Boosting the signal-to-noise of low-field MRI with deep learning image reconstruction

Engineering Principles and Bioengineering in Global Health

Medical technology plays a significant role in the reduction of disability and mortality due to the global burden of disease. The lack of diagnostic technology has been identified as the largest gap in the global health care pathway, and the cost of this technology is a driving factor for its lack of proliferation. Technology developed in high-income countries is often focused on producing high-quality, patient-specific data at a cost high-income markets can pay. While machine learning plays an important role in this process, great care must be taken to ensure appropriate translation to clinical practice.

Enhancing clinical diagnostics: novel denoising methodology for brain MRI with adaptive masking and modified non-local block

Medical image denoising has been a subject of extensive research, with various techniques employed to enhance image quality and facilitate more accurate diagnostics. The evolution of denoising methods has highlighted impressive results but struggled to strike equilibrium between noise reduction and edge preservation which limits its applicability in various domains. This paper manifests the novel methodology that integrates an adaptive masking strategy, transformer-based U-Net Prior generator, edge enhancement module, and modified non-local block (MNLB) for denoising brain MRI clinical images. The adaptive masking strategy maintains the vital information through dynamic mask generation while the prior generator by capturing hierarchical features regenerates the high-quality prior MRI images. Finally, these images are fed to the edge enhancement module to boost structural information by maintaining crucial edge details, and the MNLB produces the denoised output by deriving non-local contextual information. The comprehensive experimental assessment is performed by employing two datasets namely the brain tumor MRI dataset and Alzheimer's dataset for diverse metrics and compared with conventional denoising approaches. The proposed denoising methodology achieves a PSNR of 40.965 and SSIM of 0.938 on the Alzheimer's dataset and also achieves a PSNR of 40.002 and SSIM of 0.926 on the brain tumor MRI dataset at a noise level of 50% revealing its supremacy in noise minimization. Furthermore, the impact of different masking ratios on denoising performance is analyzed which reveals that the proposed method showed PSNR of 40.965, SSIM of 0.938, MAE of 5.847, and MSE of 3.672 at the masking ratio of 60%. Moreover, the findings pave the way for the advancement of clinical image processing, facilitating precise detection of tumors in clinical MRI images.

Joint [Formula: see text] and Image Reconstruction in Low-Field MRI by Physics-Informed Deep-Learning

OBJECTIVE

We present a model-based image reconstruction approach based on unrolled neural networks which corrects for image distortion and noise in low-field ( B0  ∼  50 mT) MRI.

METHODS

Utilising knowledge about the underlying physics, a novel network architecture (SH-Net) is introduced which involves the estimation of spherical harmonic coefficients to guarantee a spatially smooth field map estimate. The SH-Net is integrated in an end-to-end trainable model which jointly estimates the B0-field map as well as the image. Experiments were conducted on retrospectively simulated low-field data of human knees.

RESULTS

We compare our model to different model-based approaches at distinct noise levels and various B0-field distributions. Our results show that our physics-informed neural network approach outperforms the purely model-based methods by improving the PSNR up to 11.7% and the RMSE up to 86.3%.

CONCLUSION

Our end-to-end trained model-based approach outperforms existing methods in reconstructing image and B0-field maps in the low-field regime.

SIGNIFICANCE

low-field MRI is becoming increasingly more popular as it enables access to MR in challenging situations such as intensive care units or resource poor areas. Our method allows for fast and accurate image reconstruction in such low-field imaging with B0-inhomogeneity compensation under a wide range of various environmental conditions.

Single-point macromolecular proton fraction mapping using a 0.3 T permanent magnet MRI system: phantom and healthy volunteer study

In a 0.3 T permanent-magnet magnetic resonance imaging (MRI) system, quantifying myelin content is challenging owing to long imaging times and low signal-to-noise ratio. macromolecular proton fraction (MPF) offers a quantitative assessment of myelin in the nervous system. We aimed to demonstrate the practical feasibility of MPF mapping in the brain using a 0.3 T MRI. Both 0.3 T and 3.0 T MRI systems were used. The MPF-mapping protocol used a standard 3D fast spoiled gradient-echo sequence based on the single-point reference method. Proton density, T1, and magnetization transfer-weighted images were obtained from a protein phantom at 0.3 T and 3.0 T to calculate MPF maps. MPF was measured in all phantom sections to assess its relationship to protein concentration. We acquired MPF maps for 16 and 8 healthy individuals at 0.3 T and 3.0 T, respectively, measuring MPF in nine brain tissues. Differences in MPF between 0.3 T and 3.0 T, and between 0.3 T and previously reported MPF at 0.5 T, were investigated. Pearson's correlation coefficient between protein concentration and MPF at 0.3 T and 3.0 T was 0.92 and 0.90, respectively. The 0.3 T MPF of brain tissue strongly correlated with 3.0 T MPF and literature values measured at 0.5 T. The absolute mean differences in MPF between 0.3 T and 0.5 T were 0.42% and 1.70% in white and gray matter, respectively. Single-point MPF mapping using 0.3 T permanent-magnet MRI can effectively assess myelin content in neural tissue.

Let UNet Play an Adversarial Game: Investigating the Effect of Adversarial Training in Enhancing Low-Resolution MRI

Adversarial training has attracted much attention in enhancing the visual realism of images, but its efficacy in clinical imaging has not yet been explored. This work investigated adversarial training in a clinical context, by training 206 networks on the OASIS-1 dataset for improving low-resolution and low signal-to-noise ratio (SNR) magnetic resonance images. Each network corresponded to a different combination of perceptual and adversarial loss weights and distinct learning rate values. For each perceptual loss weighting, we identified its corresponding adversarial loss weighting that minimized structural disparity. Each optimally weighted adversarial loss yielded an average SSIM reduction of 1.5%. We further introduced a set of new metrics to assess other clinically relevant image features: Gradient Error (GE) to measure structural disparities; Sharpness to compute edge clarity; and Edge-Contrast Error (ECE) to quantify any distortion of the pixel distribution around edges. Including adversarial loss increased structural enhancement in visual inspection, which correlated with statistically consistent GE reductions (p-value << 0.05). This also resulted in increased Sharpness; however, the level of statistical significance was dependent on the perceptual loss weighting. Additionally, adversarial loss yielded ECE reductions for smaller perceptual loss weightings, while showing non-significant increases (p-value >> 0.05) when these weightings were higher, demonstrating that the increased Sharpness does not adversely distort the pixel distribution around the edges in the image. These studies clearly suggest that adversarial training significantly improves the performance of an MRI enhancement pipeline, and highlights the need for systematic studies of hyperparameter optimization and investigation of alternative image quality metrics.

Fast, high-quality, and unshielded 0.2 T low-field mobile MRI using minimal hardware resources

OBJECTIVE

To propose a deep learning-based low-field mobile MRI strategy for fast, high-quality, unshielded imaging using minimal hardware resources.

METHODS

Firstly, we analyze the correlation of EMI signals between the sensing coil and the MRI coil to preliminarily verify the feasibility of active EMI shielding using a single sensing coil. Then, a powerful deep learning EMI elimination model is proposed, which can accurately predict the EMI components in the MRI coil signals using EMI signals from at least one sensing coil. Further, deep learning models with different task objectives (super-resolution and denoising) are strategically stacked for multi-level post-processing to enable fast and high-quality low-field MRI. Finally, extensive phantom and brain experiments were conducted on a home-built 0.2 T mobile brain scanner for the evaluation of the proposed strategy.

RESULTS

20 healthy volunteers were recruited to participate in the experiment. The results show that the proposed strategy enables the 0.2 T scanner to generate images with sufficient anatomical information and diagnostic value under unshielded conditions using a single sensing coil. In particular, the EMI elimination outperforms the state-of-the-art deep learning methods and numerical computation methods. In addition, 2 × super-resolution (DDSRNet) and denoising (SwinIR) techniques enable further improvements in imaging speed and quality.

