An open science resource for establishing reliability and reproducibility in functional connectomics

Enhancing brain age estimation under uncertainty: A spectral-normalized neural gaussian process approach utilizing 2.5D slicing

Brain age gap, the difference between estimated brain age and chronological age via magnetic resonance imaging, has emerged as a pivotal biomarker in the detection of brain abnormalities. While deep learning is accurate in estimating brain age, the absence of uncertainty estimation may pose risks in clinical use. Moreover, current 3D brain age models are intricate, and using 2D slices hinders comprehensive dimensional data integration. Here, we introduced Spectral-normalized Neural Gaussian Process (SNGP) accompanied by 2.5D slice approach for seamless uncertainty integration in a single network with low computational expenses, and extra dimensional data integration without added model complexity. Subsequently, we compared different deep learning methods for estimating brain age uncertainty via the Pearson correlation coefficient, a metric that helps circumvent systematic underestimation of uncertainty during training. SNGP shows excellent uncertainty estimation and generalization on a dataset of 11 public datasets (N = 6327), with competitive predictive performance (MAE=2.95). Besides, SNGP demonstrates superior generalization performance (MAE=3.47) on an independent validation set (N = 301). Additionally, we conducted five controlled experiments to validate our method. Firstly, uncertainty adjustment in brain age estimation improved the detection of accelerated brain aging in adolescents with ADHD, with a 38% increase in effect size after adjustment. Secondly, the SNGP model exhibited OOD detection capabilities, showing significant differences in uncertainty across Asian and non-Asian datasets. Thirdly, the performance of DenseNet as a backbone for SNGP was slightly better than ResNeXt, attributed to DenseNet's feature reuse capability, with robust generalization on an independent validation set. Fourthly, site effect harmonization led to a decline in model performance, consistent with previous studies. Finally, the 2.5D slice approach significantly outperformed 2D methods, improving model performance without increasing network complexity. In conclusion, we present a cost-effective method for estimating brain age with uncertainty, utilizing 2.5D slicing for enhanced performance, showcasing promise for clinical applications.

Cortical thickness deviations as biomarker for subtyping and prognosis in pediatric brainstem tumors

Brainstem tumors exert profound effects on cortical organization and functionality across the whole brain. However, the precise implications of changes in cortical thickness (CTh) for patient stratification and prognostic assessment remain unclear. Our study seeks to address these gaps and provide clearer insights into the distant impact of brainstem tumors. This study involved 124 pediatric patients with brainstem tumors and 849 healthy controls. Using CAT12 segmentation on 3D T1-weighted MRI scans and Gaussian process regression modeling, we established a normative CTh model from healthy data. CTh deviations of patients were quantified and clustered, revealing two distinct subtypes: Subtype 1 with extremely positive deviations and Subtype 2 with extremely negative deviations, correlating with better survival. Kaplan-Meier analysis confirmed significant survival differences between these subtypes. Additionally, a greater number of brain regions with positive CTh deviations was found to correlate with larger tumor volumes. These findings suggest that CTh deviation is a non-invasive imaging marker, facilitating patient subtyping and survival prediction. These insights equip clinicians to tailor treatment plans and establishes a valuable precision medical tool for clinical evaluation and monitoring.

Functional network reorganization and memory impairment in unruptured brain arteriovenous malformations

Background

Brain arteriovenous malformations (AVMs) are congenital vascular anomalies that can affect cognitive, particularly memory functions. However, the underlying mechanisms of neurocognitive abnormalities in unruptured AVMs remain unclear. This study aimed to explore spontaneous functional network reorganization associated with memory impairment in unruptured AVM patients using resting-state functional MRI (rsfMRI).

Methods

Using rsfMRI data, we compared functional activity and connectivity patterns between 25 AVM patients and healthy controls, including regional homogeneity (ReHo), fractional amplitude of low-frequency fluctuations (fALFF), seed-based functional connectivity (FC), and lesion network mapping. Correlation analysis was performed to clarify the relationship between these parameters and memory performance in AVM patients.

Results

We identified memory-related spontaneous functional network reorganization in AVM patients, particularly involving the somatomotor network (SMN), frontoparietal control network (FPN), and default mode network (DMN). Subgroup analyses based on lesion location (frontal vs. non-frontal) and laterality (left vs. right) revealed location-dependent differences in connectivity reorganization. In particular, left-sided AVMs showed disrupted FC within the SMN, correlated with working memory and executive function, while right-sided and frontal AVMs exhibited more complex patterns involving multiple networks. Moreover, functional disconnection maps indicated that AVM lesions did not directly impair resting-state memory networks.

Conclusion

Patients with unruptured AVMs exhibit resting-state memory network reorganization, which is closely related to the lesion location. These findings highlight the functional network alterations in AVM patients and suggest the potential neural mechanisms underlying memory deficits.

Individualized cerebellar damage predicts the presence of behavioral disorders in children with brainstem tumors

BACKGROUND

Brainstem tumors often cause intractable neurobehavioral issues, which can be a challenge for patients and surgeons. Research on cerebellar changes in these patients is limited, despite symptoms similar to cerebellar injuries. This study aims to investigate cerebellar damage pattern resulting from brainstem tumors and its association with behavioral disorders.

METHODS

This study enrolled 147 children with brainstem tumors. A U-Net-based segmentation algorithm is used to divide their cerebellums into 26 lobules. And these lobules are then used to build a normative model for assessing individual structural deviations. Furthermore, a behavior prediction model is developed using the total outlier count (tOC) index and cerebellar lobule volume as predictive features.

RESULTS

Over 95% of patients are found to have negative deviations in cerebellar regions, particularly in anterior lobules like Left V. Higher tOC is significantly associated with severe social problems (r = 0.31, p = 0.001) and withdrawal behavior (r = 0.28, p = 0.001). Smaller size of cerebellar regions strongly correlates with more pronounced social problems (r = 0.27, p = 0.007) and withdrawal behavior (r = 0.25, p = 0.015). Notably, lobules Right X, V, IV, VIIB, Left IX, VIII, and X influence social problems, while Left V, Right IV, Vermis VI, and VIII impact withdrawal behavior.

CONCLUSIONS

Our study reveals cerebellar damage patterns in patients with brainstem tumors, emphasizing the role of both anterior and posterior cerebellar lobes in social problems and withdrawal behavior. This research sheds light on the cerebro-brainstem-cerebellar underlying complex behavioral disorders in brainstem tumor patients.

