Automatic quality assessment in structural brain magnetic resonance imaging

FetMRQC: A robust quality control system for multi-centric fetal brain MRI

Fetal brain MRI is becoming an increasingly relevant complement to neurosonography for perinatal diagnosis, allowing fundamental insights into fetal brain development throughout gestation. However, uncontrolled fetal motion and heterogeneity in acquisition protocols lead to data of variable quality, potentially biasing the outcome of subsequent studies. We present FetMRQC, an open-source machine-learning framework for automated image quality assessment and quality control that is robust to domain shifts induced by the heterogeneity of clinical data. FetMRQC extracts an ensemble of quality metrics from unprocessed anatomical MRI and combines them to predict experts' ratings using random forests. We validate our framework on a pioneeringly large and diverse dataset of more than 1600 manually rated fetal brain T2-weighted images from four clinical centers and 13 different scanners. Our study shows that FetMRQC's predictions generalize well to unseen data while being interpretable. FetMRQC is a step towards more robust fetal brain neuroimaging, which has the potential to shed new insights on the developing human brain.

Cognitive tasks, anatomical MRI, and functional MRI data evaluating the construct of self-regulation

We describe the following shared data from N = 103 healthy adults who completed a broad set of cognitive tasks, surveys, and neuroimaging measurements to examine the construct of self-regulation. The neuroimaging acquisition involved task-based fMRI, resting state fMRI, and structural MRI. Each subject completed the following ten tasks in the scanner across two 90-minute scanning sessions: attention network test (ANT), cued task switching, Columbia card task, dot pattern expectancy (DPX), delay discounting, simple and motor selective stop signal, Stroop, a towers task, and a set of survey questions. The dataset is shared openly through the OpenNeuro project, and the dataset is formatted according to the Brain Imaging Data Structure (BIDS) standard.

The effect of head motion on brain age prediction using deep convolutional neural networks

Deep learning can be used effectively to predict participants' age from brain magnetic resonance imaging (MRI) data, and a growing body of evidence suggests that the difference between predicted and chronological age-referred to as brain-predicted age difference (brain-PAD)-is related to various neurological and neuropsychiatric disease states. A crucial aspect of the applicability of brain-PAD as a biomarker of individual brain health is whether and how brain-predicted age is affected by MR image artifacts commonly encountered in clinical settings. To investigate this issue, we trained and validated two different 3D convolutional neural network architectures (CNNs) from scratch and tested the models on a separate dataset consisting of motion-free and motion-corrupted T1-weighted MRI scans from the same participants, the quality of which were rated by neuroradiologists from a clinical diagnostic point of view. Our results revealed a systematic increase in brain-PAD with worsening image quality for both models. This effect was also observed for images that were deemed usable from a clinical perspective, with brains appearing older in medium than in good quality images. These findings were also supported by significant associations found between the brain-PAD and standard image quality metrics indicating larger brain-PAD for lower-quality images. Our results demonstrate a spurious effect of advanced brain aging as a result of head motion and underline the importance of controlling for image quality when using brain-predicted age based on structural neuroimaging data as a proxy measure for brain health.

Unsupervised MRI motion artifact disentanglement: introducing MAUDGAN

Objective.This study developed an unsupervised motion artifact reduction method for magnetic resonance imaging (MRI) images of patients with brain tumors. The proposed novel design uses multi-parametric multicenter contrast-enhanced T1W (ceT1W) and T2-FLAIR MRI images.Approach.The proposed framework included two generators, two discriminators, and two feature extractor networks. A 3-fold cross-validation was used to train and fine-tune the hyperparameters of the proposed model using 230 brain MRI images with tumors, which were then tested on 148 patients'in-vivodatasets. An ablation was performed to evaluate the model's compartments. Our model was compared with Pix2pix and CycleGAN. Six evaluation metrics were reported, including normalized mean squared error (NMSE), structural similarity index (SSIM), multi-scale-SSIM (MS-SSIM), peak signal-to-noise ratio (PSNR), visual information fidelity (VIF), and multi-scale gradient magnitude similarity deviation (MS-GMSD). Artifact reduction and consistency of tumor regions, image contrast, and sharpness were evaluated by three evaluators using Likert scales and compared with ANOVA and Tukey's HSD tests.Main results.On average, our method outperforms comparative models to remove heavy motion artifacts with the lowest NMSE (18.34±5.07%) and MS-GMSD (0.07 ± 0.03) for heavy motion artifact level. Additionally, our method creates motion-free images with the highest SSIM (0.93 ± 0.04), PSNR (30.63 ± 4.96), and VIF (0.45 ± 0.05) values, along with comparable MS-SSIM (0.96 ± 0.31). Similarly, our method outperformed comparative models in removingin-vivomotion artifacts for different distortion levels except for MS- SSIM and VIF, which have comparable performance with CycleGAN. Moreover, our method had a consistent performance for different artifact levels. For the heavy level of motion artifacts, our method got the highest Likert scores of 2.82 ± 0.52, 1.88 ± 0.71, and 1.02 ± 0.14 (p-values≪0.0001) for our method, CycleGAN, and Pix2pix respectively. Similar trends were also found for other motion artifact levels.Significance.Our proposed unsupervised method was demonstrated to reduce motion artifacts from the ceT1W brain images under a multi-parametric framework.

The power of many brains: Catalyzing neuropsychiatric discovery through open neuroimaging data and large-scale collaboration

Recent advances in open neuroimaging data are enhancing our comprehension of neuropsychiatric disorders. By pooling images from various cohorts, statistical power has increased, enabling the detection of subtle abnormalities and robust associations, and fostering new research methods. Global collaborations in imaging have furthered our knowledge of the neurobiological foundations of brain disorders and aided in imaging-based prediction for more targeted treatment. Large-scale magnetic resonance imaging initiatives are driving innovation in analytics and supporting generalizable psychiatric studies. We also emphasize the significant role of big data in understanding neural mechanisms and in the early identification and precise treatment of neuropsychiatric disorders. However, challenges such as data harmonization across different sites, privacy protection, and effective data sharing must be addressed. With proper governance and open science practices, we conclude with a projection of how large-scale imaging resources and collaborations could revolutionize diagnosis, treatment selection, and outcome prediction, contributing to optimal brain health.

Simulating rigid head motion artifacts on brain magnitude MRI data-Outcome on image quality and segmentation of the cerebral cortex

Magnetic Resonance Imaging (MRI) datasets from epidemiological studies often show a lower prevalence of motion artifacts than what is encountered in clinical practice. These artifacts can be unevenly distributed between subject groups and studies which introduces a bias that needs addressing when augmenting data for machine learning purposes. Since unreconstructed multi-channel k-space data is typically not available for population-based MRI datasets, motion simulations must be performed using signal magnitude data. There is thus a need to systematically evaluate how realistic such magnitude-based simulations are. We performed magnitude-based motion simulations on a dataset (MR-ART) from 148 subjects in which real motion-corrupted reference data was also available. The similarity of real and simulated motion was assessed by using image quality metrics (IQMs) including Coefficient of Joint Variation (CJV), Signal-to-Noise-Ratio (SNR), and Contrast-to-Noise-Ratio (CNR). An additional comparison was made by investigating the decrease in the Dice-Sørensen Coefficient (DSC) of automated segmentations with increasing motion severity. Segmentation of the cerebral cortex was performed with 6 freely available tools: FreeSurfer, BrainSuite, ANTs, SAMSEG, FastSurfer, and SynthSeg+. To better mimic the real subject motion, the original motion simulation within an existing data augmentation framework (TorchIO), was modified. This allowed a non-random motion paradigm and phase encoding direction. The mean difference in CJV/SNR/CNR between the real motion-corrupted images and our modified simulations (0.004±0.054/-0.7±1.8/-0.09±0.55) was lower than that of the original simulations (0.015±0.061/0.2±2.0/-0.29±0.62). Further, the mean difference in the DSC between the real motion-corrupted images was lower for our modified simulations (0.03±0.06) compared to the original simulations (-0.15±0.09). SynthSeg+ showed the highest robustness towards all forms of motion, real and simulated. In conclusion, reasonably realistic synthetic motion artifacts can be induced on a large-scale when only magnitude MR images are available to obtain unbiased data sets for the training of machine learning based models.