DISCUSSION

The proposed strategy enables low-field mobile MRI scanners to achieve fast, high-quality imaging under unshielded conditions using minimal hardware resources, which has great significance for the widespread deployment of low-field mobile MRI scanners.

Accelerated High-Resolution Deep Learning Reconstruction Turbo Spin Echo MRI of the Knee at 7 T

OBJECTIVES

The aim of this study was to compare the image quality of 7 T turbo spin echo (TSE) knee images acquired with varying factors of parallel-imaging acceleration reconstructed with deep learning (DL)-based and conventional algorithms.

MATERIALS AND METHODS

This was a prospective single-center study. Twenty-three healthy volunteers underwent 7 T knee magnetic resonance imaging. Two-, 3-, and 4-fold accelerated high-resolution fat-signal-suppressing proton density (PD-fs) and T1-weighted coronal 2D TSE acquisitions with an encoded voxel volume of 0.31 × 0.31 × 1.5 mm3 were acquired. Each set of raw data was reconstructed with a DL-based and a conventional Generalized Autocalibrating Partially Parallel Acquisition (GRAPPA) algorithm. Three readers rated image contrast, sharpness, artifacts, noise, and overall quality. Friedman analysis of variance and the Wilcoxon signed rank test were used for comparison of image quality criteria.

RESULTS

The mean age of the participants was 32.0 ± 8.1 years (15 male, 8 female). Acquisition times at 4-fold acceleration were 4 minutes 15 seconds (PD-fs, Supplemental Video is available at http://links.lww.com/RLI/A938) and 3 minutes 9 seconds (T1, Supplemental Video available at http://links.lww.com/RLI/A939). At 4-fold acceleration, image contrast, sharpness, noise, and overall quality of images reconstructed with the DL-based algorithm were significantly better rated than the corresponding GRAPPA reconstructions (P < 0.001). Four-fold accelerated DL-reconstructed images scored significantly better than 2- to 3-fold GRAPPA-reconstructed images with regards to image contrast, sharpness, noise, and overall quality (P ≤ 0.031). Image contrast of PD-fs images at 2-fold acceleration (P = 0.087), image noise of T1-weighted images at 2-fold acceleration (P = 0.180), and image artifacts for both sequences at 2- and 3-fold acceleration (P ≥ 0.102) of GRAPPA reconstructions were not rated differently than those of 4-fold accelerated DL-reconstructed images. Furthermore, no significant difference was observed for all image quality measures among 2-fold, 3-fold, and 4-fold accelerated DL reconstructions (P ≥ 0.082).

CONCLUSIONS

This study explored the technical potential of DL-based image reconstruction in accelerated 2D TSE acquisitions of the knee at 7 T. DL reconstruction significantly improved a variety of image quality measures of high-resolution TSE images acquired with a 4-fold parallel-imaging acceleration compared with a conventional reconstruction algorithm.

Learning to deep learning: statistics and a paradigm test in selecting a UNet architecture to enhance MRI

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.

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.

Low-Field, Low-Cost, Point-of-Care Magnetic Resonance Imaging

Low-field magnetic resonance imaging (MRI) has recently experienced a renaissance that is largely attributable to the numerous technological advancements made in MRI, including optimized pulse sequences, parallel receive and compressed sensing, improved calibrations and reconstruction algorithms, and the adoption of machine learning for image postprocessing. This new attention on low-field MRI originates from a lack of accessibility to traditional MRI and the need for affordable imaging. Low-field MRI provides a viable option due to its lack of reliance on radio-frequency shielding rooms, expensive liquid helium, and cryogen quench pipes. Moreover, its relatively small size and weight allow for easy and affordable installation in most settings. Rather than replacing conventional MRI, low-field MRI will provide new opportunities for imaging both in developing and developed countries. This article discusses the history of low-field MRI, low-field MRI hardware and software, current devices on the market, advantages and disadvantages, and low-field MRI's global potential.

Applications, limitations and advancements of ultra-low-field magnetic resonance imaging: A scoping review

Background

Ultra-low-field magnetic resonance imaging (ULF-MRI) has emerged as an alternative with several portable clinical applications. This review aims to comprehensively explore its applications, potential limitations, technological advancements, and expert recommendations.

Methods

A review of the literature was conducted across medical databases to identify relevant studies. Articles on clinical usage of ULF-MRI were included, and data regarding applications, limitations, and advancements were extracted. A total of 25 articles were included for qualitative analysis.

Results

The review reveals ULF-MRI efficacy in intensive care settings and intraoperatively. Technological strides are evident through innovative reconstruction techniques and integration with machine learning approaches. Additional advantages include features such as portability, cost-effectiveness, reduced power requirements, and improved patient comfort. However, alongside these strengths, certain limitations of ULF-MRI were identified, including low signal-to-noise ratio, limited resolution and length of scanning sequences, as well as variety and absence of regulatory-approved contrast-enhanced imaging. Recommendations from experts emphasize optimizing imaging quality, including addressing signal-to-noise ratio (SNR) and resolution, decreasing the length of scan time, and expanding point-of-care magnetic resonance imaging availability.

Conclusion

This review summarizes the potential of ULF-MRI. The technology's adaptability in intensive care unit settings and its diverse clinical and surgical applications, while accounting for SNR and resolution limitations, highlight its significance, especially in resource-limited settings. Technological advancements, alongside expert recommendations, pave the way for refining and expanding ULF-MRI's utility. However, adequate training is crucial for widespread utilization.

Evaluating Machine Learning-Based MRI Reconstruction Using Digital Image Quality Phantoms

Quantitative and objective evaluation tools are essential for assessing the performance of machine learning (ML)-based magnetic resonance imaging (MRI) reconstruction methods. However, the commonly used fidelity metrics, such as mean squared error (MSE), structural similarity (SSIM), and peak signal-to-noise ratio (PSNR), often fail to capture fundamental and clinically relevant MR image quality aspects. To address this, we propose evaluation of ML-based MRI reconstruction using digital image quality phantoms and automated evaluation methods. Our phantoms are based upon the American College of Radiology (ACR) large physical phantom but created in k-space to simulate their MR images, and they can vary in object size, signal-to-noise ratio, resolution, and image contrast. Our evaluation pipeline incorporates evaluation metrics of geometric accuracy, intensity uniformity, percentage ghosting, sharpness, signal-to-noise ratio, resolution, and low-contrast detectability. We demonstrate the utility of our proposed pipeline by assessing an example ML-based reconstruction model across various training and testing scenarios. The performance results indicate that training data acquired with a lower undersampling factor and coils of larger anatomical coverage yield a better performing model. The comprehensive and standardized pipeline introduced in this study can help to facilitate a better understanding of the performance and guide future development and advancement of ML-based reconstruction algorithms.

