Overview of quantitative susceptibility mapping using deep learning: Current status, challenges and opportunities

Quantitative susceptibility mapping via deep neural networks with iterative reverse concatenations and recurrent modules

BACKGROUND

Quantitative susceptibility mapping (QSM) is a post-processing magnetic resonance imaging (MRI) technique that extracts the distribution of tissue susceptibilities and holds significant promise in the study of neurological diseases. However, the ill-conditioned nature of dipole inversion often results in noise and artifacts during QSM reconstruction from the tissue field. Deep learning methods have shown great potential in addressing these issues; however, most existing approaches rely on basic U-net structures, leading to limited performances and reconstruction artifacts sometimes.

PURPOSE

This study aims to develop a novel deep learning-based method, IR2QSM, for improving QSM reconstruction accuracy while mitigating noise and artifacts by leveraging a unique network architecture that enhances latent feature utilization.

METHODS

IR2QSM, an advanced U-net architecture featuring four iterations of reverse concatenations and middle recurrent modules, was proposed to optimize feature fusion and improve QSM accuracy, and comparative experiments based on both simulated and in vivo datasets were carried out to compare IR2QSM with two traditional iterative methods (iLSQR, MEDI) and four recently proposed deep learning methods (U-net, xQSM, LPCNN, and MoDL-QSM).

RESULTS

In this work, IR2QSM outperformed all other methods in reducing artifacts and noise in QSM images. It achieved on average the lowest XSIM (84.81%) in simulations, showing improvements of 12.80%, 12.68%, 18.66%, 10.49%, 25.57%, and 19.78% over iLSQR, MEDI, U-net, xQSM, LPCNN, and MoDL-QSM, respectively, and yielded results with the least artifacts on the in vivo data and present the most visually appealing results. In the meantime, it successfully alleviated the over-smoothing and susceptibility underestimation in LPCNN results.

CONCLUSION

Overall, the proposed IR2QSM showed superior QSM results compared to iterative and deep learning-based methods, offering a more accurate QSM solution for clinical applications.

In-vivo high-resolution χ-separation at 7T

A recently introduced quantitative susceptibility mapping (QSM) technique, χ-separation, offers the capability to separate paramagnetic (χpara) and diamagnetic (χdia) susceptibility distribution within the brain. In-vivo high-resolution mapping of iron and myelin distribution, estimated by χ-separation, could provide a deeper understanding of brain substructures, assisting the investigation of their functions and alterations. This can be achieved using 7T MRI, which benefits from a high signal-to-noise ratio and susceptibility effects. However, applying χ-separation at 7T presents difficulties due to the requirement of an R2 map, coupled with issues such as high specific absorption rate (SAR), large B1 transmit field inhomogeneities, and prolonged scan time. To address these challenges, we developed a novel deep neural network, R2PRIMEnet7T, designed to convert a 7T R2* map into a 3T R2' map. Building on this development, we present a new pipeline for χ-separation at 7T, enabling us to generate high-resolution χ-separation maps from multi-echo gradient-echo data. The proposed method is compared with alternative pipelines, such as an end-to-end network and linearly-scaled R2', and is validated against χ-separation maps at 3T, demonstrating its accuracy. The 7T χ-separation maps generated by the proposed method exhibit similar contrasts to those from 3T, while 7T high-resolution maps offer enhanced clarity and detail. Quantitative analysis confirms that the proposed method surpasses the alternative pipelines. The proposed method results well delineate the detailed brain structures associated with iron and myelin. This new pipeline holds promise for analyzing iron and myelin concentration changes in various neurodegenerative diseases through precise structural examination.

Comparing repeatability metrics for quantitative susceptibility mapping in the head and neck

OBJECTIVE

Quantitative susceptibility mapping (QSM) is a technique that has been demonstrated to be highly repeatable in the brain. As QSM is applied to other parts of the body, it is necessary to investigate metrics for quantifying repeatability, to enable optimization of repeatable QSM reconstruction pipelines beyond the brain.

MATERIALS AND METHODS

MRI data were acquired in the head and neck (HN) region in ten healthy volunteers, who underwent six acquisitions across two sessions. QSMs were reconstructed using six representative state-of-the-art techniques. Repeatability of the susceptibility values was compared using voxel-wise metrics (normalized root mean squared error and XSIM) and ROI-based metrics (within-subject and between-subject standard deviation, coefficient of variation (CV), intraclass correlation coefficient (ICC)).

RESULTS

Both within-subject and between-subject variations were smaller than the variation between QSM dipole inversion methods, in most ROIs. autoNDI produced the most repeatable susceptibility values, with ICC > 0.75 in three of six HN ROIs with an average ICC of 0.66 across all ROIs. Joint consideration of standard deviation and ICC offered the best metric of repeatability for comparisons between QSM methods, given typical distributions of positive and negative QSM values.

DISCUSSION

Repeatability of QSM in the HN region is highly dependent on the dipole inversion method chosen, but the most repeatable methods (autoNDI, QSMnet, TFI) are only moderately repeatable in most HN ROIs.

χ-sepnet: Deep Neural Network for Magnetic Susceptibility Source Separation

Magnetic susceptibility source separation (χ-separation), an advanced quantitative susceptibility mapping (QSM) method, enables the separate estimation of paramagnetic and diamagnetic susceptibility source distributions in the brain. Similar to QSM, it requires solving the ill-conditioned problem of dipole inversion, suffering from so-called streaking artifacts. Additionally, the method utilizes reversible transverse relaxation (R 2 ' = R 2 * - R 2 $$ {R}_2^{\prime }={R}_2^{\ast }-{R}_2 $$ ) to complement frequency shift information for estimating susceptibility source concentrations, requiring time-consuming data acquisition forR 2 $$ {R}_2 $$ (e.g., multi-echo spin-echo) in addition to multi-echo GRE data forR 2 * $$ {R}_2^{\ast } $$ . To address these challenges, we develop a new deep learning network, χ-sepnet, and propose two deep learning-based susceptibility source separation pipelines, χ-sepnet-R 2 ' $$ {R}_2^{\prime } $$ for inputs with multi-echo GRE and multi-echo spin-echo (or turbo spin-echo) and χ-sepnet-R 2 * $$ {R}_2^{\ast } $$ for input with multi-echo GRE only. The neural network is trained using multiple head orientation data that provide streaking artifact-free labels, generating high-quality χ-separation maps. The evaluation of the pipelines encompasses both qualitative and quantitative assessments in healthy subjects, and visual inspection of lesion characteristics in multiple sclerosis patients. The susceptibility source-separated maps of the proposed pipelines delineate detailed brain structures with substantially reduced artifacts compared to those from the conventional regularization-based reconstruction methods. In quantitative analysis, χ-sepnet-R 2 ' $$ {R}_2^{\prime } $$ achieves the best outcomes followed by χ-sepnet-R 2 * $$ {R}_2^{\ast } $$ , outperforming the conventional methods. When the lesions of multiple sclerosis patients are classified into subtypes, most lesions are identified as the same subtype in the maps from χ-sepnet-R 2 ' $$ {R}_2^{\prime } $$ and χ-sepnet-R 2 * $$ {R}_2^{\ast } $$ (paramagnetic susceptibility: 99.6% and diamagnetic susceptibility: 98.4%; both out of 250 lesions). The χ-sepnet-R 2 * $$ {R}_2^{\ast } $$ pipeline, which only requires multi-echo GRE data, has demonstrated its potential to offer broad clinical and scientific applications, although further evaluations for various diseases and pathological conditions are necessary.

XSIM: A structural similarity index measure optimized for MRI QSM

PURPOSE

The structural similarity index measure (SSIM) has become a popular quality metric to evaluate QSM in a way that is closer to human perception than RMS error (RMSE). However, SSIM may overpenalize errors in diamagnetic tissues and underpenalize them in paramagnetic tissues, resulting in biasing. In addition, extreme artifacts may compress the dynamic range, resulting in unrealistically high SSIM scores (hacking). To overcome biasing and hacking, we propose XSIM: SSIM implemented in the native QSM range, and with internal parameters optimized for QSM.