An efficient semi-supervised quality control system trained using physics-based MRI-artefact generators and adversarial training

Large medical imaging data sets are becoming increasingly available. A common challenge in these data sets is to ensure that each sample meets minimum quality requirements devoid of significant artefacts. Despite a wide range of existing automatic methods having been developed to identify imperfections and artefacts in medical imaging, they mostly rely on data-hungry methods. In particular, the scarcity of artefact-containing scans available for training has been a major obstacle in the development and implementation of machine learning in clinical research. To tackle this problem, we propose a novel framework having four main components: (1) a set of artefact generators inspired by magnetic resonance physics to corrupt brain MRI scans and augment a training dataset, (2) a set of abstract and engineered features to represent images compactly, (3) a feature selection process that depends on the class of artefact to improve classification performance, and (4) a set of Support Vector Machine (SVM) classifiers trained to identify artefacts. Our novel contributions are threefold: first, we use the novel physics-based artefact generators to generate synthetic brain MRI scans with controlled artefacts as a data augmentation technique. This will avoid the labour-intensive collection and labelling process of scans with rare artefacts. Second, we propose a large pool of abstract and engineered image features developed to identify 9 different artefacts for structural MRI. Finally, we use an artefact-based feature selection block that, for each class of artefacts, finds the set of features that provide the best classification performance. We performed validation experiments on a large data set of scans with artificially-generated artefacts, and in a multiple sclerosis clinical trial where real artefacts were identified by experts, showing that the proposed pipeline outperforms traditional methods. In particular, our data augmentation increases performance by up to 12.5 percentage points on the accuracy, F1, F2, precision and recall. At the same time, the computation cost of our pipeline remains low - less than a second to process a single scan - with the potential for real-time deployment. Our artefact simulators obtained using adversarial learning enable the training of a quality control system for brain MRI that otherwise would have required a much larger number of scans in both supervised and unsupervised settings. We believe that systems for quality control will enable a wide range of high-throughput clinical applications based on the use of automatic image-processing pipelines.

A systematic review of (semi-)automatic quality control of T1-weighted MRI scans

PURPOSE

Artifacts in magnetic resonance imaging (MRI) scans degrade image quality and thus negatively affect the outcome measures of clinical and research scanning. Considering the time-consuming and subjective nature of visual quality control (QC), multiple (semi-)automatic QC algorithms have been developed. This systematic review presents an overview of the available (semi-)automatic QC algorithms and software packages designed for raw, structural T1-weighted (T1w) MRI datasets. The objective of this review was to identify the differences among these algorithms in terms of their features of interest, performance, and benchmarks.

METHODS

We queried PubMed, EMBASE (Ovid), and Web of Science databases on the fifth of January 2023, and cross-checked reference lists of retrieved papers. Bias assessment was performed using PROBAST (Prediction model Risk Of Bias ASsessment Tool).

RESULTS

A total of 18 distinct algorithms were identified, demonstrating significant variations in methods, features, datasets, and benchmarks. The algorithms were categorized into rule-based, classical machine learning-based, and deep learning-based approaches. Numerous unique features were defined, which can be roughly divided into features capturing entropy, contrast, and normative measures.

CONCLUSION

Due to dataset-specific optimization, it is challenging to draw broad conclusions about comparative performance. Additionally, large variations exist in the used datasets and benchmarks, further hindering direct algorithm comparison. The findings emphasize the need for standardization and comparative studies for advancing QC in MR imaging. Efforts should focus on identifying a dataset-independent measure as well as algorithm-independent methods for assessing the relative performance of different approaches.

Deep learning, data ramping, and uncertainty estimation for detecting artifacts in large, imbalanced databases of MRI images

Magnetic resonance imaging (MRI) is increasingly being used to delineate morphological changes underlying neurological disorders. Successfully detecting these changes depends on the MRI data quality. Unfortunately, image artifacts frequently compromise the MRI utility, making it critical to screen the data. Currently, quality assessment requires visual inspection, a time-consuming process that suffers from inter-rater variability. Automated methods to detect MRI artifacts could improve the efficiency of the process. Such automated methods have achieved high accuracy using small datasets, with balanced proportions of MRI data with and without artifacts. With the current trend towards big data in neuroimaging, there is a need for automated methods that achieve accurate detection in large and imbalanced datasets. Deep learning (DL) is the ideal MRI artifact detection algorithm for large neuroimaging databases. However, the inference generated by DL does not commonly include a measure of uncertainty. Here, we present the first stochastic DL algorithm to generate automated, high-performing MRI artifact detection implemented on a large and imbalanced neuroimaging database. We implemented Monte Carlo dropout in a 3D AlexNet to generate probabilities and epistemic uncertainties. We then developed a method to handle class imbalance, namely data-ramping to transfer the learning by extending the dataset size and the proportion of the artifact-free data instances. We used a 34,800 scans (98% clean) dataset. At baseline, we obtained 89.3% testing accuracy (F1 = 0.230). Following the transfer learning (with data-ramping), we obtained 94.9% testing accuracy (F1 = 0.357) outperforming focal cross-entropy (92.9% testing accuracy, F1 = 0.304) incorporated for comparison at handling class imbalance. By implementing epistemic uncertainties, we improved the testing accuracy to 99.5% (F1 = 0.834), outperforming the results obtained in previous comparable studies. In addition, we estimated aleatoric uncertainties by incorporating random flips to the MRI volumes, and demonstrated that aleatoric uncertainty can be implemented as part of the pipeline. The methods we introduce enhance the efficiency of managing large databases and the exclusion of artifact images from big data analyses.

A multi-institutional pediatric dataset of clinical radiology MRIs by the Children's Brain Tumor Network

Pediatric brain and spinal cancers remain the leading cause of cancer-related death in children. Advancements in clinical decision-support in pediatric neuro-oncology utilizing the wealth of radiology imaging data collected through standard care, however, has significantly lagged other domains. Such data is ripe for use with predictive analytics such as artificial intelligence (AI) methods, which require large datasets. To address this unmet need, we provide a multi-institutional, large-scale pediatric dataset of 23,101 multi-parametric MRI exams acquired through routine care for 1,526 brain tumor patients, as part of the Children's Brain Tumor Network. This includes longitudinal MRIs across various cancer diagnoses, with associated patient-level clinical information, digital pathology slides, as well as tissue genotype and omics data. To facilitate downstream analysis, treatment-naïve images for 370 subjects were processed and released through the NCI Childhood Cancer Data Initiative via the Cancer Data Service. Through ongoing efforts to continuously build these imaging repositories, our aim is to accelerate discovery and translational AI models with real-world data, to ultimately empower precision medicine for children.

Statistical analyses of motion-corrupted MRI relaxometry data computed from multiple scans

BACKGROUND

Consistent noise variance across data points (i.e. homoscedasticity) is required to ensure the validity of statistical analyses of MRI data conducted using linear regression methods. However, head motion leads to degradation of image quality, introducing noise heteroscedasticity into ordinary-least square analyses.

NEW METHOD

The recently introduced QUIQI method restores noise homoscedasticity by means of weighted least square analyses in which the weights, specific for each dataset of an analysis, are computed from an index of motion-induced image quality degradation. QUIQI was first demonstrated in the context of brain maps of the MRI parameter R2 * , which were computed from a single set of images with variable echo time. Here, we extend this framework to quantitative maps of the MRI parameters R1, R2 * , and MTsat, computed from multiple sets of images.

RESULTS

QUIQI restores homoscedasticity in analyses of quantitative MRI data computed from multiple scans. QUIQI allows for optimization of the noise model by using metrics quantifying heteroscedasticity and free energy.

COMPARISON WITH EXISTING METHODS

QUIQI restores homoscedasticity more effectively than insertion of an image quality index in the analysis design and yields higher sensitivity than simply removing the datasets most corrupted by head motion from the analysis.

CONCLUSION

QUIQI provides an optimal approach to group-wise analyses of a range of quantitative MRI parameter maps that is robust to inherent homoscedasticity.