DeepPrep: an accelerated, scalable and robust pipeline for neuroimaging preprocessing empowered by deep learning

Neuroimaging has entered the era of big data. However, the advancement of preprocessing pipelines falls behind the rapid expansion of data volume, causing substantial computational challenges. Here we present DeepPrep, a pipeline empowered by deep learning and a workflow manager. Evaluated on over 55,000 scans, DeepPrep demonstrates tenfold acceleration, scalability and robustness compared to the state-of-the-art pipeline, thereby meeting the scalability requirements of neuroimaging.

Diffusion tensor imaging changes along the perivascular spaces may serve as a prognostic factor for high-grade glioma

PURPOSE

To investigate the alteration of glymphatic activity in high-grade glioma (HGG) using the diffusion tensor image (DTI) analysis along perivascular spaces (ALPS) method and assess its prognostic performance.

METHODS

Data of HGG and volunteer were retrieved from The Cancer Imaging Archive and Consortium for Reliability and Reproducibility databases, respectively. Image features including multicenter, cystic change, tumor location, midline structure, lateral ventricle compression, and nerve fiber involvement were evaluated for HGG. The ALPS-index was calculated, and the difference of ALPS-index (D_ALPS), was defined to represent the difference of bilateral ALPS-index.

RESULTS

In total, 236 HGG and 61 volunteers were included. The ALPS-index of the tumor-side hemisphere was larger than that of the normal-side, but it was smaller than that of volunteers. The ALPS-index of the normal-side showed a decreasing trend for HGG cases presenting a compressed lateral ventricle, deviated midline structure, and peritumor edema-involved association and projection fibers, but increased in gross total resection. The D_ALPS increased for isocitrate dehydrogenase mutation. The normal-side ALPS-index negatively correlated with edema and tumor volume. The D_ALPS positively correlated with edema volume. Univariable and multivariable Cox analysis revealed smaller D_ALPS as independent factors for poor prognosis. Survival analysis showed that high D_ALPS corresponded to longer survival times compared to low D_ALPS.

CONCLUSIONS

The glymphatic activity in HGG individuals is lower compared with that of healthy volunteers, with a potential compensation in the tumor side. Many clinical-radiological characteristics affect the glymphatic activity. The defined D_ALPS shows potential as an independent prognostic factor in HGG.

International initiatives to enhance awareness and uptake of open research in psychology: a systematic mapping review

Concerns about the replicability, reproducibility and transparency of research have ushered in a set of practices and behaviours under the umbrella of 'open research'. To this end, many new initiatives have been developed that represent procedural (i.e. behaviours and sets of commonly used practices in the research process), structural (new norms, rules, infrastructure and incentives), and community-based change (working groups, networks). The objectives of this research were to identify and outline international initiatives that enhance awareness and uptake of open research practices in the discipline of psychology. A systematic mapping review was conducted in three stages: (i) a Web search to identify open research initiatives in psychology; (ii) a literature search to identify related articles; and (iii) a hand search of grey literature. Eligible initiatives were then coded into an overarching theme of procedural, structural or community-based change. A total of 187 initiatives were identified; 30 were procedural (e.g. toolkits, resources, software), 70 structural (e.g. policies, strategies, frameworks) and 87 community-based (e.g. working groups, networks). This review highlights that open research is progressing at pace through various initiatives that share a common goal to reform research culture. We hope that this review promotes their further adoption and facilitates coordinated efforts between individuals, organizations, institutions, publishers and funders.

Reproducible Brain Charts: An open data resource for mapping brain development and its associations with mental health

Major mental disorders are increasingly understood as disorders of brain development. Large and heterogeneous samples are required to define generalizable links between brain development and psychopathology. To this end, we introduce the Reproducible Brain Charts (RBC), an open data resource that integrates data from 5 large studies of brain development in youth from three continents (N=6,346; 45% Female). Confirmatory bifactor models were used to create harmonized psychiatric phenotypes that capture major dimensions of psychopathology. Following rigorous quality assurance, neuroimaging data were carefully curated and processed using consistent pipelines in a reproducible manner with DataLad, the Configurable Pipeline for the Analysis of Connectomes (C-PAC), and FreeSurfer. Initial analyses of RBC data emphasize the benefit of careful quality assurance and data harmonization in delineating developmental effects and associations with psychopathology. Critically, all RBC data - including harmonized psychiatric phenotypes, unprocessed images, and fully processed imaging derivatives - are openly shared without a data use agreement via the International Neuroimaging Data-sharing Initiative. Together, RBC facilitates large-scale, reproducible, and generalizable research in developmental and psychiatric neuroscience.

A multi-modal neuroimaging data release for Meige Syndrome and Facial Paralysis Research

The sharing of multimodal magnetic resonance imaging (MRI) data is of utmost importance in the field, as it enables a deeper understanding of facial nerve-related pathologies. However, there is a significant lack of multi-modal neuroimaging databases specifically focused on these conditions, which hampers our comprehensive knowledge of the neural foundations of facial paralysis. To address this critical gap and propel advancements in this area, we have released the Multimodal Neuroimaging Dataset of Meige Syndrome, Facial Paralysis, and Healthy Controls (MND-MFHC). This dataset includes detailed clinical assessments of 53 individuals with facial paralysis (FP), 31 patients with Meige syndrome (MS), and 102 healthy controls (HC). To promote open access, the BIDS-formatted data and associated quality control reports can be accessed through the Science Data Bank (SciDB). By sharing this comprehensive dataset, our aim is to facilitate further research and exploration into the intricate neural mechanisms underlying facial nerve-related pathologies.

Automatic Detection of Cognitive Impairment in Patients With White Matter Hyperintensity Using Deep Learning and Radiomics

White matter hyperintensity (WMH) is associated with cognitive impairment. In this study, 79 patients with WMH from hospital 1 were randomly divided into a training set (62 patients) and an internal validation set (17 patients). In addition, 29 WMH patients from hospital 2 were used as an external validation set. Cognitive status was determined based on neuropsychological assessment results. A deep learning convolutional neural network of VB-Nets was used to automatically identify and segment whole-brain subregions and WMH. The PyRadiomics package in Python was used to automatically extract radiomic features from the WMH and bilateral hippocampi. Delong tests revealed that the random forest model based on combined features had the best performance for the detection of cognitive impairment in WMH patients, with an AUC of 0.900 in the external validation set. Our results provide clinical doctors with a reliable tool for the early diagnosis of cognitive impairment in WMH patients.

