Deep learning can accelerate and quantify simulated localized correlated spectroscopy

Magnetic Resonance Spectroscopy Quantification Aided by Deep Estimations of Imperfection Factors and Macromolecular Signal

OBJECTIVE

Magnetic Resonance Spectroscopy (MRS) is an important technique for biomedical detection. However, it is challenging to accurately quantify metabolites with proton MRS due to serious overlaps of metabolite signals, imperfections because of non-ideal acquisition conditions, and interference with strong background signals mainly from macromolecules. The most popular method, LCModel, adopts complicated non-linear least square to quantify metabolites and addresses these problems by designing empirical priors such as basis-sets, imperfection factors. However, when the signal-to-noise ratio of MRS signal is low, the solution may have large deviation.

METHODS

Linear Least Squares (LLS) is integrated with deep learning to reduce the complexity of solving this overall quantification. First, a neural network is designed to explicitly predict the imperfection factors and the overall signal from macromolecules. Then, metabolite quantification is solved analytically with the introduced LLS. In our Quantification Network (QNet), LLS takes part in the backpropagation of network training, which allows the feedback of the quantification error into metabolite spectrum estimation. This scheme greatly improves the generalization to metabolite concentrations unseen in training compared to the end-to-end deep learning method.

RESULTS

Experiments show that compared with LCModel, the proposed QNet, has smaller quantification errors for simulated data, and presents more stable quantification for 20 healthy in vivo data at a wide range of signal-to-noise ratio. QNet also outperforms other end-to-end deep learning methods.

CONCLUSION

This study provides an intelligent, reliable and robust MRS quantification.

SIGNIFICANCE

QNet is the first LLS quantification aided by deep learning.

Stationary wavelet denoising of solid-state NMR spectra using multiple similar measurements

Accumulating several scans of free induction decays is always needed to improve the signal-to-noise ratio of NMR spectra, especially for the low gyromagnetic ratio solid-state NMR. In this study, we present a new denoising approach based on the correlations between multiple similar NMR spectra. Contrary to the simple averaging of multiple scans or denoising the final averaged spectrum, we propose a Wavelet-based Denoising technique for Multiple Similar scans(WDMS). Firstly, the stationary wavelet transform is applied to decompose every spectrum into approximation coefficients and detail coefficients. Then, the detail coefficients are multiplied by weights calculated based on Pearson's correlation coefficient and structural similarity index between approximation coefficients of different spectra. Finally, the average of these detailed components is used to denoise the spectra. The proposed method is carried on the assumption that noise between multiple spectra is uncorrelated while peak signal information is similar between different spectra, thus preserving the possibility of applying further processing to the data. As a demonstration, the standard wavelet denoise is applied to the WDMS-processed spectra, achieving a further increase in the S/N ratio. We confirm the reliability of the denoising approach based on multiple scans on 1D/2D solid-state MAS/static NMR spectra. In addition, we also show that this method can be used to deal with a single Car-Purcell-Meiboom-Gill (CPMG) echo train.

Quantification of spatially localized MRS by a novel deep learning approach without spectral fitting

PURPOSE

To propose a novel end-to-end deep learning model to quantify absolute metabolite concentrations from in vivo J-point resolved spectroscopy (JPRESS) without using spectral fitting.

METHODS

A novel encoder-decoder-style neural network was created, which was trained to predict metabolite concentrations and individual component signals concurrently from 3T JPRESS data in the time domain. The training data set contained 100 000 samples created by spin-density simulations using experimentally used RF pulses. Concentrations, phase, frequencies, linewidths, and T2 relaxation times in the training data set were varied over a large range with uniform distributions. Random synthesized noise and extraneous signals were added to the data set. Two thousand validation samples were created similarly to the training data set but with mean concentrations close to in vivo values. An in vivo test was conducted with 20 samples acquired from the human brain.

RESULTS

Both validation and in vivo test results showed that the proposed model successfully predicted metabolite concentrations as well as individual metabolite signals without involving spectral fitting, while extraneous peaks or unregistered signals were filtered out. Compared with the short-TE spectral fitting by LCModel, the proposed method had the advantage that the undesired correlations between the estimated concentrations and noise levels and between metabolites were eliminated or substantially reduced.