METHODS

We used forward simulations from a COSMOS ground-truth brain susceptibility map included in the 2016 QSM Reconstruction Challenge to investigate the effect of QSM reconstruction errors on the SSIM, XSIM, and RMSE metrics. We also used these metrics to optimize QSM reconstructions of the in vivo challenge data set. We repeated this experiment with the QSM abdominal phantom. To validate the use of XSIM instead of SSIM for QSM quality assessment across a range of different reconstruction techniques/algorithms, we analyzed the reconstructions submitted to the 2019 QSM Reconstruction Challenge 2.0.

RESULTS

Our experiments confirmed the biasing and hacking effects on the SSIM metric applied to QSM. The XSIM metric was robust to those effects, penalizing the presence of streaking artifacts and reconstruction errors. Using XSIM to optimize QSM reconstruction regularization weights returned less overregularization than SSIM and RMSE.

CONCLUSION

XSIM is recommended over traditional SSIM to evaluate QSM reconstructions against a known ground truth, as it avoids biasing and hacking effects and provides a larger dynamic range of scores.

Acupuncture treatment of restless legs syndrome: a randomized clinical controlled study protocol based on PET-CT and fMRI

Introduction

Restless legs syndrome (RLS) is a sensorimotor disorder of the nervous system that is mainly characterized by nighttime leg discomfort and can be accompanied by significant anxiety, depression, and other mood disorders. RLS seriously affects the quality of life. Clinical studies have confirmed that acupuncture can alleviate the clinical symptoms of RLS. This randomized controlled trial (RCT) aims to investigate the efficacy of acupuncture in the treatment of RLS and further explore the central response mechanism of acupuncture in the treatment of RLS.

Methods and analysis

In this RCT, a total of 124 eligible patients in Shanghai will be randomly assigned to one of the following two groups: treatment group (acupuncture) and control group (sham acupuncture). Treatment will be given three times per week for 4 consecutive weeks. The primary outcome is the International Restless Legs severity rating scale (IRLSS). The secondary outcomes are the RLS-Quality of Life (RLSQoL), the Insomnia Severity Index (ISI), Pittsburgh Sleep Quality Index (PSQI), the Hamilton Depression Scale (HAMD), and the Hamilton Anxiety Scale (HAMA). The objective evaluation tools will be polysomnography, positron emission tomography-computed tomography (PET-CT), and functional magnetic resonance imaging (fMRI) of the brain. All adverse effects will be assessed by the Treatment Emergent Symptom Scale. Outcomes will be evaluated at baseline (1 week before the first intervention), during the intervention (the second week of the intervention), after the intervention (at the end of the intervention), at 1-month follow-up, and at 3-month follow-up.

Ethics and dissemination

The trial has been approved by the Ethics Committee of Yueyang Hospital of Integrated Traditional Chinese and Western Medicine (no. 2022-061). Written informed consent will be obtained from all participants. The results of this study will be published in peer-reviewed journals or presented at academic conferences.

Clinical trial registration

https://www.chictr.org.cn/, identifier ChiCTR2000037287.

Chronic active lesions in multiple sclerosis: classification, terminology, and clinical significance

In multiple sclerosis (MS), increasing disability is considered to occur due to persistent, chronic inflammation trapped within the central nervous system (CNS). This condition, known as smoldering neuroinflammation, is present across the clinical spectrum of MS and is currently understood to be relatively resistant to treatment with existing disease-modifying therapies. Chronic active white matter lesions represent a key component of smoldering neuroinflammation. Initially characterized in autopsy specimens, multiple approaches to visualize chronic active lesions (CALs) in vivo using advanced neuroimaging techniques and postprocessing methods are rapidly emerging. Among these in vivo imaging correlates of CALs, paramagnetic rim lesions (PRLs) are defined by the presence of a perilesional rim formed by iron-laden microglia and macrophages, whereas slowly expanding lesions are identified based on linear, concentric lesion expansion over time. In recent years, several longitudinal studies have linked the occurrence of in vivo detected CALs to a more aggressive disease course. PRLs are highly specific to MS and therefore have recently been incorporated into the MS diagnostic criteria. They also have prognostic potential as biomarkers to identify patients at risk of early and severe disease progression. These developments could significantly affect MS care and the evaluation of new treatments. This review describes the latest knowledge on CAL biology and imaging and the relevance of CALs to the natural history of MS. In addition, we outline considerations for current and future in vivo biomarkers of CALs, emphasizing the need for validation, standardization, and automation in their assessment.

Enhanced Reader Confidence and Differentiation of Calcification from Cerebral Microbleed Diagnosis Using QSM Relative to SWI

PURPOSE

Accurate detection of cerebral microbleeds (CMBs) is important for detection of multiple conditions. However, CMBs can be challenging to identify on MR images, especially for distinguishing CMBs from the mimic of calcification. We performed a comparative reader study to assess the diagnostic performance of two primary MR sequences for differentiating CMBs from calcification.

METHODS

Under IRB approved exempt retrospective protocol, 49 adult patients with identifiable intracranial hemorrhage who underwent multi-echo 3D Gradient Recall Echo (GRE) using 3T MRI were non-sequentially recruited under a retrospective IRB approved protocol. Multi-echo complex total field inversion quantitative susceptibility mapping (QSM) and susceptibility weighted imaging/phase (SWI/P) images were generated for all patients. 53 lesion ROIs were identified and classified on provided images by an expert panel of three neuroradiologists as either: CMB, Blood, Calcification, or Other. Three additional neuroradiologists subsequently reviewed the same SWI/P and QSM images in independent sessions and designated lesions as either blood and/or calcification using a 5-point Likert scale. Statistical analyses, on lesion classification and reader diagnostic accuracy, reader confidence-level, reader agreement-level, and the predictability of mean susceptibility values between SWI/P and QSM were conducted with logistic regression and calculation of Fleiss' κ, Kendall's w, Krippendorff's α.

RESULTS

Across all qualitative assessment and quantitative metrics measured (simple accuracy, confidence as degree of ground truth alignment, and inter-rater agreement) QSM outperformed SWI/P. Additionally, logistic regression of average QSM voxel susceptibility achieved near-perfect separation in differentiating between CMB and calcification in the limited number of CMB/Calcification ROIs, indicating a high predictability.

CONCLUSION

Our study demonstrates that QSM offers improved detectability and classification of CMBs compared to the conventionally utilized SWI/P sequence. In addition, QSM simplifies the interpretation workflow by reducing the number of requisite images compared with the conventional counterpart, with improved diagnostic confidence.

ProxiMO: Proximal Multi-operator Networks for Quantitative Susceptibility Mapping

Quantitative Susceptibility Mapping (QSM) is a technique that derives tissue magnetic susceptibility distributions from phase measurements obtained through Magnetic Resonance (MR) imaging. This involves solving an ill-posed dipole inversion problem, however, and thus time-consuming and cumbersome data acquisition from several distinct head orientations becomes necessary to obtain an accurate solution. Most recent (supervised) deep learning methods for single-phase QSM require training data obtained via multiple orientations. In this work, we present an alternative unsupervised learning approach that can efficiently train on single-orientation measurement data alone, named ProxiMO (Proximal Multi-Operator), combining Learned Proximal Convolutional Neural Networks (LP-CNN) with multi-operator imaging (MOI). This integration enables LP-CNN training for QSM on single-phase data without ground truth reconstructions. We further introduce a semi-supervised variant, which further boosts the reconstruction performance, compared to the traditional supervised fashions. Extensive experiments on multicenter datasets illustrate the advantage of unsupervised training and the superiority of the proposed approach for QSM reconstruction. Code is available at https://github.com/shmuelor/ProxiMO.