An open data for imaging acute aerobic exercise effects on brain and mind in emerging adulthood

How emerging adulthood, a period particularly susceptible to the onset of mental disorders, responds to acute aerobic exercise effects on mood and brain remains an open question. A challenge in addressing this question is the scarcity of open data derived from scientific intervention paradigms. We recruited 83 healthy volunteers aged 17 to 24, who were randomly assigned to either an exercise group or a control group. The exercise group performed 30-minutes aerobic exercise with moderate intensity on a cycle ergometer, while the control group read neutral textual material without any physical activity. All participants received structural MRI scans before their intervention periods and completed mood scales and resting-state functional MRI scans before and after their intervention periods. Their heart rates were also monitored during the intervention. The dataset represents the first open resource for probing the acute aerobic exercise effects on brain and mind, containing physical, mental, and brain measurements. It has been released as part of the Chinese Color Nest Community in the Science Data Bank.

Signed Curvature Graph Representation Learning of Brain Networks for Brain Age Estimation

Graph Neural Networks (GNNs) play a pivotal role in learning representations of brain networks for estimating brain age. However, the over-squashing impedes interactions between long-range nodes, hindering the ability of message-passing mechanism-based GNNs to learn the topological structure of brain networks. Graph rewiring methods and curvature GNNs have been proposed to alleviate over-squashing. However, most graph rewiring methods overlook node features and curvature GNNs neglect the geometric properties of signed curvature. In this study, a Signed Curvature GNN (SCGNN) was proposed to rewire the graph based on node features and curvature, and learn the representation of signed curvature. First, a Mutual Information Ollivier-Ricci Flow (MORF) was proposed to add connections in the neighborhood of edge with the minimal negative curvature based on the maximum mutual information between node features, improving the efficiency of information interaction between nodes. Then, a Signed Curvature Convolution (SCC) was proposed to aggregate node features based on positive and negative curvature, facilitating the model's ability to capture the complex topological structures of brain networks. Additionally, an Ollivier-Ricci Gradient Pooling (ORG-Pooling) was proposed to select the key nodes and topology structures by curvature gradient and attention mechanism, accurately obtaining the global representation for brain age estimation. Experiments conducted on six public datasets with structural magnetic resonance imaging (sMRI), spanning ages from 18 to 91 years, validate that our method achieves promising performance compared with existing methods. Furthermore, we employed the gaps between brain age and chronological age for identifying Alzheimer's Disease (AD), yielding the best classification performance.

Quantitative assessment of neurodevelopmental maturation: a comprehensive systematic literature review of artificial intelligence-based brain age prediction in pediatric populations

Introduction

Over the past few decades, numerous researchers have explored the application of machine learning for assessing children's neurological development. Developmental changes in the brain could be utilized to gauge the alignment of its maturation status with the child's chronological age. AI is trained to analyze changes in different modalities and estimate the brain age of subjects. Disparities between the predicted and chronological age can be viewed as a biomarker for a pathological condition. This literature review aims to illuminate research studies that have employed AI to predict children's brain age.

Methods

The inclusion criteria for this study were predicting brain age via AI in healthy children up to 12 years. The search term was centered around the keywords "pediatric," "artificial intelligence," and "brain age" and was utilized in PubMed and IEEEXplore. The selected literature was then examined for information on data acquisition methods, the age range of the study population, pre-processing, methods and AI techniques utilized, the quality of the respective techniques, model explanation, and clinical applications.

Results

Fifty one publications from 2012 to 2024 were included in the analysis. The primary modality of data acquisition was MRI, followed by EEG. Structural and functional MRI-based studies commonly used publicly available datasets, while EEG-based studies typically relied on self-recruitment. Many studies utilized pre-processing pipelines provided by toolkit suites, particularly in MRI-based research. The most frequently used model type was kernel-based learning algorithms, followed by convolutional neural networks. Overall, prediction accuracy may improve when multiple acquisition modalities are used, but comparing studies is challenging. In EEG, the prediction error decreases as the number of electrodes increases. Approximately one-third of the studies used explainable artificial intelligence methods to explain the model and chosen parameters. However, there is a significant clinical translation gap as no study has tested their model in a clinical routine setting.

Discussion

Further research should test on external datasets and include low-quality routine images for MRI. T2-weighted MRI was underrepresented. Furthermore, different kernel types should be compared on the same dataset. Implementing modern model architectures, such as convolutional neural networks, should be the next step in EEG-based research studies.

BrainMass: Advancing Brain Network Analysis for Diagnosis With Large-Scale Self-Supervised Learning

Foundation models pretrained on large-scale datasets via self-supervised learning demonstrate exceptional versatility across various tasks. Due to the heterogeneity and hard-to-collect medical data, this approach is especially beneficial for medical image analysis and neuroscience research, as it streamlines broad downstream tasks without the need for numerous costly annotations. However, there has been limited investigation into brain network foundation models, limiting their adaptability and generalizability for broad neuroscience studies. In this study, we aim to bridge this gap. In particular, 1) we curated a comprehensive dataset by collating images from 30 datasets, which comprises 70,781 samples of 46,686 participants. Moreover, we introduce pseudo-functional connectivity (pFC) to further generates millions of augmented brain networks by randomly dropping certain timepoints of the BOLD signal; 2) we propose the BrainMass framework for brain network self-supervised learning via mask modeling and feature alignment. BrainMass employs Mask-ROI Modeling (MRM) to bolster intra-network dependencies and regional specificity. Furthermore, Latent Representation Alignment (LRA) module is utilized to regularize augmented brain networks of the same participant with similar topological properties to yield similar latent representations by aligning their latent embeddings. Extensive experiments on eight internal tasks and seven external brain disorder diagnosis tasks show BrainMass's superior performance, highlighting its significant generalizability and adaptability. Nonetheless, BrainMass demonstrates powerful few/zero-shot learning abilities and exhibits meaningful interpretation to various diseases, showcasing its potential use for clinical applications.

Why experimental variation in neuroimaging should be embraced

In a perfect world, scientists would develop analyses that are guaranteed to reveal the ground truth of a research question. In reality, there are countless viable workflows that produce distinct, often conflicting, results. Although reproducibility places a necessary bound on the validity of results, it is not sufficient for claiming underlying validity, eventual utility, or generalizability. In this work we focus on how embracing variability in data analysis can improve the generalizability of results. We contextualize how design decisions in brain imaging can be made to capture variation, highlight examples, and discuss how variability capture may improve the quality of results.

