to generate semiquantitative maps and quantitatively estimate some macromolecular-specific tissue parameters.

Improving Sensitivity of Arterial Spin Labeling Perfusion MRI in Alzheimer's Disease Using Transfer Learning of Deep Learning-Based ASL Denoising

BACKGROUND

Arterial spin labeling (ASL) perfusion magnetic resonance imaging (MRI) denoising through deep learning (DL) often faces insufficient training data from patients. One solution is to train DL models using healthy subjects' data which are more widely available and transfer them to patients' data.

PURPOSE

To evaluate the transferability of a DL-based ASL MRI denoising method (DLASL).

STUDY TYPE

Retrospective.

SUBJECTS

Four hundred and twenty-eight subjects (189 females) from three cohorts.

FIELD STRENGTH/SEQUENCE

3 T two-dimensional (2D) echo-planar imaging (EPI)-based pseudo-continuous ASL (PCASL) and 2D EPI-based pulsed ASL (PASL) sequences.

ASSESSMENT

DLASL was trained using young healthy adults' PCASL data (Dataset 1: 250/30 subjects as training/validation set) and was directly transferred (DTF) to PCASL data from Dataset 2 (45 subjects test set) of normal controls (NC) and Alzheimer's disease (AD) groups. DLASL was fine-tuned (DLASLFT) and tested on PASL data from Dataset 3 (103 subjects test set) of NC and AD. An existing non-DL method (NonDL) was used for comparison. Cerebral blood flow (CBF) images from ASL MRI were compared between NC and AD to assess characteristic hypoperfusion (lower CBF) patterns in AD. CBF image quality and CBF map sensitivity for detecting hypoperfusion using peak t-value and suprathreshold cluster size are outcome measures.

STATISTICAL TESTS

Paired t-test, two-sample t-test, one-way analysis of variance, and Tukey honestly significant difference, and linear mixed-effects models were used. P < 0.05 was considered statistically significant.

RESULTS

Mean contrast-to-noise ratio (CNR) of Dataset 2 showed that DTF outperformed NonDL (AD: 3.38 vs. 2.64, NC: 3.80 vs. 3.36). On Dataset 3, DLASLFT outperformed NonDL measured by mean CNR (AD: 2.45 vs. 1.87, NC: 2.54 vs. 2.17) and mean radiologic score (2.86 vs. 2.44). Image quality improvement was significant on both test sets. DTF and DLASLFT improved sensitivity for detecting AD-related hypoperfusion patterns compared with NonDL.

DATA CONCLUSION

We demonstrated the DLASL's transferability across different ASL sequences and different populations.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 2.

Deep neural network based CEST and AREX processing: Application in imaging a model of Alzheimer's disease at 3 T

PURPOSE

To optimize and apply deep neural network based CEST (deepCEST) and apparent exchange dependent-relaxation (deepAREX) for imaging the mouse brain with Alzheimer's disease (AD) at 3T MRI.

METHODS

CEST and T₁ data of central and anterior brain slices of 10 AD mice and 10 age-matched wild type (WT) mice were acquired at a 3T animal MRI scanner. The networks of deepCEST/deepAREX were optimized and trained on the WT data. The CEST/AREX contrasts of AD and WT mice predicted by the networks were analyzed and further validated by immunohistochemistry.

RESULTS

After optimization and training on CEST data of WT mice, deepCEST/deepAREX could rapidly (~1 s) generate precise CEST and AREX results for unseen CEST data of AD mice, indicating the accuracy and generalization of the networks. Significant lower amide weighted (3.5 ppm) signal related to amyloid β-peptide (Aβ) plaque depositions, which was validated by immunohistochemistry results, was detected in both central and anterior brain slices of AD mice compared to WT mice. Decreased magnetization transfer (MT) signal was also found in AD mice especially in the anterior slice.

CONCLUSION

DeepCEST/deepAREX could rapidly generate accurate CEST/AREX contrasts in animal study. The well-optimized deepCEST/deepAREX have potential for AD differentiation at 3T MRI.

Pulseq-CEST: Towards multi-site multi-vendor compatibility and reproducibility of CEST experiments using an open-source sequence standard

PURPOSE

As the field of CEST grows, various novel preparation periods using different parameters are being introduced. At the same time, large, multisite clinical studies require clearly defined protocols, especially across different vendors. Here, we propose a CEST definition standard using the open Pulseq format for a shareable, simple, and exact definition of CEST protocols.

METHODS

We present the benefits of such a standard in three ways: (1) an open database on GitHub, where fully defined, human-readable CEST protocols can be shared; (2) an open-source Bloch-McConnell simulation to test and optimize CEST preparation periods in silico; and (3) a hybrid MR sequence that plays out the CEST preparation period and can be combined with any existing readout module.

RESULTS

The exact definition of the CEST preparation period, in combination with the flexible simulation, leads to a good match between simulations and measurements. The standard allowed finding consensus on three amide proton transfer-weighted protocols that could be compared in healthy subjects and a tumor patient. In addition, we could show coherent multisite results for a sophisticated CEST method, highlighting the benefits regarding protocol sharing and reproducibility.