Simultaneous multislice cardiac multimapping based on locally low-rank and sparsity constraints

BACKGROUND

Although quantitative myocardial T1 and T2 mappings are clinically used to evaluate myocardial diseases, their application needs a minimum of six breath-holds to cover three short-axis slices. The purpose of this work is to simultaneously quantify multislice myocardial T1 and T2 across three short-axis slices in one breath-hold by combining simultaneous multislice (SMS) with multimapping.

METHODS

An SMS-Multimapping sequence with multiband radiofrequency (RF) excitations and Cartesian fast low-angle shot readouts was developed for data acquisition. When 3 slices are simultaneously acquired, the acceleration rate is around 12-fold, causing a highly ill-conditioned reconstruction problem. To mitigate image artifacts and noise caused by the ill-conditioning, a reconstruction algorithm based on locally low-rank and sparsity (LLRS) constraints was developed. Validation was performed in phantoms and in vivo imaging, with 20 healthy subjects and 4 patients, regarding regional mean, precision, and scan-rescan reproducibility.

RESULTS

The phantom imaging shows that SMS-Multimapping with locally low-rank (LLRS) accurately reconstructed multislice T1 and T2 maps despite a six-fold acceleration of scan time. Healthy subject imaging shows that the proposed LLRS algorithm substantially improved image quality relative to split slice-generalized autocalibrating partially parallel acquisition. Compared with modified look-locker inversion recovery (MOLLI), SMS-Multimapping exhibited higher T1 mean (1118 ± 43 ms vs 1190 ± 49 ms, P < 0.01), lower precision (67 ± 17 ms vs 90 ± 17 ms, P < 0.01), and acceptable scan-rescan reproducibility measured by 2 scans 10-min apart (bias = 1.4 ms for MOLLI and 9.0 ms for SMS-Multimapping). Compared with balanced steady-state free precession (bSSFP) T2 mapping, SMS-Multimapping exhibited similar T2 mean (43.5 ± 3.3 ms vs 43.0 ± 3.5 ms, P = 0.64), similar precision (4.9 ± 2.1 ms vs 5.1 ± 1.0 ms, P = 0.93), and acceptable scan-rescan reproducibility (bias = 0.13 ms for bSSFP T2 mapping and 0.55 ms for SMS-Multimapping). In patients, SMS-Multimapping clearly showed the abnormality in a similar fashion as the reference methods despite using only one breath-hold.

CONCLUSION

SMS-Multimapping with the proposed LLRS reconstruction can measure multislice T1 and T2 maps in one breath-hold with good accuracy, reasonable precision, and acceptable reproducibility, achieving a six-fold reduction of scan time and an improvement of patient comfort.

Cerebral small vessel injury in mice with damage to ACE2-expressing cerebral vascular endothelial cells and post COVID-19 patients

INTRODUCTION

The angiotensin-converting enzyme 2 (ACE2), which is expressed in cerebral vascular endothelial cells (CVECs), has been currently identified as a functional receptor for SARS-CoV-2.

METHODS

We specifically induced injury to ACE2-expressing CVECs in mice and evaluated the effects of such targeted damage through magnetic resonance imaging (MRI) and cognitive behavioral tests. In parallel, we recruited a single-center cohort of COVID-19 survivors and further assessed their brain microvascular injury based on cognition and emotional scales, cranial MRI scans, and blood proteomic measurements.

RESULTS

Here, we show an array of pathological and behavioral alterations characteristic of cerebral small vessel disease (CSVD) in mice that targeted damage to ACE2-expressing CVECs, and COVID-19 survivors. These CSVD-like manifestations persist for at least 7 months post-recovery from COVID-19.

DISCUSSION

Our findings suggest that SARS-CoV-2 may induce cerebral small vessel damage with persistent sequelae, underscoring the imperative for heightened clinical vigilance in mitigating or treating SARS-CoV-2-mediated cerebral endothelial injury throughout infection and convalescence.

HIGHLIGHTS

Cerebral small vessel disease-associated changes were observed after targeted damage to angiotensin-converting enzyme 2-expressing cerebral vascular endothelial cells. SARS-CoV-2 may induce cerebral small vessel damage with persistent sequelae. Clinical vigilance is needed in preventing SARS-CoV-2-induced cerebral endothelial damage during infection and recovery.

DF-QSM: Data Fidelity based Hybrid Approach for Improved Quantitative Susceptibility Mapping of the Brain

Quantitative Susceptibility Mapping (QSM) is an advanced magnetic resonance imaging (MRI) technique to quantify the magnetic susceptibility of the tissue under investigation. Deep learning methods have shown promising results in deconvolving the susceptibility distribution from the measured local field obtained from the MR phase. Although existing deep learning based QSM methods can produce high-quality reconstruction, they are highly biased toward training data distribution with less scope for generalizability. This work proposes a hybrid two-step reconstruction approach to improve deep learning based QSM reconstruction. The susceptibility map prediction obtained from the deep learning methods has been refined in the framework developed in this work to ensure consistency with the measured local field. The developed method was validated on existing deep learning and model-based deep learning methods for susceptibility mapping of the brain. The developed method resulted in improved reconstruction for MRI volumes obtained with different acquisition settings, including deep learning models trained on constrained (limited) data settings.

Recent Advances in MR Imaging-based Quantification of Brain Oxygen Metabolism

The metabolic rate of oxygen (MRO2) is fundamental to tissue metabolism. Determination of MRO2 demands knowledge of the arterio-venous difference in hemoglobin-bound oxygen concentration, typically expressed as oxygen extraction fraction (OEF), and blood flow rate (BFR). MRI is uniquely suited for measurement of both these quantities, yielding MRO2 in absolute physiologic units of µmol O2 min-1/100 g tissue. Two approaches are discussed, both relying on hemoglobin magnetism. Emphasis will be on cerebral oxygen metabolism expressed in terms of the cerebral MRO2 (CMRO2), but translation of the relevant technologies to other organs, including kidney and placenta will be touched upon as well. The first class of methods exploits the blood's bulk magnetic susceptibility, which can be derived from field maps. The second is based on measurement of blood water T2, which is modulated by diffusion and exchange in the local-induced fields within and surrounding erythrocytes. Some whole-organ methods achieve temporal resolution adequate to permit time-series studies of brain energetics, for instance, during sleep in the scanner with concurrent electroencephalogram (EEG) sleep stage monitoring. Conversely, trading temporal for spatial resolution has led to techniques for spatially resolved approaches based on quantitative blood oxygen level dependent (BOLD) or calibrated BOLD models, allowing regional assessment of vascular-metabolic parameters, both also exploiting deoxyhemoglobin paramagnetism like their whole-organ counterparts.

Value of Quantitative Susceptibility Mapping in Clinical Neuroradiology

Quantitative susceptibility mapping (QSM) is a unique technique for providing quantitative information on tissue magnetic susceptibility using phase image data. QSM can provide valuable information regarding physiological and pathological processes such as iron deposition, hemorrhage, calcification, and myelin. QSM has been considered for use as an imaging biomarker to investigate physiological status and pathological changes. Although various studies have investigated the clinical applications of QSM, particularly regarding the use of QSM in clinical practice, have not been examined well. This review provides on an overview of the basics of QSM and its clinical applications in neuroradiology. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY: Stage 2.

