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

Saturation transfer MR fingerprinting for magnetization transfer contrast and chemical exchange saturation transfer quantification

PURPOSE

The aim of this study was to develop a saturation transfer MR fingerprinting (ST-MRF) technique using a biophysics model-driven deep learning approach.

METHODS

A deep learning-based quantitative saturation transfer framework was proposed to estimate water, magnetization transfer contrast, and amide proton transfer (APT) parameters plus B0 field inhomogeneity. This framework incorporated a Bloch-McConnell simulator during neural network training and enforced consistency between synthesized MRF signals and experimentally acquired ST-MRF signals. Ground-truth numerical phantoms were used to assess the accuracy of estimated tissue parameters, and in vivo tissue parameters were validated using synthetic MRI analysis.

RESULTS

The proposed ST-MRF reconstruction network achieved a normalized root mean square error (nRMSE) of 9.3% when tested against numerical phantoms with a signal-to-noise ratio of 46 dB, which outperformed conventional Bloch-McConnell fitting (nRMSE of 15.3%) and dictionary-matching approaches (nRMSE of 19.5%). Synthetic MRI analysis indicated excellent similarity (RMSE = 3.2%) between acquired and synthesized ST-MRF images, demonstrating high in vivo reconstruction accuracy. In healthy human brains, the APT pool size ratios for gray and white matter were 0.16 ± 0.02% and 0.13 ± 0.02%, respectively, and the exchange rates for gray and white matter were 101 ± 25 Hz and 131 ± 27 Hz, respectively. The reconstruction network processed the eight tissue parameter maps in approximately 27 s for ST-MRF data sized at 256 × 256 × 9 × 103.

CONCLUSION

This study highlights the feasibility of the deep learning-based ST-MRF imaging for rapid and accurate quantification of free bulk water, magnetization transfer contrast, APT parameters, and B0 field inhomogeneity.

Quantitative molecular imaging using deep magnetic resonance fingerprinting

Deep learning-based saturation transfer magnetic resonance fingerprinting (MRF) is an emerging approach for noninvasive in vivo imaging of proteins, metabolites and pH. It involves a series of steps, including sample/participant preparation, image acquisition schedule design, biophysical model formulation and artificial intelligence and computational model training, followed by image acquisition, deep reconstruction and analysis. Saturation transfer-based molecular MRI has been slow to reach clinical maturity and adoption for clinical practice due to its technical complexity, semi-quantitative contrast-weighted nature and long scan times needed for the extraction of quantitative molecular biomarkers. Deep MRF provides solutions to these challenges by providing a quantitative and rapid framework for extracting biologically and clinically meaningful molecular information. Here we define a complete protocol for quantitative molecular MRI using deep MRF. We describe in vitro sample preparation and animal and human scan considerations, and provide intuition behind the acquisition protocol design and optimization of chemical exchange saturation transfer (CEST) and semi-solid magnetization transfer (MT) quantitative imaging. We then extensively describe the building blocks for several artificial intelligence models and demonstrate their performance for different applications, including cancer monitoring, brain myelin imaging and pH quantification. Finally, we provide guidelines to further modify and expand the pipeline for imaging a variety of other pathologies (such as neurodegeneration, stroke and cardiac disease), accompanied by the related open-source code and sample data. The procedure takes between 48 min (for two proton pools or in vitro imaging) and 57 h (for complex multi-proton pool in vivo imaging) to complete and is suitable for graduate student-level users.

Ungated, plug-and-play preclinical cardiac CEST-MRI using radial FLASH with segmented saturation

PURPOSE

Electrocardiography (ECG) and respiratory-gated preclinical cardiac CEST-MRI acquisitions are difficult because of variable saturation recovery with T1, RF interference in the ECG signal, and offset-to-offset variation in Z-magnetization and cardiac phase introduced by changes in cardiac frequency and trigger delays.