Comparison of weighting algorithms to mitigate respiratory motion in free-breathing neonatal pulmonary radial UTE-MRI

Background. Thoracoabdominal MRI is limited by respiratory motion, especially in populations who cannot perform breath-holds. One approach for reducing motion blurring in radially-acquired MRI is respiratory gating. Straightforward 'hard-gating' uses only data from a specified respiratory window and suffers from reduced SNR. Proposed 'soft-gating' reconstructions may improve scan efficiency but reduce motion correction by incorporating data with nonzero weight acquired outside the specified window. However, previous studies report conflicting benefits, and importantly the choice of soft-gated weighting algorithm and effect on image quality has not previously been explored. The purpose of this study is to map how variable soft-gated weighting functions and parameters affect signal and motion blurring in respiratory-gated reconstructions of radial lung MRI, using neonates as a model population.Methods. Ten neonatal inpatients with respiratory abnormalities were imaged using a 1.5 T neonatal-sized scanner and 3D radial ultrashort echo-time (UTE) sequence. Images were reconstructed using ungated, hard-gated, and several soft-gating weighting algorithms (exponential, sigmoid, inverse, and linear weighting decay outside the period of interest), with %Nprojrepresenting the relative amount of data included. The apparent SNR (aSNR) and motion blurring (measured by the maximum derivative of image intensity at the diaphragm, MDD) were compared between reconstructions.Results. Soft-gating functions produced higher aSNR and lower MDD than hard-gated images using equivalent %Nproj, as expected. aSNR was not identical between different gating schemes for given %Nproj. While aSNR was approximately linear with %Nprojfor each algorithm, MDD performance diverged between functions as %Nprojdecreased. Algorithm performance was relatively consistent between subjects, except in images with high noise.Conclusion. The algorithm selection for soft-gating has a notable effect on image quality of respiratory-gated MRI; the timing of included data across the respiratory phase, and not simply the amount of data, plays an important role in aSNR. The specific soft-gating function and parameters should be considered for a given imaging application's requirements of signal and sharpness.

Deep learning denoising reconstruction for improved image quality in fetal cardiac cine MRI

Purpose

This study aims to evaluate deep learning (DL) denoising reconstructions for image quality improvement of Doppler ultrasound (DUS)-gated fetal cardiac MRI in congenital heart disease (CHD).

Methods

Twenty-five fetuses with CHD (mean gestational age: 35 ± 1 weeks) underwent fetal cardiac MRI at 3T. Cine imaging was acquired using a balanced steady-state free precession (bSSFP) sequence with Doppler ultrasound gating. Images were reconstructed using both compressed sensing (bSSFP CS) and a pre-trained convolutional neural network trained for DL denoising (bSSFP DL). Images were compared qualitatively based on a 5-point Likert scale (from 1 = non-diagnostic to 5 = excellent) and quantitatively by calculating the apparent signal-to-noise ratio (aSNR) and contrast-to-noise ratio (aCNR). Diagnostic confidence was assessed for the atria, ventricles, foramen ovale, valves, great vessels, aortic arch, and pulmonary veins.

Results

Fetal cardiac cine MRI was successful in 23 fetuses (92%), with two studies excluded due to extensive fetal motion. The image quality of bSSFP DL cine reconstructions was rated superior to standard bSSFP CS cine images in terms of contrast [3 (interquartile range: 2-4) vs. 5 (4-5), P < 0.001] and endocardial edge definition [3 (2-4) vs. 4 (4-5), P < 0.001], while the extent of artifacts was found to be comparable [4 (3-4.75) vs. 4 (3-4), P = 0.40]. bSSFP DL images had higher aSNR and aCNR compared with the bSSFP CS images (aSNR: 13.4 ± 6.9 vs. 8.3 ± 3.6, P < 0.001; aCNR: 26.6 ± 15.8 vs. 14.4 ± 6.8, P < 0.001). Diagnostic confidence of the bSSFP DL images was superior for the evaluation of cardiovascular structures (e.g., atria and ventricles: P = 0.003).

Conclusion

DL image denoising provides superior quality for DUS-gated fetal cardiac cine imaging of CHD compared to standard CS image reconstruction.

Cardiac MRI at Low Field Strengths

Cardiac MR imaging is well established for assessment of cardiovascular structure and function, myocardial scar, quantitative flow, parametric mapping, and myocardial perfusion. Despite the clear evidence supporting the use of cardiac MRI for a wide range of indications, it is underutilized clinically. Recent developments in low-field MRI technology, including modern data acquisition and image reconstruction methods, are enabling high-quality low-field imaging that may improve the cost-benefit ratio for cardiac MRI. Studies to-date confirm that low-field MRI offers high measurement concordance and consistent interpretation with clinical imaging for several routine sequences. Moreover, low-field MRI may enable specific new clinical opportunities for cardiac imaging such as imaging near metal implants, MRI-guided interventions, combined cardiopulmonary assessment, and imaging of patients with severe obesity. In this review, we discuss the recent progress in low-field cardiac MRI with a focus on technical developments and early clinical validation studies. EVIDENCE LEVEL: 5 TECHNICAL EFFICACY: Stage 1.

New clinical opportunities of low-field MRI: heart, lung, body, and musculoskeletal

Contemporary whole-body low-field MRI scanners (< 1 T) present new and exciting opportunities for improved body imaging. The fundamental reason is that the reduced off-resonance and reduced SAR provide substantially increased flexibility in the design of MRI pulse sequences. Promising body applications include lung parenchyma imaging, imaging adjacent to metallic implants, cardiac imaging, and dynamic imaging in general. The lower cost of such systems may make MRI favorable for screening high-risk populations and population health research, and the more open configurations allowed may prove favorable for obese subjects and for pregnant women. This article summarizes promising body applications for contemporary whole-body low-field MRI systems, with a focus on new platforms developed within the past 5 years. This is an active area of research, and one can expect many improvements as MRI physicists fully explore the landscape of pulse sequences that are feasible, and as clinicians apply these to patient populations.

Detection of Intracerebral Hemorrhage Using Low-Field, Portable Magnetic Resonance Imaging in Patients With Stroke

BACKGROUND

Neuroimaging is essential for detecting spontaneous, nontraumatic intracerebral hemorrhage (ICH). Recent data suggest ICH can be characterized using low-field magnetic resonance imaging (MRI). Our primary objective was to investigate the sensitivity and specificity of ICH on a 0.064T portable MRI (pMRI) scanner using a methodology that provided clinical information to inform rater interpretations. As a secondary aim, we investigated whether the incorporation of a deep learning (DL) reconstruction algorithm affected ICH detection.

METHODS

The pMRI device was deployed at Yale New Haven Hospital to examine patients presenting with stroke symptoms from October 26, 2020 to February 21, 2022. Three raters independently evaluated pMRI examinations. Raters were provided the images alongside the patient's clinical information to simulate real-world context of use. Ground truth was the closest conventional computed tomography or 1.5/3T MRI. Sensitivity and specificity results were grouped by DL and non-DL software to investigate the effects of software advances.

RESULTS

A total of 189 exams (38 ICH, 89 acute ischemic stroke, 8 subarachnoid hemorrhage, 3 primary intraventricular hemorrhage, 51 no intracranial abnormality) were evaluated. Exams were correctly classified as positive or negative for ICH in 185 of 189 cases (97.9% overall accuracy). ICH was correctly detected in 35 of 38 cases (92.1% sensitivity). Ischemic stroke and no intracranial abnormality cases were correctly identified as blood-negative in 139 of 140 cases (99.3% specificity). Non-DL scans had a sensitivity and specificity for ICH of 77.8% and 97.1%, respectively. DL scans had a sensitivity and specificity for ICH of 96.6% and 99.3%, respectively.

CONCLUSIONS

These results demonstrate improvements in ICH detection accuracy on pMRI that may be attributed to the integration of clinical information in rater review and the incorporation of a DL-based algorithm. The use of pMRI holds promise in providing diagnostic neuroimaging for patients with ICH.