Plug-and-Play latent feature editing for orientation-adaptive quantitative susceptibility mapping neural networks

Quantitative susceptibility mapping (QSM) is a post-processing technique for deriving tissue magnetic susceptibility distribution from MRI phase measurements. Deep learning (DL) algorithms hold great potential for solving the ill-posed QSM reconstruction problem. However, a significant challenge facing current DL-QSM approaches is their limited adaptability to magnetic dipole field orientation variations during training and testing. In this work, we propose a novel Orientation-Adaptive Latent Feature Editing (OA-LFE) module to learn the encoding of acquisition orientation vectors and seamlessly integrate them into the latent features of deep networks. Importantly, it can be directly Plug-and-Play (PnP) into various existing DL-QSM architectures, enabling reconstructions of QSM from arbitrary magnetic dipole orientations. Its effectiveness is demonstrated by combining the OA-LFE module into our previously proposed phase-to-susceptibility single-step instant QSM (iQSM) network, which was initially tailored for pure-axial acquisitions. The proposed OA-LFE-empowered iQSM, which we refer to as iQSM+, is trained in a simulated-supervised manner on a specially-designed simulation brain dataset. Comprehensive experiments are conducted on simulated and in vivo human brain datasets, encompassing subjects ranging from healthy individuals to those with pathological conditions. These experiments involve various MRI platforms (3T and 7T) and aim to compare our proposed iQSM+ against several established QSM reconstruction frameworks, including the original iQSM. The iQSM+ yields QSM images with significantly improved accuracies and mitigates artifacts, surpassing other state-of-the-art DL-QSM algorithms. The PnP OA-LFE module's versatility was further demonstrated by its successful application to xQSM, a distinct DL-QSM network for dipole inversion. In conclusion, this work introduces a new DL paradigm, allowing researchers to develop innovative QSM methods without requiring a complete overhaul of their existing architectures.

Recommended implementation of quantitative susceptibility mapping for clinical research in the brain: A consensus of the ISMRM electro-magnetic tissue properties study group

This article provides recommendations for implementing QSM for clinical brain research. It is a consensus of the International Society of Magnetic Resonance in Medicine, Electro-Magnetic Tissue Properties Study Group. While QSM technical development continues to advance rapidly, the current QSM methods have been demonstrated to be repeatable and reproducible for generating quantitative tissue magnetic susceptibility maps in the brain. However, the many QSM approaches available have generated a need in the neuroimaging community for guidelines on implementation. This article outlines considerations and implementation recommendations for QSM data acquisition, processing, analysis, and publication. We recommend that data be acquired using a monopolar 3D multi-echo gradient echo (GRE) sequence and that phase images be saved and exported in Digital Imaging and Communications in Medicine (DICOM) format and unwrapped using an exact unwrapping approach. Multi-echo images should be combined before background field removal, and a brain mask created using a brain extraction tool with the incorporation of phase-quality-based masking. Background fields within the brain mask should be removed using a technique based on SHARP or PDF, and the optimization approach to dipole inversion should be employed with a sparsity-based regularization. Susceptibility values should be measured relative to a specified reference, including the common reference region of the whole brain as a region of interest in the analysis. The minimum acquisition and processing details required when reporting QSM results are also provided. These recommendations should facilitate clinical QSM research and promote harmonized data acquisition, analysis, and reporting.

Incorporating a-priori information in deep learning models for quantitative susceptibility mapping via adaptive convolution

Quantitative susceptibility mapping (QSM) has attracted considerable interest for tissue characterization (e.g., iron and calcium accumulation, myelination, venous vasculature) in the human brain and relies on extensive data processing of gradient-echo MRI phase images. While deep learning-based field-to-susceptibility inversion has shown great potential, the acquisition parameters applied in clinical settings such as image resolution or image orientation with respect to the magnetic field have not been fully accounted for. Furthermore, the lack of comprehensive training data covering a wide range of acquisition parameters further limits the current QSM deep learning approaches. Here, we propose the integration of a priori information of imaging parameters into convolutional neural networks with our approach, adaptive convolution, that learns the mapping between the additional presented information (acquisition parameters) and the changes in the phase images associated with these varying acquisition parameters. By associating a-priori information with the network parameters itself, the optimal set of convolution weights is selected based on data-specific attributes, leading to generalizability towards changes in acquisition parameters. Moreover, we demonstrate the feasibility of pre-training on synthetic data and transfer learning to clinical brain data to achieve substantial improvements in the computation of susceptibility maps. The adaptive convolution 3D U-Net demonstrated generalizability in acquisition parameters on synthetic and in-vivo data and outperformed models lacking adaptive convolution or transfer learning. Further experiments demonstrate the impact of the side information on the adaptive model and assessed susceptibility map computation on simulated pathologic data sets and measured phase data.

A spatially adaptive regularization based three-dimensional reconstruction network for quantitative susceptibility mapping

Objective.Quantitative susceptibility mapping (QSM) is a new imaging technique for non-invasive characterization of the composition and microstructure ofin vivotissues, and it can be reconstructed from local field measurements by solving an ill-posed inverse problem. Even for deep learning networks, it is not an easy task to establish an accurate quantitative mapping between two physical quantities of different units, i.e. field shift in Hz and susceptibility value in ppm for QSM.Approach. In this paper, we propose a spatially adaptive regularization based three-dimensional reconstruction network SAQSM. A spatially adaptive module is specially designed and a set of them at different resolutions are inserted into the network decoder, playing a role of cross-modality based regularization constraint. Therefore, the exact information of both field and magnitude data is exploited to adjust the scale and shift of feature maps, and thus any information loss or deviation occurred in previous layers could be effectively corrected. The network encoding has a dynamic perceptual initialization, which enables the network to overcome receptive field intervals and also strengthens its ability to detect features of various sizes.Main results. Experimental results on the brain data of healthy volunteers, clinical hemorrhage and simulated phantom with calcification demonstrate that SAQSM can achieve more accurate reconstruction with less susceptibility artifacts, while perform well on the stability and generalization even for severe lesion areas.Significance. This proposed framework may provide a valuable paradigm to quantitative mapping or multimodal reconstruction.

Characterization of quantitative susceptibility mapping in the left ventricular myocardium

BACKGROUND

Myocardial quantitative susceptibility mapping (QSM) may offer better specificity to iron than conventional T2* imaging in the assessment of cardiac diseases, including intra-myocardial hemorrhage. However, the precision and repeatability of cardiac QSM have not yet been characterized. The aim of this study is to characterize these key metrics in a healthy volunteer cohort and show the feasibility of the method in patients.

METHODS

Free breathing respiratory-navigated multi-echo 3D gradient echo images were acquired, from which QSM maps were reconstructed using the Morphology Enhanced Dipole Inversion toolbox. This technique was first evaluated in a susceptibility phantom containing tubes with known concentrations of gadolinium. In vivo characterization of myocardial QSM was then performed in a cohort of 10 healthy volunteers where each subject was scanned twice. Mean segment susceptibility, precision (standard deviation of voxel magnetic susceptibilities within one segment), and repeatability (absolute difference in segment mean susceptibility between repeats) of QSM were calculated for each American Heart Association (AHA) myocardial segment. Finally, the feasibility of the method was shown in 10 patients, including four with hemorrhagic infarcts.

RESULTS

The phantom experiment showed a strong linear relationship between measured and predicted susceptibility shifts (R2 > 0.99). For the healthy volunteer cohort, AHA segment analysis showed the mean segment susceptibility was 0.00 ± 0.02 ppm, the mean precision was 0.05 ± 0.04 ppm, and the mean repeatability was 0.02 ± 0.02 ppm. Cardiac QSM was successfully performed in all patients. Focal iron deposits were successfully visualized in the patients with hemorrhagic myocardial infarctions.

CONCLUSION

The precision and repeatability of cardiac QSM were successfully characterized in phantom and in vivo experiments. The feasibility of the technique was also successfully demonstrated in patients. While challenges still remain, further clinical evaluation of the technique is now warranted.

TRIAL REGISTRATION

This work does not report on a health care intervention.

Toward a deep learning-based magnetic resonance imaging only workflow for postimplant dosimetry in I-125 seed brachytherapy for prostate cancer

BACKGROUND AND PURPOSE

The current standard imaging-technique for creating postplans in seed prostate brachytherapy is computed tomography (CT), that is associated with additional radiation exposure and poor soft tissue contrast. To establish a magnetic resonance imaging (MRI) only workflow combining improved tissue contrast and high seed detectability, a deep learning-approach for automatic seed segmentation on MRI-scans was developed.

