Magnetic Resonance Materials in Physics, Biology and Medicine最新文献

Objective: Increased subcutaneous and visceral adipose tissue (SAT/VAT) volume is associated with risk for cardiometabolic diseases. This work aimed to develop and evaluate automated abdominal SAT/VAT segmentation on longitudinal MRI in adults with overweight/obesity using attention-based competitive dense (ACD) 3D U-Net and 3D nnU-Net with full field-of-view volumetric multi-contrast inputs.

Materials and methods: 920 adults with overweight/obesity were scanned twice at multiple 3 T MRI scanners and institutions. The first scan was divided into training/validation/testing sets (n = 646/92/182). The second scan from the subjects in the testing set was used to evaluate the generalizability for longitudinal analysis. Segmentation performance was assessed by measuring Dice scores (DICE-SAT, DICE-VAT), false negatives (FN), and false positives (FP). Volume agreement was assessed using the intraclass correlation coefficient (ICC).

Results: ACD 3D U-Net achieved rapid (< 4.8 s/subject) segmentation with high DICE-SAT (median ≥ 0.994) and DICE-VAT (median ≥ 0.976), small FN (median ≤ 0.7%), and FP (median ≤ 1.1%). 3D nnU-Net yielded rapid (< 2.5 s/subject) segmentation with similar DICE-SAT (median ≥ 0.992), DICE-VAT (median ≥ 0.979), FN (median ≤ 1.1%) and FP (median ≤ 1.2%). Both models yielded excellent agreement in SAT/VAT volume versus reference measurements (ICC > 0.997) in longitudinal analysis.

Discussion: ACD 3D U-Net and 3D nnU-Net can be automated tools to quantify abdominal SAT/VAT volume rapidly, accurately, and longitudinally in adults with overweight/obesity.

Objective: This study aims to assess the statistical significance of training parameters in 240 dense UNets (DUNets) used for enhancing low Signal-to-Noise Ratio (SNR) and undersampled MRI in various acquisition protocols. The objective is to determine the validity of differences between different DUNet configurations and their impact on image quality metrics.

Materials and methods: To achieve this, we trained all DUNets using the same learning rate and number of epochs, with variations in 5 acquisition protocols, 24 loss function weightings, and 2 ground truths. We calculated evaluation metrics for two metric regions of interest (ROI). We employed both Analysis of Variance (ANOVA) and Mixed Effects Model (MEM) to assess the statistical significance of the independent parameters, aiming to compare their efficacy in revealing differences and interactions among fixed parameters.

Results: ANOVA analysis showed that, except for the acquisition protocol, fixed variables were statistically insignificant. In contrast, MEM analysis revealed that all fixed parameters and their interactions held statistical significance. This emphasizes the need for advanced statistical analysis in comparative studies, where MEM can uncover finer distinctions often overlooked by ANOVA.

Discussion: These findings highlight the importance of utilizing appropriate statistical analysis when comparing different deep learning models. Additionally, the surprising effectiveness of the UNet architecture in enhancing various acquisition protocols underscores the potential for developing improved methods for characterizing and training deep learning models. This study serves as a stepping stone toward enhancing the transparency and comparability of deep learning techniques for medical imaging applications.

Objective: This study investigated the feasibility of using deep learning-based super-resolution (DL-SR) technique on low-resolution (LR) images to generate high-resolution (HR) MR images with the aim of scan time reduction. The efficacy of DL-SR was also assessed through the application of brain volume measurement (BVM).

Materials and methods: In vivo brain images acquired with 3D-T1W from various MRI scanners were utilized. For model training, LR images were generated by downsampling the original 1 mm-2 mm isotropic resolution images. Pairs of LR and HR images were used for training 3D residual dense net (RDN). For model testing, actual scanned 2 mm isotropic resolution 3D-T1W images with one-minute scan time were used. Normalized root-mean-square error (NRMSE), peak signal-to-noise ratio (PSNR), and structural similarity (SSIM) were used for model evaluation. The evaluation also included brain volume measurement, with assessments of subcortical brain regions.

Results: The results showed that DL-SR model improved the quality of LR images compared with cubic interpolation, as indicated by NRMSE (24.22% vs 30.13%), PSNR (26.19 vs 24.65), and SSIM (0.96 vs 0.95). For volumetric assessments, there were no significant differences between DL-SR and actual HR images (p > 0.05, Pearson's correlation > 0.90) at seven subcortical regions.

Discussion: The combination of LR MRI and DL-SR enables addressing prolonged scan time in 3D MRI scans while providing sufficient image quality without affecting brain volume measurement.

Artificial intelligence (AI) integration in cardiac magnetic resonance imaging presents new and exciting avenues for advancing patient care, automating post-processing tasks, and enhancing diagnostic precision and outcomes. The use of AI significantly streamlines the examination workflow through the reduction of acquisition and postprocessing durations, coupled with the automation of scan planning and acquisition parameters selection. This has led to a notable improvement in examination workflow efficiency, a reduction in operator variability, and an enhancement in overall image quality. Importantly, AI unlocks new possibilities to achieve spatial resolutions that were previously unattainable in patients. Furthermore, the potential for low-dose and contrast-agent-free imaging represents a stride toward safer and more patient-friendly diagnostic procedures. Beyond these benefits, AI facilitates precise risk stratification and prognosis evaluation by adeptly analysing extensive datasets. This comprehensive review article explores recent applications of AI in the realm of cardiac magnetic resonance imaging, offering insights into its transformative potential in the field.

