Making data sharing work: the FCP/INDI experience

Assistive tools for classifying neurological disorders using fMRI and deep learning: A guide and example

BACKGROUND

Deep-learning (DL) methods are rapidly changing the way researchers classify neurological disorders. For example, combining functional magnetic resonance imaging (fMRI) and DL has helped researchers identify functional biomarkers of neurological disorders (e.g., brain activation and connectivity) and pilot innovative diagnostic models. However, the knowledge required to perform DL analyses is often domain-specific and is not widely taught in the brain sciences (e.g., psychology, neuroscience, and cognitive science). Conversely, neurological diagnoses and neuroimaging training (e.g., fMRI) are largely restricted to the brain and medical sciences. In turn, these disciplinary knowledge barriers and distinct specializations can act as hurdles that prevent the combination of fMRI and DL pipelines. The complexity of fMRI and DL methods also hinders their clinical adoption and generalization to real-world diagnoses. For example, most current models are not designed for clinical settings or use by nonspecialized populations such as students, clinicians, and healthcare workers. Accordingly, there is a growing area of assistive tools (e.g., software and programming packages) that aim to streamline and increase the accessibility of fMRI and DL pipelines for the diagnoses of neurological disorders.

OBJECTIVES AND METHODS

In this study, we present an introductory guide to some popular DL and fMRI assistive tools. We also create an example autism spectrum disorder (ASD) classification model using assistive tools (e.g., Optuna, GIFT, and the ABIDE preprocessed repository), fMRI, and a convolutional neural network.

RESULTS

In turn, we provide researchers with a guide to assistive tools and give an example of a streamlined fMRI and DL pipeline.

CONCLUSIONS

We are confident that this study can help more researchers enter the field and create accessible fMRI and deep-learning diagnostic models for neurological disorders.

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.

Brain age monotonicity and functional connectivity differences of healthy subjects

Alterations in the brain's connectivity or the interactions among brain regions have been studied with the aid of resting state (rs)fMRI data attained from large numbers of healthy subjects of various demographics. This has been instrumental in providing insight into how a phenotype as fundamental as age affects the brain. Although machine learning (ML) techniques have already been deployed in such studies, novel questions are investigated in this work. We study whether young brains develop properties that progressively resemble those of aged brains, and if the aging dynamics of older brains provide information about the aging trajectory in young subjects. The degree of a prospective monotonic relationship will be quantified, and hypotheses of brain aging trajectories will be tested via ML. Furthermore, the degree of functional connectivity across the age spectrum of three datasets will be compared at a population level and across sexes. The findings scrutinize similarities and differences among the male and female subjects at greater detail than previously performed.

Hands-On Neuroinformatics Education at the Crossroads of Online and In-Person: Lessons Learned from NeuroHackademy

NeuroHackademy ( https://neurohackademy.org ) is a two-week event designed to train early-career neuroscience researchers in data science methods and their application to neuroimaging. The event seeks to bridge the big data skills gap by introducing participants to data science methods and skills that are often ignored in traditional curricula. Such skills are needed for the analysis and interpretation of the kinds of large and complex datasets that have become increasingly important to neuroimaging research due to concerted data collection efforts. In 2020, the event rapidly pivoted from an in-person event to an online event that included hundreds of participants from all over the world. This experience and those of the participants substantially changed our valuation of large online-accessible events. In subsequent events held in 2022 and 2023, we have developed a "hybrid" format that includes both online and in-person participants. We discuss the technical and sociotechnical elements of hybrid events and discuss some of the lessons we have learned while organizing them. We emphasize in particular the role that these events can play in creating a global and inclusive community of practice in the intersection of neuroimaging and data science.

Predicting verbal and performance intelligence quotients from multimodal data in individuals with attention deficit/hyperactivity disorder

Despite the importance of understanding how intelligence is ingrained in the function and structure of the brain in some neurological disorders, the alterations of intelligence-associated neurological factors in atypical neurodevelopmental disorders, such as attention deficit/hyperactivity disorder (ADHD), are limited. Therefore, we aimed to explore the relationship between the brain functional and morphological characteristics and the intellectual performance of 139 patients with ADHD. Resting-state functional and T1-weighted structural magnetic resonance imaging (MRI) data and intellectual-performance data of the patients were collected. The MRI data were preprocessed to extract four indicators characterizing the participants' brain features: fractional amplitude of low-frequency fluctuation, regional homogeneity, and gray and white matter volumes. Then, we used a two-layer feature-selection method with support vector regression models based on three kernel functions to predict the verbal and performance intelligent quotients of the patients, along with ten fold cross-validation to evaluate the models' predictive performance. All models showed good performance; the correlation coefficients between the predicted and observed values for each predictive phenotypic variable were >0.41, with statistical significance. The brain features that could best predict the intellectual performance of the patients were concentrated in the superior and inferior frontal gyrus of the prefrontal areas, the angular gyrus and precuneus of the parietal lobe, the inferior and middle temporal gyrus of the temporal lobe, and part of the cerebellar regions. Thus, the voxel-based brain-feature indicators could adequately predict the intellectual performance of patients with ADHD, providing a foundation for future neuroimaging studies of this disorder.

Beyond network connectivity: A classification approach to brain age prediction with resting-state fMRI

The brain is a complex, dynamic organ that shows differences in the same subject at various periods. Understanding how brain activity changes across age as a function of the brain networks has been greatly abetted by fMRI. Canonical analysis consists of determining how alterations in connectivity patterns (CPs) of certain regions are affected. An alternative approach is taken here by not considering connectivity but rather features computed from recordings at the regions of interest (ROIs). Using machine learning (ML) we assess how neural signals are altered by and prospectively predictive of age and sex via a methodology that is novel in drawing upon pairwise classification across six decades of subjects' chronological ages. ML is used to answer the equally important questions of what properties of the computed features are most predictive as well as which brain networks are most affected by aging. It was found that there is decreased differentiation among the neural signals of older subjects that are separated in age by the same number of years as younger subjects. Furthermore, the burstiness of the signals change at different rates between males and females. The findings provide insight into brain aging via an ROI-based analysis, the consideration of several feature groups, and a novel classification-based ML pipeline. There is also a contribution to understanding the effects of data aggregated from different recording centers on the conclusions of fMRI studies.

Brain Age Prediction Using Multi-Hop Graph Attention Combined with Convolutional Neural Network

Convolutional neural networks (CNNs) have been used widely to predict biological brain age based on brain magnetic resonance (MR) images. However, CNNs focus mainly on spatially local features and their aggregates and barely on the connective information between distant regions. To overcome this issue, we propose a novel multi-hop graph attention (MGA) module that exploits both the local and global connections of image features when combined with CNNs. After insertion between convolutional layers, MGA first converts the convolution-derived feature map into graph-structured data by using patch embedding and embedding-distance-based scoring. Multi-hop connections between the graph nodes are modeled by using the Markov chain process. After performing multi-hop graph attention, MGA re-converts the graph into an updated feature map and transfers it to the next convolutional layer. We combined the MGA module with sSE (spatial squeeze and excitation)-ResNet18 for our final prediction model (MGA-sSE-ResNet18) and performed various hyperparameter evaluations to identify the optimal parameter combinations. With 2788 three-dimensional T1-weighted MR images of healthy subjects, we verified the effectiveness of MGA-sSE-ResNet18 with comparisons to four established, general-purpose CNNs and two representative brain age prediction models. The proposed model yielded an optimal performance with a mean absolute error of 2.822 years and Pearson's correlation coefficient (PCC) of 0.968, demonstrating the potential of the MGA module to improve the accuracy of brain age prediction.