MATERIAL AND METHODS

Patients treated with I-125 seed brachytherapy received a postplan-CT and a 1.5 T MRI-scan on nominal day 30 after implantation. For MRI-based seed visualization, DIXON-sequences were acquired and deep learning-based quantitative susceptibility maps (QSM) were generated from 3D-gradient-echo-sequences from 20 patients. Seed segmentations created on CT served as ground truth. For automatic seed segmentation on MRI, a 3D nnU-net model was trained using QSM and DIXON, both solely and combined.

RESULTS

Of the implanted seeds 94.8 ± 2.4% were detected with deep learning automatic segmentation entrained on both QSM and DIXON data. Models trained on the individual sequence data-sets performed worse with detection rates of 87.5 ± 2.6% or 88.6 ± 7.5% for QSM and DIXON respectively. The seed centers identified on CT versus QSM and DIXON were on average 1.8 ± 1.3 mm apart. Postimplant dosimetry for evaluation of positioning inaccuracies revealed only small variations of up to 0.4 ± 4.26 Gy in D90 (dose 90% of the prostate receives) between the standard CT-approach and our MRI-only workflow.

CONCLUSION

The proposed deep learning-based MRI-only workflow provided a promisingly accurate and robust seed localization and thus has the potential to compete with current state-of-the-art CT-based postimplant dosimetry in the future.

A new 3D phase unwrapping method by region partitioning and local polynomial modeling in abdominal quantitative susceptibility mapping

Background

Accurate phase unwrapping is a critical prerequisite for successful applications in phase-related MRI, including quantitative susceptibility mapping (QSM) and susceptibility weighted imaging. However, many existing 3D phase unwrapping algorithms face challenges in the presence of severe noise, rapidly changing phase, and open-end cutline.

Methods

In this study, we introduce a novel 3D phase unwrapping approach utilizing region partitioning and a local polynomial model. Initially, the method leverages phase partitioning to create initial regions. Noisy voxels connecting areas within these regions are excluded and grouped into residual voxels. The connected regions within the region of interest are then reidentified and categorized into blocks and residual voxels based on voxel count thresholds. Subsequently, the method sequentially performs inter-block and residual voxel phase unwrapping using the local polynomial model. The proposed method was evaluated on simulation and in vivo abdominal QSM data, and was compared with the classical Region-growing, Laplacian_based, Graph-cut, and PRELUDE methods.

Results

Simulation experiments, conducted under different signal-to-noise ratios and phase change levels, consistently demonstrate that the proposed method achieves accurate unwrapping results, with mean error ratios not exceeding 0.01%. In contrast, the error ratios of Region-growing (N/A, 84.47%), Laplacian_based (20.65%, N/A), Graph-cut (2.26%, 20.71%), and PRELUDE (4.28%, 10.33%) methods are all substantially higher than those of the proposed method. In vivo abdominal QSM experiments further confirm the effectiveness of the proposed method in unwrapping phase data and successfully reconstructing susceptibility maps, even in scenarios with significant noise, rapidly changing phase, and open-end cutline in a large field of view.

Conclusion

The proposed method demonstrates robust and accurate phase unwrapping capabilities, positioning it as a promising option for abdominal QSM applications.

DeepSTI: Towards tensor reconstruction using fewer orientations in susceptibility tensor imaging

Susceptibility tensor imaging (STI) is an emerging magnetic resonance imaging technique that characterizes the anisotropic tissue magnetic susceptibility with a second-order tensor model. STI has the potential to provide information for both the reconstruction of white matter fiber pathways and detection of myelin changes in the brain at mm resolution or less, which would be of great value for understanding brain structure and function in healthy and diseased brain. However, the application of STI in vivo has been hindered by its cumbersome and time-consuming acquisition requirement of measuring susceptibility induced MR phase changes at multiple head orientations. Usually, sampling at more than six orientations is required to obtain sufficient information for the ill-posed STI dipole inversion. This complexity is enhanced by the limitation in head rotation angles due to physical constraints of the head coil. As a result, STI has not yet been widely applied in human studies in vivo. In this work, we tackle these issues by proposing an image reconstruction algorithm for STI that leverages data-driven priors. Our method, called DeepSTI, learns the data prior implicitly via a deep neural network that approximates the proximal operator of a regularizer function for STI. The dipole inversion problem is then solved iteratively using the learned proximal network. Experimental results using both simulation and in vivo human data demonstrate great improvement over state-of-the-art algorithms in terms of the reconstructed tensor image, principal eigenvector maps and tractography results, while allowing for tensor reconstruction with MR phase measured at much less than six different orientations. Notably, promising reconstruction results are achieved by our method from only one orientation in human in vivo, and we demonstrate a potential application of this technique for estimating lesion susceptibility anisotropy in patients with multiple sclerosis.

Quantitative susceptibility mapping using multi-channel convolutional neural networks with dipole-adaptive multi-frequency inputs

Quantitative susceptibility mapping (QSM) quantifies the distribution of magnetic susceptibility and shows great potential in assessing tissue contents such as iron, myelin, and calcium in numerous brain diseases. The accuracy of QSM reconstruction was challenged by an ill-posed field-to-susceptibility inversion problem, which is related to the impaired information near the zero-frequency response of the dipole kernel. Recently, deep learning methods demonstrated great capability in improving the accuracy and efficiency of QSM reconstruction. However, the construction of neural networks in most deep learning-based QSM methods did not take the intrinsic nature of the dipole kernel into account. In this study, we propose a dipole kernel-adaptive multi-channel convolutional neural network (DIAM-CNN) method for the dipole inversion problem in QSM. DIAM-CNN first divided the original tissue field into high-fidelity and low-fidelity components by thresholding the dipole kernel in the frequency domain, and it then inputs the two components as additional channels into a multichannel 3D Unet. QSM maps from the calculation of susceptibility through multiple orientation sampling (COSMOS) were used as training labels and evaluation reference. DIAM-CNN was compared with two conventional model-based methods [morphology enabled dipole inversion (MEDI) and improved sparse linear equation and least squares (iLSQR) and one deep learning method (QSMnet)]. High-frequency error norm (HFEN), peak signal-to-noise-ratio (PSNR), normalized root mean squared error (NRMSE), and the structural similarity index (SSIM) were reported for quantitative comparisons. Experiments on healthy volunteers demonstrated that the DIAM-CNN results had superior image quality to those of the MEDI, iLSQR, or QSMnet results. Experiments on data with simulated hemorrhagic lesions demonstrated that DIAM-CNN produced fewer shadow artifacts around the bleeding lesion than the compared methods. This study demonstrates that the incorporation of dipole-related knowledge into the network construction has a potential to improve deep learning-based QSM reconstruction.

msQSM: Morphology-based Self-supervised Deep Learning for Quantitative Susceptibility Mapping

Quantitative susceptibility mapping (QSM) has been applied to the measurement of iron deposition and the auxiliary diagnosis of neurodegenerative disease. There still exists a dipole inversion problem in QSM reconstruction. Recently, deep learning approaches have been proposed to resolve this problem. However, most of these approaches are supervised methods that need pairs of the input phase and ground-truth. It remains a challenge to train a model for all resolutions without using the ground-truth and only using one resolution data. To address this, we proposed a self-supervised QSM deep learning method based on morphology. It consists of a morphological QSM builder to decouple the dependency of the QSM on acquisition resolution, and a morphological loss to reduce artifacts effectively and save training time efficiently. The proposed method can reconstruct arbitrary resolution QSM on both human data and animal data, regardless of whether the resolution is higher or lower than that of the training set. Our method outperforms the previous best unsupervised method with a 3.6% higher peak signal-to-noise ratio, 16.2% lower normalized root mean square error, and 22.1% lower high-frequency error norm. The morphological loss reduces training time by 22.1% with respect to the cycle gradient loss used in the previous unsupervised methods. Experimental results show that the proposed method accurately measures QSM with arbitrary resolutions, and achieves state-of-the-art results among unsupervised deep learning methods. Research on applications in neurodegenerative diseases found that our method is robust enough to measure significant increase in striatal magnetic susceptibility in patients during Alzheimer's disease progression, as well as significant increase in substantia nigra susceptibility in Parkinson's disease patients, and can be used as an auxiliary differential diagnosis tool for Alzheimer's disease and Parkinson's disease.