Evolutionarily conserved fMRI network dynamics in the mouse, macaque, and human brain

Evolutionarily relevant networks have been previously described in several mammalian species using time-averaged analyses of fMRI time-series. However, fMRI network activity is highly dynamic and continually evolves over timescales of seconds. Whether the dynamic organization of resting-state fMRI network activity is conserved across mammalian species remains unclear. Using frame-wise clustering of fMRI time-series, we find that intrinsic fMRI network dynamics in awake male macaques and humans is characterized by recurrent transitions between a set of 4 dominant, neuroanatomically homologous fMRI coactivation modes (C-modes), three of which are also plausibly represented in the male rodent brain. Importantly, in all species C-modes exhibit species-invariant dynamic features, including preferred occurrence at specific phases of fMRI global signal fluctuations, and a state transition structure compatible with infraslow coupled oscillator dynamics. Moreover, dominant C-mode occurrence reconstitutes the static organization of the fMRI connectome in all species, and is predictive of ranking of corresponding fMRI connectivity gradients. These results reveal a set of species-invariant principles underlying the dynamic organization of fMRI networks in mammalian species, and offer novel opportunities to relate fMRI network findings across the phylogenetic tree.

Moving beyond processing- and analysis-related variation in resting-state functional brain imaging

When fields lack consensus standard methods and accessible ground truths, reproducibility can be more of an ideal than a reality. Such has been the case for functional neuroimaging, where there exists a sprawling space of tools and processing pipelines. We provide a critical evaluation of the impact of differences across five independently developed minimal preprocessing pipelines for functional magnetic resonance imaging. We show that, even when handling identical data, interpipeline agreement was only moderate, critically shedding light on a factor that limits cross-study reproducibility. We show that low interpipeline agreement can go unrecognized until the reliability of the underlying data is high, which is increasingly the case as the field progresses. Crucially we show that, when interpipeline agreement is compromised, so too is the consistency of insights from brain-wide association studies. We highlight the importance of comparing analytic configurations, because both widely discussed and commonly overlooked decisions can lead to marked variation.

Brain age prediction via cross-stratified ensemble learning

As an important biomarker of neural aging, the brain age reflects the integrity and health of the human brain. Accurate prediction of brain age could help to understand the underlying mechanism of neural aging. In this study, a cross-stratified ensemble learning algorithm with staking strategy was proposed to obtain brain age and the derived predicted age difference (PAD) using T1-weighted magnetic resonance imaging (MRI) data. The approach was characterized as by implementing two modules: one was three base learners of 3D-DenseNet, 3D-ResNeXt, 3D-Inception-v4; another was 14 secondary learners of liner regressions. To evaluate performance, our method was compared with single base learners, regular ensemble learning algorithms, and state-of-the-art (SOTA) methods. The results demonstrated that our proposed model outperformed others models, with three metrics of mean absolute error (MAE), root mean-squared error (RMSE), and coefficient of determination (R2) of 2.9405 years, 3.9458 years, and 0.9597, respectively. Furthermore, there existed significant differences in PAD among the three groups of normal control (NC), mild cognitive impairment (MCI) and Alzheimer's disease (AD), with an increased trend across NC, MCI, and AD. It was concluded that the proposed algorithm could be effectively used in computing brain aging and PAD, and offering potential for early diagnosis and assessment of normal brain aging and AD.

BrainAgeNeXt: Advancing Brain Age Modeling for Individuals with Multiple Sclerosis

Aging is associated with structural brain changes, cognitive decline, and neurodegenerative diseases. Brain age, an imaging biomarker sensitive to deviations from healthy aging, offers insights into structural aging variations and is a potential prognostic biomarker in neurodegenerative conditions. This study introduces BrainAgeNeXt, a novel convolutional neural network inspired by the MedNeXt framework, designed to predict brain age from T1-weighted magnetic resonance imaging (MRI) scans. BrainAgeNeXt was trained and validated on 11,574 MRI scans from 33 private and publicly available datasets of healthy volunteers, aged 5 to 95 years, imaged with 3T and 7T MRI. Performance was compared against three state-of-the-art brain age prediction methods. BrainAgeNeXt achieved a mean absolute error (MAE) of 2.78 ± 3.64 years, lower than the compared methods (MAE = 3.55, 3.59, and 4.16 years, respectively). We tested all methods also across different levels of image quality, and BrainAgeNeXt performed well even with motion artifacts and less common 7T MRI data. In three longitudinal multiple sclerosis (MS) cohorts (273 individuals), brain age was, on average, 4.21 ± 6.51 years greater than chronological age. Longitudinal analysis indicated that brain age increased by 1.15 years per chronological year in individuals with MS (95% CI = [1.05, 1.26]). Moreover, in early MS, individuals with worsening disability had a higher annual increase in brain age compared to those with stable clinical assessments (1.24 vs. 0.75, p < 0.01). These findings suggest that brain age is a promising prognostic biomarker for MS progression and potentially a valuable endpoint for clinical trials.

The Genetic Architecture of the Human Corpus Callosum and its Subregions

The corpus callosum (CC) is the largest set of white matter fibers connecting the two hemispheres of the brain. In humans, it is essential for coordinating sensorimotor responses, performing associative/executive functions, and representing information in multiple dimensions. Understanding which genetic variants underpin corpus callosum morphometry, and their shared influence on cortical structure and susceptibility to neuropsychiatric disorders, can provide molecular insights into the CC's role in mediating cortical development and its contribution to neuropsychiatric disease. To characterize the morphometry of the midsagittal corpus callosum, we developed a publicly available artificial intelligence based tool to extract, parcellate, and calculate its total and regional area and thickness. Using the UK Biobank (UKB) and the Adolescent Brain Cognitive Development study (ABCD), we extracted measures of midsagittal corpus callosum morphometry and performed a genome-wide association study (GWAS) meta-analysis of European participants (combined N = 46,685). We then examined evidence for generalization to the non-European participants of the UKB and ABCD cohorts (combined N = 7,040). Post-GWAS analyses implicate prenatal intracellular organization and cell growth patterns, and high heritability in regions of open chromatin, suggesting transcriptional activity regulation in early development. Results suggest programmed cell death mediated by the immune system drives the thinning of the posterior body and isthmus. Global and local genetic overlap, along with causal genetic liability, between the corpus callosum, cerebral cortex, and neuropsychiatric disorders such as attention-deficit/hyperactivity and bipolar disorders were identified. These results provide insight into variability of corpus callosum development, its genetic influence on the cerebral cortex, and biological mechanisms related to neuropsychiatric dysfunction.

