Motion artifacts in MRI: A complex problem with many partial solutions

Marker-controlled watershed algorithm and fuzzy C-means clustering machine learning: automated segmentation of glioblastoma from MRI images in a case series

Introduction and importance

Automated segmentation of glioblastoma multiforme (GBM) from MRI images is crucial for accurate diagnosis and treatment planning. This paper presents a new and innovative approach for automating the segmentation of GBM from MRI images using the marker-controlled watershed segmentation (MCWS) algorithm.

Case presentation and methods

The technique involves several image processing techniques, including adaptive thresholding, morphological filtering, gradient magnitude calculation, and regional maxima identification. The MCWS algorithm efficiently segments images based on local intensity structures using the watershed transform, and fuzzy c-means (FCM) clustering improves segmentation accuracy. The presented approach achieved improved segmentation accuracy in detecting and segmenting GBM tumours from axial T2-weighted (T2-w) MRI images, as demonstrated by the mean characteristics performance metrics for GBM segmentation (sensitivity: 0.9905, specificity: 0.9483, accuracy: 0.9508, precision: 0.5481, F_measure: 0.7052, and jaccard: 0.9340).

Clinical discussion

The results of this study underline the importance of reliable and accurate image segmentation for effective diagnosis and treatment planning of GBM tumours.

Conclusion

The MCWS technique provides an effective and efficient approach for the segmentation of challenging medical images.

Intra-frame motion deterioration effects and deep-learning-based compensation in MR-guided radiotherapy

BACKGROUND

Current commercially available hybrid magnetic resonance linear accelerators (MR-Linac) use 2D+t cine MR imaging to provide intra-fractional motion monitoring. However, given the limited temporal resolution of cine MR imaging, target intra-frame motion deterioration effects, resulting in effective time latency and motion artifacts in the image domain, can be appreciable, especially in the case of fast breathing.

PURPOSE

The aim of this work is to investigate intra-frame motion deterioration effects in MR-guided radiotherapy (MRgRT) by simulating the motion-corrupted image acquisition, and to explore the feasibility of deep-learning-based compensation approaches, relying on the intra-frame motion information which is spatially and temporally encoded in the raw data (k-space).

METHODS

An intra-frame motion model was defined to simulate motion-corrupted MR images, with 4D anthropomorphic digital phantoms being exploited to provide ground truth 2D+t cine MR sequences. A total number of 10 digital phantoms were generated for lung cancer patients, with randomly selected eight patients for training or validation and the remaining two for testing. The simulation code served as the data generator, and a dedicated motion pattern perturbation scheme was proposed to build the intra-frame motion database, where three degrees of freedom were designed to guarantee the diversity of intra-frame motion trajectories, enabling a thorough exploration in the domain of the potential anatomical structure positions. U-Nets with three types of loss functions: L1 or L2 loss defined in image or Fourier domain, referred to as NNImgLoss-L1 , NNFloss-L1 and NNL2-Loss were trained to extract information from the motion-corrupted image and used to estimate the ground truth final-position image, corresponding to the end of the acquisition. Images before and after compensation were evaluated in terms of (i) image mean-squared error (MSE) and mean absolute error (MAE), and (ii) accuracy of gross tumor volume (GTV) contouring, based on optical-flow image registration.

RESULTS

Image degradation caused by intra-frame motion was observed: for a linearly and fully acquired Cartesian readout k-space trajectory, intra-frame motion resulted in an imaging latency of approximately 50% of the acquisition time; in comparison, the motion artifacts exhibited only a negligible contribution to the overall geometric errors. All three compensation models led to a decrease in image MSE/MAE and GTV position offset compared to the motion-corrupted image. In the investigated testing dataset for GTV contouring, the average dice similarity coefficients (DSC) improved from 88% to 96%, and the 95th percentile Hausdorff distance (HD95 ) dropped from 4.8 mm to 2.1 mm. Different models showed slight performance variations across different intra-frame motion amplitude categories: NNImgLoss-L1 excelled for small/medium amplitudes, whereas NNFloss-L1 demonstrated higher DSC median values at larger amplitudes. The saliency maps of the motion-corrupted image highlighted the major contribution of the later acquired k-space data, as well as the edges of the moving anatomical structures at their final positions, during the model inference stage.

CONCLUSIONS

Our results demonstrate the deep-learning-based approaches have the potential to compensate for intra-frame motion by utilizing the later acquired data to drive the convergence of the earlier acquired k-space components.

Submillimeter fMRI Acquisition Techniques for Detection of Laminar and Columnar Level Brain Activation

Since the first demonstration in the early 1990s, functional MRI (fMRI) has emerged as one of the most powerful, noninvasive neuroimaging tools to probe brain functions. Subsequently, fMRI techniques have advanced remarkably, enabling the acquisition of functional signals with a submillimeter voxel size. This innovation has opened the possibility of investigating subcortical neural activities with respect to the cortical depths or cortical columns. For this purpose, numerous previous works have endeavored to design suitable functional contrast mechanisms and dedicated imaging techniques. Depending on the choice of the functional contrast, functional signals can be detected with high sensitivity or with improved spatial specificity to the actual activation site, and the pertaining issues have been discussed in a number of earlier works. This review paper primarily aims to provide an overview of the subcortical fMRI techniques that allow the acquisition of functional signals with a submillimeter resolution. Here, the advantages and disadvantages of the imaging techniques will be described and compared. We also summarize supplementary imaging techniques that assist in the analysis of the subcortical brain activation for more accurate mapping with reduced geometric deformation. This review suggests that there is no single universally accepted method as the gold standard for subcortical fMRI. Instead, the functional contrast and the corresponding readout imaging technique should be carefully determined depending on the purpose of the study. Due to the technical limitations of current fMRI techniques, most subcortical fMRI studies have only targeted partial brain regions. As a future prospect, the spatiotemporal resolution of fMRI will be pushed to satisfy the community's need for a deeper understanding of whole-brain functions and the underlying connectivity in order to achieve the ultimate goal of a time-resolved and layer-specific spatial scale. EVIDENCE LEVEL: 1 TECHNICAL EFFICACY: Stage 1.

Influence of threshold selection and image sequence in in-vivo segmentation of enlarged perivascular spaces

BACKGROUND

Growing interest surrounds perivascular spaces (PVS) as a clinical biomarker of brain dysfunction given their association with cerebrovascular risk factors and disease. Neuroimaging techniques allowing quick and reliable quantification are being developed, but, in practice, they require optimisation as their limits of validity are usually unspecified.

NEW METHOD

We evaluate modifications and alternatives to a state-of-the-art (SOTA) PVS segmentation method that uses a vesselness filter to enhance PVS discrimination, followed by thresholding of its response, applied to brain magnetic resonance images (MRI) from patients with sporadic small vessel disease acquired at 3 T.

RESULTS

The method is robust against inter-observer differences in threshold selection, but separate thresholds for each region of interest (i.e., basal ganglia, centrum semiovale, and midbrain) are required. Noise needs to be assessed prior to selecting these thresholds, as effect of noise and imaging artefacts can be mitigated with a careful optimisation of these thresholds. PVS segmentation from T1-weighted images alone, misses small PVS, therefore, underestimates PVS count, may overestimate individual PVS volume especially in the basal ganglia, and is susceptible to the inclusion of calcified vessels and mineral deposits. Visual analyses indicated the incomplete and fragmented detection of long and thin PVS as the primary cause of errors, with the Frangi filter coping better than the Jerman filter.

COMPARISON WITH EXISTING METHODS

Limits of validity to a SOTA PVS segmentation method applied to 3 T MRI with confounding pathology are given.

CONCLUSIONS

Evidence presented reinforces the STRIVE-2 recommendation of using T2-weighted images for PVS assessment wherever possible. The Frangi filter is recommended for PVS segmentation from MRI, offering robust output against variations in threshold selection and pathology presentation.

Cerebral MRI in a prospective cohort study on depression and atherosclerosis: the BiDirect sample, processing pipelines, and analysis tools

BACKGROUND

The use of cerebral magnetic resonance imaging (MRI) in observational studies has increased exponentially in recent years, making it critical to provide details about the study sample, image processing, and extracted imaging markers to validate and replicate study results. This article reviews the cerebral MRI dataset from the now-completed BiDirect cohort study, as an update and extension of the feasibility report published after the first two examination time points.

METHODS

We report the sample and flow of participants spanning four study sessions and twelve years. In addition, we provide details on the acquisition protocol; the processing pipelines, including standardization and quality control methods; and the analytical tools used and markers available.

RESULTS

All data were collected from 2010 to 2021 at a single site in Münster, Germany, starting with a population of 2,257 participants at baseline in 3 different cohorts: a population-based cohort (n = 911 at baseline, 672 with MRI data), patients diagnosed with depression (n = 999, 736 with MRI data), and patients with manifest cardiovascular disease (n = 347, 52 with MRI data). During the study period, a total of 4,315 MRI sessions were performed, and over 535 participants underwent MRI at all 4 time points.