The Past, Present, and Future of the Brain Imaging Data Structure (BIDS)

The Brain Imaging Data Structure (BIDS) is a community-driven standard for the organization of data and metadata from a growing range of neuroscience modalities. This paper is meant as a history of how the standard has developed and grown over time. We outline the principles behind the project, the mechanisms by which it has been extended, and some of the challenges being addressed as it evolves. We also discuss the lessons learned through the project, with the aim of enabling researchers in other domains to learn from the success of BIDS.

Brain age prediction using combined deep convolutional neural network and multi-layer perceptron algorithms

The clinical applications of brain age prediction have expanded, particularly in anticipating the onset and prognosis of various neurodegenerative diseases. In the current study, we proposed a deep learning algorithm that leverages brain structural imaging data and enhances prediction accuracy by integrating biological sex information. Our model for brain age prediction, built on deep neural networks, employed a dataset of 3004 healthy subjects aged 18 and above. The T1-weighted images were minimally preprocessed and analyzed using the convolutional neural network (CNN) algorithm. The categorical sex information was then incorporated using the multi-layer perceptron (MLP) algorithm. We trained and validated both a CNN-only algorithm (utilizing only brain structural imaging data), and a combined CNN-MLP algorithm (using both structural brain imaging data and sex information) for age prediction. By integrating sex information with T1-weighted imaging data, our proposed CNN-MLP algorithm outperformed not only the CNN-only algorithm but also established algorithms, such as brainageR, in prediction accuracy. Notably, this hybrid CNN-MLP algorithm effectively distinguished between mild cognitive impairment and Alzheimer's disease groups by identifying variances in brain age gaps between them, highlighting the algorithm's potential for clinical application. Overall, these results underscore the enhanced precision of the CNN-MLP algorithm in brain age prediction, achieved through the integration of sex information.

Evaluation of Augmentation Methods in Classifying Autism Spectrum Disorders from fMRI Data with 3D Convolutional Neural Networks

Classifying subjects as healthy or diseased using neuroimaging data has gained a lot of attention during the last 10 years, and recently, different deep learning approaches have been used. Despite this fact, there has not been any investigation regarding how 3D augmentation can help to create larger datasets, required to train deep networks with millions of parameters. In this study, deep learning was applied to derivatives from resting state functional MRI data, to investigate how different 3D augmentation techniques affect the test accuracy. Specifically, resting state derivatives from 1112 subjects in ABIDE (Autism Brain Imaging Data Exchange) preprocessed were used to train a 3D convolutional neural network (CNN) to classify each subject according to presence or absence of autism spectrum disorder. The results show that augmentation only provide minor improvements to the test accuracy.

Connectome-based machine learning models are vulnerable to subtle data manipulations

Neuroimaging-based predictive models continue to improve in performance, yet a widely overlooked aspect of these models is "trustworthiness," or robustness to data manipulations. High trustworthiness is imperative for researchers to have confidence in their findings and interpretations. In this work, we used functional connectomes to explore how minor data manipulations influence machine learning predictions. These manipulations included a method to falsely enhance prediction performance and adversarial noise attacks designed to degrade performance. Although these data manipulations drastically changed model performance, the original and manipulated data were extremely similar (r = 0.99) and did not affect other downstream analysis. Essentially, connectome data could be inconspicuously modified to achieve any desired prediction performance. Overall, our enhancement attacks and evaluation of existing adversarial noise attacks in connectome-based models highlight the need for counter-measures that improve the trustworthiness to preserve the integrity of academic research and any potential translational applications.

The evolution of Big Data in neuroscience and neurology

Neurological diseases are on the rise worldwide, leading to increased healthcare costs and diminished quality of life in patients. In recent years, Big Data has started to transform the fields of Neuroscience and Neurology. Scientists and clinicians are collaborating in global alliances, combining diverse datasets on a massive scale, and solving complex computational problems that demand the utilization of increasingly powerful computational resources. This Big Data revolution is opening new avenues for developing innovative treatments for neurological diseases. Our paper surveys Big Data's impact on neurological patient care, as exemplified through work done in a comprehensive selection of areas, including Connectomics, Alzheimer's Disease, Stroke, Depression, Parkinson's Disease, Pain, and Addiction (e.g., Opioid Use Disorder). We present an overview of research and the methodologies utilizing Big Data in each area, as well as their current limitations and technical challenges. Despite the potential benefits, the full potential of Big Data in these fields currently remains unrealized. We close with recommendations for future research aimed at optimizing the use of Big Data in Neuroscience and Neurology for improved patient outcomes.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40537-023-00751-2.

A consensus protocol for functional connectivity analysis in the rat brain

Task-free functional connectivity in animal models provides an experimental framework to examine connectivity phenomena under controlled conditions and allows for comparisons with data modalities collected under invasive or terminal procedures. Currently, animal acquisitions are performed with varying protocols and analyses that hamper result comparison and integration. Here we introduce StandardRat, a consensus rat functional magnetic resonance imaging acquisition protocol tested across 20 centers. To develop this protocol with optimized acquisition and processing parameters, we initially aggregated 65 functional imaging datasets acquired from rats across 46 centers. We developed a reproducible pipeline for analyzing rat data acquired with diverse protocols and determined experimental and processing parameters associated with the robust detection of functional connectivity across centers. We show that the standardized protocol enhances biologically plausible functional connectivity patterns relative to previous acquisitions. The protocol and processing pipeline described here is openly shared with the neuroimaging community to promote interoperability and cooperation toward tackling the most important challenges in neuroscience.

Engaging participants with research findings: A rights-informed approach

BACKGROUND

Sharing research findings with participants is recognized as an ethical imperative for the research community. However, most discourse on this topic in mainstream public health takes a paternalistic approach, with researchers retaining the power to choose if, when, and how research findings are shared.

METHODS

Fieldwork took place from August 2018 to January 2019 and again from August 2019 to December 2019 among two communities in the south Indian state of Kerala. We integrated participant engagement with study findings into the research protocol, using various collaborative strategies identified during the design stage, forming partnerships with participants and determining appropriate forms of dissemination for different participant groups during fieldwork.

RESULTS

Findings from previous research projects undertaken with these communities by other researchers had not been shared with them. This was interpreted by the communities as researchers not being interested in making a difference to their situation. In the current study, building reciprocal relationships that minimized power disparities, and providing outputs in tailored formats that promoted active engagement were key factors that enabled participants to engage with results. This engagement added value by enabling us to co-develop study recommendations. This process also enabled the community to have ownership of the results and use them to advocate for health system change to improve access to health care.

CONCLUSION

Research should be transformative for participating communities. Participants have a right to know the results of the research they participate in since their knowledge provides the research data which can in turn promote community change. Operationalising this requires researchers to build partnerships with participants and their communities from the outset. The role of participants must be reimagined, and adequate resources should be built into the research process. This is both socially responsible and ethical, but also improves the impact and legitimacy of research for the participants and the communities that they represent.

PATIENT OR PUBLIC CONTRIBUTION

Participants of our research contributed to the design of various aspects of the engagement processes including the venue, the formats used for engagement, interpretation of the findings and recommendations from our research.