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 [...].

Reconstruction of Quantitative Susceptibility Mapping From Total Field Maps With Local Field Maps Guided UU-Net

Quantitative susceptibility mapping (QSM) is an emerging computational technique based on the magnetic resonance imaging (MRI) phase signal, which can provide magnetic susceptibility values of tissues. The existing deep learning-based models mainly reconstruct QSM from local field maps. However, the complicated inconsecutive reconstruction steps not only accumulate errors for inaccurate estimation, but also are inefficient in clinical practice. To this end, a novel local field maps guided UU-Net with Self- and Cross-Guided Transformer (LGUU-SCT-Net) is proposed to reconstruct QSM directly from the total field maps. Specifically, we propose to additionally generate the local field maps as the auxiliary supervision during the training stage. This strategy decomposes the more complicated mapping from total maps to QSM into two relatively easier ones, effectively alleviating the difficulty of direct mapping. Meanwhile, an improved U-Net model, named LGUU-SCT-Net, is further designed to promote the nonlinear mapping ability. The long-range connections are designed between two sequentially stacked U-Nets to bring more feature fusions and facilitate the information flow. The Self- and Cross-Guided Transformer integrated into these connections further captures multi-scale channel-wise correlations and guides the fusion of multi-scale transferred features, assisting in the more accurate reconstruction. The experimental results on an in-vivo dataset demonstrate the superior reconstruction results of our proposed algorithm.

Incomplete spectrum QSM using support information

Introduction

Reconstructing a bounded object from incomplete k-space data is a well posed problem, and it was recently shown that this incomplete spectrum approach can be used to reconstruct undersampled MRI images with similar quality to compressed sensing approaches. Here, we apply this incomplete spectrum approach to the field-to-source inverse problem encountered in quantitative magnetic susceptibility mapping (QSM). The field-to-source problem is an ill-posed problem because of conical regions in frequency space where the dipole kernel is zero or very small, which leads to the kernel's inverse being ill-defined. These "ill-posed" regions typically lead to streaking artifacts in QSM reconstructions. In contrast to compressed sensing, our approach relies on knowledge of the image-space support, more commonly referred to as the mask, of our object as well as the region in k-space with ill-defined values. In the QSM case, this mask is usually available, as it is required for most QSM background field removal and reconstruction methods.

Methods

We tuned the incomplete spectrum method (mask and band-limit) for QSM on a simulated dataset from the most recent QSM challenge and validated the QSM reconstruction results on brain images acquired in five healthy volunteers, comparing incomplete spectrum QSM to current state-of-the art-methods: FANSI, nonlinear dipole inversion, and conventional thresholded k-space division.

Results

Without additional regularization, incomplete spectrum QSM performs slightly better than direct QSM reconstruction methods such as thresholded k-space division (PSNR of 39.9 vs. 39.4 of TKD on a simulated dataset) and provides susceptibility values in key iron-rich regions similar or slightly lower than state-of-the-art algorithms, but did not improve the PSNR in comparison to FANSI or nonlinear dipole inversion. With added (ℓ1-wavelet based) regularization the new approach produces results similar to compressed sensing based reconstructions (at sufficiently high levels of regularization).

Discussion

Incomplete spectrum QSM provides a new approach to handle the "ill-posed" regions in the frequency-space data input to QSM.

Quantitative susceptibility mapping (QSM) of the cardiovascular system: challenges and perspectives

Quantitative susceptibility mapping (QSM) is a powerful, non-invasive, magnetic resonance imaging (MRI) technique that relies on measurement of magnetic susceptibility. So far, QSM has been employed mostly to study neurological disorders characterized by iron accumulation, such as Parkinson's and Alzheimer's diseases. Nonetheless, QSM allows mapping key indicators of cardiac disease such as blood oxygenation and myocardial iron content. For this reason, the application of QSM offers an unprecedented opportunity to gain a better understanding of the pathophysiological changes associated with cardiovascular disease and to monitor their evolution and response to treatment. Recent studies on cardiovascular QSM have shown the feasibility of a non-invasive assessment of blood oxygenation, myocardial iron content and myocardial fibre orientation, as well as carotid plaque composition. Significant technical challenges remain, the most evident of which are related to cardiac and respiratory motion, blood flow, chemical shift effects and susceptibility artefacts. Significant work is ongoing to overcome these challenges and integrate the QSM technique into clinical practice in the cardiovascular field.

Early differentiation of neurodegenerative diseases using the novel QSM technique: what is the biomarker of each disorder?

During neurodegenerative diseases, the brain undergoes morphological and pathological changes; Iron deposits are one of the causes of pathological changes in the brain. The Quantitative susceptibility mapping (QSM) technique, a type of magnetic resonance (MR) image reconstruction, is one of the newest diagnostic methods for iron deposits to detect changes in magnetic susceptibility. Numerous research projects have been conducted in this field. The purpose of writing this review article is to identify the first deep brain nuclei that undergo magnetic susceptibility changes during neurodegenerative diseases such as Alzheimer's or Parkinson's disease. The purpose of this article is to identify the brain nuclei that are prone to iron deposition in any specific disorder. In addition to the mentioned purpose, this paper proposes the optimal scan parameters and appropriate algorithms of each QSM reconstruction step by reviewing the results of different articles. As a result, The QSM technique can identify nuclei exposed to iron deposition in various neurodegenerative diseases. Also, the selection of scan parameters is different based on the sequence and purpose; an example of the parameters is placed in the tables. The BET toolbox in FSL, Laplacian-based phase-unwrapping process, the V_SHARP algorithm, and morphology-enabled dipole inversion (MEDI) method are the most widely used algorithms in various stages of QSM reconstruction.

Towards in vivo ground truth susceptibility for single-orientation deep learning QSM: a multi-orientation gradient-echo MRI dataset

Recently, deep neural networks have shown great potential for solving dipole inversion of quantitative susceptibility mapping (QSM) with improved results. However, these studies utilized their limited dataset for network training and inference, which may lead to untrustworthy conclusions. Thus, a common dataset is needed for a fair comparison between different QSM reconstruction networks. Additionally, finding an in vivo reference susceptibility map that matches acquired single-orientation phase data remains an open problem. Susceptibility tensor imaging (STI) χ₃₃ and Calculation of Susceptibility through Multiple Orientation Sampling (COSMOS) are considered reference susceptibility candidates. However, a large number of multi-orientation GRE data for both STI and COSMOS reconstruction are now unavailable for training supervised neural networks for QSM. In this study, we reported the largest multi-orientation dataset, to the best of our knowledge in the QSM research field, with a total of 144 scans from 8 healthy subjects collected using a 3D GRE sequence from the same MR scanner. In addition, the parcellation of deep gray matter is also provided for automatically extracting susceptibility values. Five recently developed deep neural networks, i.e., xQSM, QSMnet, autoQSM, LPCNN, and MoDL-QSM were performed on this dataset. This potential data source could provide a common framework and labels to test the accuracy and robustness of deep neural networks for QSM reconstruction. This dataset has the potential to provide a benchmark of reference susceptibility for the deep learning-based QSM methods. Additionally, the trained COSMOS-labeled and χ₃₃-labeled networks were tested on the pathological data to explore their potential applications. The data together with deep gray matter parcellation maps are now publicly available via an open repository at https://osf.io/yfms7/, and the raw multi-orientation GRE data were also available at https://osf.io/y6rc3/.

Deep learning-based quantitative susceptibility mapping (QSM) in the presence of fat using synthetically generated multi-echo phase training data

PURPOSE

To enable a fast and automatic deep learning-based QSM reconstruction of tissues with diverse chemical shifts, relevant to most regions outside the brain.