CONCLUSIONS

Images were converted to Brain Imaging Data Structure (a standard for organizing and describing neuroimaging data) and analyzed using common tools, such as CAT12, FSL, Freesurfer, and BIANCA to extract imaging biomarkers. The BiDirect study comprises a thoroughly phenotyped study population with structural and functional MRI data.

RELEVANCE STATEMENT

The BiDirect Study includes a population-based sample and two patient-based samples whose MRI data can help answer numerous neuropsychiatric and cardiovascular research questions.

KEY POINTS

• The BiDirect study included characterized patient- and population-based cohorts with MRI data. • Data were standardized to Brain Imaging Data Structure and processed with commonly available software. • MRI data and markers are available upon request.

Functional magnetic resonance imaging in schizophrenia: current evidence, methodological advances, limitations and future directions

Functional neuroimaging emerged with great promise and has provided fundamental insights into the neurobiology of schizophrenia. However, it has faced challenges and criticisms, most notably a lack of clinical translation. This paper provides a comprehensive review and critical summary of the literature on functional neuroimaging, in particular functional magnetic resonance imaging (fMRI), in schizophrenia. We begin by reviewing research on fMRI biomarkers in schizophrenia and the clinical high risk phase through a historical lens, moving from case-control regional brain activation to global connectivity and advanced analytical approaches, and more recent machine learning algorithms to identify predictive neuroimaging features. Findings from fMRI studies of negative symptoms as well as of neurocognitive and social cognitive deficits are then reviewed. Functional neural markers of these symptoms and deficits may represent promising treatment targets in schizophrenia. Next, we summarize fMRI research related to antipsychotic medication, psychotherapy and psychosocial interventions, and neurostimulation, including treatment response and resistance, therapeutic mechanisms, and treatment targeting. We also review the utility of fMRI and data-driven approaches to dissect the heterogeneity of schizophrenia, moving beyond case-control comparisons, as well as methodological considerations and advances, including consortia and precision fMRI. Lastly, limitations and future directions of research in the field are discussed. Our comprehensive review suggests that, in order for fMRI to be clinically useful in the care of patients with schizophrenia, research should address potentially actionable clinical decisions that are routine in schizophrenia treatment, such as which antipsychotic should be prescribed or whether a given patient is likely to have persistent functional impairment. The potential clinical utility of fMRI is influenced by and must be weighed against cost and accessibility factors. Future evaluations of the utility of fMRI in prognostic and treatment response studies may consider including a health economics analysis.

Assessment of Subject Head Motion in Diffusion MRI

Subject head motion during the acquisition of diffusion-weighted imaging (DWI) of the brain induces artifacts and affects image quality. Information about the frequency and extent of motion could reveal which aspects of motion correction are most necessary. Therefore, we investigate the extent of translation and rotation among participants, and how the motion changes during the scan acquisition. We analyze 5,380 DWI scans from 1,034 participants. We measure the rotations and translations in the sagittal, coronal and transverse planes needed to align the volumes to the first and previous volumes, as well as the displacement. The different types of motion are compared with each other and compared over time. The largest rotation (per minute) is around the right - left axis (median 0.378 °/min, range 0.000 - 11.466°) and the largest translation (per minute) is along the anterior - posterior axis (median 1.867 mm/min, range 0.000 - 10.944 mm). We additionally observe that spikes in movement occur at the beginning of the scan, particularly in anterior - posterior translation. The results show that all scans are affected by subtle head motion, which may impact subsequent image analysis.

A three-dimensional Magnetic Resonance Spin Tomography in Time-domain protocol for high-resolution multiparametric quantitative magnetic resonance imaging

Magnetic Resonance Spin TomogrAphy in Time-domain (MR-STAT) is a multiparametric quantitative MR framework, which allows for simultaneously acquiring quantitative tissue parameters such as T1, T2, and proton density from one single short scan. A typical two-dimensional (2D) MR-STAT acquisition uses a gradient-spoiled, gradient-echo sequence with a slowly varying RF flip-angle train and Cartesian readouts, and the quantitative tissue maps are reconstructed by an iterative, model-based optimization algorithm. In this work, we design a three-dimensional (3D) MR-STAT framework based on previous 2D work, in order to achieve better image signal-to-noise ratio, higher though-plane resolution, and better tissue characterization. Specifically, we design a 7-min, high-resolution 3D MR-STAT sequence, and the corresponding two-step reconstruction algorithm for the large-scale dataset. To reduce the long acquisition time, Cartesian undersampling strategies such as SENSE are adopted in our transient-state quantitative framework. To reduce the computational burden, a data-splitting scheme is designed for decoupling the 3D reconstruction problem into independent 2D reconstructions. The proposed 3D framework is validated by numerical simulations, phantom experiments, and in vivo experiments. High-quality knee quantitative maps with 0.8 × 0.8 × 1.5 mm3 resolution and bilateral lower leg maps with 1.6 mm isotropic resolution can be acquired using the proposed 7-min acquisition sequence and the 3-min-per-slice decoupled reconstruction algorithm. The proposed 3D MR-STAT framework could have wide clinical applications in the future.

When remediating one artifact results in another: control, confounders, and correction

Scientists aim to remediate artifacts in their experimental datasets. However, the remediation of one artifact can result in another. Why might this happen, and what does this consequence tell us about how we should account for artifacts and their control? In this paper, I explore a case in functional neuroimaging where remediation appears to have caused this problem. I argue that remediation amounts to a change to an experimental arrangement. These changes need not be surgical, and the arrangement need not satisfy the criterion of causal modularity. Thus, remediation can affect more than just the factor responsible for the artifact. However, if researchers can determine the consequences of their remediation, they can make adjustments that control for the present artifact as well as for previously controlled ones. Current philosophical accounts of artifacts and the factors responsible for them cannot adequately address this issue, as they do not account for what is needed for artifact remediation (and specifically correction). I support my argument by paralleling it with ongoing concerns regarding the transparency of complex computational systems, as near future remediation across the experimental life sciences will likely make greater use of AI tools to correct for artifacts.

Learning ADC maps from accelerated radial k-space diffusion-weighted MRI in mice using a deep CNN-transformer model

PURPOSE

To accelerate radially sampled diffusion weighted spin-echo (Rad-DW-SE) acquisition method for generating high quality ADC maps.

METHODS

A deep learning method was developed to generate accurate ADC maps from accelerated DWI data acquired with the Rad-DW-SE method. The deep learning method integrates convolutional neural networks (CNNs) with vision transformers to generate high quality ADC maps from accelerated DWI data, regularized by a monoexponential ADC model fitting term. A model was trained on DWI data of 147 mice and evaluated on DWI data of 36 mice, with acceleration factors of 4× and 8× compared to the original acquisition parameters.

RESULTS

Ablation studies and experimental results have demonstrated that the proposed deep learning model generates higher quality ADC maps from accelerated DWI data than alternative deep learning methods under comparison when their performance is quantified in whole images as well as in regions of interest, including tumors, kidneys, and muscles.

CONCLUSIONS

The deep learning method with integrated CNNs and transformers provides an effective means to accurately compute ADC maps from accelerated DWI data acquired with the Rad-DW-SE method.

Impact of magnetic resonance imaging-related geometric distortion of dose distribution in fractionated stereotactic radiotherapy in patients with brain metastases

PURPOSE

The geometric distortion related to magnetic resonance (MR) imaging in a diagnostic radiology (MRDR) and radiotherapy (MRRT) setup is evaluated, and the dosimetric impact of MR distortion on fractionated stereotactic radiotherapy (FSRT) in patients with brain metastases is simulated.

MATERIALS AND METHODS

An anthropomorphic skull phantom was scanned using a 1.5‑T MR scanner, and the magnitude of MR distortion was calculated with (MRDR-DC and MRRT-DC) and without (MRDR-nDC and MRRT-nDC) distortion-correction algorithms. Automated noncoplanar volumetric modulated arc therapy (HyperArc, HA; Varian Medical Systems, Palo Alto, CA, USA) plans were generated for 53 patients with 186 brain metastases. The MR distortion at each gross tumor volume (GTV) was calculated using the distance between the center of the GTV and the MR image isocenter (MIC) and the quadratic regression curve derived from the phantom study (MRRT-DC and MRRT-nDC). Subsequently, the radiation isocenter of the HA plans was shifted according to the MR distortion at each GTV (HADC and HAnDC).

RESULTS

The median MR distortions were approximately 0.1 mm when the distance from the MIC was < 30 mm, whereas the median distortion varied widely when the distance was > 60 mm (0.23, 0.47, 0.37, and 0.57 mm in MRDR-DC, MRDR-nDC, MRRT-DC, and MRRT-nDC, respectively). The dose to the 98% of the GTV volume (D98%) decreased as the distance from the MIC increased. In the HADC plans, the relative dose difference of D98% was less than 5% when the GTV was located within 70 mm from the MIC, whereas the underdose of GTV exceeded 5% when it was 48 mm (-26.5% at maximum) away from the MIC in the HAnDC plans.