Low-field MRI: A report on the 2022 ISMRM workshop

In March 2022, the first ISMRM Workshop on Low-Field MRI was held virtually. The goals of this workshop were to discuss recent low field MRI technology including hardware and software developments, novel methodology, new contrast mechanisms, as well as the clinical translation and dissemination of these systems. The virtual Workshop was attended by 368 registrants from 24 countries, and included 34 invited talks, 100 abstract presentations, 2 panel discussions, and 2 live scanner demonstrations. Here, we report on the scientific content of the Workshop and identify the key themes that emerged. The subject matter of the Workshop reflected the ongoing developments of low-field MRI as an accessible imaging modality that may expand the usage of MRI through cost reduction, portability, and ease of installation. Many talks in this Workshop addressed the use of computational power, efficient acquisitions, and contemporary hardware to overcome the SNR limitations associated with low field strength. Participants discussed the selection of appropriate clinical applications that leverage the unique capabilities of low-field MRI within traditional radiology practices, other point-of-care settings, and the broader community. The notion of "image quality" versus "information content" was also discussed, as images from low-field portable systems that are purpose-built for clinical decision-making may not replicate the current standard of clinical imaging. Speakers also described technical challenges and infrastructure challenges related to portability and widespread dissemination, and speculated about future directions for the field to improve the technology and establish clinical value.

Deep learning enabled fast 3D brain MRI at 0.055 tesla

In recent years, there has been an intensive development of portable ultralow-field magnetic resonance imaging (MRI) for low-cost, shielding-free, and point-of-care applications. However, its quality is poor and scan time is long. We propose a fast acquisition and deep learning reconstruction framework to accelerate brain MRI at 0.055 tesla. The acquisition consists of a single average three-dimensional (3D) encoding with 2D partial Fourier sampling, reducing the scan time of T1- and T2-weighted imaging protocols to 2.5 and 3.2 minutes, respectively. The 3D deep learning leverages the homogeneous brain anatomy available in high-field human brain data to enhance image quality, reduce artifacts and noise, and improve spatial resolution to synthetic 1.5-mm isotropic resolution. Our method successfully overcomes low-signal barrier, reconstructing fine anatomical structures that are reproducible within subjects and consistent across two protocols. It enables fast and quality whole-brain MRI at 0.055 tesla, with potential for widespread biomedical applications.

Brain imaging with portable low-field MRI

The advent of portable, low-field MRI (LF-MRI) heralds new opportunities in neuroimaging. Low power requirements and transportability have enabled scanning outside the controlled environment of a conventional MRI suite, enhancing access to neuroimaging for indications that are not well suited to existing technologies. Maximizing the information extracted from the reduced signal-to-noise ratio of LF-MRI is crucial to developing clinically useful diagnostic images. Progress in electromagnetic noise cancellation and machine learning reconstruction algorithms from sparse k-space data as well as new approaches to image enhancement have now enabled these advancements. Coupling technological innovation with bedside imaging creates new prospects in visualizing the healthy brain and detecting acute and chronic pathological changes. Ongoing development of hardware, improvements in pulse sequences and image reconstruction, and validation of clinical utility will continue to accelerate this field. As further innovation occurs, portable LF-MRI will facilitate the democratization of MRI and create new applications not previously feasible with conventional systems.

Synthetic MRI for the quantitative and morphologic assessment of head and neck tumors: a preliminary study

OBJECTIVES

To evaluate the feasibility of synthetic MRI for quantitative and morphologic assessment of head and neck tumors and compare the results with the conventional MRI approach.

METHODS AND MATERIALS

A total of 92 patients with different head and neck tumor histology who underwent conventional and synthetic MRI were retrospectively recruited. The quantitative T1, T2, proton density (PD), and apparent diffusion coefficient (ADC) values of 38 benign and 54 malignant tumors were measured and compared. Diagnostic efficacy for differentiating malignant and benign tumors was evaluated with receiver operating characteristic (ROC) analysis and integrated discrimination index. The image quality of conventional and synthetic T1W/T2W images on a 5-level Likert scale was also compared with Wilcoxon signed rank test.

RESULTS

T1, T2 and ADC values of malignant head and neck tumors were smaller than those of benign tumors (all p < 0.05). T2 and ADC values showed better diagnostic efficacy than T1 for distinguishing malignant tumors from benign tumors (both p < 0.05). Adding the T2 value to ADC increased the area under the curve from 0.839 to 0.886, with an integrated discrimination index of 4.28% (p < 0.05). In terms of overall image quality, synthetic T2W images were comparable to conventional T2W images, while synthetic T1W images were inferior to conventional T1W images.

CONCLUSIONS

Synthetic MRI can facilitate the characterization of head and neck tumors by providing quantitative relaxation parameters and synthetic T2W images. T2 values added to ADC values may further improve the differentiation of tumors.

Intraoperative use of ultra-low-field, portable magnetic resonance imaging - first report

Background

Intraoperative use of portable magnetic resonance imaging (pMRI) has become a valuable tool in a surgeon's arsenal since its inception. It allows intraoperative localization of tumor extent and identification of residual disease, hence maximizing tumor resection. Its utility has been widespread in high-income countries for the past 20 years, but in lower-middle-income countries (LMIC), it is still not widely available due to several reasons, including cost constraints. The use of intraoperative pMRI may be a cost-effective and efficient substitute for conventional MRI machines. The authors present a case where a pMRI device was used intraoperatively in an LMIC setting.

Case Description

The authors performed a microscopic transsphenoidal resection of a sellar lesion with intraoperative imaging using the pMRI system on a 45-year-old man with a nonfunctioning pituitary macroadenoma. Without the need for an MRI suite or other MRI-compatible equipment, the scan was conducted within the confinements of a standard operating room. Low-field MRI showed some residual disease and postsurgical changes, comparable to postoperative high-field MRI.

Conclusion

To the best of our knowledge, our report provides the first documented successful intraoperative transsphenoidal resection of a pituitary adenoma using an ultra-low-field pMRI device. The device can potentially enhance neurosurgical capacity in resource-constrained settings and improve patient outcomes in developing country.

M4Raw: A multi-contrast, multi-repetition, multi-channel MRI k-space dataset for low-field MRI research

Recently, low-field magnetic resonance imaging (MRI) has gained renewed interest to promote MRI accessibility and affordability worldwide. The presented M4Raw dataset aims to facilitate methodology development and reproducible research in this field. The dataset comprises multi-channel brain k-space data collected from 183 healthy volunteers using a 0.3 Tesla whole-body MRI system, and includes T1-weighted, T2-weighted, and fluid attenuated inversion recovery (FLAIR) images with in-plane resolution of ~1.2 mm and through-plane resolution of 5 mm. Importantly, each contrast contains multiple repetitions, which can be used individually or to form multi-repetition averaged images. After excluding motion-corrupted data, the partitioned training and validation subsets contain 1024 and 240 volumes, respectively. To demonstrate the potential utility of this dataset, we trained deep learning models for image denoising and parallel imaging tasks and compared their performance with traditional reconstruction methods. This M4Raw dataset will be valuable for the development of advanced data-driven methods specifically for low-field MRI. It can also serve as a benchmark dataset for general MRI reconstruction algorithms.

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 [...].

Hyperpolarized 129Xe MRI at low field: Current status and future directions

Magnetic Resonance Imaging (MRI) is dictated by the magnetization of the sample, and is thus a low-sensitivity imaging method. Inhalation of hyperpolarized (HP) noble gases, such as helium-3 and xenon-129, is a non-invasive, radiation-risk free imaging technique permitting high resolution imaging of the lungs and pulmonary functions, such as the lung microstructure, diffusion, perfusion, gas exchange, and dynamic ventilation. Instead of increasing the magnetic field strength, the higher spin polarization achievable from this method results in significantly higher net MR signal independent of tissue/water concentration. Moreover, the significantly longer apparent transverse relaxation time T₂* of these HP gases at low magnetic field strengths results in fewer necessary radiofrequency (RF) pulses, permitting larger flip angles; this allows for high-sensitivity imaging of in vivo animal and human lungs at conventionally low (<0.5 T) field strengths and suggests that the low field regime is optimal for pulmonary MRI using hyperpolarized gases. In this review, theory on the common spin-exchange optical-pumping method of hyperpolarization and the field dependence of the MR signal of HP gases are presented, in the context of human lung imaging. The current state-of-the-art is explored, with emphasis on both MRI hardware (low field scanners, RF coils, and polarizers) and image acquisition techniques (pulse sequences) advancements. Common challenges surrounding imaging of HP gases and possible solutions are discussed, and the future of low field hyperpolarized gas MRI is posed as being a clinically-accessible and versatile imaging method, circumventing the siting restrictions of conventional high field scanners and bringing point-of-care pulmonary imaging to global facilities.

