Quantification of MR spectra by deep learning in an idealized setting: Investigation of forms of input, network architectures, optimization by ensembles of networks, and training bias

Simultaneous multi-transient linear-combination modeling of MRS data improves uncertainty estimation

PURPOSE

The interest in applying and modeling dynamic MRS has recently grown. Two-dimensional modeling yields advantages for the precision of metabolite estimation in interrelated MRS data. However, it is unknown whether including all transients simultaneously in a 2D model without averaging (presuming a stable signal) performs similarly to one-dimensional (1D) modeling of the averaged spectrum. Therefore, we systematically investigated the accuracy, precision, and uncertainty estimation of both described model approaches.

METHODS

Monte Carlo simulations of synthetic MRS data were used to compare the accuracy and uncertainty estimation of simultaneous 2D multitransient linear-combination modeling (LCM) with 1D-LCM of the average. A total of 2,500 data sets per condition with different noise representations of a 64-transient MRS experiment at six signal-to-noise levels for two separate spin systems (scyllo-inositol and gamma-aminobutyric acid) were analyzed. Additional data sets with different levels of noise correlation were also analyzed. Modeling accuracy was assessed by determining the relative bias of the estimated amplitudes against the ground truth, and modeling precision was determined by SDs and Cramér-Rao lower bounds (CRLBs).

RESULTS

Amplitude estimates for 1D- and 2D-LCM agreed well and showed a similar level of bias compared with the ground truth. Estimated CRLBs agreed well between both models and with ground-truth CRLBs. For correlated noise, the estimated CRLBs increased with the correlation strength for the 1D-LCM but remained stable for the 2D-LCM.

CONCLUSION

Our results indicate that the model performance of 2D multitransient LCM is similar to averaged 1D-LCM. This validation on a simplified scenario serves as a necessary basis for further applications of 2D modeling.

TensorFit: A torch-based tool for ultrafast metabolite fitting of large MRSI data sets

PURPOSE

To introduce a tool (TensorFit) for ultrafast and robust metabolite fitting of MRSI data based on Torch's auto-differentiation and optimization framework.

METHODS

TensorFit was implemented in Python based on Torch's auto-differentiation to fit individual metabolites in MRS spectra. The underlying time domain and/or frequency domain fitting model is based on a linear combination of metabolite spectroscopic response. The computational time efficiency and accuracy of TensorFit were tested on simulated and in vivo MRS data and compared against TDFDFit and QUEST.

RESULTS

TensorFit demonstrates a significant improvement in computation speed, achieving a 165-times acceleration compared with TDFDFit and 115 times against QUEST. TensorFit showed smaller percentual errors on simulated data compared with TDFDFit and QUEST. When tested on in vivo data, it performed similarly to TDFDFit with a 2% better fit in terms of mean squared error while obtaining a 169-fold speedup.

CONCLUSION

TensorFit enables fast and robust metabolite fitting in large MRSI data sets compared with conventional metabolite fitting methods. This tool could boost the clinical applicability of large 3D MRSI by enabling the fitting of large MRSI data sets within computation times acceptable in a clinical environment.

Spectro-ViT: A vision transformer model for GABA-edited MEGA-PRESS reconstruction using spectrograms

This study investigated the use of a Vision Transformer (ViT) for reconstructing GABA-edited Magnetic Resonance Spectroscopy (MRS) data from a reduced number of transients. Transients refer to the samples collected during an MRS acquisition by repeating the experiment to generate a signal of sufficient quality. Specifically, 80 transients were used instead of the typical 320 transients, aiming to reduce scan time. The 80 transients were pre-processed and converted into a spectrogram image representation using the Short-Time Fourier Transform (STFT). A pre-trained ViT, named Spectro-ViT, was fine-tuned and then tested using in-vivo GABA-edited MEGA-PRESS data. Its performance was compared against other pipelines in the literature using quantitative quality metrics and estimated metabolite concentration values, with the typical 320-transient scans serving as the reference for comparison. The Spectro-ViT model exhibited the best overall quality metrics among all other pipelines against which it was compared. The metabolite concentrations from Spectro-ViT's reconstructions for GABA+ achieved the best average R2 value of 0.67 and the best average Mean Absolute Percentage Error (MAPE) value of 9.68%, with no significant statistical differences found compared to the 320-transient reference. The code to reproduce this research is available at https://github.com/MICLab-Unicamp/Spectro-ViT.