FAIR human neuroscientific data sharing to advance AI driven research and applications: Legal frameworks and missing metadata standards

Modern AI supported research holds many promises for basic and applied science. However, the application of AI methods is often limited because most labs cannot, on their own, acquire large and diverse datasets, which are best for training these methods. Data sharing and open science initiatives promise some relief to the problem, but only if the data are provided in a usable way. The FAIR principles state very general requirements for useful data sharing: they should be findable, accessible, interoperable, and reusable. This article will focus on two challenges to implement the FAIR framework for human neuroscience data. On the one hand, human data can fall under special legal protection. The legal frameworks regulating how and what data can be openly shared differ greatly across countries which can complicate data sharing or even discourage researchers from doing so. Moreover, openly accessible data require standardization of data and metadata organization and annotation in order to become interpretable and useful. This article briefly introduces open neuroscience initiatives that support the implementation of the FAIR principles. It then reviews legal frameworks, their consequences for accessibility of human neuroscientific data and some ethical implications. We hope this comparison of legal jurisdictions helps to elucidate that some alleged obstacles for data sharing only require an adaptation of procedures but help to protect the privacy of our most generous donors to research … our study participants. Finally, it elaborates on the problem of missing standards for metadata annotation and introduces initiatives that aim at developing tools to make neuroscientific data acquisition and analysis pipelines FAIR by design. While the paper focuses on making human neuroscience data useful for data-intensive AI the general considerations hold for other fields where large amounts of openly available human data would be helpful.

Resting-state functional MRI in multicenter studies on multiple sclerosis: a report on raw data quality and functional connectivity features from the Italian Neuroimaging Network Initiative

The Italian Neuroimaging Network Initiative (INNI) is an expanding repository of brain MRI data from multiple sclerosis (MS) patients recruited at four Italian MRI research sites. We describe the raw data quality of resting-state functional MRI (RS-fMRI) time-series in INNI and the inter-site variability in functional connectivity (FC) features after unified automated data preprocessing. MRI datasets from 489 MS patients and 246 healthy control (HC) subjects were retrieved from the INNI database. Raw data quality metrics included temporal signal-to-noise ratio (tSNR), spatial smoothness (FWHM), framewise displacement (FD), and differential variation in signals (DVARS). Automated preprocessing integrated white-matter lesion segmentation (SAMSEG) into a standard fMRI pipeline (fMRIPrep). FC features were calculated on pre-processed data and harmonized between sites (Combat) prior to assessing general MS-related alterations. Across centers (both groups), median tSNR and FWHM ranged from 47 to 84 and from 2.0 to 2.5, and median FD and DVARS ranged from 0.08 to 0.24 and from 1.06 to 1.22. After preprocessing, only global FC-related features were significantly correlated with FD or DVARS. Across large-scale networks, age/sex/FD-adjusted and harmonized FC features exhibited both inter-site and site-specific inter-group effects. Significant general reductions were obtained for somatomotor and limbic networks in MS patients (vs. HC). The implemented procedures provide technical information on raw data quality and outcome of fully automated preprocessing that might serve as reference in future RS-fMRI studies within INNI. The unified pipeline introduced little bias across sites and appears suitable for multisite FC analyses on harmonized network estimates.

Connectome-based predictive modelling of cognitive reserve using task-based functional connectivity

Cognitive reserve supports cognitive function in the presence of pathology or atrophy. Functional neuroimaging may enable direct and accurate measurement of cognitive reserve which could have considerable clinical potential. The present study aimed to develop and validate a measure of cognitive reserve using task-based fMRI data that could then be applied to independent resting-state data. Connectome-based predictive modelling with leave-one-out cross-validation was applied to predict a residual measure of cognitive reserve using task-based functional connectivity from the Cognitive Reserve/Reference Ability Neural Network studies (n = 220, mean age = 51.91 years, SD = 17.04 years). This model generated summary measures of connectivity strength that accurately predicted a residual measure of cognitive reserve in unseen participants. The theoretical validity of these measures was established via a positive correlation with a socio-behavioural proxy of cognitive reserve (verbal intelligence) and a positive correlation with global cognition, independent of brain structure. This fitted model was then applied to external test data: resting-state functional connectivity data from The Irish Longitudinal Study on Ageing (TILDA, n = 294, mean age = 68.3 years, SD = 7.18 years). The network-strength predicted measures were not positively associated with a residual measure of cognitive reserve nor with measures of verbal intelligence and global cognition. The present study demonstrated that task-based functional connectivity data can be used to generate theoretically valid measures of cognitive reserve. Further work is needed to establish if, and how, measures of cognitive reserve derived from task-based functional connectivity can be applied to independent resting-state data.

Graph-Based Disease Prediction in Neuroimaging: Investigating the Impact of Feature Selection

In biomedical machine learning, data often appear in the form of graphs. Biological systems such as protein interactions and ecological or brain networks are instances of applications that benefit from graph representations. Geometric deep learning is an arising field of techniques that has extended deep neural networks to non-Euclidean domains such as graphs. In particular, graph convolutional neural networks have achieved advanced performance in semi-supervised learning in those domains. Over the last years, these methods have gained traction in neuroscience as they could be the key to a deeper understanding in clinical diagnosis at the systems or network level (for an individual brain but also for across a cohort of subjects). As a proof-of-principle, we study and validate a previous implementation of graph-based semi-supervised classification using a ridge classifier and graph convolutional neural networks. The models are trained on population graphs that integrate imaging and phenotypic information. Our analysis employs neuroimaging data of structural and functional connectivity for prediction of neurodevelopmental and neurodegenerative disorders. Here, we particularly study the effect of different strategies to reduce the dimensionality of the neuroimaging features on the graph nodes on the classification performance.

PhiPipe: A multi-modal MRI data processing pipeline with test-retest reliability and predicative validity assessments

Magnetic resonance imaging (MRI) has been one of the primary instruments to measure the properties of the human brain non-invasively in vivo. MRI data generally needs to go through a series of processing steps (i.e., a pipeline) before statistical analysis. Currently, the processing pipelines for multi-modal MRI data are still rare, in contrast to single-modal pipelines. Furthermore, the reliability and validity of the output of the pipelines are critical for the MRI studies. However, the reliability and validity measures are not available or adequate for almost all pipelines. Here, we present PhiPipe, a multi-modal MRI processing pipeline. PhiPipe could process T1-weighted, resting-state BOLD, and diffusion-weighted MRI data and generate commonly used brain features in neuroimaging. We evaluated the test-retest reliability of PhiPipe's brain features by computing intra-class correlations (ICC) in four public datasets with repeated scans. We further evaluated the predictive validity by computing the correlation of brain features with chronological age in three public adult lifespan datasets. The multivariate reliability and predictive validity of the PhiPipe results were also evaluated. The results of PhiPipe were consistent with previous studies, showing comparable or better reliability and validity when compared with two popular single-modality pipelines, namely DPARSF and PANDA. The publicly available PhiPipe provides a simple-to-use solution to multi-modal MRI data processing. The accompanied reliability and validity assessments could help researchers make informed choices in experimental design and statistical analysis. Furthermore, this study provides a framework for evaluating the reliability and validity of image processing pipelines.

Functional network properties derived from wide-field calcium imaging differ with wakefulness and across cell type

To improve 'bench-to-bedside' translation, it is integral that knowledge flows bidirectionally-from animal models to humans, and vice versa. This requires common analytical frameworks, as well as open software and data sharing practices. We share a new pipeline (and test dataset) for the preprocessing of wide-field optical fluorescence imaging data-an emerging mode applicable in animal models-as well as results from a functional connectivity and graph theory analysis inspired by recent work in the human neuroimaging field. The approach is demonstrated using a dataset comprised of two test-cases: (1) data from animals imaged during awake and anesthetized conditions with excitatory neurons labeled, and (2) data from awake animals with different genetically encoded fluorescent labels that target either excitatory neurons or inhibitory interneuron subtypes. Both seed-based connectivity and graph theory measures (global efficiency, transitivity, modularity, and characteristic path-length) are shown to be useful in quantifying differences between wakefulness states and cell populations. Wakefulness state and cell type show widespread effects on canonical network connectivity with variable frequency band dependence. Differences between excitatory neurons and inhibitory interneurons are observed, with somatostatin expressing inhibitory interneurons emerging as notably dissimilar from parvalbumin and vasoactive polypeptide expressing cells. In sum, we demonstrate that our pipeline can be used to examine brain state and cell-type differences in mesoscale imaging data, aiding translational neuroscience efforts. In line with open science practices, we freely release the pipeline and data to encourage other efforts in the community.