The impact of quality control on cortical morphometry comparisons in autism

Structural magnetic resonance imaging (MRI) quality is known to impact and bias neuroanatomical estimates and downstream analysis, including case-control comparisons, and a growing body of work has demonstrated the importance of careful quality control (QC) and evaluated the impact of image and image-processing quality. However, the growing size of typical neuroimaging datasets presents an additional challenge to QC, which is typically extremely time and labour intensive. One of the most important aspects of MRI quality is the accuracy of processed outputs, which have been shown to impact estimated neurodevelopmental trajectories. Here, we evaluate whether the quality of surface reconstructions by FreeSurfer (one of the most widely used MRI processing pipelines) interacts with clinical and demographic factors. We present a tool, FSQC, that enables quick and efficient yet thorough assessment of outputs of the FreeSurfer processing pipeline. We validate our method against other existing QC metrics, including the automated FreeSurfer Euler number, two other manual ratings of raw image quality, and two popular automated QC methods. We show strikingly similar spatial patterns in the relationship between each QC measure and cortical thickness; relationships for cortical volume and surface area are largely consistent across metrics, though with some notable differences. We next demonstrate that thresholding by QC score attenuates but does not eliminate the impact of quality on cortical estimates. Finally, we explore different ways of controlling for quality when examining differences between autistic individuals and neurotypical controls in the Autism Brain Imaging Data Exchange (ABIDE) dataset, demonstrating that inadequate control for quality can alter results of case-control comparisons.

Cognitive tasks, anatomical MRI, and functional MRI data evaluating the construct of self-regulation

We describe the following shared data from N=103 healthy adults who completed a broad set cognitive tasks, surveys, and neuroimaging measurements to examine the construct of self-regulation. The neuroimaging acquisition involved task-based fMRI, resting fMRI, and structural MRI. Each subject completed the following ten tasks in the scanner across two 90-minute scanning sessions: attention network test (ANT), cued task switching, Columbia card task, dot pattern expectancy (DPX), delay discounting, simple and motor selective stop signal, Stroop, a towers task, and a set of survey questions. Subjects also completed resting state scans. The dataset is shared openly through the OpenNeuro project, and the dataset is formatted according to the Brain Imaging Data Structure (BIDS) standard.

Mediation of the association between disadvantaged neighborhoods and cortical microstructure by body mass index

BACKGROUND

Living in a disadvantaged neighborhood is associated with worse health outcomes, including brain health, yet the underlying biological mechanisms are incompletely understood. We investigated the relationship between neighborhood disadvantage and cortical microstructure, assessed as the T1-weighted/T2-weighted ratio (T1w/T2w) on magnetic resonance imaging, and the potential mediating roles of body mass index (BMI) and stress, as well as the relationship between trans-fatty acid intake and cortical microstructure.

METHODS

Participants comprised 92 adults (27 men; 65 women) who underwent neuroimaging and provided residential address information. Neighborhood disadvantage was assessed as the 2020 California State area deprivation index (ADI). The T1w/T2w ratio was calculated at four cortical ribbon levels (deep, lower-middle, upper-middle, and superficial). Perceived stress and BMI were assessed as potential mediating factors. Dietary data was collected in 81 participants.

RESULTS

Here, we show that worse ADI is positively correlated with BMI (r = 0.27, p = .01) and perceived stress (r = 0.22, p = .04); decreased T1w/T2w ratio in middle/deep cortex in supramarginal, temporal, and primary motor regions (p < .001); and increased T1w/T2w ratio in superficial cortex in medial prefrontal and cingulate regions (p < .001). Increased BMI partially mediates the relationship between worse ADI and observed T1w/T2w ratio increases (p = .02). Further, trans-fatty acid intake (high in fried fast foods and obesogenic) is correlated with these T1w/T2w ratio increases (p = .03).

CONCLUSIONS

Obesogenic aspects of neighborhood disadvantage, including poor dietary quality, may disrupt information processing flexibility in regions involved in reward, emotion regulation, and cognition. These data further suggest ramifications of living in a disadvantaged neighborhood on brain health.

Convergent imaging-transcriptomic evidence for disturbed iron homeostasis in Gilles de la Tourette syndrome

Gilles de la Tourette syndrome (GTS) is a neuropsychiatric movement disorder with reported abnormalities in various neurotransmitter systems. Considering the integral role of iron in neurotransmitter synthesis and transport, it is hypothesized that iron exhibits a role in GTS pathophysiology. As a surrogate measure of brain iron, quantitative susceptibility mapping (QSM) was performed in 28 patients with GTS and 26 matched controls. Significant susceptibility reductions in the patients, consistent with reduced local iron content, were obtained in subcortical regions known to be implicated in GTS. Regression analysis revealed a significant negative association of tic scores and striatal susceptibility. To interrogate genetic mechanisms that may drive these reductions, spatially specific relationships between susceptibility and gene-expression patterns from the Allen Human Brain Atlas were assessed. Correlations in the striatum were enriched for excitatory, inhibitory, and modulatory neurochemical signaling mechanisms in the motor regions, mitochondrial processes driving ATP production and iron‑sulfur cluster biogenesis in the executive subdivision, and phosphorylation-related mechanisms affecting receptor expression and long-term potentiation in the limbic subdivision. This link between susceptibility reductions and normative transcriptional profiles suggests that disruptions in iron regulatory mechanisms are involved in GTS pathophysiology and may lead to pervasive abnormalities in mechanisms regulated by iron-containing enzymes.

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.

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.

Convergent imaging-transcriptomic evidence for disturbed iron homeostasis in Gilles de la Tourette syndrome

Gilles de la Tourette syndrome (GTS) is a neuropsychiatric movement disorder with reported abnormalities in various neurotransmitter systems. Considering the integral role of iron in neurotransmitter synthesis and transport, it is hypothesized that iron exhibits a role in GTS pathophysiology. As a surrogate measure of brain iron, quantitative susceptibility mapping (QSM) was performed in 28 patients with GTS and 26 matched controls. Significant susceptibility reductions in the patient cohort, consistent with reduced local iron content, were obtained in subcortical regions known to be implicated in GTS. Regression analysis revealed a significant negative association of tic scores and striatal susceptibility. To interrogate genetic mechanisms that may drive these reductions, spatially specific relationships between susceptibility and gene-expression patterns extracted from the Allen Human Brain Atlas were assessed. Correlations in the striatum were enriched for excitatory, inhibitory, and modulatory neurochemical signaling mechanisms in the motor regions, mitochondrial processes driving ATP production and iron-sulfur cluster biogenesis in the executive subdivision, and phosphorylation-related mechanisms that affect receptor expression and long-term potentiation. This link between susceptibility reductions and normative transcriptional profiles suggests that disruptions in iron regulatory mechanisms are involved in GTS pathophysiology and may lead to pervasive abnormalities in mechanisms regulated by iron-containing enzymes.

Mediating role of obesity on the association between disadvantaged neighborhoods and intracortical myelination

We investigated the relationship between neighborhood disadvantage (area deprivation index [ADI]) and intracortical myelination (T1-weighted/T2-weighted ratio at deep to superficial cortical levels), and the potential mediating role of the body mass index (BMI) and perceived stress in 92 adults. Worse ADI was correlated with increased BMI and perceived stress (p's<.05). Non-rotated partial least squares analysis revealed associations between worse ADI and decreased myelination in middle/deep cortex in supramarginal, temporal, and primary motor regions and increased myelination in superficial cortex in medial prefrontal and cingulate regions (p<.001); thus, neighborhood disadvantage may influence the flexibility of information processing involved in reward, emotion regulation, and cognition. Structural equation modelling revealed increased BMI as partially mediating the relationship between worse ADI and observed myelination increases (p=.02). Further, trans-fatty acid intake was correlated with observed myelination increases (p=.03), suggesting the importance of dietary quality. These data further suggest ramifications of neighborhood disadvantage on brain health.