Simultaneous multi-region detection of GABA+ and Glx using 3D spatially resolved SLOW-editing and EPSI-readout at 7T

GABA+ and Glx (glutamate and glutamine) are widely studied metabolites, yet the commonly used magnetic resonance spectroscopy (MRS) techniques have significant limitations, including sensitivity to B0 and B1+-inhomogeneities, limited bandwidth of MEGA-pulses, high SAR which is accentuated at 7T. To address these limitations, we propose SLOW-EPSI method, employing a large 3D MRSI coverage and achieving a high resolution down to 0.26 ml. Simulation results demonstrate the robustness of SLOW-editing for both GABA+ and Glx against B0 and B1+-inhomogeneities within the range of [-0.3, +0.3] ppm and [40 %, 250 %], respectively. Two protocols, both utilizing a 70 mm thick FOV slab, were employed to target distinct brain regions in vivo, differentiated by their orientation: transverse and tilted. Protocol 1 (n = 11) encompassed 5 locations (cortical gray matter, white matter, frontal lobe, parietal lobe, and cingulate gyrus). Protocol 2 (n = 5) involved 9 locations (cortical gray matter, white matter, frontal lobe, occipital lobe, cingulate gyrus, caudate nucleus, hippocampus, putamen, and inferior thalamus). Quantitative analysis of GABA+ and Glx was conducted in a stepwise manner. First, B1+/B1--inhomogeneities were corrected using water reference data. Next, GABA+ and Glx values were calculated employing spectral fitting. Finally, the GABA+ level for each selected region was compared to the global Glx within the same subject, generating the GABA+/Glx_global ratio. Our findings from two protocols indicate that the GABA+/Glx_global level in cortical gray matter was approximately 16 % higher than in white matter. Elevated GABA+/Glx_global levels acquired with protocol 2 were observed in specific regions such as the caudate nucleus (0.118±0.067), putamen (0.108±0.023), thalamus (0.092±0.036), and occipital cortex (0.091±0.010), when compared to the cortical gray matter (0.079±0.012). Overall, our results highlight the effectiveness of SLOW-EPSI as a robust and efficient technique for accurate measurements of GABA+ and Glx at 7T. In contrast to previous SVS and 2D-MRSI based editing sequences with which only one or a limited number of brain regions can be measured simultaneously, the method presented here measures GABA+ and Glx from any brain area and any arbitrarily shaped volume that can be flexibly selected after the examination. Quantification of GABA+ and Glx across multiple brain regions through spectral fitting is achievable with a 9-minute acquisition. Additionally, acquisition times of 18-27 min (GABA+) and 9-18 min (Glx) are required to generate 3D maps, which are constructed using Gaussian fitting and peak integration.

Simultaneous multi-transient linear-combination modeling of MRS data improves uncertainty estimation

Purpose

The interest in applying and modeling dynamic MRS has recently grown. 2D modeling yields advantages for the precision of metabolite estimation in interrelated MRS data. However, it is unknown whether including all transients simultaneously in a 2D model without averaging (presuming a stable signal) performs similarly to 1D modeling of the averaged spectrum. Therefore, we systematically investigated the accuracy, precision, and uncertainty estimation of both described model approaches.