An analysis-ready and quality controlled resource for pediatric brain white-matter research

We created a set of resources to enable research based on openly-available diffusion MRI (dMRI) data from the Healthy Brain Network (HBN) study. First, we curated the HBN dMRI data (N = 2747) into the Brain Imaging Data Structure and preprocessed it according to best-practices, including denoising and correcting for motion effects, susceptibility-related distortions, and eddy currents. Preprocessed, analysis-ready data was made openly available. Data quality plays a key role in the analysis of dMRI. To optimize QC and scale it to this large dataset, we trained a neural network through the combination of a small data subset scored by experts and a larger set scored by community scientists. The network performs QC highly concordant with that of experts on a held out set (ROC-AUC = 0.947). A further analysis of the neural network demonstrates that it relies on image features with relevance to QC. Altogether, this work both delivers resources to advance transdiagnostic research in brain connectivity and pediatric mental health, and establishes a novel paradigm for automated QC of large datasets.

A longitudinal resource for studying connectome development and its psychiatric associations during childhood

Most psychiatric disorders are chronic, associated with high levels of disability and distress, and present during pediatric development. Scientific innovation increasingly allows researchers to probe brain-behavior relationships in the developing human. As a result, ambitions to (1) establish normative pediatric brain development trajectories akin to growth curves, (2) characterize reliable metrics for distinguishing illness, and (3) develop clinically useful tools to assist in the diagnosis and management of mental health and learning disorders have gained significant momentum. To this end, the NKI-Rockland Sample initiative was created to probe lifespan development as a large-scale multimodal dataset. The NKI-Rockland Sample Longitudinal Discovery of Brain Development Trajectories substudy (N = 369) is a 24- to 30-month multi-cohort longitudinal pediatric investigation (ages 6.0-17.0 at enrollment) carried out in a community-ascertained sample. Data include psychiatric diagnostic, medical, behavioral, and cognitive phenotyping, as well as multimodal brain imaging (resting fMRI, diffusion MRI, morphometric MRI, arterial spin labeling), genetics, and actigraphy. Herein, we present the rationale, design, and implementation of the Longitudinal Discovery of Brain Development Trajectories protocol.

Convolutional Neural Networks for Segmenting Cerebellar Fissures from Magnetic Resonance Imaging

The human cerebellum plays an important role in coordination tasks. Diseases such as spinocerebellar ataxias tend to cause severe damage to the cerebellum, leading patients to a progressive loss of motor coordination. The detection of such damages can help specialists to approximate the state of the disease, as well as to perform statistical analysis, in order to propose treatment therapies for the patients. Manual segmentation of such patterns from magnetic resonance imaging is a very difficult and time-consuming task, and is not a viable solution if the number of images to process is relatively large. In recent years, deep learning techniques such as convolutional neural networks (CNNs or convnets) have experienced an increased development, and many researchers have used them to automatically segment medical images. In this research, we propose the use of convolutional neural networks for automatically segmenting the cerebellar fissures from brain magnetic resonance imaging. Three models are presented, based on the same CNN architecture, for obtaining three different binary masks: fissures, cerebellum with fissures, and cerebellum without fissures. The models perform well in terms of precision and efficiency. Evaluation results show that convnets can be trained for such purposes, and could be considered as additional tools in the diagnosis and characterization of neurodegenerative diseases.

The spectrum of data sharing policies in neuroimaging data repositories

Sharing data is a scientific imperative that accelerates scientific discoveries, reinforces open science inquiry, and allows for efficient use of public investment and research resources. Considering these benefits, data sharing has been widely promoted in diverse fields and neuroscience has been no exception to this movement. For all its promise, however, the sharing of human neuroimaging data raises critical ethical and legal issues, such as data privacy. Recently, the heightened risks to data privacy posed by the rapid advances in artificial intelligence and machine learning techniques have made data sharing more challenging; the regulatory landscape around data sharing has also been evolving rapidly. Here we present an in-depth ethical and regulatory analysis that examines how neuroimaging data are currently shared against the backdrop of the relevant regulations and policies in the United States and how advanced software tools and algorithms might undermine subjects' privacy in neuroimaging data sharing. The implications of these novel technological threats to privacy in neuroimaging data sharing practices and policies will also be discussed. We then conclude with a proposal for a legal prohibition against malicious use of neuroscience data as a regulatory mechanism to address privacy risks associated with the data while maximizing the benefits of data sharing and open science practice in the field of neuroscience.

Global Trends in Scientific Research on Pediatric Obesity

(1) Introduction: The aim of this study was to analyze scientific production, collaboration among countries, and research topics focusing on pediatric obesity. (2) Methods: The papers that were included in the study were retrieved from the Web of Science Core Collection from Clarivate Analytics. A bibliometric analysis of several focuses, including journals of publication, subject categories, most frequent author keywords, and journal impact factors, was conducted. Social network analysis was used to recognize collaboration groups between countries and the co-occurrences of author keywords. (3) Results: A total of 12,171 research articles were published in 2036 journals classified under a variety of subject areas, with pediatrics (27.7%), nutrition and dietetics (18.5%), and public environmental and occupational health (18.4%) accounting for the most frequent study areas, and Pediatric Obesity (309), the International Journal of Obesity (299), and BMC Public Health being the most productive journals. The main challenges identified for pediatric obesity include general topics such as physical activity, nutrition, diet, and prevention as well as other more specific challenges such as metabolic syndrome, insulin resistance, eating behavior, and cardiovascular diseases. (4) Conclusions: We observed a growth rate in the number of published articles of 59.8%, which serves as evidence of the importance of the topic. The number of funded papers also doubled from 2010 to 2019. There has been significant global collaboration on the topic, with countries across five continents being involved. The results of the thematic analysis reveal the importance of exercise and nutrition-related topics along with specialized health terms and terms related to public health.

Scan Once, Analyse Many: Using Large Open-Access Neuroimaging Datasets to Understand the Brain

We are now in a time of readily available brain imaging data. Not only are researchers now sharing data more than ever before, but additionally large-scale data collecting initiatives are underway with the vision that many future researchers will use the data for secondary analyses. Here I provide an overview of available datasets and some example use cases. Example use cases include examining individual differences, more robust findings, reproducibility-both in public input data and availability as a replication sample, and methods development. I further discuss a variety of considerations associated with using existing data and the opportunities associated with large datasets. Suggestions for further readings on general neuroimaging and topic-specific discussions are also provided.