Quality control in functional MRI studies with MRIQC and fMRIPrep

The implementation of adequate quality assessment (QA) and quality control (QC) protocols within the magnetic resonance imaging (MRI) research workflow is resource- and time-consuming and even more so is their execution. As a result, QA/QC practices highly vary across laboratories and "MRI schools", ranging from highly specialized knowledge spots to environments where QA/QC is considered overly onerous and costly despite evidence showing that below-standard data increase the false positive and false negative rates of the final results. Here, we demonstrate a protocol based on the visual assessment of images one-by-one with reports generated by MRIQC and fMRIPrep, for the QC of data in functional (blood-oxygen dependent-level; BOLD) MRI analyses. We particularize the proposed, open-ended scope of application to whole-brain voxel-wise analyses of BOLD to correspondingly enumerate and define the exclusion criteria applied at the QC checkpoints. We apply our protocol on a composite dataset (n = 181 subjects) drawn from open fMRI studies, resulting in the exclusion of 97% of the data (176 subjects). This high exclusion rate was expected because subjects were selected to showcase artifacts. We describe the artifacts and defects more commonly found in the dataset that justified exclusion. We moreover release all the materials we generated in this assessment and document all the QC decisions with the expectation of contributing to the standardization of these procedures and engaging in the discussion of QA/QC by the community.

Demonstrating quality control procedures for fMRI in DPABI

Quality control (QC) is an important stage for functional magnetic resonance imaging (fMRI) studies. The methods for fMRI QC vary in different fMRI preprocessing pipelines. The inflating sample size and number of scanning sites for fMRI studies further add to the difficulty and working load of the QC procedure. Therefore, as a constituent part of the Demonstrating Quality Control Procedures in fMRI research topic in Frontiers, we preprocessed a well-organized open-available dataset using DPABI pipelines to illustrate the QC procedure in DPABI. Six categories of DPABI-derived reports were used to eliminate images without adequate quality. After the QC procedure, twelve participants (8.6%) were categorized as excluded and eight participants (5.8%) were categorized as uncertain. More automatic QC tools were needed in the big-data era while visually inspecting images was still indispensable now.

Application of a convolutional neural network to the quality control of MRI defacing

Large-scale neuroimaging datasets present unique challenges for automated processing pipelines. Motivated by a large clinical trials dataset with over 235,000 MRI scans, we consider the challenge of defacing - anonymisation to remove identifying facial features. The defacing process must undergo quality control (QC) checks to ensure that the facial features have been removed and that the brain tissue is left intact. Visual QC checks are time-consuming and can cause delays in preparing data. We have developed a convolutional neural network (CNN) that can assist with the QC of the application of MRI defacing; our CNN is able to distinguish between scans that are correctly defaced and can classify defacing failures into three sub-types to facilitate parameter tuning during remedial re-defacing. Since integrating the CNN into our anonymisation pipeline, over 75,000 scans have been processed. Strict thresholds have been applied so that ambiguous classifications are referred for visual QC checks, however all scans still undergo an efficient verification check before being marked as passed. After applying the thresholds, our network is 92% accurate and can classify nearly half of the scans without the need for protracted manual checks. Our model can generalise across MRI modalities and has comparable performance when tested on an independent dataset. Even with the introduction of the verification checks, incorporation of the CNN has reduced the time spent undertaking QC checks by 42% during initial defacing, and by 35% overall. With the help of the CNN, we have been able to successfully deface 96% of the scans in the project whilst maintaining high QC standards. In a similarly sized new project, we would expect the model to reduce the time spent on manual QC checks by 125 h. Our approach is applicable to other projects with the potential to greatly improve the efficiency of imaging anonymisation pipelines.

Long-term fasting: Multi-system adaptations in humans (GENESIS) study–A single-arm interventional trial

Fasting provokes fundamental changes in the activation of metabolic and signaling pathways leading to longer and healthier lifespans in animal models. Although the involvement of different metabolites in fueling human fasting metabolism is well known, the contribution of tissues and organs to their supply remains partly unclear. Also, changes in organ volume and composition remain relatively unexplored. Thus, processes involved in remodeling tissues during fasting and food reintroduction need to be better understood. Therefore, this study will apply state-of-the-art techniques to investigate the effects of long-term fasting (LF) and food reintroduction in humans by a multi-systemic approach focusing on changes in body composition, organ and tissue volume, lipid transport and storage, sources of protein utilization, blood metabolites, and gut microbiome profiles in a single cohort. This is a prospective, single-arm, monocentric trial. One hundred subjects will be recruited and undergo 9 ± 3 day-long fasting periods (250 kcal/day). We will assess changes in the composition of organs, bones and blood lipid profiles before and after fasting, as well as high-density lipoprotein (HDL) transport and storage, untargeted metabolomics of peripheral blood mononuclear cells (PBMCs), protein persulfidation and shotgun metagenomics of the gut microbiome. The first 32 subjects, fasting for 12 days, will be examined in more detail by magnetic resonance imaging (MRI) and spectroscopy to provide quantitative information on changes in organ volume and function, followed by an additional follow-up examination after 1 and 4 months. The study protocol was approved by the ethics board of the State Medical Chamber of Baden-Württemberg on 26.07.2021 and registered at ClinicalTrials.gov (NCT05031598). The results will be disseminated through peer-reviewed publications, international conferences and social media.

Clinical trial registration

[ClinicalTrials.gov], identifier [NCT05031598].

Fully automatic quantification of transient severe respiratory motion artifact of gadoxetate disodium-enhanced MRI during arterial phase

PURPOSE

It is important to fully automate the evaluation of gadoxetate disodium-enhanced arterial phase images because the efficient quantification of transient severe motion artifacts can be used in a variety of applications. Our study proposes a fully automatic evaluation method of motion artifacts during the arterial phase of gadoxetate disodium-enhanced MR imaging.

METHODS

The proposed method was based on the construction of quality-aware features to represent the motion artifact using MR image statistics and multidirectional filtered coefficients. Using the quality-aware features, the method calculated quantitative quality scores of gadoxetate disodium-enhanced images fully automatically. The performance of our proposed method, as well as two other methods, was acquired by correlating scores against subjective scores from radiologists based on the 5-point scale and binary evaluation. The subjective scores evaluated by two radiologists were severity scores of motion artifacts in the evaluation set on a scale of 1 (no motion artifacts) to 5 (severe motion artifacts).

RESULTS

Pearson's linear correlation coefficient (PLCC) and Spearman's rank-ordered correlation coefficient (SROCC) values of our proposed method against the subjective scores were 0.9036 and 0.9057, respectively, whereas the PLCC values of two other methods were 0.6525 and 0.8243, and the SROCC values were 0.6070 and 0.8348. Also, in terms of binary quantification of transient severe respiratory motion, the proposed method achieved 0.9310 sensitivity, 0.9048 specificity, and 0.9200 accuracy, whereas the other two methods achieved 0.7586, 0.8996 sensitivities, 0.8098, 0.8905 specificities, and 0.9200, 0.9048 accuracies CONCLUSIONS: This study demonstrated the high performance of the proposed automatic quantification method in evaluating transient severe motion artifacts in arterial phase images.

A novel algorithm for comprehensive quality assessment of clinical magnetic resonance images based on natural scene statistics in spatial domain

BACKGROUND

A magnetic resonance imaging (MRI)-specific objective image quality assessment (IQA) algorithm, the quality evaluation using multidirectional filters for MRI (QEMDIM), was previously reported. QEMDIM requires a set of reference images to calculate the quality score (S_Q) for an assessed image. S_Q may be affected by the quality of the reference set owing to the calculation procedure.

PURPOSE

To propose a modified version of the IQA algorithm and compare the IQA performance of the original and modified algorithms.

ASSESSMENT

Brain axial T₁- and T₂-weighted spin-echo images of varying quality levels (noise and blurring) were acquired from seven healthy men. Subjective IQA (paired comparisons) was conducted on the images, and subjective quality scores were obtained. With reference sets of various quality levels, QEMDIM and modified IQA were applied to the same images that underwent the subjective IQA. The correlation of each S_Q and modified score (S_mod) with the subjective scores was evaluated for content-related subsets of assessed images and for each reference set. The effect of the reference-set quality on the distribution of the correlation coefficients (CCs) was statistically evaluated for S_Q and S_mod using a one-way analysis of variance test with a significance level of 0.05. We also evaluated the variation in S_mod for images with almost the same qualities using the standard deviation (SD).