CONCLUSION

The proposed method provides a working deep learning model that directly maps in vivo JPRESS data to metabolite concentrations. Because spectral fitting is not used, the trained model does not depend on the assumptions associated with parameter tuning when applied to in vivo data.

Application of a 1H Brain MRS Benchmark Dataset to Deep Learning for Out-of-Voxel Artifacts

Neural networks are potentially valuable for many of the challenges associated with MRS data. The purpose of this manuscript is to describe the AGNOSTIC dataset, which contains 259,200 synthetic 1H MRS examples for training and testing neural networks. AGNOSTIC was created using 270 basis sets that were simulated across 18 field strengths and 15 echo times. The synthetic examples were produced to resemble in vivo brain data with combinations of metabolite, macromolecule, residual water signals, and noise. To demonstrate the utility, we apply AGNOSTIC to train two Convolutional Neural Networks (CNNs) to address out-of-voxel (OOV) echoes. A Detection Network was trained to identify the point-wise presence of OOV echoes, providing proof of concept for real-time detection. A Prediction Network was trained to reconstruct OOV echoes, allowing subtraction during post-processing. Complex OOV signals were mixed into 85% of synthetic examples to train two separate CNNs for the detection and prediction of OOV signals. AGNOSTIC is available through Dryad and all Python 3 code is available through GitHub. The Detection network was shown to perform well, identifying 95% of OOV echoes. Traditional modeling of these detected OOV signals was evaluated and may prove to be an effective method during linear-combination modeling. The Prediction Network greatly reduces OOV echoes within FIDs and achieved a median log10 normed-MSE of -1.79, an improvement of almost two orders of magnitude.

A review of machine learning applications for the proton MR spectroscopy workflow

This literature review presents a comprehensive overview of machine learning (ML) applications in proton MR spectroscopy (MRS). As the use of ML techniques in MRS continues to grow, this review aims to provide the MRS community with a structured overview of the state-of-the-art methods. Specifically, we examine and summarize studies published between 2017 and 2023 from major journals in the MR field. We categorize these studies based on a typical MRS workflow, including data acquisition, processing, analysis, and artificial data generation. Our review reveals that ML in MRS is still in its early stages, with a primary focus on processing and analysis techniques, and less attention given to data acquisition. We also found that many studies use similar model architectures, with little comparison to alternative architectures. Additionally, the generation of artificial data is a crucial topic, with no consistent method for its generation. Furthermore, many studies demonstrate that artificial data suffers from generalization issues when tested on in vivo data. We also conclude that risks related to ML models should be addressed, particularly for clinical applications. Therefore, output uncertainty measures and model biases are critical to investigate. Nonetheless, the rapid development of ML in MRS and the promising results from the reviewed studies justify further research in this field.

Label-Free Chemically and Molecularly Selective Magnetic Resonance Imaging

Biomedical imaging, especially molecular imaging, has been a driving force in scientific discovery, technological innovation, and precision medicine in the past two decades. While substantial advances and discoveries in chemical biology have been made to develop molecular imaging probes and tracers, translating these exogenous agents to clinical application in precision medicine is a major challenge. Among the clinically accepted imaging modalities, magnetic resonance imaging (MRI) and magnetic resonance spectroscopy (MRS) exemplify the most effective and robust biomedical imaging tools. Both MRI and MRS enable a broad range of chemical, biological and clinical applications from determining molecular structures in biochemical analysis to imaging diagnosis and characterization of many diseases and image-guided interventions. Using chemical, biological, and nuclear magnetic resonance properties of specific endogenous metabolites and native MRI contrast-enhancing biomolecules, label-free molecular and cellular imaging with MRI can be achieved in biomedical research and clinical management of patients with various diseases. This review article outlines the chemical and biological bases of several label-free chemically and molecularly selective MRI and MRS methods that have been applied in imaging biomarker discovery, preclinical investigation, and image-guided clinical management. Examples are provided to demonstrate strategies for using endogenous probes to report the molecular, metabolic, physiological, and functional events and processes in living systems, including patients. Future perspectives on label-free molecular MRI and its challenges as well as potential solutions, including the use of rational design and engineered approaches to develop chemical and biological imaging probes to facilitate or combine with label-free molecular MRI, are discussed.