NeuroCrypt: Machine Learning Over Encrypted Distributed Neuroimaging Data

The field of neuroimaging can greatly benefit from building machine learning models to detect and predict diseases, and discover novel biomarkers, but much of the data collected at various organizations and research centers is unable to be shared due to privacy or regulatory concerns (especially for clinical data or rare disorders). In addition, aggregating data across multiple large studies results in a huge amount of duplicated technical debt and the resources required can be challenging or impossible for an individual site to build. Training on the data distributed across organizations can result in models that generalize much better than models trained on data from any of organizations alone. While there are approaches for decentralized sharing, these often do not provide the highest possible guarantees of sample privacy that only cryptography can provide. In addition, such approaches are often focused on probabilistic solutions. In this paper, we propose an approach that leverages the potential of datasets spread among a number of data collecting organizations by performing joint analyses in a secure and deterministic manner when only encrypted data is shared and manipulated. The approach is based on secure multiparty computation which refers to cryptographic protocols that enable distributed computation of a function over distributed inputs without revealing additional information about the inputs. It enables multiple organizations to train machine learning models on their joint data and apply the trained models to encrypted data without revealing their sensitive data to the other parties. In our proposed approach, organizations (or sites) securely collaborate to build a machine learning model as it would have been trained on the aggregated data of all the organizations combined. Importantly, the approach does not require a trusted party (i.e. aggregator), each contributing site plays an equal role in the process, and no site can learn individual data of any other site. We demonstrate effectiveness of the proposed approach, in a range of empirical evaluations using different machine learning algorithms including logistic regression and convolutional neural network models on human structural and functional magnetic resonance imaging datasets.

Large, open datasets for human connectomics research: Considerations for reproducible and responsible data use

Large, open datasets have emerged as important resources in the field of human connectomics. In this review, the evolution of data sharing involving magnetic resonance imaging is described. A summary of the challenges and progress in conducting reproducible data analyses is provided, including description of recent progress made in the development of community guidelines and recommendations, software and data management tools, and initiatives to enhance training and education. Finally, this review concludes with a discussion of ethical conduct relevant to analyses of large, open datasets and a researcher's responsibility to prevent further stigmatization of historically marginalized racial and ethnic groups. Moving forward, future work should include an enhanced emphasis on the social determinants of health, which may further contextualize findings among diverse population-based samples. Leveraging the progress to date and guided by interdisciplinary collaborations, the future of connectomics promises to be an impressive era of innovative research, yielding a more inclusive understanding of brain structure and function.

The OpenNeuro resource for sharing of neuroscience data

The sharing of research data is essential to ensure reproducibility and maximize the impact of public investments in scientific research. Here, we describe OpenNeuro, a BRAIN Initiative data archive that provides the ability to openly share data from a broad range of brain imaging data types following the FAIR principles for data sharing. We highlight the importance of the Brain Imaging Data Structure standard for enabling effective curation, sharing, and reuse of data. The archive presently shares more than 600 datasets including data from more than 20,000 participants, comprising multiple species and measurement modalities and a broad range of phenotypes. The impact of the shared data is evident in a growing number of published reuses, currently totalling more than 150 publications. We conclude by describing plans for future development and integration with other ongoing open science efforts.

A Convolutional Neural Network Combined With Prototype Learning Framework for Brain Functional Network Classification of Autism Spectrum Disorder

The application of deep learning methods in brain disease diagnosis is becoming a new research hotspot. This study constructed brain functional networks based on the functional magnetic resonance imaging (fMRI) data, and proposed a novel convolutional neural network combined with a prototype learning (CNNPL) framework to classify brain functional networks for the diagnosis of autism spectrum disorder (ASD). At the bottom of CNNPL, traditional CNN was employed as the basic feature extractor, while at the top of CNNPL multiple prototypes were automatically learnt on the features to represent different categories. A generalized prototype loss based on distance cross-entropy was proposed to jointly learn the parameters of the CNN feature extractor and the prototypes. The classification was implemented with prototype matching. A transfer learning strategy was introduced to our CNNPL for weight initialization in the subsequent fine-tuning phase to promote model training. We conducted systematic experiments on the aggregate multi-sites ASD dataset. Experimental results revealed that our model outperforms the current state-of-the-art methods in ASD classification and can reliably learn inter-site biomarkers, indicating the robustness of our model on large-scale dataset with inter-site variability. Furthermore, our model demonstrated robust learning capability for high-level organization of brain functionality. Our study also identified important brain regions as biomarkers associated with ASD classification. Together, our proposed model provides a promising solution for learning and classifying brain functional networks, and thus contributes to the biomarker extraction and imaging diagnosis of ASD.

The "Narratives" fMRI dataset for evaluating models of naturalistic language comprehension

The "Narratives" collection aggregates a variety of functional MRI datasets collected while human subjects listened to naturalistic spoken stories. The current release includes 345 subjects, 891 functional scans, and 27 diverse stories of varying duration totaling ~4.6 hours of unique stimuli (~43,000 words). This data collection is well-suited for naturalistic neuroimaging analysis, and is intended to serve as a benchmark for models of language and narrative comprehension. We provide standardized MRI data accompanied by rich metadata, preprocessed versions of the data ready for immediate use, and the spoken story stimuli with time-stamped phoneme- and word-level transcripts. All code and data are publicly available with full provenance in keeping with current best practices in transparent and reproducible neuroimaging.

A comparison of machine learning classifiers for pediatric epilepsy using resting-state functional MRI latency data

Epilepsy affects 1 in 150 children under the age of 10 and is the most common chronic pediatric neurological condition; poor seizure control can irreversibly disrupt normal brain development. The present study compared the ability of different machine learning algorithms trained with resting-state functional MRI (rfMRI) latency data to detect epilepsy. Preoperative rfMRI and anatomical MRI scans were obtained for 63 patients with epilepsy and 259 healthy controls. The normal distribution of latency z-scores from the epilepsy and healthy control cohorts were analyzed for overlap in 36 seed regions. In these seed regions, overlap between the study cohorts ranged from 0.44-0.58. Machine learning features were extracted from latency z-score maps using principal component analysis. Extreme Gradient Boosting (XGBoost), Support Vector Machines (SVM), and Random Forest algorithms were trained with these features. Area under the receiver operating characteristics curve (AUC), accuracy, sensitivity, specificity and F1-scores were used to evaluate model performance. The XGBoost model outperformed all other models with a test AUC of 0.79, accuracy of 74%, specificity of 73%, and a sensitivity of 77%. The Random Forest model performed comparably to XGBoost across multiple metrics, but it had a test sensitivity of 31%. The SVM model did not perform >70% in any of the test metrics. The XGBoost model had the highest sensitivity and accuracy for the detection of epilepsy. Development of machine learning algorithms trained with rfMRI latency data could provide an adjunctive method for the diagnosis and evaluation of epilepsy with the goal of enabling timely and appropriate care for patients.

Abnormal hemispheric asymmetry of both brain function and structure in attention deficit/hyperactivity disorder: a meta-analysis of individual participant data

Aberration in the asymmetric nature of the human brain is associated with several mental disorders, including attention deficit/hyperactivity disorder (ADHD). In ADHD, these aberrations are thought to reflect key hemispheric differences in the functioning of attention, although the structural and functional bases of these defects are yet to be fully characterized. In this study, we applied a comprehensive meta-analysis to multimodal imaging datasets from 627 subjects (303 typically developing control [TDCs] and 324 patients with ADHD) with both resting-state functional and structural magnetic resonance imaging (MRI), from seven independent publicly available datasets of the ADHD-200 sample. We performed lateralization analysis and calculated the combined effects of ADHD on each of three cortical regional measures (grey matter volume - GMV, fractional amplitude of low frequency fluctuations at rest -fALFF, and regional homogeneity -ReHo). We found that compared with TDC, 68%,73% and 66% of regions showed statistically significant ADHD disorder effects on the asymmetry of GMV, fALFF, and ReHo, respectively, (false discovery rate corrected, q = 0.05). Forty-one percent (41%) of regions had both structural and functional abnormalities in asymmetry, located in the prefrontal, frontal, and subcortical cortices, and the cerebellum. Furthermore, brain asymmetry indices in these regions were higher in children with more severe ADHD symptoms, indicating a crucial pathoplastic role for asymmetry. Our findings highlight the functional asymmetry in ADHD which has (1) a strong structural basis, and thus is likely to be developmental in nature; and (2) is strongly linked to symptom burden and IQ and may carry a possible prognostic value for grading the severity of ADHD.