RESULTS

The CCs of S_Q varied significantly with the quality of the reference set, whereas that of S_mod did not. The SD of S_mod for almost-same-quality images was less than that corresponding to the confidence interval of the subjective scores.

CONCLUSION

Our modified algorithm was superior to QEMDIM in terms of IQA performance in clinical practice, especially in terms of accuracy, robustness, and reproducibility.

Open and reproducible neuroimaging: From study inception to publication

Empirical observations of how labs conduct research indicate that the adoption rate of open practices for transparent, reproducible, and collaborative science remains in its infancy. This is at odds with the overwhelming evidence for the necessity of these practices and their benefits for individual researchers, scientific progress, and society in general. To date, information required for implementing open science practices throughout the different steps of a research project is scattered among many different sources. Even experienced researchers in the topic find it hard to navigate the ecosystem of tools and to make sustainable choices. Here, we provide an integrated overview of community-developed resources that can support collaborative, open, reproducible, replicable, robust and generalizable neuroimaging throughout the entire research cycle from inception to publication and across different neuroimaging modalities. We review tools and practices supporting study inception and planning, data acquisition, research data management, data processing and analysis, and research dissemination. An online version of this resource can be found at https://oreoni.github.io. We believe it will prove helpful for researchers and institutions to make a successful and sustainable move towards open and reproducible science and to eventually take an active role in its future development.

[Comprehensive evaluation method of real-time non-reference ultrasound image involving soft tissue deformation]

Ultrasound guided percutaneous interventional therapy has been widely used in clinic. Aiming at the problem of soft tissue deformation caused by probe contact force in robot-assisted ultrasound-guided therapy, a real-time non-reference ultrasound image evaluation method considering soft tissue deformation is proposed. On the basis of ultrasound image brightness and sharpness, a multi-dimensional ultrasound image evaluation index was designed, which incorporated the aggregation characteristics of the organization. In order to verify the effectiveness of the proposed method, ultrasound images of four different models were collected for experiments, including prostate phantom, phantom with cyst, pig liver tissue, and pig liver tissue with cyst. In addition, the correlation between subjective and objective evaluations was analyzed based on Spearman's rank correlation coefficient. Experimental results showed that the average evaluation time of a single image was 68.8 milliseconds. The evaluation time could satisfy real-time applications. The proposed method realizes the effective evaluation of real-time ultrasound image quality in robot-assisted therapy, and has good consistency with the evaluation of supervisors.

A Brief Survey on No-Reference Image Quality Assessment Methods for Magnetic Resonance Images

No-reference image quality assessment (NR-IQA) methods automatically and objectively predict the perceptual quality of images without access to a reference image. Therefore, due to the lack of pristine images in most medical image acquisition systems, they play a major role in supporting the examination of resulting images and may affect subsequent treatment. Their usage is particularly important in magnetic resonance imaging (MRI) characterized by long acquisition times and a variety of factors that influence the quality of images. In this work, a survey covering recently introduced NR-IQA methods for the assessment of MR images is presented. First, typical distortions are reviewed and then popular NR methods are characterized, taking into account the way in which they describe MR images and create quality models for prediction. The survey also includes protocols used to evaluate the methods and popular benchmark databases. Finally, emerging challenges are outlined along with an indication of the trends towards creating accurate image prediction models.

Physically implausible signals as a quantitative quality assessment metric in prostate diffusion-weighted MR imaging

PURPOSE

To provide a quantitative assessment of diffusion-weighted MR images of the prostate through identification of PIDS which clearly represents artifacts in the data. We calculated the percentage and distribution of PIDS in prostate DWI and compare the amount of PIDS between mpMRI images obtained with and without an endorectal coil.

METHODS

This IRB approved retrospective study (from 03/03/2014 to 03/10/2020), included 40 patients scanned with endorectal coil (ERC) and 40 without ER coil (NERC). PIDS contains any voxel where: (1) the diffusion signal increases despite an increase in b-value; and/or (2) apparent diffusion coefficient (ADC) is more than 3.0 μm²/ms (the ADC of pure water at 37 °C and it is physically implausible for any material to have a higher ADC). PIDS for transition zone (TZ) and peripheral zone (PZ) was calculated using an in-house MATLAB program. DWI images were quantitatively inspected for noise, motion, and distortion. T-test was used to compare the difference between PIDS levels in ERC versus NERC and ANOVA to compare the PIDS levels in the anatomic zones. The images were evaluated by a fellowship-trained radiologist in Abdominal Imaging with more than 10 years of experience in reading prostate MRI. This was tested only in prostate in this study.

RESULTS

80 patients (58 ± 8 years old, 80 men) were evaluated. The percentage of voxels exhibiting PIDS was 17.1 ± 8.1% for the ERC cohort and 22.2 ± 15.5% for the NERC cohort. PIDS for NERC versus ERC were not significantly different (p = 0.14). The apex and base showed similar percentages of PIDS in ERC (p = 0.30) and NERC (p = 0.86). The mid (13.8 ± 8.6%) in ERC showed lower values (p = 0.02) of PIDS compared to apex (19.9 ± 11.1%) and base (17.5 ± 8.3%).

CONCLUSION

PIDS maps provide a spatially resolved quantitative quality assessment for prostate DWI. Average PIDS over the entire prostate were similar for the ERC and NERC cohorts, and did not differ significantly across prostate zones. However, for many of the patients, PIDS was focally much higher in specific prostate zones. PIDS assessment can guide Radiologist's evaluation of images and the development of improved DWI sequences.

Image quality assessment for machine learning tasks using meta-reinforcement learning

In this paper, we consider image quality assessment (IQA) as a measure of how images are amenable with respect to a given downstream task, or task amenability. When the task is performed using machine learning algorithms, such as a neural-network-based task predictor for image classification or segmentation, the performance of the task predictor provides an objective estimate of task amenability. In this work, we use an IQA controller to predict the task amenability which, itself being parameterised by neural networks, can be trained simultaneously with the task predictor. We further develop a meta-reinforcement learning framework to improve the adaptability for both IQA controllers and task predictors, such that they can be fine-tuned efficiently on new datasets or meta-tasks. We demonstrate the efficacy of the proposed task-specific, adaptable IQA approach, using two clinical applications for ultrasound-guided prostate intervention and pneumonia detection on X-ray images.

Impact of prenatal alcohol exposure on intracortical myelination and deep white matter in children with attention deficit hyperactivity disorder

White matter alterations have been reported in children with prenatal alcohol exposure (PAE) and in children with attention deficit hyperactivity disorder (ADHD); however, as children with PAE often present with ADHD, covert PAE may have contributed to previous ADHD findings. Additionally, data regarding intracortical myelination in ADHD are lacking. Therefore, we evaluated intracortical myelination (assessed as the T1w/T2w ratio at 4 cortical ribbon levels) and myelin-related deep white matter features in children (aged 8-13 years) with ADHD with PAE (ADHD + PAE), children with familial ADHD without PAE (ADHD-PAE), and typically developing (TD) children. In widespread tracts, ADHD + PAE children showed higher mean and radial diffusivity than TD and ADHD-PAE children and lower fractional anisotropy than ADHD-PAE children; ADHD-PAE and TD children did not differ significantly. Compared to TD children, ADHD + PAE children had lower intracortical myelination only at the deepest cortical level (mainly in right insula and cingulate cortices), while ADHD-PAE children had lower intracortical myelination at multiple cortical levels (mainly in right insula, sensorimotor, and cingulate cortices); ADHD + PAE and ADHD-PAE children did not differ significantly in intracortical myelination. Considering the two ADHD groups jointly (via non-parametric combination) revealed common reductions in intracortical myelination, but no common deep white matter abnormalities. These results suggest the importance of considering PAE in ADHD studies of white matter pathology. ADHD + PAE may be associated with deeper, white matter abnormalities, while familial ADHD without PAE may be associated with more superficial, cortical abnormalities. This may be relevant to the different treatment response observed in these two ADHD etiologies.