METHODS

A UNET was trained to reconstruct susceptibility maps using synthetically generated, unwrapped, multi-echo phase data as input. The RMS error with respect to synthetic validation data was computed. The method was tested on two in vivo knee and two pelvis data sets. Comparisons were made to a conventional fat-water separation pipeline by applying a commonly used graph-cut algorithm, both without and with an extended mask for background field removal (FWS-CONV-QSM and FWS-MASK-CONV-QSM, respectively). Several regions of interest were segmented and compared. Furthermore, the approach was tested on a prostate cancer patient receiving low-dose-rate brachytherapy, to detect and localize the seeds by MRI.

RESULTS

The RMS error was 0.292 ppm with FWS-CONV-QSM and 0.123 ppm for the UNET approach. Susceptibility maps were reconstructed much faster (< 10 s) and completely automatically (no background masking needed) by the UNET compared with the other applied techniques (5 min 51 s and 22 min 44 s for CONV-QSM and FWS-MASK-CONV-QSM, respectively. Background artifacts, fat-water swaps, and hypointense artifacts between I-125 seeds of a patient receiving low-dose brachytherapy in the prostate were largely reduced in the UNET approach.

CONCLUSIONS

Deep learning-based QSM reconstruction, trained solely with synthetic data, is well-suited to rapidly reconstructing high-quality susceptibility maps in the presence of fat without needing masking for background field removal.

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.

DIFFnet: Diffusion Parameter Mapping Network Generalized for Input Diffusion Gradient Schemes and b-Value

In MRI, deep neural networks have been proposed to reconstruct diffusion model parameters. However, the inputs of the networks were designed for a specific diffusion gradient scheme (i.e., diffusion gradient directions and numbers) and a specific b-value that are the same as the training data. In this study, a new deep neural network, referred to as DIFFnet, is developed to function as a generalized reconstruction tool of the diffusion-weighted signals for various gradient schemes and b-values. For generalization, diffusion signals are normalized in a q-space and then projected and quantized, producing a matrix (Qmatrix) as an input for the network. To demonstrate the validity of this approach, DIFFnet is evaluated for diffusion tensor imaging (DIFFnet_DTI) and for neurite orientation dispersion and density imaging (DIFFnet_NODDI). In each model, two datasets with different gradient schemes and b-values are tested. The results demonstrate accurate reconstruction of the diffusion parameters at substantially reduced processing time (approximately 8.7 times and 2240 times faster processing time than conventional methods in DTI and NODDI, respectively; less than 4% mean normalized root-mean-square errors (NRMSE) in DTI and less than 8% in NODDI). The generalization capability of the networks was further validated using reduced numbers of diffusion signals from the datasets and a public dataset from Human Connection Project. Different from previously proposed deep neural networks, DIFFnet does not require any specific gradient scheme and b-value for its input. As a result, it can be adopted as an online reconstruction tool for various complex diffusion imaging.

QSM reconstruction challenge 2.0: Design and report of results

PURPOSE

The aim of the second quantitative susceptibility mapping (QSM) reconstruction challenge (Oct 2019, Seoul, Korea) was to test the accuracy of QSM dipole inversion algorithms in simulated brain data.

METHODS

A two-stage design was chosen for this challenge. The participants were provided with datasets of multi-echo gradient echo images synthesized from two realistic in silico head phantoms using an MR simulator. At the first stage, participants optimized QSM reconstructions without ground truth data available to mimic the clinical setting. At the second stage, ground truth data were provided for parameter optimization. Submissions were evaluated using eight numerical metrics and visual ratings.

RESULTS

A total of 98 reconstructions were submitted for stage 1 and 47 submissions for stage 2. Iterative methods had the best quantitative metric scores, followed by deep learning and direct inversion methods. Priors derived from magnitude data improved the metric scores. Algorithms based on iterative approaches and total variation (and its derivatives) produced the best overall results. The reported results and analysis pipelines have been made public to allow researchers to compare new methods to the current state of the art.

CONCLUSION

The synthetic data provide a consistent framework to test the accuracy and robustness of QSM algorithms in the presence of noise, calcifications and minor voxel dephasing effects. Total Variation-based algorithms produced the best results among all metrics. Future QSM challenges should assess whether this good performance with synthetic datasets translates to more realistic scenarios, where background fields and dipole-incompatible phase contributions are included.

Deep grey matter quantitative susceptibility mapping from small spatial coverages using deep learning

INTRODUCTION

Quantitative Susceptibility Mapping (QSM) is generally acquired with full brain coverage, even though many QSM brain-iron studies focus on the deep grey matter (DGM) region only. Reducing the spatial coverage to the DGM vicinity can substantially shorten the scan time or enhance the spatial resolution without increasing scan time; however, this may lead to significant DGM susceptibility underestimation.

METHOD

A recently proposed deep learning-based QSM method, namely xQSM, is investigated to assess the accuracy of dipole inversion on reduced brain coverages. The xQSM method is compared with two conventional dipole inversion methods using simulated and in vivo experiments from 4 healthy subjects at 3T. Pre-processed magnetic field maps are extended symmetrically from the centre of globus pallidus in the coronal plane to simulate QSM acquisitions of difference spatial coverages, ranging from 100% (∼32mm) to 400% (∼128mm) of the actual DGM physical size.

RESULTS

The proposed xQSM network led to the lowest DGM contrast loss in both simulated and in vivo subjects, with the smallest susceptibility variation range across all spatial coverages. For the digital brain phantom simulation, xQSM improved the DGM susceptibility underestimation more than 20% in small spatial coverages, as compared to conventional methods. For the in vivo acquisition, less than 5% DGM susceptibility error was achieved in 48mm axial slabs using the xQSM network, while a minimum of 112mm coverage was required for conventional methods. It is also shown that the background field removal process performed worse in reduced brain coverages, which further deteriorated the subsequent dipole inversion.

CONCLUSION

The recently proposed deep learning-based xQSM method significantly improves the accuracy of DGM QSM from small spatial coverages as compared with conventional QSM algorithms, which can shorten DGM QSM acquisition time substantially.

QSM reconstruction challenge 2.0: A realistic in silico head phantom for MRI data simulation and evaluation of susceptibility mapping procedures

PURPOSE

To create a realistic in silico head phantom for the second QSM reconstruction challenge and for future evaluations of processing algorithms for QSM.

METHODS

We created a digital whole-head tissue property phantom by segmenting and postprocessing high-resolution (0.64 mm isotropic), multiparametric MRI data acquired at 7 T from a healthy volunteer. We simulated the steady-state magnetization at 7 T using a Bloch simulator and mimicked a Cartesian sampling scheme through Fourier-based processing. Computer code for generating the phantom and performing the MR simulation was designed to facilitate flexible modifications of the phantom in the future, such as the inclusion of pathologies as well as the simulation of a wide range of acquisition protocols. Specifically, the following parameters and effects were implemented: TR and TE, voxel size, background fields, and RF phase biases. Diffusion-weighted imaging phantom data are provided, allowing future investigations of tissue-microstructure effects in phase and QSM algorithms.

RESULTS

The brain part of the phantom featured realistic morphology with spatial variations in relaxation and susceptibility values similar to the in vivo setting. We demonstrated some of the phantom's properties, including the possibility of generating phase data with nonlinear evolution over TE due to partial-volume effects or complex distributions of frequency shifts within the voxel.

CONCLUSION

The presented phantom and computer programs are publicly available and may serve as a ground truth in future assessments of the faithfulness of quantitative susceptibility reconstruction algorithms.