CONCLUSION

Use of a distortion-correction algorithm in the studied MR diagnoses is essential, and the dosimetric impact of MR distortion is not negligible, particularly for tumors located far away from the MIC.

Update on Optimization of Prostate MR Imaging Technique and Image Quality

Prostate MR imaging quality has improved dramatically over recent times, driven by advances in hardware, software, and improved functional imaging techniques. MRI now plays a key role in prostate cancer diagnostic work-up, but outcomes of the MRI-directed pathway are heavily dependent on image quality and optimization. MR sequences can be affected by patient-related degradations relating to motion and susceptibility artifacts which may enable only partial mitigation. In this Review, we explore issues relating to prostate MRI acquisition and interpretation, mitigation strategies at a patient and scanner level, PI-QUAL reporting, and future directions in image quality, including artificial intelligence solutions.

Motion-resolved four-dimensional abdominal diffusion-weighted imaging using PROPELLER EPI (4D-DW-PROPELLER-EPI)

PURPOSE

To develop a distortion-free motion-resolved four-dimensional diffusion-weighted PROPELLER EPI (4D-DW-PROPELLER-EPI) technique for benefiting clinical abdominal radiotherapy (RT).

METHODS

An improved abdominal 4D-DWI technique based on 2D diffusion-weighted PROPELLER-EPI (2D-DW-PROPELLER-EPI), termed 4D-DW-PROPELLER-EPI, was proposed to improve the frame rate of repeated data acquisition and produce distortion-free 4D-DWI images. Since the radial or PROPELLER sampling with golden-angle rotation can achieve an efficient k-space coverage with a flexible time-resolved acquisition, the golden-angle multi-blade acquisition was used in the proposed 4D-DW-PROPELLER-EPI to improve the performance of data sorting. A new k-space and blade (K-B) amplitude binning method was developed for the proposed 4D-DW-PROPELLER-EPI to optimize the number of blades and the k-space uniformity before performing conventional PROPELLER-EPI reconstruction, by using two metrics to evaluate the adequacy of the acquired data. The proposed 4D-DW-PROPELLER-EPI was preliminarily evaluated in both simulation experiments and in vivo experiments with varying frame rates and different numbers of repeated acquisition.

RESULTS

The feasibility of achieving distortion-free 4D-DWI images by using the proposed 4D-DW-PROPELLER-EPI technique was demonstrated in both digital phantom and healthy subjects. Evaluation of the 4D completeness metrics shows that the K-B amplitude binning method could simultaneously improve the acquisition efficiency and data reconstruction performance for 4D-DW-PROPELLER-EPI.

CONCLUSION

4D-DW-PROPELLER-EPI with K-B amplitude binning is an advanced technique that can provide distortion-free 4D-DWI images for resolving respiratory motion, and may benefit the application of image-guided abdominal RT.

Contrast-Enhanced MRI in Women with Endometrial Cancer: Dynamic Versus Single-Phase Acquisitions

Background

The 2019 European Society of Urogenital Radiology (ESUR) guidelines for endometrial cancer recommend performing either dynamic contrast-enhanced magnetic resonance imaging (CE MRI) or single-phase CE MRI. However, no study has directly compared these options. Therefore, this study compared dynamic versus single-phase CE MRI for the evaluation of myometrial invasion in women with endometrial cancer.

Methods

This retrospective, single-institution comparative study was conducted among women with surgically proven endometrial cancer, including 30 consecutive women with single-phase CE MRI and 30 age- and pathologic stage-matched women with dynamic CE MRI. Three readers independently compared dynamic and single-phase CE MRI in terms of the tumor-myometrium signal intensity (SI) difference ratio, depth of myometrial invasion, image quality, and image number. Pathologic findings served as a reference standard for the depth of myometrial invasion.

Results

The estimated mean SI difference ratios of dynamic CE MRI and single-phase CE MRI fell within an equivalence margin of 0.05 (90% confidence intervals [CIs] = [-0.0497 to -0.0165], [-0.0226 to -0.0403], and [-0.0429 to -0.0433], respectively, for readers A, B, and C). The area under the receiver operating characteristic curve for the detection of deep myometrial invasion was not significantly different between the acquisitions (P = .3315, P = .3345, and P = .8593, respectively). Single-phase CE MRI showed significantly better image quality than dynamic CE MRI (P = .0143, P = .0042, and P = .0066, respectively), while the median number of images for dynamic CE MRI was 2.4 times higher than that for single-phase CE MRI.

Conclusion

Single-phase acquisition may be a better option for CE MRI in women with endometrial cancer than dynamic acquisition.

A selection and targeting framework of cortical locations for line-scanning fMRI

Depth-resolved functional magnetic resonance imaging (fMRI) is an emerging field growing in popularity given the potential of separating signals from different computational processes in cerebral cortex. Conventional acquisition schemes suffer from low spatial and temporal resolutions. Line-scanning methods allow depth-resolved fMRI by sacrificing spatial coverage to sample blood oxygenated level-dependent (BOLD) responses at ultra-high temporal and spatial resolution. For neuroscience applications, it is critical to be able to place the line accurately to (1) sample the right neural population and (2) target that neural population with tailored stimuli or tasks. To this end, we devised a multi-session framework where a target cortical location is selected based on anatomical and functional properties. The line is then positioned according to this information in a separate second session, and we tailor the experiment to focus on the target location. Anatomically, the precision of the line placement was confirmed by projecting a nominal representation of the acquired line back onto the surface. Functional estimates of neural selectivities in the line, as quantified by a visual population-receptive field model, resembled the target selectivities well for most subjects. This functional precision was quantified in detail by estimating the distance between the visual field location of the targeted vertex and the location in visual cortex (V1) that most closely resembled the line-scanning estimates; this distance was on average ~5.5 mm. Given the dimensions of the line, differences in acquisition, session, and stimulus design, this validates that line-scanning can be used to probe local neural sensitivities across sessions. In summary, we present an accurate framework for line-scanning MRI; we believe such a framework is required to harness the full potential of line-scanning and maximize its utility. Furthermore, this approach bridges canonical fMRI experiments with electrophysiological experiments, which in turn allows novel avenues for studying human physiology non-invasively.

fMRI with whole-brain coverage, 75-ms temporal resolution and high SNR by combining HiHi reshuffling and multiband imaging

Increasing the temporal resolution of the blood‑oxygen level-dependent (BOLD) response is usually accompanied by a decrease in repetition time and therefore also a reduction of the magnetic resonance (MR) signal due to incomplete T1 relaxation and thus a loss of signal-to-noise ratio (SNR). A previous data reordering method can achieve higher temporal sampling rate without the loss of SNR but at the cost of increased scan time. In this proof-of-principle work, we show that combining HiHi reshuffling with multiband acceleration allows us to measure the in vivo BOLD response with a 75-ms sampling rate that is decoupled from the acquisition repetition time (here 1.5 s and hence higher SNR) while covering the entire forebrain with 60 2-mm slices in a ~ 35-min scan. We provide single-voxel time-courses of the BOLD responses in the primary visual and primary motor cortices in three fMRI experiments on a 7 T scanner - 1 male (scanned twice on different days for test-retest reproducibility) and 1 female participant.

Decoding force production of skeletal muscle from the female brain using functional near-infrared spectroscopy

OBJECTIVE

Noninvasive neural decoding enables predicting motor output from neural activities without physically damaging the human body. A recent study demonstrated the applicability of functional near-infrared spectroscopy (fNIRS) to decode muscle force production from hemodynamic signals measured in the male brain. However, given the sex differences in cerebral blood flow and muscle physiology, whether the fNIRS approach can also be applied to the female brain remains elusive. Therefore, this study aimed to evaluate whether fNIRS can be used to identify the optimal cortical region and hemodynamic predictor to decode muscle force output in females.

RESULTS

Statistical group analysis for eight healthy female adults showed that the cortical region for wrist control was topologically dorsal to that for finger control over the primary sensorimotor cortex. This cortical area was maximally activated while the wrist flexor muscles were contracted to hold a load on the subject's palm, as was the case for males. However, the dynamics of oxyhemoglobin concentration measured from the most activated cortical area differed between females and males. The signal intensity during 100% maximal voluntary contraction and the signal increase rate at 50% maximal voluntary contraction was lower and faster in females. Eight predictors were used to characterize hemodynamic signals' amplitude and temporal variation in the female cortex. Unlike the case for males, only the trajectory predictors for the amplitude of oxyhemoglobin concentration change were strongly correlated with the strengths of force produced by the wrist flexor muscles, showing a linear relationship. These results suggest gender-specific hemodynamics must be considered for decoding low-level motor control with fNIRS in females.