METHODS

The proposed method consists of segmented saturation modules with radial FLASH readouts and golden angle progression. The segmented saturation blocks drive the system to steady-state, and because center k-space is sampled repeatedly, steady-state saturation dominates contrast during gridding and reconstruction. Ten complete Z-spectra were acquired in healthy mice using both ECG and respiratory-gated and ungated methods. Z-spectra were also acquired at multiple saturation B1 values to optimize for amide and Cr contrasts.

RESULTS

There was no significant difference between CEST contrasts (amide, Cr, magnetization transfer) calculated from images acquired using ECG and respiratory-gated and ungated methods (p = 0.27, 0.11, 0.47). A saturation power of 1.8μT provides optimal contrast amplitudes for both amide and total Cr contrast without significantly complicating CEST contrast quantification because of water direct saturation, magnetization transfer, and RF spillover between amide and Cr pools. Further, variability in CEST contrast measurements was significantly reduced using the ungated radial FLASH acquisition (p = 0.002, 0.006 for amide and Cr, respectively).

CONCLUSION

This method enables CEST mapping in the murine myocardium without the need for cardiac or respiratory gating. Quantitative CEST contrasts are consistent with those obtained using gated sequences, and per-contrast variance is significantly reduced. This approach makes preclinical cardiac CEST-MRI easily accessible, even for investigators without prior experience in cardiac imaging.

Simultaneous quantification of PCr, Cr, and pH in muscle CEST-MRI

PURPOSE

CEST-MRI allows sensitive in vivo detection of PCr and Cr in muscle. However, the accurate quantification is difficult due to overlapped "peaks" from multiple solutes and mixed contributions from fractional concentration (f b $$ {f}_{\mathrm{b}} $$ ) and exchange rate (k b $$ {k}_{\mathrm{b}} $$ ). This study aims to achieve simultaneous and accurate mapping of PCr, Cr, and pH in muscle.

METHODS

A two-step quantification method was proposed, by considering the co-existence of PCr and Cr in muscle and their dynamic transition. Firstly, exchangeable protons resonating at +2.6 ppm (PCr 2.6 $$ {\mathrm{PCr}}_{2.6} $$ ) were quantified using our previous gQUCESOP. In the second gQUCESOP for resolving parameters at +1.9 ppm, we included both Cr's and another exchangeable guanidino proton of PCr resonating at +1.9 ppm (PCr 1.9 $$ {\mathrm{PCr}}_{1.9} $$ ), withf b $$ {f}_{\mathrm{b}} $$ andk b $$ {k}_{\mathrm{b}} $$ forPCr 1.9 $$ {\mathrm{PCr}}_{1.9} $$ estimated fromPCr 2.6 $$ {\mathrm{PCr}}_{2.6} $$ estimation in the first step. The method was validated by simulation and phantom study. In vivo rat experiments were performed at 9.4T, with pH measured also by 31P-MRS.

RESULTS

Simulation suggested an over-estimatedf b $$ {f}_{\mathrm{b}} $$ and an under-estimatedk b $$ {k}_{\mathrm{b}} $$ of Cr if including a non-neglectable content of PCr. For a phantom with mixed PCr and Cr, the proposed method allowed accurate calculation of both concentrations and pH. For in vivo rat scans performed before and right after euthanasia, our methods achieved coincidedf b $$ {f}_{\mathrm{b}} $$ andk b $$ {k}_{\mathrm{b}} $$ with literatures. Furthermore, the pH values from 31P-MRS,k b $$ {k}_{\mathrm{b}} $$ ofPCr 2.6 $$ {\mathrm{PCr}}_{2.6} $$ , andk b $$ {k}_{\mathrm{b}} $$ of Cr could verify each other.

CONCLUSION

The proposed method is promising for quantifying thef b $$ {f}_{\mathrm{b}} $$ andk b $$ {k}_{\mathrm{b}} $$ for both PCr and Cr in skeletal muscular tissue.

Toward quantitative CEST imaging of glutamate in the mouse brain using a multi-pool exchange model calibrated by 1H-MRS

PURPOSE

To develop a CEST quantification model to map glutamate concentration in the mouse brain at 11.7 T, overcoming the limitations of conventional glutamate-weighted CEST (gluCEST) contrast (magnetization transfer ratio with asymmetric analysis).