Impact of analytic decisions on test-retest reliability of individual and group estimates in functional magnetic resonance imaging: a multiverse analysis using the monetary incentive delay task

Empirical studies reporting low test-retest reliability of individual blood oxygen-level dependent (BOLD) signal estimates in functional magnetic resonance imaging (fMRI) data have resurrected interest among cognitive neuroscientists in methods that may improve reliability in fMRI. Over the last decade, several individual studies have reported that modeling decisions, such as smoothing, motion correction and contrast selection, may improve estimates of test-retest reliability of BOLD signal estimates. However, it remains an empirical question whether certain analytic decisions consistently improve individual and group level reliability estimates in an fMRI task across multiple large, independent samples. This study used three independent samples (Ns: 60, 81, 119) that collected the same task (Monetary Incentive Delay task) across two runs and two sessions to evaluate the effects of analytic decisions on the individual (intraclass correlation coefficient [ICC(3,1)]) and group (Jaccard/Spearman rho) reliability estimates of BOLD activity of task fMRI data. The analytic decisions in this study vary across four categories: smoothing kernel (five options), motion correction (four options), task parameterizing (three options) and task contrasts (four options), totaling 240 different pipeline permutations. Across all 240 pipelines, the median ICC estimates are consistently low, with a maximum median ICC estimate of .43 - .55 across the three samples. The analytic decisions with the greatest impact on the median ICC and group similarity estimates are the Implicit Baseline contrast, Cue Model parameterization and a larger smoothing kernel. Using an Implicit Baseline in a contrast condition meaningfully increased group similarity and ICC estimates as compared to using the Neutral cue. This effect was largest for the Cue Model parameterization; however, improvements in reliability came at the cost of interpretability. This study illustrates that estimates of reliability in the MID task are consistently low and variable at small samples, and a higher test-retest reliability may not always improve interpretability of the estimated BOLD signal.

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.

Inter- and intra-subject similarity in network functional connectivity across a full narrative movie

Naturalistic paradigms, such as watching movies during functional magnetic resonance imaging (fMRI), are thought to prompt the emotional and cognitive processes typically elicited in real life situations. Therefore, naturalistic viewing (NV) holds great potential for studying individual differences. However, in how far NV elicits similarity within and between subjects on a network level, particularly depending on emotions portrayed in movies, is currently unknown. We used the studyforrest dataset to investigate the inter- and intra-subject similarity in network functional connectivity (NFC) of 14 meta-analytically defined networks across a full narrative, audio-visual movie split into 8 consecutive movie segments. We characterized the movie segments by valence and arousal portrayed within the sequences, before utilizing a linear mixed model to analyze which factors explain inter- and intra-subject similarity. Our results showed that the model best explaining inter-subject similarity comprised network, movie segment, valence and a movie segment by valence interaction. Intra-subject similarity was influenced significantly by the same factors and an additional three-way interaction between movie segment, valence and arousal. Overall, inter- and intra-subject similarity in NFC were sensitive to the ongoing narrative and emotions in the movie. Lowest similarity both within and between subjects was seen in the emotional regulation network and networks associated with long-term memory processing, which might be explained by specific features and content of the movie. We conclude that detailed characterization of movie features is crucial for NV research.

Postoperative cerebellar mutism syndrome is an acquired autism-like network disturbance

BACKGROUND

Cerebellar mutism syndrome (CMS) is a common and debilitating complication of posterior fossa tumor surgery in children. Affected children exhibit communication and social impairments that overlap phenomenologically with subsets of deficits exhibited by children with Autism spectrum disorder (ASD). Although both CMS and ASD are thought to involve disrupted cerebro-cerebellar circuitry, they are considered independent conditions due to an incomplete understanding of their shared neural substrates.

METHODS

In this study, we analyzed postoperative cerebellar lesions from 90 children undergoing posterior fossa resection of medulloblastoma, 30 of whom developed CMS. Lesion locations were mapped to a standard atlas, and the networks functionally connected to each lesion were computed in normative adult and pediatric datasets. Generalizability to ASD was assessed using an independent cohort of children with ASD and matched controls (n = 427).

RESULTS

Lesions in children who developed CMS involved the vermis and inferomedial cerebellar lobules. They engaged large-scale cerebellothalamocortical circuits with a preponderance for the prefrontal and parietal cortices in the pediatric and adult connectomes, respectively. Moreover, with increasing connectomic age, CMS-associated lesions demonstrated stronger connectivity to the midbrain/red nuclei, thalami and inferior parietal lobules and weaker connectivity to the prefrontal cortex. Importantly, the CMS-associated lesion network was independently reproduced in ASD and correlated with communication and social deficits, but not repetitive behaviors.

CONCLUSIONS

Our findings indicate that CMS-associated lesions may result in an ASD-like network disturbance that occurs during sensitive windows of brain development. A common network disturbance between CMS and ASD may inform improved treatment strategies for affected children.

SUGAR: Spherical ultrafast graph attention framework for cortical surface registration

Cortical surface registration plays a crucial role in aligning cortical functional and anatomical features across individuals. However, conventional registration algorithms are computationally inefficient. Recently, learning-based registration algorithms have emerged as a promising solution, significantly improving processing efficiency. Nonetheless, there remains a gap in the development of a learning-based method that exceeds the state-of-the-art conventional methods simultaneously in computational efficiency, registration accuracy, and distortion control, despite the theoretically greater representational capabilities of deep learning approaches. To address the challenge, we present SUGAR, a unified unsupervised deep-learning framework for both rigid and non-rigid registration. SUGAR incorporates a U-Net-based spherical graph attention network and leverages the Euler angle representation for deformation. In addition to the similarity loss, we introduce fold and multiple distortion losses to preserve topology and minimize various types of distortions. Furthermore, we propose a data augmentation strategy specifically tailored for spherical surface registration to enhance the registration performance. Through extensive evaluation involving over 10,000 scans from 7 diverse datasets, we showed that our framework exhibits comparable or superior registration performance in accuracy, distortion, and test-retest reliability compared to conventional and learning-based methods. Additionally, SUGAR achieves remarkable sub-second processing times, offering a notable speed-up of approximately 12,000 times in registering 9,000 subjects from the UK Biobank dataset in just 32 min. This combination of high registration performance and accelerated processing time may greatly benefit large-scale neuroimaging studies.