Identifying core MRI sequences for reliable automatic brain metastasis segmentation

BACKGROUND

Many automatic approaches to brain tumor segmentation employ multiple magnetic resonance imaging (MRI) sequences. The goal of this project was to compare different combinations of input sequences to determine which MRI sequences are needed for effective automated brain metastasis (BM) segmentation.

METHODS

We analyzed preoperative imaging (T1-weighted sequence ± contrast-enhancement (T1/T1-CE), T2-weighted sequence (T2), and T2 fluid-attenuated inversion recovery (T2-FLAIR) sequence) from 339 patients with BMs from seven centers. A baseline 3D U-Net with all four sequences and six U-Nets with plausible sequence combinations (T1-CE, T1, T2-FLAIR, T1-CE + T2-FLAIR, T1-CE + T1 + T2-FLAIR, T1-CE + T1) were trained on 239 patients from two centers and subsequently tested on an external cohort of 100 patients from five centers.

RESULTS

The model based on T1-CE alone achieved the best segmentation performance for BM segmentation with a median Dice similarity coefficient (DSC) of 0.96. Models trained without T1-CE performed worse (T1-only: DSC = 0.70 and T2-FLAIR-only: DSC = 0.73). For edema segmentation, models that included both T1-CE and T2-FLAIR performed best (DSC = 0.93), while the remaining four models without simultaneous inclusion of these both sequences reached a median DSC of 0.81-0.89.

CONCLUSIONS

A T1-CE-only protocol suffices for the segmentation of BMs. The combination of T1-CE and T2-FLAIR is important for edema segmentation. Missing either T1-CE or T2-FLAIR decreases performance. These findings may improve imaging routines by omitting unnecessary sequences, thus allowing for faster procedures in daily clinical practice while enabling optimal neural network-based target definitions.

Correction of Arterial-Phase Motion Artifacts in Gadoxetic Acid-Enhanced Liver MRI Using an Innovative Unsupervised Network

This study aims to propose and evaluate DR-CycleGAN, a disentangled unsupervised network by introducing a novel content-consistency loss, for removing arterial-phase motion artifacts in gadoxetic acid-enhanced liver MRI examinations. From June 2020 to July 2021, gadoxetic acid-enhanced liver MRI data were retrospectively collected in this center to establish training and testing datasets. Motion artifacts were semi-quantitatively assessed using a five-point Likert scale (1 = no artifact, 2 = mild, 3 = moderate, 4 = severe, and 5 = non-diagnostic) and quantitatively evaluated using the structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR). The datasets comprised a training dataset (308 examinations, including 58 examinations with artifact grade = 1 and 250 examinations with artifact grade ≥ 2), a paired test dataset (320 examinations, including 160 examinations with artifact grade = 1 and paired 160 examinations with simulated motion artifacts of grade ≥ 2), and an unpaired test dataset (474 examinations with artifact grade ranging from 1 to 5). The performance of DR-CycleGAN was evaluated and compared with a state-of-the-art network, Cycle-MedGAN V2.0. As a result, in the paired test dataset, DR-CycleGAN demonstrated significantly higher SSIM and PSNR values and lower motion artifact grades compared to Cycle-MedGAN V2.0 (0.89 ± 0.07 vs. 0.84 ± 0.09, 32.88 ± 2.11 vs. 30.81 ± 2.64, and 2.7 ± 0.7 vs. 3.0 ± 0.9, respectively; p < 0.001 each). In the unpaired test dataset, DR-CycleGAN also exhibited a superior motion artifact correction performance, resulting in a significant decrease in motion artifact grades from 2.9 ± 1.3 to 2.0 ± 0.6 compared to Cycle-MedGAN V2.0 (to 2.4 ± 0.9, p < 0.001). In conclusion, DR-CycleGAN effectively reduces motion artifacts in the arterial phase images of gadoxetic acid-enhanced liver MRI examinations, offering the potential to enhance image quality.

Improving MR image quality with a multi-task model, using convolutional losses

PURPOSE

During the acquisition of MRI data, patient-, sequence-, or hardware-related factors can introduce artefacts that degrade image quality. Four of the most significant tasks for improving MRI image quality have been bias field correction, super-resolution, motion-, and noise correction. Machine learning has achieved outstanding results in improving MR image quality for these tasks individually, yet multi-task methods are rarely explored.

METHODS

In this study, we developed a model to simultaneously correct for all four aforementioned artefacts using multi-task learning. Two different datasets were collected, one consisting of brain scans while the other pelvic scans, which were used to train separate models, implementing their corresponding artefact augmentations. Additionally, we explored a novel loss function that does not only aim to reconstruct the individual pixel values, but also the image gradients, to produce sharper, more realistic results. The difference between the evaluated methods was tested for significance using a Friedman test of equivalence followed by a Nemenyi post-hoc test.

RESULTS

Our proposed model generally outperformed other commonly-used correction methods for individual artefacts, consistently achieving equal or superior results in at least one of the evaluation metrics. For images with multiple simultaneous artefacts, we show that the performance of using a combination of models, trained to correct individual artefacts depends heavily on the order that they were applied. This is not an issue for our proposed multi-task model. The model trained using our novel convolutional loss function always outperformed the model trained with a mean squared error loss, when evaluated using Visual Information Fidelity, a quality metric connected to perceptual quality.

CONCLUSION

We trained two models for multi-task MRI artefact correction of brain, and pelvic scans. We used a novel loss function that significantly improves the image quality of the outputs over using mean squared error. The approach performs well on real world data, and it provides insight into which artefacts it detects and corrects for. Our proposed model and source code were made publicly available.

Robust retrospective motion correction of head motion using navigator-based and markerless motion tracking techniques

PURPOSE

This study investigated the artifacts arising from different types of head motion in brain MR images and how well these artifacts can be compensated using retrospective correction based on two different motion-tracking techniques.

METHODS

MPRAGE images were acquired using a 3 T MR scanner on a cohort of nine healthy participants. Subjects moved their head to generate circular motion (4 or 6 cycles/min), stepwise motion (small and large) and "simulated realistic" motion (nodding and slow diagonal motion), based on visual instructions. One MPRAGE scan without deliberate motion was always acquired as a "no motion" reference. Three dimensional fat-navigator (FatNavs) and a Tracoline markerless device (TracInnovations) were used to obtain motion estimates and images were separately reconstructed retrospectively from the raw data based on these different motion estimates.

RESULTS

Image quality was recovered from both motion tracking techniques in our stepwise and slow diagonal motion scenarios in almost all cases, with the apparent visual image quality comparable to the no-motion case. FatNav-based motion correction was further improved in the case of stepwise motion using a skull masking procedure to exclude non-rigid motion of the neck from the co-registration step. In the case of circular motion, both methods struggled to correct for all motion artifacts.

CONCLUSION

High image quality could be recovered in cases of stepwise and slow diagonal motion using both motion estimation techniques. The circular motion scenario led to more severe image artifacts that could not be fully compensated by the retrospective motion correction techniques used.

Unsupervised dual-domain disentangled network for removal of rigid motion artifacts in MRI

Motion artifacts in magnetic resonance imaging (MRI) have always been a serious issue because they can affect subsequent diagnosis and treatment. Supervised deep learning methods have been investigated for the removal of motion artifacts; however, they require paired data that are difficult to obtain in clinical settings. Although unsupervised methods are widely proposed to fully use clinical unpaired data, they generally focus on anatomical structures generated by the spatial domain while ignoring phase error (deviations or inaccuracies in phase information that are possibly caused by rigid motion artifacts during image acquisition) provided by the frequency domain. In this study, a 2D unsupervised deep learning method named unsupervised disentangled dual-domain network (UDDN) was proposed to effectively disentangle and remove unwanted rigid motion artifacts from images. In UDDN, a dual-domain encoding module was presented to capture different types of information from the spatial and frequency domains to enrich the information. Moreover, a cross-domain attention fusion module was proposed to effectively fuse information from different domains, reduce information redundancy, and improve the performance of motion artifact removal. UDDN was validated on a publicly available dataset and a clinical dataset. Qualitative and quantitative experimental results showed that our method could effectively remove motion artifacts and reconstruct image details. Moreover, the performance of UDDN surpasses that of several state-of-the-art unsupervised methods and is comparable with that of the supervised method. Therefore, our method has great potential for clinical application in MRI, such as real-time removal of rigid motion artifacts.

Quality assurance for magnetic resonance angiography of the chest in patients suspected of pulmonary embolism during iodinated contrast shortage in the emergency department setting

Objectives

COVID-19 lockdowns resulted in a global shortage of iodinated contrast media. Therefore, alternative imaging protocols were devised to evaluate patients arriving to the emergency department (ED) with suspicion of pulmonary embolism (PE). This quality assurance (QA) aims to compare diagnostic potential between alternative magnetic resonance angiography (MRA) protocol over the gold standard computed tomography angiography (CTA) by evaluating MRA imaging quality, scanner type/imaging sequence, and any risk of misdiagnosis in patients with symptoms of PE.