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.

Neurodegenerative disorders, including Multiple Sclerosis (MS), are heterogenous disorders which affect the myelin sheath of the central nervous system (CNS). Magnetic Resonance Imaging (MRI) provides a non-invasive method for studying, diagnosing, and monitoring disease progression. As an emerging research area, many studies have attempted to connect MR metrics to underlying pathophysiological presentations of heterogenous neurodegeneration. Most commonly, small animal models are used, including Experimental Autoimmune Encephalomyelitis (EAE), Theiler’s Murine Encephalomyelitis (TMEV), and toxin models including cuprizone (CPZ), lysolecithin, and ethidium bromide (EtBr). A contrast and comparison of these models is presented, with focus on the cuprizone model, followed by a review of literature studying neurodegeneration using MRI and the cuprizone model. Conventional MRI methods including T₁ Weighted (T₁W) and T₂ Weighted (T₂W) Imaging are mentioned. Quantitative MRI methods which are sensitive to diffusion, magnetization transfer, susceptibility, relaxation, and chemical composition are discussed in relation to studying the CPZ model. Overall, additional studies are needed to improve both the sensitivity and specificity of MRI metrics for underlying pathophysiology of neurodegeneration and the relationships in attempts to clear the clinico-radiological paradox. We therefore propose a multiparametric approach for the investigation of MR metrics for underlying pathophysiology.

Purpose

Use a conference challenge format to compare machine learning-based gamma-aminobutyric acid (GABA)-edited magnetic resonance spectroscopy (MRS) reconstruction models using one-quarter of the transients typically acquired during a complete scan.

Methods

There were three tracks: Track 1: simulated data, Track 2: identical acquisition parameters with in vivo data, and Track 3: different acquisition parameters with in vivo data. The mean squared error, signal-to-noise ratio, linewidth, and a proposed shape score metric were used to quantify model performance. Challenge organizers provided open access to a baseline model, simulated noise-free data, guides for adding synthetic noise, and in vivo data.

Results

Three submissions were compared. A covariance matrix convolutional neural network model was most successful for Track 1. A vision transformer model operating on a spectrogram data representation was most successful for Tracks 2 and 3. Deep learning (DL) reconstructions with 80 transients achieved equivalent or better SNR, linewidth and fit error compared to conventional 320 transient reconstructions. However, some DL models optimized linewidth and SNR without actually improving overall spectral quality, indicating a need for more robust metrics.

Conclusion

DL-based reconstruction pipelines have the promise to reduce the number of transients required for GABA-edited MRS.

Objective

Quantitative susceptibility mapping (QSM) provides an estimate of the magnetic susceptibility of tissue using magnetic resonance (MR) phase measurements. The tissue magnetic susceptibility (source) from the measured magnetic field distribution/local tissue field (effect) inherent in the MR phase images is estimated by numerically solving the inverse source-effect problem. This study aims to develop an effective model-based deep-learning framework to solve the inverse problem of QSM.

Materials and methods

This work proposes a Schatten (textit{p})-norm-driven model-based deep learning framework for QSM with a learnable norm parameter (textit{p}) to adapt to the data. In contrast to other model-based architectures that enforce the l(_{text {2}})-norm or l(_{text {1}})-norm for the denoiser, the proposed approach can enforce any (textit{p})-norm ((text {0}<textit{p}le text {2})) on a trainable regulariser.

Results

The proposed method was compared with deep learning-based approaches, such as QSMnet, and model-based deep learning approaches, such as learned proximal convolutional neural network (LPCNN). Reconstructions performed using 77 imaging volumes with different acquisition protocols and clinical conditions, such as hemorrhage and multiple sclerosis, showed that the proposed approach outperformed existing state-of-the-art methods by a significant margin in terms of quantitative merits.

Conclusion

The proposed SpiNet-QSM showed a consistent improvement of at least 5% in terms of the high-frequency error norm (HFEN) and normalized root mean squared error (NRMSE) over other QSM reconstruction methods with limited training data.

Objective

To clarify the relationship between myelin water fraction (MWF) and R₁⋅R₂^* and to develop a method to calculate MWF directly from parameters derived from QPM, i.e., MWF converted from QPM (MWF_QPM).

Materials and methods

Subjects were 12 healthy volunteers. On a 3 T MR scanner, dataset was acquired using spoiled gradient-echo sequence for QPM. MWF and R₁⋅R₂^* maps were derived from the multi-gradient-echo (mGRE) dataset. Volume-of-interest (VOI) analysis using the JHU-white matter (WM) atlas was performed. All the data in the 48 WM regions measured VOI were plotted, and quadratic polynomial approximations of each region were derived from the relationship between R₁·R₂^* and the two-pool model-MWF. The R₁·R₂^* map was converted to MWF_QPM map. MWF atlas template was generated using converted to MWF from R₁·R₂^* per WM region.

Results

The mean MWF and R₁·R₂^* values for the 48 WM regions were 11.96 ± 6.63%, and 19.94 ± 4.59 s⁻², respectively. A non-linear relationship in 48 regions of the WM between MWF and R₁·R₂^* values was observed by quadratic polynomial approximation (R² ≥ 0.963, P < 0.0001).

Discussion

MWF_QPM map improved image quality compared to the mGRE-MWF map. Myelin water atlas template derived from MWF_QPM may be generated with combined multiple WM regions.