METHODS

1H-MRS was used as a gold standard for glutamate quantification to calibrate a CEST-based quantitative pipeline. Joint localized measurements of Z-spectra at B1 = 5 μT and quantitative 1H-MRS were carried out in two voxels of interest in the mouse brain. A six-pool Bloch-McConnell model was found appropriate to fit experimental data. Glutamate exchange rate was estimated in both regions with this dedicated multi-pool fitting model and using glutamate concentration determined by 1H-MRS.

RESULTS

Glutamate exchange rate was estimated to be ˜1300 Hz in the mouse brain. Using this calibrated value, maps of glutamate concentration in the mouse brain were obtained by pixel-by-pixel fitting of Z-spectra at B1 = 5 μT. A complementary study of simulations, however, showed that the quantitative model has high sensitivity to noise, and therefore, requires high-SNR acquisitions. Interestingly, fitted [Glu] seemed to be overestimated compared to 1H-MRS measurements, although it was estimated with simulations that the model has no intrinsic fitting bias with our experimental level of noise. The hypothesis of an unknown proton-exchanging pool contributing to gluCEST signal is discussed.

CONCLUSION

High-resolution mapping of glutamate in the brain was made possible using the proposed calibrated quantification model of gluCEST data. Further studying of the in vivo molecular contributions to gluCEST signal could improve modeling.

Synthesis of MR fingerprinting information from magnitude-only MR imaging data using a parallelized, multi network U-Net convolutional neural network

Background

MR fingerprinting (MRF) is a novel method for quantitative assessment of in vivo MR relaxometry that has shown high precision and accuracy. However, the method requires data acquisition using customized, complex acquisition strategies and dedicated post processing methods thereby limiting its widespread application.

Objective

To develop a deep learning (DL) network for synthesizing MRF signals from conventional magnitude-only MR imaging data and to compare the results to the actual MRF signal acquired.

Methods

A U-Net DL network was developed to synthesize MRF signals from magnitude-only 3D T 1-weighted brain MRI data acquired from 37 volunteers aged between 21 and 62 years of age. Network performance was evaluated by comparison of the relaxometry data (T 1, T 2) generated from dictionary matching of the deep learning synthesized and actual MRF data from 47 segmented anatomic regions. Clustered bootstrapping involving 10,000 bootstraps followed by calculation of the concordance correlation coefficient were performed for both T 1 and T 2 MRF data pairs. 95% confidence limits and the mean difference between true and DL relaxometry values were also calculated.

Results

The concordance correlation coefficient (and 95% confidence limits) for T 1 and T 2 MRF data pairs over the 47 anatomic segments were 0.8793 (0.8136-0.9383) and 0.9078 (0.8981-0.9145) respectively. The mean difference (and 95% confidence limits) were 48.23 (23.0-77.3) s and 2.02 (-1.4 to 4.8) s.

Conclusion

It is possible to synthesize MRF signals from MRI data using a DL network, thereby creating the potential for performing quantitative relaxometry assessment without the need for a dedicated MRF pulse sequence.

Synthesis of higher-B0 CEST Z-spectra from lower-B0 data via deep learning and singular value decomposition