Physics-informed deep learning approach to quantification of human brain metabolites from magnetic resonance spectroscopy data

PURPOSE

While the recommended analysis method for magnetic resonance spectroscopy data is linear combination model (LCM) fitting, the supervised deep learning (DL) approach for quantification of MR spectroscopy (MRS) and MR spectroscopic imaging (MRSI) data recently showed encouraging results; however, supervised learning requires ground truth fitted spectra, which is not practical. Moreover, this work investigates the feasibility and efficiency of the LCM-based self-supervised DL method for the analysis of MRS data.

METHOD

We present a novel DL-based method for the quantification of relative metabolite concentrations, using quantum-mechanics simulated metabolite responses and neural networks. We trained, validated, and evaluated the proposed networks with simulated and publicly accessible in-vivo human brain MRS data and compared the performance with traditional methods. A novel adaptive macromolecule fitting algorithm is included. We investigated the performance of the proposed methods in a Monte Carlo (MC) study.

RESULT

The validation using low-SNR simulated data demonstrated that the proposed methods could perform quantification comparably to other methods. The applicability of the proposed method for the quantification of in-vivo MRS data was demonstrated. Our proposed networks have the potential to reduce computation time significantly.

CONCLUSION

The proposed model-constrained deep neural networks trained in a self-supervised manner can offer fast and efficient quantification of MRS and MRSI data. Our proposed method has the potential to facilitate clinical practice by enabling faster processing of large datasets such as high-resolution MRSI datasets, which may have thousands of spectra.

Subnormothermic Ex Vivo Porcine Kidney Perfusion Improves Energy Metabolism: Analysis Using 31P Magnetic Resonance Spectroscopic Imaging

The ideal preservation temperature for donation after circulatory death kidney grafts is unknown. We investigated whether subnormothermic (22 °C) ex vivo kidney machine perfusion could improve kidney metabolism and reduce ischemia-reperfusion injury.

Improved signal-to-noise performance of MultiNet GRAPPA 1 H FID MRSI reconstruction with semi-synthetic calibration data

PURPOSE

To further develop MultiNet GRAPPA, a neural-network-based reconstruction, for lower SNR proton MRSI (¹ H MRSI) data using adapted undersampling schemes and improved training sets.

METHODS

¹ H FID-MRSI data and an anatomical image for GRAPPA reconstruction were acquired in two slices in the human brain (n = 6) at 7T. MRSI data were retrospectively undersampled for a 4×, 6×, and 7× acceleration rate. Signal-to-noise, relative error (RE) between accelerated and fully sampled metabolic maps, RMS of the lipid artifacts, and fitting reliability were compared across acceleration rates, to the fully sampled data, and with different kinds and amounts of training images.

RESULTS

Training with semi-synthetic images resulted in higher SNR and lower lipid RMS relative to training with acquired images from one or several subjects. SNR increased with the number of semi-synthetic training images and the 4× accelerated data retains ∼30% more SNR than other accelerated data. Spectra reconstructed with 20 semi-synthetic averages retained ∼100% more SNR and had ∼5% lower lipid RMS than those reconstructed with the center k-space points of one image as was originally proposed for very high SNR MRSI data and had higher fitting reliability. The metabolite RE was lowest when training with 20-semi-synthetic training images and highest when training with the center k-space points of one image.

CONCLUSION

MultiNet GRAPPA is feasible with lower SNR ¹ H MRSI data if 20-semi-synthetic training images are used at a 4× acceleration rate. This acceleration rate provided the best trade-off between scan time and spectral SNR.

Emerging MR Imaging and Spectroscopic Methods to Study Brain Tumor Metabolism

Proton magnetic resonance spectroscopy (1H-MRS) provides a non-invasive biochemical profile of brain tumors. The conventional 1H-MRS methods present a few challenges mainly related to limited spatial coverage and low spatial and spectral resolutions. In the recent past, the advent and development of more sophisticated metabolic imaging and spectroscopic sequences have revolutionized the field of neuro-oncologic metabolomics. In this review article, we will briefly describe the scientific premises of three-dimensional echoplanar spectroscopic imaging (3D-EPSI), two-dimensional correlation spectroscopy (2D-COSY), and chemical exchange saturation technique (CEST) MRI techniques. Several published studies have shown how these emerging techniques can significantly impact the management of patients with glioma by determining histologic grades, molecular profiles, planning treatment strategies, and assessing the therapeutic responses. The purpose of this review article is to summarize the potential clinical applications of these techniques in studying brain tumor metabolism.