Methods

Monte Carlo simulations of synthetic MRS data were used to compare the accuracy and uncertainty estimation of simultaneous 2D multi-transient LCM with 1D-LCM of the average. 2,500 datasets per condition with different noise representations of a 64-transient MRS experiment at 6 signal-to-noise levels for two separate spin systems (scyllo-inositol and GABA) were analyzed. Additional datasets with different levels of noise correlation were also analyzed. Modeling accuracy was assessed by determining the relative bias of the estimated amplitudes against the ground truth, and modeling precision was determined by standard deviations and Cramér-Rao Lower Bounds (CRLB).

Results

Amplitude estimates for 1D- and 2D-LCM agreed well and showed similar level of bias compared to the ground truth. Estimated CRLBs agreed well between both models and with ground truth CRLBs. For correlated noise the estimated CRLBs increased with the correlation strength for the 1D-LCM but remained stable for the 2D-LCM.

Conclusion

Our results indicate that the model performance of 2D multi-transient LCM is similar to averaged 1D-LCM. This validation on a simplified scenario serves as necessary basis for further applications of 2D modeling.

Denoising single MR spectra by deep learning: Miracle or mirage?

PURPOSE

The inherently poor SNR of MRS measurements presents a significant hurdle to its clinical application. Denoising by machine or deep learning (DL) was proposed as a remedy. It is investigated whether such denoising leads to lower estimate uncertainties or whether it essentially reduces noise in signal-free areas only.

METHODS

Noise removal based on supervised DL with U-nets was implemented using simulated 1 H MR spectra of human brain in two approaches: (1) via time-frequency domain spectrograms and (2) using 1D spectra as input. Quality of denoising was evaluated in three ways: (1) by an adapted fit quality score, (2) by traditional model fitting, and (3) by quantification via neural networks.

RESULTS

Visually appealing spectra were obtained; hinting that denoising is well-suited for MRS. However, an adapted denoising score showed that noise removal is inhomogeneous and more efficient for signal-free areas. This was confirmed by quantitative analysis of traditional fit results as well as DL quantitation following DL denoising. DL denoising, although apparently successful as judged by mean squared errors, led to substantially biased estimates in both implementations.

CONCLUSION

The implemented DL-based denoising techniques may be useful for display purposes, but do not help quantitative evaluations, confirming expectations based on estimation theory: Cramér Rao lower bounds defined by the original data and the appropriate fitting model cannot be circumvented in an unbiased way for single data sets, unless additional prior knowledge can be incurred in the form of parameter restrictions/relations or applicable substates.

Comparison of convolutional-neural-networks-based method and LCModel on the quantification of in vivo magnetic resonance spectroscopy

BACKGROUND

Quantification of metabolites concentrations in institutional unit (IU) is important for inter-subject and long-term comparisons in the applications of magnetic resonance spectroscopy (MRS). Recently, deep learning (DL) algorithms have found a variety of applications on the process of MRS data. A quantification strategy compatible to DL base MRS spectral processing method is, therefore, useful.

MATERIALS AND METHODS

This study aims to investigate whether metabolite concentrations quantified using a convolutional neural network (CNN) based method, coupled with a scaling procedure that normalizes spectral signals for CNN input and linear regression, can effectively reflect variations in metabolite concentrations in IU across different brain regions with varying signal-to-noise ratios (SNR) and linewidths (LW). An error index based on standard error (SE) is proposed to indicate the confidence levels associated with metabolite predictions. In vivo MRS spectra were acquired from three brain regions of 43 subjects using a 3T system.

RESULTS

The metabolite concentrations in IU of five major metabolites, quantified using CNN and LCModel, exhibit similar ranges with Pearson's correlation coefficients ranging from 0.24 to 0.78. The SE of the metabolites shows a positive correlation with Cramer-Rao lower bound (CRLB) (r=0.46) and  absolute CRLB (r=0.81), calculated by multiplying CRLBs with the quantified metabolite content.

CONCLUSION

In conclusion, the CNN based method with the proposed scaling procedures can be employed to quantify in vivo MRS spectra and derive metabolites concentrations in IU. The SE can be used as error index, indicating predicted uncertainties for metabolites and sharing information similar to the absolute CRLB.

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.