Emerging Applications for Quantitative Susceptibility Mapping in the Detection of Traumatic Brain Injury Pathology

Traumatic brain injury (TBI) is a common but heterogeneous injury underpinned by numerous complex and interrelated pathophysiological mechanisms. An essential trace element, iron is abundant within the brain and involved in many fundamental neurobiological processes, including oxygen transportation, oxidative phosphorylation, myelin production and maintenance, as well as neurotransmitter synthesis and metabolism. Excessive levels of iron are neurotoxic and thus iron homeostasis is tightly regulated in the brain, however, many details about the mechanisms by which this is achieved are yet to be elucidated. A key mediator of oxidative stress, mitochondrial dysfunction and neuroinflammatory response, iron dysregulation is an important contributor to secondary injury in TBI. Advances in neuroimaging that leverage magnetic susceptibility properties have enabled increasingly comprehensive investigations into the distribution and behaviour of iron in the brain amongst healthy individuals as well as disease states such as TBI. Quantitative Susceptibility Mapping (QSM) is an advanced neuroimaging technique that promises quantitative estimation of local magnetic susceptibility at the voxel level. In this review, we provide an overview of brain iron and its homeostasis, describe recent advances enabling applications of QSM within the context of TBI and summarise the current state of the literature. Although limited, the emergent research suggests that QSM is a promising neuroimaging technique that can be used to investigate a host of pathophysiological changes that are associated with TBI.

xQSM: quantitative susceptibility mapping with octave convolutional and noise-regularized neural networks

Quantitative susceptibility mapping (QSM) provides a valuable MRI contrast mechanism that has demonstrated broad clinical applications. However, the image reconstruction of QSM is challenging due to its ill-posed dipole inversion process. In this study, a new deep learning method for QSM reconstruction, namely xQSM, was designed by introducing noise regularization and modified octave convolutional layers into a U-net backbone and trained with synthetic and in vivo datasets, respectively. The xQSM method was compared with two recent deep learning (QSMnet⁺ and DeepQSM) and two conventional dipole inversion (MEDI and iLSQR) methods, using both digital simulations and in vivo experiments. Reconstruction error metrics, including peak signal-to-noise ratio, structural similarity, normalized root mean squared error and deep gray matter susceptibility measurements, were evaluated for comparison of the different methods. The results showed that the proposed xQSM network trained with in vivo datasets achieved the best reconstructions of all the deep learning methods. In particular, it led to, on average, 32.3%, 25.4% and 11.7% improvement in the accuracy of globus pallidus susceptibility estimation for digital simulations and 39.3%, 21.8% and 6.3% improvements for in vivo acquisitions compared with DeepQSM, QSMnet⁺ and iLSQR, respectively. It also exhibited the highest linearity against different susceptibility intensity scales and demonstrated the most robust generalization capability to various spatial resolutions of all the deep learning methods. In addition, the xQSM method also substantially shortened the reconstruction time from minutes using MEDI to only a few seconds.

Systematic Review: Quantitative Susceptibility Mapping (QSM) of Brain Iron Profile in Neurodegenerative Diseases

Iron has been increasingly implicated in the pathology of neurodegenerative diseases. In the past decade, development of the new magnetic resonance imaging technique, quantitative susceptibility mapping (QSM), has enabled for the more comprehensive investigation of iron distribution in the brain. The aim of this systematic review was to provide a synthesis of the findings from existing QSM studies in neurodegenerative diseases. We identified 80 records by searching MEDLINE, Embase, Scopus, and PsycInfo databases. The disorders investigated in these studies included Alzheimer's disease, Parkinson's disease, amyotrophic lateral sclerosis, Wilson's disease, Huntington's disease, Friedreich's ataxia, spinocerebellar ataxia, Fabry disease, myotonic dystrophy, pantothenate-kinase-associated neurodegeneration, and mitochondrial membrane protein-associated neurodegeneration. As a general pattern, QSM revealed increased magnetic susceptibility (suggestive of increased iron content) in the brain regions associated with the pathology of each disorder, such as the amygdala and caudate nucleus in Alzheimer's disease, the substantia nigra in Parkinson's disease, motor cortex in amyotrophic lateral sclerosis, basal ganglia in Huntington's disease, and cerebellar dentate nucleus in Friedreich's ataxia. Furthermore, the increased magnetic susceptibility correlated with disease duration and severity of clinical features in some disorders. Although the number of studies is still limited in most of the neurodegenerative diseases, the existing evidence suggests that QSM can be a promising tool in the investigation of neurodegeneration.

Magnetic Resonance Iron Imaging in Amyotrophic Lateral Sclerosis

Amyotrophic lateral sclerosis (ALS) results in progressive impairment of upper and lower motor neurons. Increasing evidence from both in vivo and ex vivo studies suggest that iron accumulation in the motor cortex is a neuropathological hallmark in ALS. An in vivo neuroimaging marker of iron dysregulation in ALS would be useful in disease diagnosis and prognosis. Magnetic resonance imaging (MRI), with its unique capability to generate a variety of soft tissue contrasts, provides opportunities to image iron distribution in the human brain with millimeter to sub-millimeter anatomical resolution. Conventionally, MRI T1-weighted, T2-weighted, and T2*-weighted images have been used to investigate iron dysregulation in the brain in vivo. Susceptibility weighted imaging has enhanced contrast for para-magnetic materials that provides superior sensitivity to iron in vivo. Recently, the development of quantitative susceptibility mapping (QSM) has realized the possibility of using quantitative assessments of magnetic susceptibility measures in brain tissues as a surrogate measurement of in vivo brain iron. In this review, we provide an overview of MRI techniques that have been used to investigate iron dysregulation in ALS in vivo. The potential uses, strengths, and limitations of these techniques in clinical trials, disease diagnosis, and prognosis are presented and discussed. We recommend further longitudinal studies with appropriate cohort characterization to validate the efficacy of these techniques. We conclude that quantitative iron assessment using recent advances in MRI including QSM holds great potential to be a sensitive diagnostic and prognostic marker in ALS. The use of multimodal neuroimaging markers in combination with iron imaging may also offer improved sensitivity in ALS diagnosis and prognosis that could make a major contribution to clinical care and treatment trials. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY: Stage 3.

Electrical Properties Tomography: A Methodological Review

Electrical properties tomography (EPT) is an imaging method that uses a magnetic resonance (MR) system to non-invasively determine the spatial distribution of the conductivity and permittivity of the imaged object. This manuscript starts by providing clear definitions about the data required for, and acquired in, EPT, followed by comprehensively formulating the physical equations underlying a large number of analytical EPT techniques. This thorough mathematical overview of EPT harmonizes several EPT techniques in a single type of formulation and gives insight into how they act on the data and what their data requirements are. Furthermore, the review describes machine learning-based algorithms. Matlab code of several differential and iterative integral methods is available upon request.

Learned Proximal Networks for Quantitative Susceptibility Mapping

Quantitative Susceptibility Mapping (QSM) estimates tissue magnetic susceptibility distributions from Magnetic Resonance (MR) phase measurements by solving an ill-posed dipole inversion problem. Conventional single orientation QSM methods usually employ regularization strategies to stabilize such inversion, but may suffer from streaking artifacts or over-smoothing. Multiple orientation QSM such as calculation of susceptibility through multiple orientation sampling (COSMOS) can give well-conditioned inversion and an artifact free solution but has expensive acquisition costs. On the other hand, Convolutional Neural Networks (CNN) show great potential for medical image reconstruction, albeit often with limited interpretability. Here, we present a Learned Proximal Convolutional Neural Network (LP-CNN) for solving the ill-posed QSM dipole inversion problem in an iterative proximal gradient descent fashion. This approach combines the strengths of data-driven restoration priors and the clear interpretability of iterative solvers that can take into account the physical model of dipole convolution. During training, our LP-CNN learns an implicit regularizer via its proximal, enabling the decoupling between the forward operator and the data-driven parameters in the reconstruction algorithm. More importantly, this framework is believed to be the first deep learning QSM approach that can naturally handle an arbitrary number of phase input measurements without the need for any ad-hoc rotation or re-training. We demonstrate that the LP-CNN provides state-of-the-art reconstruction results compared to both traditional and deep learning methods while allowing for more flexibility in the reconstruction process.