Restoring statistical validity in group analyses of motion-corrupted MRI data

Motion during the acquisition of magnetic resonance imaging (MRI) data degrades image quality, hindering our capacity to characterise disease in patient populations. Quality control procedures allow the exclusion of the most affected images from analysis. However, the criterion for exclusion is difficult to determine objectively and exclusion can lead to a suboptimal compromise between image quality and sample size. We provide an alternative, data‐driven solution that assigns weights to each image, computed from an index of image quality using restricted maximum likelihood. We illustrate this method through the analysis of quantitative MRI data. The proposed method restores the validity of statistical tests, and performs near optimally in all brain regions, despite local effects of head motion. This method is amenable to the analysis of a broad type of MRI data and can accommodate any measure of image quality.

Mega-analysis methods in ENIGMA: The experience of the generalized anxiety disorder working group

The ENIGMA group on Generalized Anxiety Disorder (ENIGMA-Anxiety/GAD) is part of a broader effort to investigate anxiety disorders using imaging and genetic data across multiple sites worldwide. The group is actively conducting a mega-analysis of a large number of brain structural scans. In this process, the group was confronted with many methodological challenges related to study planning and implementation, between-country transfer of subject-level data, quality control of a considerable amount of imaging data, and choices related to statistical methods and efficient use of resources. This report summarizes the background information and rationale for the various methodological decisions, as well as the approach taken to implement them. The goal is to document the approach and help guide other research groups working with large brain imaging data sets as they develop their own analytic pipelines for mega-analyses.

3D hemisphere-based convolutional neural network for whole-brain MRI segmentation

Whole-brain segmentation is a crucial pre-processing step for many neuroimaging analyses pipelines. Accurate and efficient whole-brain segmentations are important for many neuroimage analysis tasks to provide clinically relevant information. Several recently proposed convolutional neural networks (CNN) perform whole brain segmentation using individual 2D slices or 3D patches as inputs due to graphical processing unit (GPU) memory limitations, and use sliding windows to perform whole brain segmentation during inference. However, these approaches lack global and spatial information about the entire brain and lead to compromised efficiency during both training and testing. We introduce a 3D hemisphere-based CNN for automatic whole-brain segmentation of T1-weighted magnetic resonance images of adult brains. First, we trained a localization network to predict bounding boxes for both hemispheres. Then, we trained a segmentation network to segment one hemisphere, and segment the opposing hemisphere by reflecting it across the mid-sagittal plane. Our network shows high performance both in terms of segmentation efficiency and accuracy (0.84 overall Dice similarity and 6.1 mm overall Hausdorff distance) in segmenting 102 brain structures. On multiple independent test datasets, our method demonstrated a competitive performance in the subcortical segmentation task and a high consistency in volumetric measurements of intra-session scans.

R2* and quantitative susceptibility mapping in deep gray matter of 498 healthy controls from 5 to 90 years

Putative MRI markers of iron in deep gray matter have demonstrated age related changes during discrete periods of healthy childhood or adulthood, but few studies have included subjects across the lifespan. This study reports both transverse relaxation rate (R2*) and quantitative susceptibility mapping (QSM) of four primary deep gray matter regions (thalamus, putamen, caudate, and globus pallidus) in 498 healthy individuals aged 5–90 years. In the caudate, putamen, and globus pallidus, increases of QSM and R2* were steepest during childhood continuing gradually throughout adulthood, except caudate susceptibility which reached a plateau in the late 30s. The thalamus had a unique profile with steeper changes of R2* (reflecting additive effects of myelin and iron) than QSM during childhood, both reaching a plateau in the mid‐30s to early 40s and decreasing thereafter. There were no hemispheric or sex differences for any region. Notably, both R2* and QSM values showed more inter‐subject variability with increasing age from 5 to 90 years, potentially reflecting a common starting point in iron/myelination during childhood that diverges as a result of lifestyle and genetic factors that accumulate with age.

TAPAS: An Open-Source Software Package for Translational Neuromodeling and Computational Psychiatry

Psychiatry faces fundamental challenges with regard to mechanistically guided differential diagnosis, as well as prediction of clinical trajectories and treatment response of individual patients. This has motivated the genesis of two closely intertwined fields: (i) Translational Neuromodeling (TN), which develops "computational assays" for inferring patient-specific disease processes from neuroimaging, electrophysiological, and behavioral data; and (ii) Computational Psychiatry (CP), with the goal of incorporating computational assays into clinical decision making in everyday practice. In order to serve as objective and reliable tools for clinical routine, computational assays require end-to-end pipelines from raw data (input) to clinically useful information (output). While these are yet to be established in clinical practice, individual components of this general end-to-end pipeline are being developed and made openly available for community use. In this paper, we present the Translational Algorithms for Psychiatry-Advancing Science (TAPAS) software package, an open-source collection of building blocks for computational assays in psychiatry. Collectively, the tools in TAPAS presently cover several important aspects of the desired end-to-end pipeline, including: (i) tailored experimental designs and optimization of measurement strategy prior to data acquisition, (ii) quality control during data acquisition, and (iii) artifact correction, statistical inference, and clinical application after data acquisition. Here, we review the different tools within TAPAS and illustrate how these may help provide a deeper understanding of neural and cognitive mechanisms of disease, with the ultimate goal of establishing automatized pipelines for predictions about individual patients. We hope that the openly available tools in TAPAS will contribute to the further development of TN/CP and facilitate the translation of advances in computational neuroscience into clinically relevant computational assays.

Automatic MR image quality evaluation using a Deep CNN: A reference-free method to rate motion artifacts in neuroimaging

Motion artifacts on magnetic resonance (MR) images degrade image quality and thus negatively affect clinical and research scanning. Considering the difficulty in preventing patient motion during MR examinations, the identification of motion artifact has attracted significant attention from researchers. We propose an automatic method for the evaluation of motion corrupted images using a deep convolutional neural network (CNN). Deep CNNs has been used widely in image classification tasks. While such methods require a significant amount of annotated training data, a scarce resource in medical imaging, the transfer learning and fine-tuning approaches allow us to use a smaller amount of data. Here we selected four renowned architectures, initially trained on Imagenet contest dataset, to fine-tune. The models were fine-tuned using patches from an annotated dataset composed of 68 T1-weighted volumetric acquisitions from healthy volunteers. For training and validation 48 images were used, while the remaining 20 images were used for testing. Each architecture was fine-tuned for each MR axis, detecting the motion artifact per patches from the three orthogonal MR acquisition axes. The overall average accuracy for the twelve models (three axes for each of four architecture) was 86.3%. As our goal was to detect fine-grained corruption in the image, we performed an extensive search on lower layers from each of the four architectures, since they filter small regions in the original input. Experiments showed that architectures with fewer layers than the original ones reported the better results for image patches with an overall average accuracy of 90.4%. The accuracies per architecture were similar so we decided to explore all four architectures performing a result consensus. Also, to determine the probability of motion artifacts presence on the whole acquisition a combination of the three axes were performed. The final architecture consists of an artificial neural network (ANN) classifier combining all models from the four shallower architectures, which overall acquisition-based accuracy was 100.0%. The proposed method generalization was tested using three different MR data: (1) MR image acquired in epilepsy patients (93 acquisitions); (2) MR image presenting susceptibility artifact (22 acquisitions); and (3) MR image acquired from different scanner vendor (20 acquisitions). The achieved acquisition-based accuracy on generalization tests (1) 90.3%, (2) 63.6%, and (3) 75.0%) suggests that domain adaptation is necessary. Our proposed method can be rapidly applied to large amounts of image data, providing a motion probability p∈[0,1] per acquisition. This method output can be used as a scale to identify the motion corrupted images from the dataset, thus minimizing the time spent on visual quality control.

Plasma neurofilament light and phosphorylated tau 181 as biomarkers of Alzheimer's disease pathology and clinical disease progression

Background

To assess the performance of plasma neurofilament light (NfL) and phosphorylated tau 181 (p-tau181) to inform about cerebral Alzheimer’s disease (AD) pathology and predict clinical progression in a memory clinic setting.