World Cancer Day 2021 - Perspectives in Pediatric and Adult Neuro-Oncology

Significant advances in our understanding of the molecular genetics of pediatric and adult brain tumors and the resulting rapid expansion of clinical molecular neuropathology have led to improvements in diagnostic accuracy and identified new targets for therapy. Moreover, there have been major improvements in all facets of clinical care, including imaging, surgery, radiation and supportive care. In selected cohorts of patients, targeted and immunotherapies have resulted in improved patient outcomes. Furthermore, adaptations to clinical trial design have facilitated our study of new agents and other therapeutic innovations. However, considerable work remains to be done towards extending survival for all patients with primary brain tumors, especially children and adults with diffuse midline gliomas harboring Histone H3 K27 mutations and adults with isocitrate dehydrogenase (IDH) wild-type, O6 guanine DNA-methyltransferase gene (MGMT) promoter unmethylated high grade gliomas. In addition to improvements in therapy and care, access to the advances in technology, such as particle radiation or biologic therapy, neuroimaging and molecular diagnostics in both developing and developed countries is needed to improve the outcome of patients with brain tumors.

"Impact of ICA Dimensionality on the Test-Retest Reliability of Resting-State Functional Connectivity

As resting-state functional connectivity (rsFC) research moves toward the study of individual differences, test-retest reliability is increasingly important to understand. Previous literature supports the test-retest reliability of rsFC derived with independent component analysis (ICA) and dual regression, yet the impact of dimensionality (i.e., the number of components to extract from group-ICA) remained obscure in the current context of large-scale datasets. To provide principled guidelines on this issue, ICA at dimensionalities varying from 25 to 350 was applied to the cortical surface with resting-state functional magnetic resonance imaging data from 1003 participants in the Human Connectome Project. The reliability of two rsFC measures: (within-component) coherence and (between-component) connectivity was estimated. Reliability and its change with dimensionality varied by network: the cognitive (frontoparietal, cingulo-opercular, dorsal attention, and default) networks were measured with the highest reliability which improved with increased dimensionality until at least 150; the visual and somatomotor networks were measured with lower reliability which benefited mildly from increased dimensionality; the temporal pole/orbitofrontal cortex (TP/OFC) network was measured with the lowest reliability. Overall, ICA reliability was optimized at dimensionalities of 150 or above. Compared with two popular binary, non-overlapping cortical atlases, ICA and dual regression resulted in higher reliability for the cognitive networks, lower reliability for the somatomotor network, and similar reliability for the visual and TP/OFC networks. These findings highlight analytical decisions that maximize the reliability of rsFC measures and how they depend on one's networks of interest.

Management and Quality Control of Large Neuroimaging Datasets: Developments From the Barcelonaβeta Brain Research Center

Recent decades have witnessed an increasing number of large to very large imaging studies, prominently in the field of neurodegenerative diseases. The datasets collected during these studies form essential resources for the research aiming at new biomarkers. Collecting, hosting, managing, processing, or reviewing those datasets is typically achieved through a local neuroinformatics infrastructure. In particular for organizations with their own imaging equipment, setting up such a system is still a hard task, and relying on cloud-based solutions, albeit promising, is not always possible. This paper proposes a practical model guided by core principles including user involvement, lightweight footprint, modularity, reusability, and facilitated data sharing. This model is based on the experience from an 8-year-old research center managing cohort research programs on Alzheimer’s disease. Such a model gave rise to an ecosystem of tools aiming at improved quality control through seamless automatic processes combined with a variety of code libraries, command line tools, graphical user interfaces, and instant messaging applets. The present ecosystem was shaped around XNAT and is composed of independently reusable modules that are freely available on GitLab/GitHub. This paradigm is scalable to the general community of researchers working with large neuroimaging datasets.

Functional Magnetic Resonance Connectivity in Patients With Temporomadibular Joint Disorders

Myofascial pain in the masticatory region, generally referred to as headache, is a common temporomandibular disorder (TMD) characterized by the hypersensitive regions of the contracted skeletal muscle fibers. A correct clinical treatment of myofascial pain has the potential to modify the functional activation of cerebral networks associated with pain and unconscious teeth clenching, specifically the pain network (PN) and default mode network (DMN). In this study, research is presented as a case series of five patients with myofascial pain: three were diagnosed with intra- and extra-articular disorders, and two were diagnosed with only extra-articular disorders. All five patients received gnathological therapy consisting of passive splints and biofeedback exercises for tongue–palatal vault coordination. Before and after treatment, patients underwent pain assessments (through measures of visual analog scales and muscular palpation tests), nuclear magnetic resonance of the temporomandibular joint, and functional nuclear magnetic resonance of the brain. In each patient, temporomandibular joint nuclear magnetic resonance results were similar before and after the gnathological treatment. However, the treatment resulted in a considerable reduction in pain for all patients, according to the visual analog scales and the palpation test. Furthermore, functional nuclear magnetic resonance of the brain clearly showed a homogeneous modification in cerebral networks associated with pain (i.e., PN and DMN), in all patients. In conclusion, gnathological therapy consisting of passive aligners and biofeedback exercises improved myofascial pain in all five patients. Most importantly, this study showed that all five patients had a homogeneous functional modification of pain and default mode networks. Using passive splints in combination with jaw exercises may be an effective treatment option for patients with TMD. This research could be a starting point for future investigations and for clinicians who want to approach similar situations.

Quantity and quality: Normative open-access neuroimaging databases

The focus of this article is to compare twenty normative and open-access neuroimaging databases based on quantitative measures of image quality, namely, signal-to-noise (SNR) and contrast-to-noise ratios (CNR). We further the analysis through discussing to what extent these databases can be used for the visualization of deeper regions of the brain, such as the subcortex, as well as provide an overview of the types of inferences that can be drawn. A quantitative comparison of contrasts including T1-weighted (T1w) and T2-weighted (T2w) images are summarized, providing evidence for the benefit of ultra-high field MRI. Our analysis suggests a decline in SNR in the caudate nuclei with increasing age, in T1w, T2w, qT1 and qT2* contrasts, potentially indicative of complex structural age-dependent changes. A similar decline was found in the corpus callosum of the T1w, qT1 and qT2* contrasts, though this relationship is not as extensive as within the caudate nuclei. These declines were accompanied by a declining CNR over age in all image contrasts. A positive correlation was found between scan time and the estimated SNR as well as a negative correlation between scan time and spatial resolution. Image quality as well as the number and types of contrasts acquired by these databases are important factors to take into account when selecting structural data for reuse. This article highlights the opportunities and pitfalls associated with sampling existing databases, and provides a quantitative backing for their usage.

Sex differences in brain aging among adults with family history of Alzheimer's disease and APOE4 genetic risk

Emerging evidence suggests that Alzheimer's Disease (AD) risk factors may differentially contribute to disease trajectory in women than men. Determining the effect of AD risk factors on brain aging in women, compared to men, is critical for understanding whether there are sex differences in the pathways towards AD in cognitively intact but at-risk adults. Brain Age Gap (BAG) is a concept used increasingly as a measure of brain health; BAG is defined as the difference between predicted age (based on structural MRI) and chronological age, with negative values reflecting preserved brain health with age. Using BAG, we investigated whether there were sex differences in the brain effects of AD risk factors (i.e., family history of AD, and carrying an apolipoprotein E ε4 allele [+APOE4]) in cognitively intact adults, and if this relationship was moderated by modifiable factors (i.e. body mass index [BMI], blood pressure and physical activity). We undertook a cross-sectional study of structural MRIs from 1067 cognitively normal adults across four neuroimaging datasets. An elastic net regression model found that women with a family history of AD and +APOE4 genotype had more advanced brain aging than their male counterparts. In a sub-cohort of women with those risk factors, higher BMI was associated with less brain aging whereas lower BMI was not. In a sub-cohort of women and men with +APOE4, engaging in physical activity was more beneficial to men's brain aging than women's. Our results demonstrate that AD risk factors are associated with greater brain aging in women than men, although there may be more unexplored modifiable factors that influence this relationship. These findings suggest that the complex interplay between unmodifiable and modifiable AD risk factors can potentially protect against brain aging in women and men.