Material and Methods

This retrospective study compromised of 55 patients who arrived to ED and underwent MRA of the chest for suspicion of PE during the months of May to June 2022. Data regarding their chief complaints, imaging sequence, and MRA results were collected. Two fellowship-trained faculty radiologists reviewed the MRA scans of the patients and scored the quality using a Likert scale.

Results

Two patients were positive for PE and 53 patients showed negative results. Regarding the scan quality issues, motion was noted in 80% of the 55 studies that we reviewed. Significant associations (P < 0.009) between Likert scale scores and initial complaint category were found. The characteristic symptoms associated with suspicion of PE, namely, shortness of breath, chest pain, and cough were distributed among the 1 and 2 categories, reflecting the most optimal vessel opacification scores. We found no risk of misdiagnosis after reviewing the electronic medical record for follow-up appointments within 6 months of ED visit.

Conclusion

Patients were screened for PE with MRA as an alternative imaging tool during times of contrast shortage. Further, evaluation of MRA with CTA, side by side, in a larger patient population is required to increase the validity of our QA study.

A review of PET attenuation correction methods for PET-MR

Despite being thirteen years since the installation of the first PET-MR system, the scanners constitute a very small proportion of the total hybrid PET systems installed. This is in stark contrast to the rapid expansion of the PET-CT scanner, which quickly established its importance in patient diagnosis within a similar timeframe. One of the main hurdles is the development of an accurate, reproducible and easy-to-use method for attenuation correction. Quantitative discrepancies in PET images between the manufacturer-provided MR methods and the more established CT- or transmission-based attenuation correction methods have led the scientific community in a continuous effort to develop a robust and accurate alternative. These can be divided into four broad categories: (i) MR-based, (ii) emission-based, (iii) atlas-based and the (iv) machine learning-based attenuation correction, which is rapidly gaining momentum. The first is based on segmenting the MR images in various tissues and allocating a predefined attenuation coefficient for each tissue. Emission-based attenuation correction methods aim in utilising the PET emission data by simultaneously reconstructing the radioactivity distribution and the attenuation image. Atlas-based attenuation correction methods aim to predict a CT or transmission image given an MR image of a new patient, by using databases containing CT or transmission images from the general population. Finally, in machine learning methods, a model that could predict the required image given the acquired MR or non-attenuation-corrected PET image is developed by exploiting the underlying features of the images. Deep learning methods are the dominant approach in this category. Compared to the more traditional machine learning, which uses structured data for building a model, deep learning makes direct use of the acquired images to identify underlying features. This up-to-date review goes through the literature of attenuation correction approaches in PET-MR after categorising them. The various approaches in each category are described and discussed. After exploring each category separately, a general overview is given of the current status and potential future approaches along with a comparison of the four outlined categories.

Assessment of Microvascular Disease in Heart and Brain by MRI: Application in Heart Failure with Preserved Ejection Fraction and Cerebral Small Vessel Disease

The objective of this review is to investigate the commonalities of microvascular (small vessel) disease in heart failure with preserved ejection fraction (HFpEF) and cerebral small vessel disease (CSVD). Furthermore, the review aims to evaluate the current magnetic resonance imaging (MRI) diagnostic techniques for both conditions. By comparing the two conditions, this review seeks to identify potential opportunities to improve the understanding of both HFpEF and CSVD.

Regional, circuit and network heterogeneity of brain abnormalities in psychiatric disorders

The substantial individual heterogeneity that characterizes people with mental illness is often ignored by classical case-control research, which relies on group mean comparisons. Here we present a comprehensive, multiscale characterization of the heterogeneity of gray matter volume (GMV) differences in 1,294 cases diagnosed with one of six conditions (attention-deficit/hyperactivity disorder, autism spectrum disorder, bipolar disorder, depression, obsessive-compulsive disorder and schizophrenia) and 1,465 matched controls. Normative models indicated that person-specific deviations from population expectations for regional GMV were highly heterogeneous, affecting the same area in <7% of people with the same diagnosis. However, these deviations were embedded within common functional circuits and networks in up to 56% of cases. The salience-ventral attention system was implicated transdiagnostically, with other systems selectively involved in depression, bipolar disorder, schizophrenia and attention-deficit/hyperactivity disorder. Phenotypic differences between cases assigned the same diagnosis may thus arise from the heterogeneous localization of specific regional deviations, whereas phenotypic similarities may be attributable to the dysfunction of common functional circuits and networks.

A History of Innovation: Tracing the Evolution of Imaging Modalities for the Preoperative Planning of Microsurgical Breast Reconstruction

Breast reconstruction is an essential component in the multidisciplinary management of breast cancer patients. Over the years, preoperative planning has played a pivotal role in assisting surgeons in planning operative decisions prior to the day of surgery. The evolution of preoperative planning can be traced back to the introduction of modalities such as ultrasound and colour duplex ultrasonography, enabling surgeons to evaluate the donor site's vasculature and thereby plan operations more accurately. However, the limitations of these techniques paved the way for the implementation of modern three-dimensional imaging technologies. With the advancements in 3D imaging, including computed tomography and magnetic resonance imaging, surgeons gained the ability to obtain detailed anatomical information. Moreover, numerous adjuncts have been developed to aid in the planning process. The integration of 3D-printing technologies has made significant contributions, enabling surgeons to create complex haptic models of the underlying anatomy. Direct infrared thermography provides a non-invasive, visual assessment of abdominal wall vascular physiology. Additionally, augmented reality technologies are poised to reshape surgical planning by providing an immersive and interactive environment for surgeons to visualize and manipulate 3D reconstructions. Still, the future of preoperative planning in breast reconstruction holds immense promise. Most recently, artificial intelligence algorithms, utilising machine learning and deep learning techniques, have the potential to automate and enhance preoperative planning processes. This review provides a comprehensive assessment of the history of innovation in preoperative planning for breast reconstruction, while also outlining key future directions, and the impact of artificial intelligence in this field.

Multi-parametric MRI for radiotherapy simulation

Magnetic resonance imaging (MRI) has become an important imaging modality in the field of radiotherapy (RT) in the past decade, especially with the development of various novel MRI and image-guidance techniques. In this review article, we will describe recent developments and discuss the applications of multi-parametric MRI (mpMRI) in RT simulation. In this review, mpMRI refers to a general and loose definition which includes various multi-contrast MRI techniques. Specifically, we will focus on the implementation, challenges, and future directions of mpMRI techniques for RT simulation.

Deep Learning-Generated Synthetic MR Imaging STIR Spine Images Are Superior in Image Quality and Diagnostically Equivalent to Conventional STIR: A Multicenter, Multireader Trial

BACKGROUND AND PURPOSE

Deep learning image reconstruction allows faster MR imaging acquisitions while matching or exceeding the standard of care and can create synthetic images from existing data sets. This multicenter, multireader spine study evaluated the performance of synthetically created STIR compared with acquired STIR.

MATERIALS AND METHODS

From a multicenter, multiscanner data base of 328 clinical cases, a nonreader neuroradiologist randomly selected 110 spine MR imaging studies in 93 patients (sagittal T1, T2, and STIR) and classified them into 5 categories of disease and healthy. A DICOM-based deep learning application generated a synthetically created STIR series from the sagittal T1 and T2 images. Five radiologists (3 neuroradiologists, 1 musculoskeletal radiologist, and 1 general radiologist) rated the STIR quality and classified disease pathology (study 1, n = 80). They then assessed the presence or absence of findings typically evaluated with STIR in patients with trauma (study 2, n = 30). The readers evaluated studies with either acquired STIR or synthetically created STIR in a blinded and randomized fashion with a 1-month washout period. The interchangeability of acquired STIR and synthetically created STIR was assessed using a noninferiority threshold of 10%.

RESULTS

For classification, there was a decrease in interreader agreement expected by randomly introducing synthetically created STIR of 3.23%. For trauma, there was an overall increase in interreader agreement by +1.9%. The lower bound of confidence for both exceeded the noninferiority threshold, indicating interchangeability of synthetically created STIR with acquired STIR. Both the Wilcoxon signed-rank and t tests showed higher image-quality scores for synthetically created STIR over acquired STIR (P < .0001).

CONCLUSIONS

Synthetically created STIR spine MR images were diagnostically interchangeable with acquired STIR, while providing significantly higher image quality, suggesting routine clinical practice potential.