Effect of scanning duration and sample size on reliability in resting state fMRI dynamic causal modeling analysis

Despite its widespread use, resting-state functional magnetic resonance imaging (rsfMRI) has been criticized for low test-retest reliability. To improve reliability, researchers have recommended using extended scanning durations, increased sample size, and advanced brain connectivity techniques. However, longer scanning runs and larger sample sizes may come with practical challenges and burdens, especially in rare populations. Here we tested if an advanced brain connectivity technique, dynamic causal modeling (DCM), can improve reliability of fMRI effective connectivity (EC) metrics to acceptable levels without extremely long run durations or extremely large samples. Specifically, we employed DCM for EC analysis on rsfMRI data from the Human Connectome Project. To avoid bias, we assessed four distinct DCMs and gradually increased sample sizes in a randomized manner across ten permutations. We employed pseudo true positive and pseudo false positive rates to assess the efficacy of shorter run durations (3.6, 7.2, 10.8, 14.4 min) in replicating the outcomes of the longest scanning duration (28.8 min) when the sample size was fixed at the largest (n = 160 subjects). Similarly, we assessed the efficacy of smaller sample sizes (n = 10, 20, …, 150 subjects) in replicating the outcomes of the largest sample (n = 160 subjects) when the scanning duration was fixed at the longest (28.8 min). Our results revealed that the pseudo false positive rate was below 0.05 for all the analyses. After the scanning duration reached 10.8 min, which yielded a pseudo true positive rate of 92%, further extensions in run time showed no improvements in pseudo true positive rate. Expanding the sample size led to enhanced pseudo true positive rate outcomes, with a plateau at n = 70 subjects for the targeted top one-half of the largest ECs in the reference sample, regardless of whether the longest run duration (28.8 min) or the viable run duration (10.8 min) was employed. Encouragingly, smaller sample sizes exhibited pseudo true positive rates of approximately 80% for n = 20, and 90% for n = 40 subjects. These data suggest that advanced DCM analysis may be a viable option to attain reliable metrics of EC when larger sample sizes or run times are not feasible.

The time-evolving epileptic brain network: concepts, definitions, accomplishments, perspectives

Epilepsy is now considered a network disease that affects the brain across multiple levels of spatial and temporal scales. The paradigm shift from an epileptic focus-a discrete cortical area from which seizures originate-to a widespread epileptic network-spanning lobes and hemispheres-considerably advanced our understanding of epilepsy and continues to influence both research and clinical treatment of this multi-faceted high-impact neurological disorder. The epileptic network, however, is not static but evolves in time which requires novel approaches for an in-depth characterization. In this review, we discuss conceptual basics of network theory and critically examine state-of-the-art recording techniques and analysis tools used to assess and characterize a time-evolving human epileptic brain network. We give an account on current shortcomings and highlight potential developments towards an improved clinical management of epilepsy.

Delineating a Pathway for the Discovery of Functional Connectome Biomarkers of Autism

The promise of individually tailored care for autism has driven efforts to establish biomarkers. This chapter appraises the state of precision-medicine research focused on biomarkers based on the functional brain connectome. This work is grounded on abundant evidence supporting the brain dysconnection model of autism and the advantages of resting-state functional MRI (R-fMRI) for studying the brain in vivo. After considering biomarker requirements of consistency and clinical relevance, we provide a scoping review of R-fMRI studies of individual prediction in autism. In the past 10 years, responding to the availability of open data through the Autism Brain Imaging Data Exchange, machine learning studies have surged. Nearly all have focused on diagnostic label classification. These efforts have shown that autism prediction is feasible using functional connectome markers, with accuracy reported well above chance. In parallel, emerging approaches more directly addressing autism heterogeneity are paving the way for much-needed biomarkers of longitudinal outcome and treatment response. We conclude with key challenges to be addressed by the next generation of studies.

Bridging functional and anatomical neural connectivity through cluster synchronization

The dynamics of the brain results from the complex interplay of several neural populations and is affected by both the individual dynamics of these areas and their connection structure. Hence, a fundamental challenge is to derive models of the brain that reproduce both structural and functional features measured experimentally. Our work combines neuroimaging data, such as dMRI, which provides information on the structure of the anatomical connectomes, and fMRI, which detects patterns of approximate synchronous activity between brain areas. We employ cluster synchronization as a tool to integrate the imaging data of a subject into a coherent model, which reconciles structural and dynamic information. By using data-driven and model-based approaches, we refine the structural connectivity matrix in agreement with experimentally observed clusters of brain areas that display coherent activity. The proposed approach leverages the assumption of homogeneous brain areas; we show the robustness of this approach when heterogeneity between the brain areas is introduced in the form of noise, parameter mismatches, and connection delays. As a proof of concept, we apply this approach to MRI data of a healthy adult at resting state.

Neural habituation during acute stress signals a blunted endocrine response and poor resilience

BACKGROUND

A blunted hypothalamic-pituitary-adrenal (HPA) axis response to acute stress is associated with psychiatric symptoms. Although the prefrontal cortex and limbic areas are important regulators of the HPA axis, whether the neural habituation of these regions during stress signals both blunted HPA axis responses and psychiatric symptoms remains unclear. In this study, neural habituation during acute stress and its associations with the stress cortisol response, resilience, and depression were evaluated.

METHODS

Seventy-seven participants (17-22 years old, 37 women) were recruited for a ScanSTRESS brain imaging study, and the activation changes between the first and last stress blocks were used as the neural habituation index. Meanwhile, participants' salivary cortisol during test was collected. Individual-level resilience and depression were measured using questionnaires. Correlation and moderation analyses were conducted to investigate the association between neural habituation and endocrine data and mental symptoms. Validated analyses were conducted using a Montreal Image Stress Test dataset in another independent sample (48 participants; 17-22 years old, 24 women).

RESULTS

Neural habituation of the prefrontal cortex and limbic area was negatively correlated with cortisol responses in both datasets. In the ScanSTRESS paradigm, neural habituation was both positively correlated with depression and negatively correlated with resilience. Moreover, resilience moderated the relationship between neural habituation in the ventromedial prefrontal cortex and cortisol response.

CONCLUSIONS

This study suggested that neural habituation of the prefrontal cortex and limbic area could reflect motivation dysregulation during repeated failures and negative feedback, which might further lead to maladaptive mental states.

Automated temporalis muscle quantification and growth charts for children through adulthood

Lean muscle mass (LMM) is an important aspect of human health. Temporalis muscle thickness is a promising LMM marker but has had limited utility due to its unknown normal growth trajectory and reference ranges and lack of standardized measurement. Here, we develop an automated deep learning pipeline to accurately measure temporalis muscle thickness (iTMT) from routine brain magnetic resonance imaging (MRI). We apply iTMT to 23,876 MRIs of healthy subjects, ages 4 through 35, and generate sex-specific iTMT normal growth charts with percentiles. We find that iTMT was associated with specific physiologic traits, including caloric intake, physical activity, sex hormone levels, and presence of malignancy. We validate iTMT across multiple demographic groups and in children with brain tumors and demonstrate feasibility for individualized longitudinal monitoring. The iTMT pipeline provides unprecedented insights into temporalis muscle growth during human development and enables the use of LMM tracking to inform clinical decision-making.