Functional connectivity of the default mode, dorsal attention and fronto-parietal executive control networks in glial tumor patients

PURPOSE

Resting state functional magnetic resonance imaging (rsfMRI) is an emerging tool to explore the functional connectivity of different brain regions. We aimed to assess the disruption of functional connectivity of the Default Mode Network (DMN), Dorsal Attention Network(DAN) and Fronto-Parietal Network (FPN) in patients with glial tumors.

METHODS

rsfMRI data acquired on 3T-MR of treatment-naive glioma patients prospectively recruited (2015-2019) and matched controls from the 1000 functional-connectomes-project were analyzed using the CONN functional toolbox. Seed-Based Connectivity Analysis (SBCA) and Independent Component Analysis (ICA, with 10 to 100 components) were performed to study reliably the three networks of interest.

RESULTS

35 patients with gliomas (17 WHO grade I-II, 18 grade III-IV) and 70 controls were included. Global increased DMN connectivity was consistently found with SBCA and ICA in patients compared to controls (Cluster1: Precuneus, height: p < 10^-6; Cluster2: subcallosum; height: p < 10^-5). However, an area of decreased connectivity was found in the posterior corpus callosum, particularly in high-grade gliomas (height: p < 10^-5). The DAN demonstrated small areas of increased connectivity in frontal and occipital regions (height: p < 10^-6). For the FPN, increased connectivity was noted in the precuneus, posterior cingulate gyrus, and frontal cortex. No difference in the connectivity of the networks of interest was demonstrated between low- and high-grade gliomas, as well as when stratified by their IDH1-R132H (isocitrate dehydrogenase) mutation status.

CONCLUSION

Altered functional connectivity is reliably found with SBCA and ICA in the DMN, DAN, and FPN in glioma patients, possibly explained by decreased connectivity between the cerebral hemispheres across the corpus callosum due to disruption of the connections.

Opportunities for increased reproducibility and replicability of developmental neuroimaging

Many workflows and tools that aim to increase the reproducibility and replicability of research findings have been suggested. In this review, we discuss the opportunities that these efforts offer for the field of developmental cognitive neuroscience, in particular developmental neuroimaging. We focus on issues broadly related to statistical power and to flexibility and transparency in data analyses. Critical considerations relating to statistical power include challenges in recruitment and testing of young populations, how to increase the value of studies with small samples, and the opportunities and challenges related to working with large-scale datasets. Developmental studies involve challenges such as choices about age groupings, lifespan modelling, analyses of longitudinal changes, and data that can be processed and analyzed in a multitude of ways. Flexibility in data acquisition, analyses and description may thereby greatly impact results. We discuss methods for improving transparency in developmental neuroimaging, and how preregistration can improve methodological rigor. While outlining challenges and issues that may arise before, during, and after data collection, solutions and resources are highlighted aiding to overcome some of these. Since the number of useful tools and techniques is ever-growing, we highlight the fact that many practices can be implemented stepwise.

A hitchhiker's guide to working with large, open-source neuroimaging datasets

Large datasets that enable researchers to perform investigations with unprecedented rigor are growing increasingly common in neuroimaging. Due to the simultaneous increasing popularity of open science, these state-of-the-art datasets are more accessible than ever to researchers around the world. While analysis of these samples has pushed the field forward, they pose a new set of challenges that might cause difficulties for novice users. Here we offer practical tips for working with large datasets from the end-user's perspective. We cover all aspects of the data lifecycle: from what to consider when downloading and storing the data to tips on how to become acquainted with a dataset one did not collect and what to share when communicating results. This manuscript serves as a practical guide one can use when working with large neuroimaging datasets, thus dissolving barriers to scientific discovery.

Convolutional Neural Networks for Pediatric Refractory Epilepsy Classification Using Resting-State Functional Magnetic Resonance Imaging

OBJECTIVE

This study aims to evaluate the performance of convolutional neural networks (CNNs) trained with resting-state functional magnetic resonance imaging (rfMRI) latency data in the classification of patients with pediatric epilepsy from healthy controls.

METHODS

Preoperative rfMRI and anatomic magnetic resonance imaging scans were obtained from 63 pediatric patients with refractory epilepsy and 259 pediatric healthy controls. Latency maps of the temporal difference between rfMRI and the global mean signal were calculated using voxel-wise cross-covariance. Healthy control and epilepsy latency z score maps were pseudorandomized and partitioned into training data (60%), validation data (20%), and test data (20%). Healthy control individuals and patients with epilepsy were labeled as negative and positive, respectively. CNN models were then trained with the designated training data. Model hyperparameters were evaluated with a grid-search method. The model with the highest sensitivity was evaluated using unseen test data. Accuracy, sensitivity, specificity, F1 score, and area under the receiver operating characteristic curve were used to evaluate the ability of the model to classify epilepsy in the test data set.

RESULTS

The model with the highest validation sensitivity correctly classified 74% of unseen test patients with 85% sensitivity, 71% specificity, F1 score of 0.56, and an area under the receiver operating characteristic curve of 0.86.

CONCLUSIONS

Using rfMRI latency data, we trained a CNN model to classify patients with pediatric epilepsy from healthy controls with good performance. CNN could serve as an adjunct in the diagnosis of pediatric epilepsy. Identification of pediatric epilepsy earlier in the disease course could decrease time to referral to specialized epilepsy centers and thus improve prognosis in this population.

Supervised machine learning for diagnostic classification from large-scale neuroimaging datasets

There are growing concerns about the generalizability of machine learning classifiers in neuroimaging. In order to evaluate this aspect across relatively large heterogeneous populations, we investigated four disorders: Autism spectrum disorder (N = 988), Attention deficit hyperactivity disorder (N = 930), Post-traumatic stress disorder (N = 87) and Alzheimer's disease (N = 132). We applied 18 different machine learning classifiers (based on diverse principles) wherein the training/validation and the hold-out test data belonged to samples with the same diagnosis but differing in either the age range or the acquisition site. Our results indicate that overfitting can be a huge problem in heterogeneous datasets, especially with fewer samples, leading to inflated measures of accuracy that fail to generalize well to the general clinical population. Further, different classifiers tended to perform well on different datasets. In order to address this, we propose a consensus-classifier by combining the predictive power of all 18 classifiers. The consensus-classifier was less sensitive to unmatched training/validation and holdout test data. Finally, we combined feature importance scores obtained from all classifiers to infer the discriminative ability of connectivity features. The functional connectivity patterns thus identified were robust to the classification algorithm used, age and acquisition site differences, and had diagnostic predictive ability in addition to univariate statistically significant group differences between the groups. A MATLAB toolbox called Machine Learning in NeuroImaging (MALINI), which implements all the 18 different classifiers along with the consensus classifier is available from Lanka et al. (2019) The toolbox can also be found at the following URL: https://github.com/pradlanka/malini .