Methods

Plasma NfL and p-tau181, along with established cerebrospinal fluid (CSF) biomarkers of AD pathology, were measured in participants with normal cognition (CN) and memory clinic patients with cognitive impairment (mild cognitive impairment and dementia, CI). Clinical and neuropsychological assessments were performed at inclusion and follow-up visits at 18 and 36 months. Multivariate analysis assessed associations of plasma NfL and p-tau181 levels with AD, single CSF biomarkers, hippocampal volume, and clinical measures of disease progression.

Results

Plasma NfL levels were higher in CN participants with an AD CSF profile (defined by a CSF p-tau181/Aβ_1–42 > 0.0779) as compared with CN non-AD, while p-tau181 plasma levels were higher in CI patients with AD. Plasma NfL levels correlated with CSF tau and p-tau181 in CN, and with CSF tau in CI patients. Plasma p-tau181 correlated with CSF p-tau181 in CN and with CSF tau, p-tau181, Aβ_1–42, and Aβ_1–42/Aβ_1–40 in CI participants. Compared with a reference model, adding plasma p-tau181 improved the prediction of AD in CI patients while adding NfL did not. Adding p-tau181, but not NfL levels, to a reference model improved prediction of cognitive decline in CI participants.

Conclusion

Plasma NfL indicates neurodegeneration while plasma p-tau181 levels can serve as a biomarker of cerebral AD pathology and cognitive decline. Their predictive performance depends on the presence of cognitive impairment.

Regression dynamic causal modeling for resting-state fMRI

“Resting‐state” functional magnetic resonance imaging (rs‐fMRI) is widely used to study brain connectivity. So far, researchers have been restricted to measures of functional connectivity that are computationally efficient but undirected, or to effective connectivity estimates that are directed but limited to small networks. Here, we show that a method recently developed for task‐fMRI—regression dynamic causal modeling (rDCM)—extends to rs‐fMRI and offers both directional estimates and scalability to whole‐brain networks. First, simulations demonstrate that rDCM faithfully recovers parameter values over a wide range of signal‐to‐noise ratios and repetition times. Second, we test construct validity of rDCM in relation to an established model of effective connectivity, spectral DCM. Using rs‐fMRI data from nearly 200 healthy participants, rDCM produces biologically plausible results consistent with estimates by spectral DCM. Importantly, rDCM is computationally highly efficient, reconstructing whole‐brain networks (>200 areas) within minutes on standard hardware. This opens promising new avenues for connectomics.

Brain MRI artefact detection and correction using convolutional neural networks

BACKGROUND AND OBJECTIVE

Brain MRI is one of the most commonly used diagnostic imaging tools to detect neurodegenerative disease. Diagnostic image quality is a key factor to enable robust image analysis algorithms developed for downstream tasks such as segmentation. In clinical practice, one of the main challenges is the presence of image artefacts, which can lead to low diagnostic image quality.

METHODS

In this paper, we propose using dense convolutional neural networks to detect and a residual U-net architecture to correct motion related brain MRI artefacts. We first generate synthetic artefacts using an MR physics based corruption strategy. Then, we use a detection strategy based on dense convolutional neural network to detect artefacts. The detected artefacts are corrected using a residual U-net network trained on corrupted data.

RESULTS

Our pipeline for detection and correction of artefacts is capable of reaching not only better quality image quality, but also better segmentation accuracy of stroke segmentation. The algorithm is validated using 28 cases brain MRI stroke segmentation dataset and showed an accuracy of 97.8% for detecting artefacts in our experiments. We also illustrated the improved image quality and segmentation accuracy with the proposed correction algorithm.

CONCLUSIONS

Ensuring high image quality and high segmentation quality jointly can improve the automatic image analysis pipelines and reduce the influence of low image quality on final prognosis. With this work, we illustrate a performance analysis on brain MRI stroke segmentation.

Retrospective motion artifact correction of structural MRI images using deep learning improves the quality of cortical surface reconstructions

Head motion during MRI acquisition presents significant challenges for neuroimaging analyses. In this work, we present a retrospective motion correction framework built on a Fourier domain motion simulation model combined with established 3D convolutional neural network (CNN) architectures. Quantitative evaluation metrics were used to validate the method on three separate multi-site datasets. The 3D CNN was trained using motion-free images that were corrupted using simulated artifacts. CNN based correction successfully diminished the severity of artifacts on real motion affected data on a separate test dataset as measured by significant improvements in image quality metrics compared to a minimal motion reference image. On the test set of 13 image pairs, the mean peak signal-to-noise-ratio was improved from 31.7 to 33.3 dB. Furthermore, improvements in cortical surface reconstruction quality were demonstrated using a blinded manual quality assessment on the Parkinson's Progression Markers Initiative (PPMI) dataset. Upon applying the correction algorithm, out of a total of 617 images, the number of quality control failures was reduced from 61 to 38. On this same dataset, we investigated whether motion correction resulted in a more statistically significant relationship between cortical thickness and Parkinson's disease. Before correction, significant cortical thinning was found to be restricted to limited regions within the temporal and frontal lobes. After correction, there was found to be more widespread and significant cortical thinning bilaterally across the temporal lobes and frontal cortex. Our results highlight the utility of image domain motion correction for use in studies with a high prevalence of motion artifacts, such as studies of movement disorders as well as infant and pediatric subjects.

Is it time to switch your T1W sequence? Assessing the impact of prospective motion correction on the reliability and quality of structural imaging

New large neuroimaging studies, such as the Adolescent Brain Cognitive Development study (ABCD) and Human Connectome Project (HCP) Development studies are adopting a new T1-weighted imaging sequence with prospective motion correction (PMC) in favor of the more traditional 3-Dimensional Magnetization-Prepared Rapid Gradient-Echo Imaging (MPRAGE) sequence. Here, we used a developmental dataset (ages 5-21, N = 348) from the Healthy Brain Network (HBN) Initiative to directly compare two widely used MRI structural sequences: one based on the Human Connectome Project (MPRAGE) and another based on the ABCD study (MPRAGE+PMC). We aimed to determine if the morphometric measurements obtained from both protocols are equivalent or if one sequence has a clear advantage over the other. The sequences were also compared through quality control measurements. Inter- and intra-sequence reliability were assessed with another set of participants (N = 71) from HBN that performed two MPRAGE and two MPRAGE+PMC sequences within the same imaging session, with one MPRAGE (MPRAGE1) and MPRAGE+PMC (MPRAGE+PMC1) pair at the beginning of the session and another pair (MPRAGE2 and MPRAGE+PMC2) at the end of the session. Intraclass correlation coefficients (ICC) scores for morphometric measurements such as volume and cortical thickness showed that intra-sequence reliability is the highest with the two MPRAGE+PMC sequences and lowest with the two MPRAGE sequences. Regarding inter-sequence reliability, ICC scores were higher for the MPRAGE1 - MPRAGE+PMC1 pair at the beginning of the session than the MPRAGE1 - MPRAGE2 pair, possibly due to the higher motion artifacts in the MPRAGE2 run. Results also indicated that the MPRAGE+PMC sequence is robust, but not impervious, to high head motion. For quality control metrics, the traditional MPRAGE yielded better results than MPRAGE+PMC in 5 of the 8 measurements. In conclusion, morphometric measurements evaluated here showed high inter-sequence reliability between the MPRAGE and MPRAGE+PMC sequences, especially in images with low head motion. We suggest that studies targeting hyperkinetic populations use the MPRAGE+PMC sequence, given its robustness to head motion and higher reliability scores. However, neuroimaging researchers studying non-hyperkinetic participants can choose either MPRAGE or MPRAGE+PMC sequences, but should carefully consider the apparent tradeoff between relatively increased reliability, but reduced quality control metrics when using the MPRAGE+PMC sequence.

Neuroharmony: A new tool for harmonizing volumetric MRI data from unseen scanners

•We present Neuroharmony, a harmonization tool for images from unseen scanners. •We developed Neuroharmony using a total of 15,026 sMRI images. •The tool was able to reduce scanner-related bias from unseen scans. •Neuroharmony represents a significant step towards imaging-based clinical tools. •Neuroharmony is available at https://github.com/garciadias/Neuroharmony .