Automatic brain MRI motion artifact detection based on end-to-end deep learning is similarly effective as traditional machine learning trained on image quality metrics

Head motion artifacts in magnetic resonance imaging (MRI) are an important confounding factor concerning brain research as well as clinical practice. For this reason, several machine learning-based methods have been developed for the automatic quality control of structural MRI scans. Deep learning offers a promising solution to this problem, however, given its data-hungry nature and the scarcity of expert-annotated datasets, its advantage over traditional machine learning methods in identifying motion-corrupted brain scans is yet to be determined. In the present study, we investigated the relative advantage of the two methods in structural MRI quality control. To this end, we collected publicly available T1-weighted images and scanned subjects in our own lab under conventional and active head motion conditions. The quality of the images was rated by a team of radiologists from the point of view of clinical diagnostic use. We present a relatively simple, lightweight 3D convolutional neural network trained in an end-to-end manner that achieved a test set (N = 411) balanced accuracy of 94.41% in classifying brain scans into clinically usable or unusable categories. A support vector machine trained on image quality metrics achieved a balanced accuracy of 88.44% on the same test set. Statistical comparison of the two models yielded no significant difference in terms of confusion matrices, error rates, or receiver operating characteristic curves. Our results suggest that these machine learning methods are similarly effective in identifying severe motion artifacts in brain MRI scans, and underline the efficacy of end-to-end deep learning-based systems in brain MRI quality control, allowing the rapid evaluation of diagnostic utility without the need for elaborate image pre-processing.

Mixed methodology in human brain research: integrating MRI and histology

Postmortem magnetic resonance imaging (MRI) can provide a bridge between histological observations and the in vivo anatomy of the human brain. Approaches aimed at the co-registration of data derived from the two techniques are gaining interest. Optimal integration of the two research fields requires detailed knowledge of the tissue property requirements for individual research techniques, as well as a detailed understanding of the consequences of tissue fixation steps on the imaging quality outcomes for both MRI and histology. Here, we provide an overview of existing studies that bridge between state-of-the-art imaging modalities, and discuss the background knowledge incorporated into the design, execution and interpretation of postmortem studies. A subset of the discussed challenges transfer to animal studies as well. This insight can contribute to furthering our understanding of the normal and diseased human brain, and to facilitate discussions between researchers from the individual disciplines.

Generalizable Deep Learning Method for Suppressing Unseen and Multiple MRI Artifacts Using Meta-learning

Magnetic Resonance (MR) images suffer from various types of artifacts due to motion, spatial resolution, and under-sampling. Conventional deep learning methods deal with removing a specific type of artifact, leading to separately trained models for each artifact type that lack the shared knowledge generalizable across artifacts. Moreover, training a model for each type and amount of artifact is a tedious process that consumes more training time and storage of models. On the other hand, the shared knowledge learned by jointly training the model on multiple artifacts might be inadequate to generalize under deviations in the types and amounts of artifacts. Model-agnostic meta-learning (MAML), a nested bi-level optimization framework is a promising technique to learn common knowledge across artifacts in the outer level of optimization, and artifact-specific restoration in the inner level. We propose curriculum-MAML (CMAML), a learning process that integrates MAML with curriculum learning to impart the knowledge of variable artifact complexity to adaptively learn restoration of multiple artifacts during training. Comparative studies against Stochastic Gradient Descent and MAML, using two cardiac datasets reveal that CMAML exhibits (i) better generalization with improved PSNR for 83% of unseen types and amounts of artifacts and improved SSIM in all cases, and (ii) better artifact suppression in 4 out of 5 cases of composite artifacts (scans with multiple artifacts).Clinical relevance- Our results show that CMAML has the potential to minimize the number of artifact-specific models; which is essential to deploy deep learning models for clinical use. Furthermore, we have also taken another practical scenario of an image affected by multiple artifacts and show that our method performs better in 80% of cases.

Image quality assessment using deep learning in high b-value diffusion-weighted breast MRI

The objective of this IRB approved retrospective study was to apply deep learning to identify magnetic resonance imaging (MRI) artifacts on maximum intensity projections (MIP) of the breast, which were derived from diffusion weighted imaging (DWI) protocols. The dataset consisted of 1309 clinically indicated breast MRI examinations of 1158 individuals (median age [IQR]: 50 years [16.75 years]) acquired between March 2017 and June 2020, in which a DWI sequence with a high b-value equal to 1500 s/mm2 was acquired. From these, 2D MIP images were computed and the left and right breast were cropped out as regions of interest (ROI). The presence of MRI image artifacts on the ROIs was rated by three independent observers. Artifact prevalence in the dataset was 37% (961 out of 2618 images). A DenseNet was trained with a fivefold cross-validation to identify artifacts on these images. In an independent holdout test dataset (n = 350 images) artifacts were detected by the neural network with an area under the precision-recall curve of 0.921 and a positive predictive value of 0.981. Our results show that a deep learning algorithm is capable to identify MRI artifacts in breast DWI-derived MIPs, which could help to improve quality assurance approaches for DWI sequences of breast examinations in the future.

Photon Counting Detector Computed Tomography: A New Frontier of Myeloma Bone Disease Evaluation

Photon counting detector (PCD) computed tomography (CT) is a paradigm-shifting innovation in CT imaging which was recently granted approval for clinical use by the US Food and Drug Administration. PCD-CT allows the generation of multi-energy images with increased contrast and scanning speed or ultra-high spatial resolution (UHR) images with lower radiation doses, compared to the currently used energy integrating detector (EID) CT. Since the recognition of bone disease related to multiple myeloma is important for the diagnosis and management of patients, the advent of PCD-CT heralds a new era in superior diagnostic evaluation of myeloma bone disease. In a first-in-human pilot study, patients with multiple myeloma were imaged with UHR-PCD-CT to validate and establish the utility of this technology in routine imaging and clinical care. We describe 2 cases from that cohort to highlight the superior imaging performance and diagnostic potential of PCD-CT for multiple myeloma compared to clinical standard EID-CT. We also discuss how the advanced imaging capabilities from PCD-CT enhances clinical diagnostics to improve care and overall outcomes for patients.

Single Breath-Hold 3-Dimensional Magnetic Resonance Elastography Depicts Liver Fibrosis and Inflammation in Obese Patients

OBJECTIVES

Three-dimensional (3D) magnetic resonance elastography (MRE) measures liver fibrosis and inflammation but requires several breath-holds that hamper clinical acceptance. The aim of this study was to evaluate the technical and clinical feasibility of a single breath-hold 3D MRE sequence as a means of measuring liver fibrosis and inflammation in obese patients.

METHODS

From November 2020 to December 2021, subjects were prospectively enrolled and divided into 2 groups. Group 1 included healthy volunteers (n = 10) who served as controls to compare the single breath-hold 3D MRE sequence with a multiple-breath-hold 3D MRE sequence. Group 2 included liver patients (n = 10) who served as participants to evaluate the clinical feasibility of the single breath-hold 3D MRE sequence in measuring liver fibrosis and inflammation. Controls and participants were scanned at 60 Hz mechanical excitation with the single breath-hold 3D MRE sequence to retrieve the magnitude of the complex-valued shear modulus (|G*| [kPa]), the shear wave speed (Cs [m/s]), and the loss modulus (G" [kPa]). The controls were also scanned with a multiple-breath-hold 3D MRE sequence for comparison, and the participants had histopathology (Ishak scores) for correlation with Cs and G".

RESULTS

For the 10 controls, 5 were female, and the mean age and body mass index were 33.1 ± 9.5 years and 23.0 ± 2.1 kg/m 2 , respectively. For the 10 participants, 8 were female, and the mean age and body mass index were 45.1 ± 16.5 years and 33.1 ± 4.0 kg/m 2 (obese range), respectively. All participants were suspected of having nonalcoholic fatty liver disease. Bland-Altman analysis of the comparison in controls shows there are nonsignificant differences in |G*|, Cs, and G" below 6.5%, suggesting good consensus between the 2 sequences. For the participants, Cs and G" correlated significantly with Ishak fibrosis and inflammation grades, respectively ( ρ = 0.95, P < 0.001, and ρ = 0.84, P = 0.002).

CONCLUSION

The single breath-hold 3D MRE sequence may be effective in measuring liver fibrosis and inflammation in obese patients.

Clinical Impact of Deep Learning Reconstruction in MRI

Deep learning has been recognized as a paradigm-shifting tool in radiology. Deep learning reconstruction (DLR) has recently emerged as a technology used in the image reconstruction process of MRI, which is an essential procedure in generating MR images. Denoising, which is the first DLR application to be realized in commercial MRI scanners, improves signal-to-noise ratio. When applied to lower magnetic field-strength scanners, the signal-to-noise ratio can be increased without extending the imaging time, and image quality is comparable to that of higher-field-strength scanners. Shorter imaging times decrease patient discomfort and reduce MRI scanner running costs. The incorporation of DLR into accelerated acquisition imaging techniques, such as parallel imaging or compressed sensing, shortens the reconstruction time. DLR is based on supervised learning using convolutional layers and is divided into the following three categories: image domain, k-space learning, and direct mapping types. Various studies have reported other derivatives of DLR, and several have shown the feasibility of DLR in clinical practice. Although DLR efficiently reduces Gaussian noise from MR images, denoising makes image artifacts more prominent, and a solution to this problem is desired. Depending on the training of the convolutional neural network, DLR may change the imaging features of lesions and obscure small lesions. Therefore, radiologists may need to adopt the habit of questioning whether any information has been lost on images that appear clean. ^©RSNA, 2023 Quiz questions for this article are available in the supplemental material.