Chemical exchange saturation transfer (CEST) MRI at 3 T suffers from low specificity due to overlapping CEST effects from multiple metabolites, while higher field strengths (B0) allow for better separation of Z-spectral "peaks," aiding signal interpretation and quantification. However, data acquisition at higher B0 is restricted by equipment access, field inhomogeneity and safety issues. Herein, we aim to synthesize higher-B0 Z-spectra from readily available data acquired with 3 T clinical scanners using a deep learning framework. Trained with simulation data using models based on Bloch-McConnell equations, this framework comprised two deep neural networks (DNNs) and a singular value decomposition (SVD) module. The first DNN identified B0 shifts in Z-spectra and aligned them to correct frequencies. After B0 correction, the lower-B0 Z-spectra were streamlined to the second DNN, casting into the key feature representations of higher-B0 Z-spectra, obtained through SVD truncation. Finally, the complete higher-B0 Z-spectra were recovered from inverse SVD, given the low-rank property of Z-spectra. This study constructed and validated two models, a phosphocreatine (PCr) model and a pseudo-in-vivo one. Each experimental dataset, including PCr phantoms, egg white phantoms, and in vivo rat brains, was sequentially acquired on a 3 T human and a 9.4 T animal scanner. Results demonstrated that the synthetic 9.4 T Z-spectra were almost identical to the experimental ground truth, showing low RMSE (0.11% ± 0.0013% for seven PCr tubes, 1.8% ± 0.2% for three egg white tubes, and 0.79% ± 0.54% for three rat slices) and high R2 (>0.99). The synthesized amide and NOE contrast maps, calculated using the Lorentzian difference, were also well matched with the experiments. Additionally, the synthesis model exhibited robustness to B0 inhomogeneities, noise, and other acquisition imperfections. In conclusion, the proposed framework enables synthesis of higher-B0 Z-spectra from lower-B0 ones, which may facilitate CEST MRI quantification and applications.

In vivo mapping of the chemical exchange relayed nuclear Overhauser effect using deep magnetic resonance fingerprinting

Noninvasive magnetic resonance imaging (MRI) of the relayed nuclear Overhauser effect (rNOE) constitutes a promising approach for gaining biological insights into various pathologies, including brain cancer, kidney injury, ischemic stroke, and liver disease. However, rNOE imaging is time-consuming and prone to biases stemming from the water T1 and the semisolid magnetization transfer (MT) contrasts. Here, we developed a rapid rNOE quantification approach, combining magnetic resonance fingerprinting (MRF) acquisition with deep-learning-based reconstruction. The method was systematically validated using tissue-mimicking phantoms, wild-type mice (n = 7), and healthy human volunteers (n = 5). In vitro rNOE parameter maps generated by MRF were highly correlated with ground truth (r > 0.98, p < 0.001). Simultaneous mapping of the rNOE and the semisolid MT exchange parameters in mice and humans were in agreement with previously reported literature values. Whole-brain 3D parameter mapping in humans took less than 5 min (282 s for acquisition and less than 2 s for reconstruction). With its demonstrated ability to rapidly extract quantitative molecular maps, deep rNOE-MRF can potentially serve as a valuable tool for the characterization and detection of molecular abnormalities in vivo.

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.

Artificial intelligence for neuro MRI acquisition: a review

OBJECT

To review recent advances of artificial intelligence (AI) in enhancing the efficiency and throughput of the MRI acquisition workflow in neuroimaging, including planning, sequence design, and correction of acquisition artifacts.

MATERIALS AND METHODS

A comprehensive analysis was conducted on recent AI-based methods in neuro MRI acquisition. The study focused on key technological advances, their impact on clinical practice, and potential risks associated with these methods.

RESULTS

The findings indicate that AI-based algorithms have a substantial positive impact on the MRI acquisition process, improving both efficiency and throughput. Specific algorithms were identified as particularly effective in optimizing acquisition steps, with reported improvements in workflow efficiency.

DISCUSSION

The review highlights the transformative potential of AI in neuro MRI acquisition, emphasizing the technological advances and clinical benefits. However, it also discusses potential risks and challenges, suggesting areas for future research to mitigate these concerns and further enhance AI integration in MRI acquisition.

Deep learning for accelerated and robust MRI reconstruction

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

CMRsim-A python package for cardiovascular MR simulations incorporating complex motion and flow

PURPOSE

To present an open-source MR simulation framework that facilitates the incorporation of complex motion and flow for studying cardiovascular MR (CMR) acquisition and reconstruction.

METHODS

CMRsim is a Python package that allows simulation of CMR images using dynamic digital phantoms with complex motion as input. Two simulation paradigms are available, namely, numerical and analytical solutions to the Bloch equations, using a common motion representation. Competitive simulation speeds are achieved using TensorFlow for GPU acceleration. To demonstrate the capability of the package, one introductory and two advanced CMR simulation experiments are presented. The latter showcase phase-contrast imaging of turbulent flow downstream of a stenotic section and cardiac diffusion tensor imaging on a contracting left ventricle. Additionally, extensive documentation and example resources are provided.