A comprehensive survey of complex brain network representation

Recent years have shown great merits in utilizing neuroimaging data to understand brain structural and functional changes, as well as its relationship to different neurodegenerative diseases and other clinical phenotypes. Brain networks, derived from different neuroimaging modalities, have attracted increasing attention due to their potential to gain system-level insights to characterize brain dynamics and abnormalities in neurological conditions. Traditional methods aim to pre-define multiple topological features of brain networks and relate these features to different clinical measures or demographical variables. With the enormous successes in deep learning techniques, graph learning methods have played significant roles in brain network analysis. In this survey, we first provide a brief overview of neuroimaging-derived brain networks. Then, we focus on presenting a comprehensive overview of both traditional methods and state-of-the-art deep-learning methods for brain network mining. Major models, and objectives of these methods are reviewed within this paper. Finally, we discuss several promising research directions in this field.

Functional neuroimaging as a catalyst for integrated neuroscience

Functional magnetic resonance imaging (fMRI) enables non-invasive access to the awake, behaving human brain. By tracking whole-brain signals across a diverse range of cognitive and behavioural states or mapping differences associated with specific traits or clinical conditions, fMRI has advanced our understanding of brain function and its links to both normal and atypical behaviour. Despite this headway, progress in human cognitive neuroscience that uses fMRI has been relatively isolated from rapid advances in other subdomains of neuroscience, which themselves are also somewhat siloed from one another. In this Perspective, we argue that fMRI is well-placed to integrate the diverse subfields of systems, cognitive, computational and clinical neuroscience. We first summarize the strengths and weaknesses of fMRI as an imaging tool, then highlight examples of studies that have successfully used fMRI in each subdomain of neuroscience. We then provide a roadmap for the future advances that will be needed to realize this integrative vision. In this way, we hope to demonstrate how fMRI can help usher in a new era of interdisciplinary coherence in neuroscience.

Increased MRI-based Brain Age in chronic migraine patients

INTRODUCTION

Neuroimaging has revealed that migraine is linked to alterations in both the structure and function of the brain. However, the relationship of these changes with aging has not been studied in detail. Here we employ the Brain Age framework to analyze migraine, by building a machine-learning model that predicts age from neuroimaging data. We hypothesize that migraine patients will exhibit an increased Brain Age Gap (the difference between the predicted age and the chronological age) compared to healthy participants.

METHODS

We trained a machine learning model to predict Brain Age from 2,771 T1-weighted magnetic resonance imaging scans of healthy subjects. The processing pipeline included the automatic segmentation of the images, the extraction of 1,479 imaging features (both morphological and intensity-based), harmonization, feature selection and training inside a 10-fold cross-validation scheme. Separate models based only on morphological and intensity features were also trained, and all the Brain Age models were later applied to a discovery cohort composed of 247 subjects, divided into healthy controls (HC, n=82), episodic migraine (EM, n=91), and chronic migraine patients (CM, n=74).

RESULTS

CM patients showed an increased Brain Age Gap compared to HC (4.16 vs -0.56 years, P=0.01). A smaller Brain Age Gap was found for EM patients, not reaching statistical significance (1.21 vs -0.56 years, P=0.19). No associations were found between the Brain Age Gap and headache or migraine frequency, or duration of the disease. Brain imaging features that have previously been associated with migraine were among the main drivers of the differences in the predicted age. Also, the separate analysis using only morphological or intensity-based features revealed different patterns in the Brain Age biomarker in patients with migraine.

CONCLUSION

The brain-predicted age has shown to be a sensitive biomarker of CM patients and can help reveal distinct aging patterns in migraine.

Impact of brain segmentation methods on regional metabolism quantification in 18F-FDG PET/MR analysis

BACKGROUND

Accurate analysis of quantitative PET data plays a crucial role in studying small, specific brain structures. The integration of PET and MRI through an integrated PET/MR system presents an opportunity to leverage the benefits of precisely aligned structural MRI and molecular PET images in both spatial and temporal dimensions. However, in many clinical workflows, PET studies are often performed without the aid of individually matched structural MRI scans, primarily for the sake of convenience in the data collection and brain segmentation possesses. Currently, two commonly employed segmentation strategies for brain PET analysis are distinguished: methods with or without MRI registration and methods employing either atlas-based or individual-based algorithms. Moreover, the development of artificial intelligence (AI)-assisted methods for predicting brain segmentation holds promise but requires further validation of their efficiency and accuracy for clinical applications. This study aims to compare and evaluate the correlations, consistencies, and differences among the above-mentioned brain segmentation strategies in quantification of brain metabolism in 18F-FDG PET/MR analysis.

RESULTS

Strong correlations were observed among all methods (r = 0.932 to 0.999, P < 0.001). The variances attributable to subject and brain region were higher than those caused by segmentation methods (P < 0.001). However, intraclass correlation coefficient (ICC)s between methods with or without MRI registration ranged from 0.924 to 0.975, while ICCs between methods with atlas- or individual-based algorithms ranged from 0.741 to 0.879. Brain regions exhibiting significant standardized uptake values (SUV) differences due to segmentation methods were the basal ganglia nuclei (maximum to 11.50 ± 4.67%), and various cerebral cortexes in temporal and occipital regions (maximum to 18.03 ± 5.52%). The AI-based method demonstrated high correlation (r = 0.998 and 0.999, P < 0.001) and ICC (0.998 and 0.997) with FreeSurfer, substantially reducing the time from 8.13 h to 57 s on per subject.

CONCLUSIONS

Different segmentation methods may have impact on the calculation of brain metabolism in basal ganglia nuclei and specific cerebral cortexes. The AI-based approach offers improved efficiency and is recommended for its enhanced performance.