Benchmarking the performance of a low-cost magnetic resonance control system at multiple sites in the open MaRCoS community

PURPOSE

To describe the current properties and capabilities of an open-source hardware and software package that is being developed by many sites internationally with the aim of providing an inexpensive yet flexible platform for low-cost MRI.

METHODS

This article describes three different setups from 50 to 360 mT in different settings, all of which used the MaRCoS console for acquiring data, and different types of software interface (custom-built GUI or Pulseq overlay) to acquire it.

RESULTS

Images are presented both from phantoms and in vivo from healthy volunteers to demonstrate the image quality that can be obtained from the MaRCoS hardware/software interfaced to different low-field magnets.

CONCLUSIONS

The results presented here show that a number of different sequences commonly used in the clinic can be programmed into an open-source system relatively quickly and easily, and can produce good quality images even at this early stage of development. Both the hardware and software will continue to develop, and it is an aim of this article to encourage other groups to join this international consortium.

The future of MRI in radiation therapy: Challenges and opportunities for the MR community

Radiation therapy is a major component of cancer treatment pathways worldwide. The main aim of this treatment is to achieve tumor control through the delivery of ionizing radiation while preserving healthy tissues for minimal radiation toxicity. Because radiation therapy relies on accurate localization of the target and surrounding tissues, imaging plays a crucial role throughout the treatment chain. In the treatment planning phase, radiological images are essential for defining target volumes and organs-at-risk, as well as providing elemental composition (e.g., electron density) information for radiation dose calculations. At treatment, onboard imaging informs patient setup and could be used to guide radiation dose placement for sites affected by motion. Imaging is also an important tool for treatment response assessment and treatment plan adaptation. MRI, with its excellent soft tissue contrast and capacity to probe functional tissue properties, holds great untapped potential for transforming treatment paradigms in radiation therapy. The MR in Radiation Therapy ISMRM Study Group was established to provide a forum within the MR community to discuss the unmet needs and fuel opportunities for further advancement of MRI for radiation therapy applications. During the summer of 2021, the study group organized its first virtual workshop, attended by a diverse international group of clinicians, scientists, and clinical physicists, to explore our predictions for the future of MRI in radiation therapy for the next 25 years. This article reviews the main findings from the event and considers the opportunities and challenges of reaching our vision for the future in this expanding field.

Susceptibility-weighted imaging at high-performance 0.5T magnetic resonance imaging system: Protocol considerations and experimental results

The high-performance low-field magnetic resonance imaging (MRI) system, equipped with modern hardware and contemporary imaging capabilities, has garnered interest within the MRI community in recent years. It has also been proven to have unique advantages over high-field MRI in both physical and cost aspects. However, for susceptibility weighted imaging (SWI), the low signal-to-noise ratio and the long echo time inherent at low field hinder the SWI from being applied to clinical applications. This work optimized the imaging protocol to select suitable parameters such as the values of time of echo (TE), repetition time (TR), and the flip angle (FA) of the RF pulse according to the signal simulations for low-field SWI. To improve the signal-to-noise ratio (SNR) performance, averaging multi-echo magnitude images and BM4D phase denoising were proposed. A comparison of the SWI in 0.5T and 1.5T was carried out, demonstrating the capability to identify magnetic susceptibility differences between variable tissues, especially, the blood veins. This would open the possibility to extend SWI applications in the high-performance low field MRI.

An optimized quadrature RF receive coil for very-low-field (50.4 mT) magnetic resonance brain imaging

The radiofrequency (RF) receive coil is a direct probe for magnetic resonance imaging (MRI), and its performance determines the quality of MRI results. The RF coil employed for low-field MRI has a low working frequency, which makes its characteristic different from the RF coil exploited for conventional clinic MRI and may result in a different optimum RF coil configuration. To design and optimize a head RF receive coil for a very-low-field (50.4 mT) MRI system, we investigated the relationship between the structure and performance of the RF coil. Specifically, we focused on a quadrature RF coil consisting of a saddle coil and a modified Helmholtz coil wound around the surface of an elliptical cylinder. First, we evaluated the efficiency and RF magnetic field inhomogeneity of one-loop RF coil and determined the optimum dimension for saddle coil and modified Helmholtz RF coil. Then, we further studied the performance of the optimum-dimension RF coil from the perspective of the number of RF coil loops and revealed that the number of loops of RF coil for very-low-field MRI was a remarkable feature influencing the alternative current (AC) resistance of the RF coil and therefore make the SNR increase first and then decrease with the number of RF coil loops. We finally obtained the optimum number of loops for the saddle coil, modified Helmholtz coil, and fabricated a quadrature RF coil. The performance of the quadrature coil was evaluated through CuSO₄ phantom imaging and in vivo human brain imaging. In phantom imaging, the SNR of quadrature RF coil increased by about 40% compared with that of single-channel RF coil.

Advanced imaging for risk stratification for ventricular arrhythmias and sudden cardiac death

Sudden cardiac death (SCD) is a leading cause of mortality, comprising approximately half of all deaths from cardiovascular disease. In the US, the majority of SCD (85%) occurs in patients with ischemic cardiomyopathy (ICM) and a subset in patients with non-ischemic cardiomyopathy (NICM), who tend to be younger and whose risk of mortality is less clearly delineated than in ischemic cardiomyopathies. The conventional means of SCD risk stratification has been the determination of the ejection fraction (EF), typically via echocardiography, which is currently a means of determining candidacy for primary prevention in the form of implantable cardiac defibrillators (ICDs). Advanced cardiac imaging methods such as cardiac magnetic resonance imaging (CMR), single-photon emission computerized tomography (SPECT) and positron emission tomography (PET), and computed tomography (CT) have emerged as promising and non-invasive means of risk stratification for sudden death through their characterization of the underlying myocardial substrate that predisposes to SCD. Late gadolinium enhancement (LGE) on CMR detects myocardial scar, which can inform ICD decision-making. Overall scar burden, region-specific scar burden, and scar heterogeneity have all been studied in risk stratification. PET and SPECT are nuclear methods that determine myocardial viability and innervation, as well as inflammation. CT can be used for assessment of myocardial fat and its association with reentrant circuits. Emerging methodologies include the development of "virtual hearts" using complex electrophysiologic modeling derived from CMR to attempt to predict arrhythmic susceptibility. Recent developments have paired novel machine learning (ML) algorithms with established imaging techniques to improve predictive performance. The use of advanced imaging to augment risk stratification for sudden death is increasingly well-established and may soon have an expanded role in clinical decision-making. ML could help shift this paradigm further by advancing variable discovery and data analysis.