RESULTS

The Bloch simulation with turbulent flow using approximately 1.5 million particles and a sequence duration of 710 ms for each of the seven different velocity encodings took a total of 29 min on a NVIDIA Titan RTX GPU. The results show characteristic phase contrast and magnitude modulation present in real data. The analytical simulation of cardiac diffusion tensor imaging with bulk-motion phase sensitivity took approximately 10 s per diffusion-weighted image, including preparation and loading steps. The results exhibit the expected alteration of diffusion metrics due to strain.

CONCLUSION

CMRsim is the first simulation framework that allows one to feasibly incorporate complex motion, including turbulent flow, to systematically study advanced CMR acquisition and reconstruction approaches. The open-source package features modularity and transparency, facilitating maintainability and extensibility in support of reproducible research.

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.

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

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

An end-to-end LSTM-Attention based framework for quasi-steady-state CEST prediction

Chemical exchange saturation transfer (CEST)-magnetic resonance imaging (MRI) often takes prolonged saturation duration (Ts) and relaxation delay (Td) to reach the steady state, and yet the insufficiently long Ts and Td in actual experiments may underestimate the CEST measurement. In this study, we aimed to develop a deep learning-based model for quasi-steady-state (QUASS) prediction from non-steady-state CEST acquired in experiments, therefore overcoming the limitation of the CEST effect which needs prolonged saturation time to reach a steady state. To support network training, a multi-pool Bloch-McConnell equation was designed to derive wide-ranging simulated Z-spectra, so as to solve the problem of time and labor consumption in manual annotation work. Following this, we formulated a hybrid architecture of long short-term memory (LSTM)-Attention to improve the predictive ability. The multilayer perceptron, recurrent neural network, LSTM, gated recurrent unit, BiLSTM, and LSTM-Attention were included in comparative experiments of QUASS CEST prediction, and the best performance was obtained by the proposed LSTM-Attention model. In terms of the linear regression analysis, structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), and mean-square error (MSE), the results of LSTM-Attention demonstrate that the coefficient of determination in the linear regression analysis was at least R2 = 0.9748 for six different representative frequency offsets, the mean values of prediction accuracies in terms of SSIM, PSNR and MSE were 0.9991, 49.6714, and 1.68 × 10-4 for all frequency offsets. It was concluded that the LSTM-Attention model enabled high-quality QUASS CEST prediction.

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.

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

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

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.

CEST-MRI for body oncologic imaging: are we there yet?

Chemical exchange saturation transfer (CEST) MRI has gained recognition as a valuable addition to the molecular imaging and quantitative biomarker arsenal, especially for characterization of brain tumors. There is also increasing interest in the use of CEST-MRI for applications beyond the brain. However, its translation to body oncology applications lags behind those in neuro-oncology. The slower migration of CEST-MRI to non-neurologic applications reflects the technical challenges inherent to imaging of the torso. In this review, we discuss the application of CEST-MRI to oncologic conditions of the breast and torso (i.e., body imaging), emphasizing the challenges and potential solutions to address them. While data are still limited, reported studies suggest that CEST signal is associated with important histology markers such as tumor grade, receptor status, and proliferation index, some of which are often associated with prognosis and response to therapy. However, further technical development is still needed to make CEST a reliable clinical application for body imaging and establish its role as a predictive and prognostic biomarker.

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.

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

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

calf - Software for CEST Analysis with Lorentzian Fitting

Analysis of chemical exchange saturation transfer (CEST) MRI data requires sophisticated methods to obtain reliable results about metabolites in the tissue under study. CEST generates z-spectra with multiple components, each originating from individual molecular groups. The individual lines with Lorentzian line shape are mostly overlapping and disturbed by various effects. We present an elaborate method based on an adaptive nonlinear least squares algorithm that provides robust quantification of z-spectra and incorporates prior knowledge in the fitting process. To disseminate CEST to the research community, we developed software as part of this study that runs on the Microsoft Windows operating system and will be made freely available to the community. Special attention has been paid to establish a low entrance threshold and high usability, so that even less experienced users can successfully analyze CEST data.