Evaluation of motion artefact reduction depending on the artefacts' directions in head MRI using conditional generative adversarial networks

Motion artefacts caused by the patient's body movements affect magnetic resonance imaging (MRI) accuracy. This study aimed to compare and evaluate the accuracy of motion artefacts correction using a conditional generative adversarial network (CGAN) with an autoencoder and U-net models. The training dataset consisted of motion artefacts generated through simulations. Motion artefacts occur in the phase encoding direction, which is set to either the horizontal or vertical direction of the image. To create T2-weighted axial images with simulated motion artefacts, 5500 head images were used in each direction. Of these data, 90% were used for training, while the remainder were used for the evaluation of image quality. Moreover, the validation data used in the model training consisted of 10% of the training dataset. The training data were divided into horizontal and vertical directions of motion artefact appearance, and the effect of combining this data with the training dataset was verified. The resulting corrected images were evaluated using structural image similarity (SSIM) and peak signal-to-noise ratio (PSNR), and the metrics were compared with the images without motion artefacts. The best improvements in the SSIM and PSNR were observed in the consistent condition in the direction of the occurrence of motion artefacts in the training and evaluation datasets. However, SSIM > 0.9 and PSNR > 29 dB were accomplished for the learning model with both image directions. The latter model exhibited the highest robustness for actual patient motion in head MRI images. Moreover, the image quality of the corrected image with the CGAN was the closest to that of the original image, while the improvement rates for SSIM and PSNR were approximately 26% and 7.7%, respectively. The CGAN model demonstrated a high image reproducibility, and the most significant model was the consistent condition of the learning model and the direction of the appearance of motion artefacts.

Quantifying MR Head Motion in the Rhineland Study - A Robust Method for Population Cohorts

Head motion during MR acquisition reduces image quality and has been shown to bias neuromorphometric analysis. The quantification of head motion, therefore, has both neuroscientific as well as clinical applications, for example, to control for motion in statistical analyses of brain morphology, or as a variable of interest in neurological studies. The accuracy of markerless optical head tracking, however, is largely unexplored. Furthermore, no quantitative analysis of head motion in a general, mostly healthy population cohort exists thus far. In this work, we present a robust registration method for the alignment of depth camera data that sensitively estimates even small head movements of compliant participants. Our method outperforms the vendor-supplied method in three validation experiments: 1. similarity to fMRI motion traces as a low-frequency reference, 2. recovery of the independently acquired breathing signal as a high-frequency reference, and 3. correlation with image-based quality metrics in structural T1-weighted MRI. In addition to the core algorithm, we establish an analysis pipeline that computes average motion scores per time interval or per sequence for inclusion in downstream analyses. We apply the pipeline in the Rhineland Study, a large population cohort study, where we replicate age and body mass index (BMI) as motion correlates and show that head motion significantly increases over the duration of the scan session. We observe weak, yet significant interactions between this within-session increase and age, BMI, and sex. High correlations between fMRI and camera-based motion scores of proceeding sequences further suggest that fMRI motion estimates can be used as a surrogate score in the absence of better measures to control for motion in statistical analyses.

Application of magnetic resonance image compilation (MAGiC) in the diagnosis of middle-aged and elderly women with osteoporosis

OBJECTIVE

To investigate the feasibility of diagnosing osteoporosis (OP) in women through magnetic resonance image compilation (MAGiC).

METHODS

A total of 110 patients who underwent lumbar magnetic resonance imaging and dual X-ray absorptiometry examinations were collected and divided into two groups according bone mineral density: osteoporotic group (OP) and non-osteoporotic group (non-OP). The variation trends of T1 (longitudinal relaxation time), T2 (transverse relaxation time) and BMD (bone mineral density) with the increase of age, and the correlation of T1 and T2 with BMD were examined by establishing a clinical mathematical model.

RESULTS

With the increase of age, BMD and T1 value decreased gradually, while T2 value increased. T1 and T2 had statistical significance in diagnosing OP (P < 0.001), and there is moderate positive correlation between T1 and BMD values (R = 0.636, P < 0.001), while moderate negative correlation between T2 and BMD values (R=-0.694, P < 0.001). Receiver characteristic curve test showed that T1 and T2 had high accuracy in diagnosing OP (T1 AUC = 0.982, T2 AUC = 0.978), and the critical values of T1 and T2 for evaluating osteoporosis were 0.625s and 0.095s, respectively. Besides, the combined utilization of T1 and T2 had higher diagnostic efficiency (AUC = 0.985). Combined T1 and T2 had higher diagnostic efficiency (AUC = 0.985). Function fitting results of OP group: BMD=-0.0037* age - 0.0015*T1 + 0.0037*T2 + 0.86, sum of squared error (SSE) = 0.0392, and non-OP group: BMD = 0.0024* age - 0.0071*T1 + 0.0007*T2 + 1.41, SSE = 0.1007.

CONCLUSION

T1 and T2 value of MAGiC have high efficiency in diagnosing OP by establishing a function fitting formula of BMD with T1, T2 and age.

Motion guidance lines for robust data consistency-based retrospective motion correction in 2D and 3D MRI

PURPOSE

To develop a robust retrospective motion-correction technique based on repeating k-space guidance lines for improving motion correction in Cartesian 2D and 3D brain MRI.

METHODS

The motion guidance lines are inserted into the standard sequence orderings for 2D turbo spin echo and 3D MPRAGE to inform a data consistency-based motion estimation and reconstruction, which can be guided by a low-resolution scout. The extremely limited number of required guidance lines are repeated during each echo train and discarded in the final image reconstruction. Thus, integration within a standard k-space acquisition ordering ensures the expected image quality/contrast and motion sensitivity of that sequence.

RESULTS

Through simulation and in vivo 2D multislice and 3D motion experiments, we demonstrate that respectively 2 or 4 optimized motion guidance lines per shot enables accurate motion estimation and correction. Clinically acceptable reconstruction times are achieved through fully separable on-the-fly motion optimizations (˜1 s/shot) using standard scanner GPU hardware.

CONCLUSION

The addition of guidance lines to scout accelerated motion estimation facilitates robust retrospective motion correction that can be effectively introduced without perturbing standard clinical protocols and workflows.

A numerical human brain phantom for dynamic glucose-enhanced (DGE) MRI: On the influence of head motion at 3T

PURPOSE

Dynamic glucose-enhanced (DGE) MRI relates to a group of exchange-based MRI techniques where the uptake of glucose analogues is studied dynamically. However, motion artifacts can be mistaken for true DGE effects, while motion correction may alter true signal effects. The aim was to design a numerical human brain phantom to simulate a realistic DGE MRI protocol at 3T that can be used to assess the influence of head movement on the signal before and after retrospective motion correction.

METHODS

MPRAGE data from a tumor patient were used to simulate dynamic Z-spectra under the influence of motion. The DGE responses for different tissue types were simulated, creating a ground truth. Rigid head movement patterns were applied as well as physiological dilatation and pulsation of the lateral ventricles and head-motion-induced B0 -changes in presence of first-order shimming. The effect of retrospective motion correction was evaluated.

RESULTS

Motion artifacts similar to those previously reported for in vivo DGE data could be reproduced. Head movement of 1 mm translation and 1.5 degrees rotation led to a pseudo-DGE effect on the order of 1% signal change. B0 effects due to head motion altered DGE changes due to a shift in the water saturation spectrum. Pseudo DGE effects were partly reduced or enhanced by rigid motion correction depending on tissue location.

CONCLUSION

DGE MRI studies can be corrupted by motion artifacts. Designing post-processing methods using retrospective motion correction including B0 correction will be crucial for clinical implementation. The proposed phantom should be useful for evaluation and optimization of such techniques.

Germany's journey toward 14 Tesla human magnetic resonance

Multiple sites within Germany operate human MRI systems with magnetic fields either at 7 Tesla or 9.4 Tesla. In 2013, these sites formed a network to facilitate and harmonize the research being conducted at the different sites and make this technology available to a larger community of researchers and clinicians not only within Germany, but also worldwide. The German Ultrahigh Field Imaging (GUFI) network has defined a strategic goal to establish a 14 Tesla whole-body human MRI system as a national research resource in Germany as the next progression in magnetic field strength. This paper summarizes the history of this initiative, the current status, the motivation for pursuing MR imaging and spectroscopy at such a high magnetic field strength, and the technical and funding challenges involved. It focuses on the scientific and science policy process from the perspective in Germany, and is not intended to be a comprehensive systematic review of the benefits and technical challenges of higher field strengths.