Portable magnetic resonance imaging of patients indoors, outdoors and at home

Mobile medical imaging devices are invaluable for clinical diagnostic purposes both in and outside healthcare institutions. Among the various imaging modalities, only a few are readily portable. Magnetic resonance imaging (MRI), the gold standard for numerous healthcare conditions, does not traditionally belong to this group. Recently, low-field MRI technology companies have demonstrated the first decisive steps towards portability within medical facilities and vehicles. However, these scanners' weight and dimensions are incompatible with more demanding use cases such as in remote and developing regions, sports facilities and events, medical and military camps, or home healthcare. Here we present in vivo images taken with a light, small footprint, low-field extremity MRI scanner outside the controlled environment provided by medical facilities. To demonstrate the true portability of the system and benchmark its performance in various relevant scenarios, we have acquired images of a volunteer's knee in: (i) an MRI physics laboratory; (ii) an office room; (iii) outside a campus building, connected to a nearby power outlet; (iv) in open air, powered from a small fuel-based generator; and (v) at the volunteer's home. All images have been acquired within clinically viable times, and signal-to-noise ratios and tissue contrast suffice for 2D and 3D reconstructions with diagnostic value. Furthermore, the volunteer carries a fixation metallic implant screwed to the femur, which leads to strong artifacts in standard clinical systems but appears sharp in our low-field acquisitions. Altogether, this work opens a path towards highly accessible MRI under circumstances previously unrealistic.

Mapping the human connectome using diffusion MRI at 300 mT/m gradient strength: Methodological advances and scientific impact

Tremendous efforts have been made in the last decade to advance cutting-edge MRI technology in pursuit of mapping structural connectivity in the living human brain with unprecedented sensitivity and speed. The first Connectom 3T MRI scanner equipped with a 300 mT/m whole-body gradient system was installed at the Massachusetts General Hospital in 2011 and was specifically constructed as part of the Human Connectome Project. Since that time, numerous technological advances have been made to enable the broader use of the Connectom high gradient system for diffusion tractography and tissue microstructure studies and leverage its unique advantages and sensitivity to resolving macroscopic and microscopic structural information in neural tissue for clinical and neuroscientific studies. The goal of this review article is to summarize the technical developments that have emerged in the last decade to support and promote large-scale and scientific studies of the human brain using the Connectom scanner. We provide a brief historical perspective on the development of Connectom gradient technology and the efforts that led to the installation of three other Connectom 3T MRI scanners worldwide - one in the United Kingdom in Cardiff, Wales, another in continental Europe in Leipzig, Germany, and the latest in Asia in Shanghai, China. We summarize the key developments in gradient hardware and image acquisition technology that have formed the backbone of Connectom-related research efforts, including the rich array of high-sensitivity receiver coils, pulse sequences, image artifact correction strategies and data preprocessing methods needed to optimize the quality of high-gradient strength diffusion MRI data for subsequent analyses. Finally, we review the scientific impact of the Connectom MRI scanner, including advances in diffusion tractography, tissue microstructural imaging, ex vivo validation, and clinical investigations that have been enabled by Connectom technology. We conclude with brief insights into the unique value of strong gradients for diffusion MRI and where the field is headed in the coming years.

Bedside monitoring of hypoxic ischemic brain injury using low-field, portable brain magnetic resonance imaging after cardiac arrest

BACKGROUND

Assessment of brain injury severity is critically important after survival from cardiac arrest (CA). Recent advances in low-field MRI technology have permitted the acquisition of clinically useful bedside brain imaging. Our objective was to deploy a novel approach for evaluating brain injury after CA in critically ill patients at high risk for adverse neurological outcome.

METHODS

This retrospective, single center study involved review of all consecutive portable MRIs performed as part of clinical care for CA patients between September 2020 and January 2022. Portable MR images were retrospectively reviewed by a blinded board-certified neuroradiologist (S.P.). Fluid-inversion recovery (FLAIR) signal intensities were measured in select regions of interest.

RESULTS

We performed 22 low-field MRI examinations in 19 patients resuscitated from CA (68.4% male, mean [standard deviation] age, 51.8 [13.1] years). Twelve patients (63.2%) had findings consistent with HIBI on conventional neuroimaging radiology report. Low-field MRI detected findings consistent with HIBI in all of these patients. Low-field MRI was acquired at a median (interquartile range) of 78 (40-136) hours post-arrest. Quantitatively, we measured FLAIR signal intensity in three regions of interest, which were higher amongst patients with confirmed HIBI. Low-field MRI was completed in all patients without disruption of intensive care unit equipment monitoring and no safety events occurred.

CONCLUSION

In a critically ill CA population in whom MR imaging is often not feasible, low-field MRI can be deployed at the bedside to identify HIBI. Low-field MRI provides an opportunity to evaluate the time-dependent nature of MRI findings in CA survivors.

Deep learning-based acceleration of Compressed Sense MR imaging of the ankle

OBJECTIVES

To evaluate a compressed sensing artificial intelligence framework (CSAI) to accelerate MRI acquisition of the ankle.

METHODS

Thirty patients were scanned at 3T. Axial T2-w, coronal T1-w, and coronal/sagittal intermediate-w scans with fat saturation were acquired using compressed sensing only (12:44 min, CS), CSAI with an acceleration factor of 4.6-5.3 (6:45 min, CSAI2x), and CSAI with an acceleration factor of 6.9-7.7 (4:46 min, CSAI3x). Moreover, a high-resolution axial T2-w scan was obtained using CSAI with a similar scan duration compared to CS. Depiction and presence of abnormalities were graded. Signal-to-noise and contrast-to-noise were calculated. Wilcoxon signed-rank test and Cohen's kappa were used to compare CSAI with CS sequences.

RESULTS

The correlation was perfect between CS and CSAI2x (κ = 1.0) and excellent for CS and CSAI3x (κ = 0.86-1.0). No significant differences were found for the depiction of structures between CS and CSAI2x and the same abnormalities were detected in both protocols. For CSAI3x the depiction was graded lower (p ≤ 0.001), though most abnormalities were also detected. For CSAI2x contrast-to-noise fluid/muscle was higher compared to CS (p ≤ 0.05), while no differences were found for other tissues. Signal-to-noise and contrast-to-noise were higher for CSAI3x compared to CS (p ≤ 0.05). The high - resolution axial T2-w sequence specifically improved the depiction of tendons and the tibial nerve (p ≤ 0.005).

CONCLUSIONS

Acquisition times can be reduced by 47% using CSAI compared to CS without decreasing diagnostic image quality. Reducing acquisition times by 63% is feasible but should be reserved for specific patients. The depiction of specific structures is improved using a high-resolution axial T2-w CSAI scan.

KEY POINTS

• Prospective study showed that CSAI enables reduction in acquisition times by 47% without decreasing diagnostic image quality. • Reducing acquisition times by 63% still produces images with an acceptable diagnostic accuracy but should be reserved for specific patients. • CSAI may be implemented to scan at a higher resolution compared to standard CS images without increasing acquisition times.

Sustainable low-field cardiovascular magnetic resonance in changing healthcare systems

Cardiovascular disease continues to be a major burden facing healthcare systems worldwide. In the developed world, cardiovascular magnetic resonance (CMR) is a well-established non-invasive imaging modality in the diagnosis of cardiovascular disease. However, there is significant global inequality in availability and access to CMR due to its high cost, technical demands as well as existing disparities in healthcare and technical infrastructures across high-income and low-income countries. Recent renewed interest in low-field CMR has been spurred by the clinical need to provide sustainable imaging technology capable of yielding diagnosticquality images whilst also being tailored to the local populations and healthcare ecosystems. This review aims to evaluate the technical, practical and cost considerations of low field CMR whilst also exploring the key barriers to implementing sustainable MRI in both the developing and developed world.

Stabilizing deep tomographic reconstruction: Part B. Convergence analysis and adversarial attacks

Due to lack of the kernel awareness, some popular deep image reconstruction networks are unstable. To address this problem, here we introduce the bounded relative error norm (BREN) property, which is a special case of the Lipschitz continuity. Then, we perform a convergence study consisting of two parts: (1) a heuristic analysis on the convergence of the analytic compressed iterative deep (ACID) scheme (with the simplification that the CS module achieves a perfect sparsification), and (2) a mathematically denser analysis (with the two approximations: [1] AT is viewed as an inverse A- 1 in the perspective of an iterative reconstruction procedure and [2] a pseudo-inverse is used for a total variation operator H). Also, we present adversarial attack algorithms to perturb the selected reconstruction networks respectively and, more importantly, to attack the ACID workflow as a whole. Finally, we show the numerical convergence of the ACID iteration in terms of the Lipschitz constant and the local stability against noise.