LEGO-compatible modular mapping phantom for magnetic resonance imaging

Physical phantoms have been widely used for performance evaluation of magnetic resonance imaging (MRI). Although there are many kinds of physical phantoms, most MRI phantoms use fixed configurations with specific sizes that may fit one or a few different types of radio frequency (RF) coils. Therefore, it has limitations for various image quality assessments of scanning areas. In this article, we report a novel design for a truly customizable MRI phantom called the LEGO-compatible Modular Mapping (MOMA) phantom, which not only serves as a general quality assurance phantom for a wide range of RF coils, but also a flexible calibration phantom for quantitative imaging. The MOMA phantom has a modular architecture which includes individual assessment functionality of the modules and LEGO-type assembly compatibility. We demonstrated the feasibility of the MOMA phantom for quantitative evaluation of image quality using customized module assembly compatible with head, breast, spine, knee, and body coil features. This unique approach allows comprehensive image quality evaluation with wide versatility. In addition, we provide detailed MOMA phantom development and imaging characteristics of the modules.

Sharpness in motion corrected quantitative imaging at 7T

Sub-millimeter imaging at 7T has opened new possibilities for qualitatively and quantitatively studying brain structure as it evolves throughout the life span. However, subject motion introduces image blurring on the order of magnitude of the spatial resolution and is thus detrimental to image quality. Such motion can be corrected for, but widespread application has not yet been achieved and quantitative evaluation is lacking. This raises a need to quantitatively measure image sharpness throughout the brain. We propose a method to quantify sharpness of brain structures at sub-voxel resolution, and use it to assess to what extent limited motion is related to image sharpness. The method was evaluated in a cohort of 24 healthy volunteers with a wide and uniform age range, aiming to arrive at results that largely generalize to larger populations. Using 3D fat-excited motion navigators, quantitative R₁, R₂^* and Quantitative Susceptibility Maps and T₁-weighted images were retrospectively corrected for motion. Sharpness was quantified in all modalities for selected regions of interest (ROI) by fitting the sigmoidally shaped error function to data within locally homogeneous clusters. A strong, almost linear correlation between motion and sharpness improvement was observed, and motion correction significantly improved sharpness. Overall, the Full Width at Half Maximum reduced from 0.88 mm to 0.70 mm after motion correction, equivalent to a 2.0 times smaller voxel volume. Motion and sharpness were not found to correlate with the age of study participants. We conclude that in our data, motion correction using fat navigators is overall able to restore the measured sharpness to the imaging resolution, irrespective of the amount of motion observed during scanning.

A two-step automated quality assessment for liver MR images based on convolutional neural network

PURPOSE

To propose an automatic approach based on a convolutional neural network (CNN) to evaluate the quality of T2-weighted liver magnetic resonance (MR) images as nondiagnostic (ND) or diagnostic (D).

MATERIALS AND METHODS

We included 150 T2-weighted liver MR imaging examinations in this retrospective study. Each slice of liver image was annotated with a label D or ND by two radiologists with seven and six years of experience, respectively. Additionally, the radiologists segmented the liver region manually as the ground truth for liver segmentation. A CNN was trained to segment the liver region and another CNN was used to classify the qualities of patches extracted from the liver region. The quality of an image was obtained from the percentage of nondiagnostic patches in all liver patches in the image. Treating nondiagnostic as positive, the accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), area under the receiver operating characteristic curve (AUC), and confusion matrix were used to evaluate our model. A Mann-Whitney U test was performed with the statistical significance set at 0.05.

RESULTS

Our model achieved good performance with an accuracy of 88.3 %, sensitivity of 86.0 %, specificity of 89.4 %, PPV of 78.6 %, NPV of 93.4 %, and AUC of 0.911 (95 % confidence interval: 0.882-0.939, p < 0.05). The confusion matrix of our model indicated good concordance with that of the radiologists.

CONCLUSIONS

The proposed two-step patch-based model achieved excellent performance when assessing the quality of liver MR images.

Imputation Strategy for Reliable Regional MRI Morphological Measurements

Regional morphological analysis represents a crucial step in most neuroimaging studies. Results from brain segmentation techniques are intrinsically prone to certain degrees of variability, mainly as results of suboptimal segmentation. To reduce this inherent variability, the errors are often identified through visual inspection and then corrected (semi)manually. Identification and correction of incorrect segmentation could be very expensive for large-scale studies. While identification of the incorrect results can be done relatively fast even with manual inspection, the correction step is extremely time-consuming, as it requires training staff to perform laborious manual corrections. Here we frame the correction phase of this problem as a missing data problem. Instead of manually adjusting the segmentation outputs, our computational approach aims to derive accurate morphological measures by machine learning imputation. Data imputation techniques may be used to replace missing or incorrect region average values with carefully chosen imputed values, all of which are computed based on other available multivariate information. We examined our approach of correcting segmentation outputs on a cohort of 970 subjects, which were undergone an extensive, time-consuming, manual post-segmentation correction. A random forest imputation technique recovered the gold standard results with a significant accuracy (r = 0.93, p < 0.0001; when 30% of the segmentations were considered incorrect in a non-random fashion). The random forest technique proved to be most effective for big data studies (N > 250).

Influence of Acquisition Time on MR Image Quality Estimated with Nonparametric Measures Based on Texture Features

Correlation of parametrized image texture features (ITF) analyses conducted in different regions of interest (ROIs) overcomes limitations and reliably reflects image quality. The aim of this study is to propose a nonparametrical method and classify the quality of a magnetic resonance (MR) image that has undergone controlled degradation by using textural features in the image. Images of 41 patients, 17 women and 24 men, aged between 23 and 56 years were analyzed. T2-weighted sagittal sequences of the lumbar spine, cervical spine, and knee and T2-weighted coronal sequences of the shoulder and wrist were generated. The implementation of parallel imaging with the use of GRAPPA2, GRAPPA3, and GRAPPA4 led to a substantial reduction in the scanning time but also degraded image quality. The number of degraded image textural features was correlated with the scanning time. Longer scan times correlated with markedly higher ITF image persistence in comparison with images computed with reduced scan times. Higher ITF preservation was observed in images of bones in the spine and femur as compared to images of soft tissues, i.e., tendons and muscles. Finally, a nonparametrized image quality assessment based on an analysis of the ITF, computed for different tissues, correlating with the changes in acquisition time of the MR images, was successfully developed. The correlation between acquisition time and the number of reproducible features present in an MR image was found to yield the necessary assumptions to calculate the quality index.

The LONI QC System: A Semi-Automated, Web-Based and Freely-Available Environment for the Comprehensive Quality Control of Neuroimaging Data

Quantifying, controlling, and monitoring image quality is an essential prerequisite for ensuring the validity and reproducibility of many types of neuroimaging data analyses. Implementation of quality control (QC) procedures is the key to ensuring that neuroimaging data are of high-quality and their validity in the subsequent analyses. We introduce the QC system of the Laboratory of Neuro Imaging (LONI): a web-based system featuring a workflow for the assessment of various modality and contrast brain imaging data. The design allows users to anonymously upload imaging data to the LONI-QC system. It then computes an exhaustive set of QC metrics which aids users to perform a standardized QC by generating a range of scalar and vector statistics. These procedures are performed in parallel using a large compute cluster. Finally, the system offers an automated QC procedure for structural MRI, which can flag each QC metric as being 'good' or 'bad.' Validation using various sets of data acquired from a single scanner and from multiple sites demonstrated the reproducibility of our QC metrics, and the sensitivity and specificity of the proposed Auto QC to 'bad' quality images in comparison to visual inspection. To the best of our knowledge, LONI-QC is the first online QC system that uniquely supports the variety of functionality where we compute numerous QC metrics and perform visual/automated image QC of multi-contrast and multi-modal brain imaging data. The LONI-QC system has been used to assess the quality of large neuroimaging datasets acquired as part of various multi-site studies such as the Transforming Research and Clinical Knowledge in Traumatic Brain Injury (TRACK-TBI) Study and the Alzheimer's Disease Neuroimaging Initiative (ADNI). LONI-QC's functionality is freely available to users worldwide and its adoption by imaging researchers is likely to contribute substantially to upholding high standards of brain image data quality and to implementing these standards across the neuroimaging community.