CONCLUSION

With Pulseq-CEST, we provide a straightforward approach to standardize, share, simulate, and measure different CEST preparation schemes, which are inherently completely defined.

Training data distribution significantly impacts the estimation of tissue microstructure with machine learning

PURPOSE

Supervised machine learning (ML) provides a compelling alternative to traditional model fitting for parameter mapping in quantitative MRI. The aim of this work is to demonstrate and quantify the effect of different training data distributions on the accuracy and precision of parameter estimates when supervised ML is used for fitting.

METHODS

We fit a two- and three-compartment biophysical model to diffusion measurements from in-vivo human brain, as well as simulated diffusion data, using both traditional model fitting and supervised ML. For supervised ML, we train several artificial neural networks, as well as random forest regressors, on different distributions of ground truth parameters. We compare the accuracy and precision of parameter estimates obtained from the different estimation approaches using synthetic test data.

RESULTS

When the distribution of parameter combinations in the training set matches those observed in healthy human data sets, we observe high precision, but inaccurate estimates for atypical parameter combinations. In contrast, when training data is sampled uniformly from the entire plausible parameter space, estimates tend to be more accurate for atypical parameter combinations but may have lower precision for typical parameter combinations.

CONCLUSION

This work highlights that estimation of model parameters using supervised ML depends strongly on the training-set distribution. We show that high precision obtained using ML may mask strong bias, and visual assessment of the parameter maps is not sufficient for evaluating the quality of the estimates.

Hyperpolarized MRI, functional MRI, MR spectroscopy and CEST to provide metabolic information in vivo

Access to metabolic information in vivo using magnetic resonance (MR) technologies has generally been the niche of MR spectroscopy (MRS) and spectroscopic imaging (MRSI). Metabolic fluxes can be studied using the infusion of substrates labeled with magnetic isotopes, with the use of hyperpolarization especially powerful. Unfortunately, these promising methods are not yet accepted clinically, where fast, simple, and reliable measurement and diagnosis are key. Recent advances in functional MRI and chemical exchange saturation transfer (CEST) MRI allow the use of water imaging to study oxygen metabolism and tissue metabolite levels. These, together with the use of novel data analysis approaches such as machine learning for all of these metabolic MR approaches, are increasing the likelihood of their clinical translation.

Brain tissues have single-voxel signatures in multi-spectral MRI

Since the seminal works by Brodmann and contemporaries, it is well-known that different brain regions exhibit unique cytoarchitectonic and myeloarchitectonic features. Transferring the approach of classifying brain tissues - and other tissues - based on their intrinsic features to the realm of magnetic resonance (MR) is a longstanding endeavor. In the 1990s, atlas-based segmentation replaced earlier multi-spectral classification approaches because of the large overlap between the class distributions. Here, we explored the feasibility of performing global brain classification based on intrinsic MR features, and used several technological advances: ultra-high field MRI, q-space trajectory diffusion imaging revealing voxel-intrinsic diffusion properties, chemical exchange saturation transfer and semi-solid magnetization transfer imaging as a marker of myelination and neurochemistry, and current neural network architectures to analyze the data. In particular, we used the raw image data as well to increase the number of input features. We found that a global brain classification of roughly 97 brain regions was feasible with gross classification accuracy of 60%; and that mapping from voxel-intrinsic MR data to the brain region to which the data belongs is possible. This indicates the presence of unique MR signals of different brain regions, similar to their cytoarchitectonic and myeloarchitectonic fingerprints.

Unsupervised learning for magnetization transfer contrast MR fingerprinting: Application to CEST and nuclear Overhauser enhancement imaging

PURPOSE

To develop a fast, quantitative 3D magnetization transfer contrast (MTC) framework based on an unsupervised learning scheme, which will provide baseline reference signals for CEST and nuclear Overhauser enhancement imaging.

METHODS

Pseudo-randomized RF saturation parameters and relaxation delay times were applied in an MR fingerprinting framework to generate transient-state signal evolutions for different MTC parameters. Prospectively compressed sensing-accelerated (four-fold) MR fingerprinting images were acquired from 6 healthy volunteers at 3 T. A convolutional neural network framework in an unsupervised fashion was designed to solve an inverse problem of a two-pool MTC Bloch equation, and was compared with a conventional Bloch equation-based fitting approach. The MTC images synthesized by the convolutional neural network architecture were used for amide proton transfer and nuclear Overhauser enhancement imaging as a reference baseline image.

RESULTS

The fully unsupervised learning scheme incorporated with the two-pool exchange model learned a set of unique features that can describe the MTC-MR fingerprinting input, and allowed only small amounts of unlabeled data for training. The MTC parameter values estimated by the unsupervised learning method were in excellent agreement with values estimated by the conventional Bloch fitting approach, but dramatically reduced computation time by ~1000-fold.

CONCLUSION

Given the considerable time efficiency compared to conventional Bloch fitting, unsupervised learning-based MTC-MR fingerprinting could be a powerful tool for quantitative MTC and CEST/nuclear Overhauser enhancement imaging.