Sharing voxelwise neuroimaging results from rhesus monkeys and other species with Neurovault

Animal neuroimaging studies can provide unique insights into brain structure and function, and can be leveraged to bridge the gap between animal and human neuroscience. In part, this power comes from the ability to com bine mechanistic interventions with brain-wide neuroimaging. Due to their phylogenetic proximity to humans, nonhuman primate neuroimaging holds particular promise. Because nonhuman primate neuroimaging studies are often underpowered, there is a great need to share data amongst translational researchers. Data sharing efforts have been limited, however, by the lack of standardized tools and repositories through which nonhuman neuroimaging data can easily be archived and accessed. Here, we provide an extension of the Neurovault framework to enable sharing of statistical maps and related voxelwise neuroimaging data from other species and template-spaces. Neurovault, which was previously limited to human neuroimaging data, now allows researchers to easily upload and share nonhuman primate neuroimaging results. This promises to facilitate open, integrative cross-species science while affording researchers the increased statistical power provided by data aggregation. In addition, the Neurovault code-base now enables the addition of other species and template-spaces. Together, these advances promise to bring neuroimaging data sharing to research in other species, for supplemental data location-based atlases, and data that would otherwise be relegated to a “file-drawer”. As increasing numbers of researchers share their nonhuman neuroimaging data on Neurovault, this resource will enable novel, large-scale, cross-species comparisons that were previously impossible.

Spatio-temporal correlates of gene expression and cortical morphology across lifespan and aging

Evidence from neuroimaging and genetic studies supports the concept that brain aging mirrors development. However, it is unclear whether mechanisms linking brain development and aging provide new insights to delay aging and potentially reverse it. This study determined biological mechanisms and phenotypic traits underpinning brain alterations across the lifespan and in aging by examining spatio-temporal correlations between gene expression and cortical volumes using datasets d with the age range from 2 to 82 years. We revealed that a large proportion of genes whose expression was associated with cortical volumes across the lifespan were in astrocytes. These genes, which showed up-regulation during development and down-regulation during aging, contributed to fundamental homeostatic functions of astrocytes. Included among these genes were those encoding components of cAMP, Ras, and retrograde endocannabinoid signaling pathways. Genes associated with cortical volumes in the same data aged above 55 years were also enriched for the sphingolipid, renin-angiotensin system (RAS), proteasome, and TGF-β signaling pathway, which is linked to senescence-associated secretory phenotypes. Neuroticism, drinking, and smoking were the common phenotypic traits in the lifespan and aging, while memory was the unique phenotype associated with aging. These findings provide biological mechanisms mirroring development and aging as well as unique to aging.

An assessment of the autism neuroimaging literature for the prospects of re-executability

Background: The degree of reproducibility of the neuroimaging literature in psychiatric application areas has been called into question and the issues that relate to this reproducibility are extremely complex. Some of these complexities have to do with the underlying biology of the disorders that we study and others arise due to the technology we apply to the analysis of the data we collect. Ultimately, the observations we make get communicated to the rest of the community through publications in the scientific literature. Methods: We sought to perform a 're-executability survey' to evaluate the recent neuroimaging literature with an eye toward seeing if the technical aspects of our publication practices are helping or hindering the overall quest for a more reproducible understanding of brain development and aging. The topic areas examined include availability of the data, the precision of the imaging method description and the reporting of the statistical analytic approach, and the availability of the complete results. We applied the survey to 50 publications in the autism neuroimaging literature that were published between September 16, 2017 to October 1, 2018. Results: The results of the survey indicate that for the literature examined, data that is not already part of a public repository is rarely available, software tools are usually named but versions and operating system are not, it is expected that reasonably skilled analysts could approximately perform the analyses described, and the complete results of the studies are rarely available.  Conclusions: We have identified that there is ample room for improvement in research publication practices. We hope exposing these issues in the retrospective literature can provide guidance and motivation for improving this aspect of our reporting practices in the future.

An assessment of the autism neuroimaging literature for the prospects of re-executability

Background: The degree of reproducibility of the neuroimaging literature in psychiatric application areas has been called into question and the issues that relate to this reproducibility are extremely complex. Some of these complexities have to do with the underlying biology of the disorders that we study and others arise due to the technology we apply to the analysis of the data we collect. Ultimately, the observations we make get communicated to the rest of the community through publications in the scientific literature. Methods: We sought to perform a 're-executability survey' to evaluate the recent neuroimaging literature with an eye toward seeing if our publication practices are helping or hindering the overall quest for a more reproducible understanding of brain development and aging. The topic areas examined include availability of the data, the precision of the imaging method description and the reporting of the statistical analytic approach, and the availability of the complete results. We applied the survey to 50 publications in the autism neuroimaging literature that were published between September 16, 2017 to October 1, 2018. Results: The results of the survey indicate that for the literature examined, data that is not already part of a public repository is rarely available, software tools are usually named but versions and operating system are not, it is expected that reasonably skilled analysts could approximately perform the analyses described, and the complete results of the studies are rarely available.  Conclusions: We have identified that there is ample room for improvement in research publication practices. We hope exposing these issues in the retrospective literature can provide guidance and motivation for improving this aspect of our reporting practices in the future.

Modelling subject variability in the spatial and temporal characteristics of functional modes

Recent work has highlighted the scale and ubiquity of subject variability in observations from functional MRI data (fMRI). Furthermore, it is highly likely that errors in the estimation of either the spatial presentation of, or the coupling between, functional regions can confound cross-subject analyses, making accurate and unbiased representations of functional data essential for interpreting any downstream analyses. Here, we extend the framework of probabilistic functional modes (PFMs) (Harrison et al., 2015) to capture cross-subject variability not only in the mode spatial maps, but also in the functional coupling between modes and in mode amplitudes. A new implementation of the inference now also allows for the analysis of modern, large-scale data sets, and the combined inference and analysis package, PROFUMO, is available from git.fmrib.ox.ac.uk/samh/profumo. A new implementation of the inference now also allows for the analysis of modern, large-scale data sets. Using simulated data, resting-state data from 1000 subjects collected as part of the Human Connectome Project (Van Essen et al., 2013), and an analysis of 14 subjects in a variety of continuous task-states (Kieliba et al., 2019), we demonstrate how PFMs are able to capture, within a single model, a rich description of how the spatio-temporal structure of resting-state fMRI activity varies across subjects. We also compare the new PFM model to the well established independent component analysis with dual regression (ICA-DR) pipeline. This reveals that, under PFM assumptions, much more of the (behaviorally relevant) cross-subject variability in fMRI activity should be attributed to the variability in spatial maps, and that, after accounting for this, functional coupling between modes primarily reflects current cognitive state. This has fundamental implications for the interpretation of cross-sectional studies of functional connectivity that do not capture cross-subject variability to the same extent as PFMs.

MRI-based biomarkers of accelerated aging and dementia risk in midlife: how close are we?

The global population is aging, leading to an increasing burden of age-related neurodegenerative disease. Efforts to intervene against age-related dementias in older adults have generally proven ineffective. These failures suggest that a lifetime of brain aging may be difficult to reverse once widespread deterioration has occurred. To test interventions in younger populations, biomarkers of brain aging are needed that index subtle signs of accelerated brain deterioration that are part of the putative pathway to dementia. Here I review potential MRI-based biomarkers that could connect midlife brain aging to later life dementia. I survey the literature with three questions in mind, 1) Does the biomarker index age-related changes across the lifespan? 2) Does the biomarker index cognitive ability and cognitive decline? 3) Is the biomarker sensitive to known risk factors for dementia? I find that while there is preliminary support for some midlife MRI-based biomarkers for accelerated aging, the longitudinal research that would best answer these questions is still in its infancy and needs to be further developed. I conclude with suggestions for future research.