The MotoNet: A 3 Tesla MRI-Conditional EEG Net with Embedded Motion Sensors

We introduce a new electroencephalogram (EEG) net, which will allow clinicians to monitor EEG while tracking head motion. Motion during MRI limits patient scans, especially of children with epilepsy. EEG is also severely affected by motion-induced noise, predominantly ballistocardiogram (BCG) noise due to the heartbeat.

METHODS

The MotoNet was built using polymer thick film (PTF) EEG leads and motion sensors on opposite sides in the same flex circuit. EEG/motion measurements were made with a standard commercial EEG acquisition system in a 3 Tesla (T) MRI. A Kalman filtering-based BCG correction tool was used to clean the EEG in healthy volunteers.

RESULTS

MRI safety studies in 3 T confirmed the maximum heating below 1 °C. Using an MRI sequence with spatial localization gradients only, the position of the head was linearly correlated with the average motion sensor output. Kalman filtering was shown to reduce the BCG noise and recover artifact-clean EEG.

CONCLUSIONS

The MotoNet is an innovative EEG net design that co-locates 32 EEG electrodes with 32 motion sensors to improve both EEG and MRI signal quality. In combination with custom gradients, the position of the net can, in principle, be determined. In addition, the motion sensors can help reduce BCG noise.

A radiofrequency coil for infants and toddlers

Infants and toddlers are a challenging population upon which to perform magnetic resonance imaging (MRI) of the brain, both in research and clinical settings. Because of the large range in head size during the early years of development, paediatric neuro-MRI requires a radiofrequency (RF) coil, or set of coils, that is tailored to head size to provide the highest image quality. Mitigating techniques must also be employed to reduce and correct for subject motion. This manuscript describes an RF coil with a tailored mechanical-electrical design that can adapt to the head size of 3-month-old infants to 3-year-old toddlers. The RF coil was designed with tight-fitting coil elements to improve the signal-to-noise ratio (SNR) in comparison with commercially available adult head coils, while simultaneously aiding in immobilization. The coil was designed without visual obstruction to facilitate an unimpeded view of the child's face and the potential application of camera or motion-tracking systems. Despite the lack of elements over the face, the paediatric coil produced higher SNR over most of the brain compared with adult coils, including more than twofold in the periphery. Acceleration rates of fourfold in each Cartesian direction could be achieved. High SNR allowed for short acquisition times through accelerated imaging protocols and reduced the probability of motion during a scan. Modification of the acquisition protocol, with immobilization of the head through the adjustable coil geometry, and subsequently being combined with a motion-tracking system, provides a compelling platform for scanning paediatric populations without sedation and with improved image quality.

Camera-based Prospective Motion Correction in Paediatric Epilepsy Patients Enables EEG-fMRI Localization Even in High-motion States

BACKGROUND

EEG-fMRI is a useful additional test to localize the epileptogenic zone (EZ) particularly in MRI negative cases. However subject motion presents a particular challenge owing to its large effects on both MRI and EEG signal. Traditionally it is assumed that prospective motion correction (PMC) of fMRI precludes EEG artifact correction.

METHODS

Children undergoing presurgical assessment at Great Ormond Street Hospital were included into the study. PMC of fMRI was done using a commercial system with a Moiré Phase Tracking marker and MR-compatible camera. For retrospective EEG correction both a standard and a motion educated EEG artefact correction (REEGMAS) were compared to each other.

RESULTS

Ten children underwent simultaneous EEG-fMRI. Overall head movement was high (mean RMS velocity < 1.5 mm/s) and showed high inter- and intra-individual variability. Comparing motion measured by the PMC camera and the (uncorrected residual) motion detected by realignment of fMRI images, there was a five-fold reduction in motion from its prospective correction. Retrospective EEG correction using both standard approaches and REEGMAS allowed the visualization and identification of physiological noise and epileptiform discharges. Seven of 10 children had significant maps, which were concordant with the clinical EZ hypothesis in 6 of these 7.

CONCLUSION

To our knowledge this is the first application of camera-based PMC for MRI in a pediatric clinical setting. Despite large amount of movement PMC in combination with retrospective EEG correction recovered data and obtained clinically meaningful results during high levels of subject motion. Practical limitations may currently limit the widespread use of this technology.

Compare image quality of T2-weighted imaging with different phase acceleration factors

Previous studies demonstrated that adjusting the phase acceleration (PA) factors could influence image quality. To improve image quality and decrease respiratory artifacts of lesions in the liver on T2-weighted image by adjusting PA factor and number of excitation (NEX). Sixty consecutive patients with hepatic lesions were enrolled in this prospective research between May 2020 and June 2020. All patients had 3.0T magnetic resonance imaging with 4 sequences (combining PA factors and NEXs, the former was 2 and 3, the latter were 1.5 and 2, respectively, with the same other scanning parameters). Two readers used 5-point quality scales to assess image quality. The signal intensity was measured by drawing regions of interest in the liver, spleen, and background on the T2-weighted imaging. Artifacts, overall image impression, and vascular conspicuity were better when the PA factor was 3 than 2. Artifacts and vascular conspicuity were better when NEX was 2 than 1.5. PA factor 3 and NEX 2 got a higher score in 5-point quality scales and less scan time than the other 3 sequences. Meanwhile, the signal-to-noise ratio of PA factor 3 and NEX 2 was best among these 4 sequences. PA factor and NEX could influence the imaging quality and lesion-to-hepatic contrast in detecting hepatic lesions on T2-weighted images. PA factor 3 and NEX 2 may have a positive effect in the clinic, especially for those with irregular respiration, as it decreased artifacts and reduced scan time.

iBEAT V2.0: a multisite-applicable, deep learning-based pipeline for infant cerebral cortical surface reconstruction

The human cerebral cortex undergoes dramatic and critical development during early postnatal stages. Benefiting from advances in neuroimaging, many infant brain magnetic resonance imaging (MRI) datasets have been collected from multiple imaging sites with different scanners and imaging protocols for the investigation of normal and abnormal early brain development. However, it is extremely challenging to precisely process and quantify infant brain development with these multisite imaging data because infant brain MRI scans exhibit (a) extremely low and dynamic tissue contrast caused by ongoing myelination and maturation and (b) inter-site data heterogeneity resulting from the use of diverse imaging protocols/scanners. Consequently, existing computational tools and pipelines typically perform poorly on infant MRI data. To address these challenges, we propose a robust, multisite-applicable, infant-tailored computational pipeline that leverages powerful deep learning techniques. The main functionality of the proposed pipeline includes preprocessing, brain skull stripping, tissue segmentation, topology correction, cortical surface reconstruction and measurement. Our pipeline can handle both T1w and T2w structural infant brain MR images well in a wide age range (from birth to 6 years of age) and is effective for different imaging protocols/scanners, despite being trained only on the data from the Baby Connectome Project. Extensive comparisons with existing methods on multisite, multimodal and multi-age datasets demonstrate superior effectiveness, accuracy and robustness of our pipeline. We have maintained a website, iBEAT Cloud, for users to process their images with our pipeline ( http://www.ibeat.cloud ), which has successfully processed over 16,000 infant MRI scans from more than 100 institutions with various imaging protocols/scanners.

BigBrain-MR: a new digital phantom with anatomically-realistic magnetic resonance properties at 100-µm resolution for magnetic resonance methods development

The benefits, opportunities and growing availability of ultra-high field magnetic resonance imaging (MRI) for humans have prompted an expansion in research and development efforts towards increasingly more advanced high-resolution imaging techniques. To maximize their effectiveness, these efforts need to be supported by powerful computational simulation platforms that can adequately reproduce the biophysical characteristics of MRI, with high spatial resolution. In this work, we have sought to address this need by developing a novel digital phantom with realistic anatomical detail up to 100-µm resolution, including multiple MRI properties that affect image generation. This phantom, termed BigBrain-MR, was generated from the publicly available BigBrain histological dataset and lower-resolution in-vivo 7T-MRI data, using a newly-developed image processing framework that allows mapping the general properties of the latter into the fine anatomical scale of the former. Overall, the mapping framework was found to be effective and robust, yielding a diverse range of realistic "in-vivo-like" MRI contrasts and maps at 100-µm resolution. BigBrain-MR was then tested in three imaging applications (motion effects and interpolation, super-resolution imaging, and parallel imaging reconstruction) to investigate its properties, value and validity as a simulation platform. The results consistently showed that BigBrain-MR can closely approximate the behavior of real in-vivo data, more realistically and with more extensive features than a more classic option such as the Shepp-Logan phantom. Its flexibility in simulating different contrast mechanisms and artifacts may also prove valuable for educational applications. BigBrain-MR is therefore deemed a favorable choice to support methodological development and demonstration in brain MRI, and has been made freely available to the community.