Simultaneous high-resolution T2 -weighted imaging and quantitative T2 mapping at low magnetic field strengths using a multiple TE and multi-orientation acquisition approach

PURPOSE

Low magnetic field systems provide an important opportunity to expand MRI to new and diverse clinical and research study populations. However, a fundamental limitation of low field strength systems is the reduced SNR compared to 1.5 or 3T, necessitating compromises in spatial resolution and imaging time. Most often, images are acquired with anisotropic voxels with low through-plane resolution, which provide acceptable image quality with reasonable scan times, but can impair visualization of subtle pathology.

METHODS

Here, we describe a super-resolution approach to reconstruct high-resolution isotropic T₂ -weighted images from a series of low-resolution anisotropic images acquired in orthogonal orientations. Furthermore, acquiring each image with an incremented TE allows calculations of quantitative T₂ images without time penalty.

RESULTS

Our approach is demonstrated via phantom and in vivo human brain imaging, with simultaneous 1.5 × 1.5 × 1.5 mm³ T₂ -weighted and quantitative T₂ maps acquired using a clinically feasible approach that combines three acquisition that require approximately 4-min each to collect. Calculated T₂ values agree with reference multiple TE measures with intraclass correlation values of 0.96 and 0.85 in phantom and in vivo measures, respectively, in line with previously reported brain T₂ values at 150 mT, 1.5T, and 3T.

CONCLUSION

Our multi-orientation and multi-TE approach is a time-efficient method for high-resolution T₂ -weighted images for anatomical visualization with simultaneous quantitative T₂ imaging for increased sensitivity to tissue microstructure and chemical composition.

The stability of oncologic MRI radiomic features and the potential role of deep learning: a review

The use of MRI radiomic models for the diagnosis, prognosis and treatment response prediction of tumors has been increasingly reported in literature. However, its widespread adoption in clinics is hampered by issues related to features stability. In the MRI radiomic workflow, the main factors that affect radiomic features computation can be found in the image acquisition and reconstruction phase, in the image pre-processing steps, and in the segmentation of the region of interest on which radiomic indices are extracted. Deep Neural Networks (DNNs), having shown their potentiality in the medical image processing and analysis field, can be seen as an attractive strategy to partially overcome the issues related to radiomic stability and mitigate their impact. In fact, DNN approaches can be prospectively integrated in the MRI radiomic workflow to improve image quality, obtain accurate and reproducible segmentations and generate standardized images. In this review, DNN methods that can be included in the image processing steps of the radiomic workflow are described and discussed, in the light of a detailed analysis of the literature in the context of MRI radiomic reliability.

Convolutional neural network-based reconstruction for acceleration of prostate T2 weighted MR imaging: a retro- and prospective study

OBJECTIVE

The aim of this study was to develop a deep neural network (DNN)-based parallel imaging reconstruction for highly accelerated 2D turbo spin echo (TSE) data in prostate MRI without quality degradation compared to conventional scans.

METHODS

155 participant data were acquired for training and testing. Two DNN models were generated according to the number of acquisitions (NAQ) of input images: DNN-N1 for NAQ = 1 and DNN-N2 for NAQ = 2. In the test data, DNN and TSE images were compared by quantitative error metrics. The visual appropriateness of DNN reconstructions on accelerated scans (DNN-N1 and DNN-N2) and conventional scans (TSE-Conv) was assessed for nine parameters by two radiologists. The lesion detection was evaluated at DNNs and TES-Conv by prostate imaging-reporting and data system.

RESULTS

The scan time was reduced by 71% at NAQ = 1, and 42% at NAQ = 2. Quantitative evaluation demonstrated the better error metrics of DNN images (29-43% lower NRMSE, 4-13% higher structure similarity index, and 2.8-4.8 dB higher peak signal-to-noise ratio; p < 0.001) than TSE images. In the assessment of the visual appropriateness, both radiologists evaluated that DNN-N2 showed better or comparable performance in all parameters compared to TSE-Conv. In the lesion detection, DNN images showed almost perfect agreement (κ > 0.9) scores with TSE-Conv.

CONCLUSIONS

DNN-based reconstruction in highly accelerated prostate TSE imaging showed comparable quality to conventional TSE.

ADVANCES IN KNOWLEDGE

Our framework reduces the scan time by 42% of conventional prostate TSE imaging without sequence modification, revealing great potential for clinical application.

Deep learning-based single image super-resolution for low-field MR brain images

Low-field MRI scanners are significantly less expensive than their high-field counterparts, which gives them the potential to make MRI technology more accessible all around the world. In general, images acquired using low-field MRI scanners tend to be of a relatively low resolution, as signal-to-noise ratios are lower. The aim of this work is to improve the resolution of these images. To this end, we present a deep learning-based approach to transform low-resolution low-field MR images into high-resolution ones. A convolutional neural network was trained to carry out single image super-resolution reconstruction using pairs of noisy low-resolution images and their noise-free high-resolution counterparts, which were obtained from the publicly available NYU fastMRI database. This network was subsequently applied to noisy images acquired using a low-field MRI scanner. The trained convolutional network yielded sharp super-resolution images in which most of the high-frequency components were recovered. In conclusion, we showed that a deep learning-based approach has great potential when it comes to increasing the resolution of low-field MR images.

fastMRI+, Clinical pathology annotations for knee and brain fully sampled magnetic resonance imaging data

Improving speed and image quality of Magnetic Resonance Imaging (MRI) using deep learning reconstruction is an active area of research. The fastMRI dataset contains large volumes of raw MRI data, which has enabled significant advances in this field. While the impact of the fastMRI dataset is unquestioned, the dataset currently lacks clinical expert pathology annotations, critical to addressing clinically relevant reconstruction frameworks and exploring important questions regarding rendering of specific pathology using such novel approaches. This work introduces fastMRI+, which consists of 16154 subspecialist expert bounding box annotations and 13 study-level labels for 22 different pathology categories on the fastMRI knee dataset, and 7570 subspecialist expert bounding box annotations and 643 study-level labels for 30 different pathology categories for the fastMRI brain dataset. The fastMRI+ dataset is open access and aims to support further research and advancement of medical imaging in MRI reconstruction and beyond.

Implicit data crimes: Machine learning bias arising from misuse of public data

SignificancePublic databases are an important resource for machine learning research, but their growing availability sometimes leads to "off-label" usage, where data published for one task are used for another. This work reveals that such off-label usage could lead to biased, overly optimistic results of machine-learning algorithms. The underlying cause is that public data are processed with hidden processing pipelines that alter the data features. Here we study three well-known algorithms developed for image reconstruction from magnetic resonance imaging measurements and show they could produce biased results with up to 48% artificial improvement when applied to public databases. We relate to the publication of such results as implicit "data crimes" to raise community awareness of this growing big data problem.

Highly accelerated 3D MPRAGE using deep neural network-based reconstruction for brain imaging in children and young adults

OBJECTIVES

This study aimed to accelerate the 3D magnetization-prepared rapid gradient-echo (MPRAGE) sequence for brain imaging through the deep neural network (DNN).