Molecular MRI-Based Monitoring of Cancer Immunotherapy Treatment Response

Immunotherapy constitutes a paradigm shift in cancer treatment. Its FDA approval for several indications has yielded improved prognosis for cases where traditional therapy has shown limited efficiency. However, many patients still fail to benefit from this treatment modality, and the exact mechanisms responsible for tumor response are unknown. Noninvasive treatment monitoring is crucial for longitudinal tumor characterization and the early detection of non-responders. While various medical imaging techniques can provide a morphological picture of the lesion and its surrounding tissue, a molecular-oriented imaging approach holds the key to unraveling biological effects that occur much earlier in the immunotherapy timeline. Magnetic resonance imaging (MRI) is a highly versatile imaging modality, where the image contrast can be tailored to emphasize a particular biophysical property of interest using advanced engineering of the imaging pipeline. In this review, recent advances in molecular-MRI based cancer immunotherapy monitoring are described. Next, the presentation of the underlying physics, computational, and biological features are complemented by a critical analysis of the results obtained in preclinical and clinical studies. Finally, emerging artificial intelligence (AI)-based strategies to further distill, quantify, and interpret the image-based molecular MRI information are discussed in terms of perspectives for the future.

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.

Noninvasively differentiating acute and chronic nephropathies via multiparametric urea-CEST, nuclear Overhauser enhancement-CEST, and quantitative magnetization transfer MRI

PURPOSE

Standardized blood tests often lack adequate sensitivity and specificity to capture the gradual progression of renal injuries. We suggest a multiparametric molecular MRI approach as a noninvasive tool for monitoring renal function loss and distinguishing different types of renal injuries.

METHODS

CEST and quantitative magnetization transfer (qMT) imaging were performed on cisplatin (n = 16) and aristolochic acid (AA)-induced nephropathy (n = 22) mouse models at 7T with an infusion of either saline or urea. Seven-pool Lorentzian fitting was applied for the analysis of CEST Z-spectra, and the T1 -corrected CEST contrast apparent exchange-dependent relaxation (AREX) from urea (+1 ppm) and two nuclear Overhauser enhancement (NOE) pools (-1.6 and -3.5 ppm) were measured. Similarly, qMT spectra were fitted into two-pool Ramani equation and the relative semi-solid macromolecular pool-size ratio was measured. Histology of mouse kidneys was performed to validate the MR findings.

RESULTS

AA model showed disrupted spatial gradients of urea in the kidney and significantly decreased NOE CEST and qMT contrast. The cisplatin model showed slightly decreased qMT contrast only. The orrelation of MR parameters to histological features showed that NOE CEST and qMT imaging are sensitive to both acute and chronic injuries, whereas urea CEST shows a significant correlation only to acute injuries.

CONCLUSION

These results indicate that our multiparametric approach allows comprehensive and totally noninvasive monitoring of renal function and histological changes for distinguishing different nephropathies.

Stabilizing deep tomographic reconstruction: Part A. Hybrid framework and experimental results

A recent PNAS paper reveals that several popular deep reconstruction networks are unstable. Specifically, three kinds of instabilities were reported: (1) strong image artefacts from tiny perturbations, (2) small features missed in a deeply reconstructed image, and (3) decreased imaging performance with increased input data. Here, we propose an analytic compressed iterative deep (ACID) framework to address this challenge. ACID synergizes a deep network trained on big data, kernel awareness from compressed sensing (CS)-inspired processing, and iterative refinement to minimize the data residual relative to real measurement. Our study demonstrates that the ACID reconstruction is accurate, is stable, and sheds light on the converging mechanism of the ACID iteration under a bounded relative error norm assumption. ACID not only stabilizes an unstable deep reconstruction network but also is resilient against adversarial attacks to the whole ACID workflow, being superior to classic sparsity-regularized reconstruction and eliminating the three kinds of instabilities.