METHODS

This retrospective study used the k-space data of 240 scans (160 for the training set, mean ± standard deviation age, 93 ± 80 months, 94 males; 80 for the test set, 106 ± 83 months, 44 males) of conventional MPRAGE (C-MPRAGE) and 102 scans (77 ± 74 months, 52 males) of both C-MPRAGE and accelerated MPRAGE. All scans were acquired with 3T scanners. DNN was developed with simulated-acceleration data generated by under-sampling. Quantitative error metrics were compared between images reconstructed with DNN, GRAPPA, and E-SPIRIT using the paired t-test. Qualitative image quality was compared between C-MPRAGE and accelerated MPRAGE reconstructed with DNN (DNN-MPRAGE) by two readers. Lesions were segmented and the agreement between C-MPRAGE and DNN-MPRAGE was assessed using linear regression.

RESULTS

Accelerated MPRAGE reduced scan times by 38% compared to C-MPRAGE (142 s vs. 320 s). For quantitative error metrics, DNN showed better performance than GRAPPA and E-SPIRIT (p < 0.001). For qualitative evaluation, overall image quality of DNN-MPRAGE was comparable (p > 0.999) or better (p = 0.025) than C-MPRAGE, depending on the reader. Pixelation was reduced in DNN-MPRAGE (p < 0.001). Other qualitative parameters were comparable (p > 0.05). Lesions in C-MPRAGE and DNN-MPRAGE showed good agreement for the dice similarity coefficient (= 0.68) and linear regression (R² = 0.97; p < 0.001).

CONCLUSIONS

DNN-MPRAGE reduced acquisition time by 38% and revealed comparable image quality to C-MPRAGE.

KEY POINTS

• DNN-MPRAGE reduced acquisition times by 38%. • DNN-MPRAGE outperformed conventional reconstruction on accelerated scans (SSIM of DNN-MPRAGE = 0.96, GRAPPA = 0.43, E-SPIRIT = 0.88; p < 0.001). • Compared to C-MPRAGE scans, DNN-MPRAGE showed improved mean scores for overall image quality (2.46 vs. 2.52; p < 0.001) or comparable perceived SNR (2.56 vs. 2.58; p = 0.08).

External Dynamic InTerference Estimation and Removal (EDITER) for low field MRI

PURPOSE

Point-of-care MRI requires operation outside of Faraday shielded rooms normally used to block image-degrading electromagnetic interference (EMI). To address this, we introduce the EDITER method (External Dynamic InTerference Estimation and Removal), an external sensor-based method to retrospectively remove image artifacts from time-varying external interference sources.

THEORY AND METHODS

The method acquires data from multiple EMI detectors (tuned receive coils as well as untuned electrodes placed on the body) simultaneously with the primary MR coil during and between image data acquisition. We calculate impulse response functions dynamically that map the data from the detectors to the time varying artifacts then remove the transformed detected EMI from the MR data. Performance of the EDITER algorithm was assessed in phantom and in vivo imaging experiments in an 80 mT portable brain MRI in a controlled EMI environment and with an open 47.5 mT MRI scanner in an uncontrolled EMI setting.

RESULTS

In the controlled setting, the effectiveness of the EDITER technique was demonstrated for specific types of introduced EMI sources with up to a 97% reduction of structured EMI and up to 76% reduction of broadband EMI in phantom experiments. In the uncontrolled EMI experiments, we demonstrate EMI reductions of up to 99% using an electrode and pick-up coil in vivo. We demonstrate up to a nine-fold improvement in image SNR with the method.

CONCLUSION

The EDITER technique is a flexible and robust method to improve image quality in portable MRI systems with minimal passive shielding and could reduce the reliance of MRI on shielded rooms and allow for truly portable MRI.

Rapid calculation of static magnetic field perturbation generated by magnetized objects in arbitrary orientations

PURPOSE

Most previous work on the calculation of susceptibility-induced static magnetic field (B₀ ) inhomogeneity has considered strictly unidirectional magnetic fields. Here, we present the theory and implementation of a computational method to rapidly calculate static magnetic field vectors produced by an arbitrary distribution of voxelated magnetization vectors.

THEORY AND METHODS

Two existing B₀ calculation methods were systematically extended to include arbitrary orientations of the magnetization and the magnetic field; they are (1) Fourier-domain convolution with k-space-discretized (KD) dipolar field, and (2) generalized susceptibility voxel convolution (gSVC). The methods were tested on an analytical ellipsoid model and a tilted human head model, as well as against experimentally measured B₀ fields induced by a stainless-steel implant located in an inhomogeneous region of a clinical 3T MRI magnet.

RESULTS

Both methods were capable of correctly calculating B₀ fields inside a magnetized ellipsoid in all tested orientations. The KD method generally required a larger grid and longer computation time to achieve accuracy comparable to gSVC. Measured B₀ fields due to the implant showed a good match with the gSVC-calculated fields that accounted for the spatial variation of the applied magnetic field including the radial components.

CONCLUSION

Our method can provide a reliable and efficient computational tool to calculate B₀ perturbation by magnetized objects under a variety of circumstances, including those with inhomogeneous magnetizing fields, anisotropic susceptibility, and a rotated coordinate system.

Partial Fourier reconstruction of complex MR images using complex-valued convolutional neural networks

PURPOSE

To provide a complex-valued deep learning approach for partial Fourier (PF) reconstruction of complex MR images.

METHODS

Conventional PF reconstruction methods, such as projection onto convex sets (POCS), uses low-resolution image phase information from the central symmetrically sampled k-space for image reconstruction. However, this smooth phase constraint undermines the phase estimation accuracy in presence of rapid local phase variations, causing image artifacts and limiting the extent of PF reconstruction. Using both magnitude and phase characteristics in big complex image datasets, we propose a complex-valued deep learning approach with an unrolled network architecture for PF reconstruction that iteratively reconstructs PF sampled data and enforces data consistency. We evaluate our approach for reconstructing both spin-echo and gradient-echo data.

RESULTS

The proposed method outperformed the iterative POCS PF reconstruction method. It produced better artifact suppression and recovery of both image magnitude and phase details in presence of local phase changes. No noise amplification was observed even for highly PF reconstruction. Moreover, the network trained on axial brain data could reconstruct sagittal and coronal brain and knee data. This method could be extended to 2D PF reconstruction and joint multi-slice PF reconstruction.

CONCLUSION

Our proposed method can effectively reconstruct MR data even at low PF fractions, yielding high-fidelity magnitude and phase images. It presents a valuable alternative to conventional PF reconstruction, especially for phase-sensitive 2D or 3D MRI applications.

Accessible pediatric neuroimaging using a low field strength MRI scanner

Magnetic resonance imaging (MRI) has played an increasingly relevant role in understanding infant, child, and adolescent neurodevelopment, providing new insight into developmental patterns in neurotypical development, as well as those associated with potential psychopathology, learning disorders, and other neurological conditions. In addition, studies have shown the impact of a child's physical and psychosocial environment on developing brain structure and function. A rate-limiting complication in these studies, however, is the high cost and infrastructural requirements of modern MRI systems. High costs mean many neuroimaging studies typically include fewer than 100 individuals and are performed predominately in high resource hospitals and university settings within high income countries (HICs). As a result, our knowledge of brain development, particularly in children who live in lower and middle income countries (LMICs) is relatively limited. Low field systems, with magnetic fields less than 100mT offer the promise of lower scanning costs and wide-spread global adoption, but routine low field pediatric neuroimaging has yet to be demonstrated. Here we present the first pediatric MRI data collected on a low cost and assessable 64mT scanner in children 6 weeks to 16 years of age and replicate brain volumes estimates and developmental trajectories derived from 3T MRI data. While preliminary, these results illustrate the potential of low field imaging as a viable complement to more conventional high field imaging systems, and one that may further enhance our knowledge of neurodevelopment in LMICs where malnutrition, psychosocial adversities, and other environmental exposures may profoundly affect brain maturation.