A longitudinal resource for population neuroscience of school-age children and adolescents in China

During the past decade, cognitive neuroscience has been calling for population diversity to address the challenge of validity and generalizability, ushering in a new era of population neuroscience. The developing Chinese Color Nest Project (devCCNP, 2013-2022), the first ten-year stage of the lifespan CCNP (2013-2032), is a two-stages project focusing on brain-mind development. The project aims to create and share a large-scale, longitudinal and multimodal dataset of typically developing children and adolescents (ages 6.0-17.9 at enrolment) in the Chinese population. The devCCNP houses not only phenotypes measured by demographic, biophysical, psychological and behavioural, cognitive, affective, and ocular-tracking assessments but also neurotypes measured with magnetic resonance imaging (MRI) of brain morphometry, resting-state function, naturalistic viewing function and diffusion structure. This Data Descriptor introduces the first data release of devCCNP including a total of 864 visits from 479 participants. Herein, we provided details of the experimental design, sampling strategies, and technical validation of the devCCNP resource. We demonstrate and discuss the potential of a multicohort longitudinal design to depict normative brain growth curves from the perspective of developmental population neuroscience. The devCCNP resource is shared as part of the "Chinese Data-sharing Warehouse for In-vivo Imaging Brain" in the Chinese Color Nest Project (CCNP) - Lifespan Brain-Mind Development Data Community ( https://ccnp.scidb.cn ) at the Science Data Bank.

Big Brain Data Initiatives in Universiti Sains Malaysia: Data Stewardship to Data Repository and Data Sharing

The sharing of open-access neuroimaging data has increased significantly during the last few years. Sharing neuroimaging data is crucial to accelerating scientific advancement, particularly in the field of neuroscience. A number of big initiatives that will increase the amount of available neuroimaging data are currently in development. The Big Brain Data Initiative project was started by Universiti Sains Malaysia as the first neuroimaging data repository platform in Malaysia for the purpose of data sharing. In order to ensure that the neuroimaging data in this project is accessible, usable, and secure, as well as to offer users high-quality data that can be consistently accessed, we first came up with good data stewardship practices. Then, we developed MyneuroDB, an online repository database system for data sharing purposes. Here, we describe the Big Brain Data Initiative and MyneuroDB, a data repository that provides the ability to openly share neuroimaging data, currently including magnetic resonance imaging (MRI), electroencephalography (EEG), and magnetoencephalography (MEG), following the FAIR principles for data sharing.

Neuroimaging-based analysis of DBS outcomes in pediatric dystonia: Insights from the GEPESTIM registry

INTRODUCTION

Deep brain stimulation (DBS) is an established treatment in patients of various ages with pharmaco-resistant neurological disorders. Surgical targeting and postoperative programming of DBS depend on the spatial location of the stimulating electrodes in relation to the surrounding anatomical structures, and on electrode connectivity to a specific distribution pattern within brain networks. Such information is usually collected using group-level analysis, which relies on the availability of normative imaging resources (atlases and connectomes). Analysis of DBS data in children with debilitating neurological disorders such as dystonia would benefit from such resources, especially given the developmental differences in neuroimaging data between adults and children. We assembled pediatric normative neuroimaging resources from open-access datasets in order to comply with age-related anatomical and functional differences in pediatric DBS populations. We illustrated their utility in a cohort of children with dystonia treated with pallidal DBS. We aimed to derive a local pallidal sweetspot and explore a connectivity fingerprint associated with pallidal stimulation to exemplify the utility of the assembled imaging resources.

METHODS

An average pediatric brain template (the MNI brain template 4.5-18.5 years) was implemented and used to localize the DBS electrodes in 20 patients from the GEPESTIM registry cohort. A pediatric subcortical atlas, analogous to the DISTAL atlas known in DBS research, was also employed to highlight the anatomical structures of interest. A local pallidal sweetspot was modeled, and its degree of overlap with stimulation volumes was calculated as a correlate of individual clinical outcomes. Additionally, a pediatric functional connectome of 100 neurotypical subjects from the Consortium for Reliability and Reproducibility was built to allow network-based analyses and decipher a connectivity fingerprint responsible for the clinical improvements in our cohort.

RESULTS

We successfully implemented a pediatric neuroimaging dataset that will be made available for public use as a tool for DBS analyses. Overlap of stimulation volumes with the identified DBS-sweetspot model correlated significantly with improvement on a local spatial level (R = 0.46, permuted p = 0.019). The functional connectivity fingerprint of DBS outcomes was determined to be a network correlate of therapeutic pallidal stimulation in children with dystonia (R = 0.30, permuted p = 0.003).

CONCLUSIONS

Local sweetspot and distributed network models provide neuroanatomical substrates for DBS-associated clinical outcomes in dystonia using pediatric neuroimaging surrogate data. Implementation of this pediatric neuroimaging dataset might help to improve the practice and pave the road towards a personalized DBS-neuroimaging analyses in pediatric patients.

Characterization of the effects of outliers on ComBat harmonization for removing inter-site data heterogeneity in multisite neuroimaging studies

Data harmonization is a key step widely used in multisite neuroimaging studies to remove inter-site heterogeneity of data distribution. However, data harmonization may even introduce additional inter-site differences in neuroimaging data if outliers are present in the data of one or more sites. It remains unclear how the presence of outliers could affect the effectiveness of data harmonization and consequently the results of analyses using harmonized data. To address this question, we generated a normal simulation dataset without outliers and a series of simulation datasets with outliers of varying properties (e.g., outlier location, outlier quantity, and outlier score) based on a real large-sample neuroimaging dataset. We first verified the effectiveness of the most commonly used ComBat harmonization method in the removal of inter-site heterogeneity using the normal simulation data, and then characterized the effects of outliers on the effectiveness of ComBat harmonization and on the results of association analyses between brain imaging-derived phenotypes and a simulated behavioral variable using the simulation datasets with outliers. We found that, although ComBat harmonization effectively removed the inter-site heterogeneity in multisite data and consequently improved the detection of the true brain-behavior relationships, the presence of outliers could damage severely the effectiveness of ComBat harmonization in the removal of data heterogeneity or even introduce extra heterogeneity in the data. Moreover, we found that the effects of outliers on the improvement of the detection of brain-behavior associations by ComBat harmonization were dependent on how such associations were assessed (i.e., by Pearson correlation or Spearman correlation), and on the outlier location, quantity, and outlier score. These findings help us better understand the influences of outliers on data harmonization and highlight the importance of detecting and removing outliers prior to data harmonization in multisite neuroimaging studies.

A generalizable connectome-based marker of in-scan sustained attention in neurodiverse youth

Difficulty with attention is an important symptom in many conditions in psychiatry, including neurodiverse conditions such as autism. There is a need to better understand the neurobiological correlates of attention and leverage these findings in healthcare settings. Nevertheless, it remains unclear if it is possible to build dimensional predictive models of attentional state in a sample that includes participants with neurodiverse conditions. Here, we use 5 datasets to identify and validate functional connectome-based markers of attention. In dataset 1, we use connectome-based predictive modeling and observe successful prediction of performance on an in-scan sustained attention task in a sample of youth, including participants with a neurodiverse condition. The predictions are not driven by confounds, such as head motion. In dataset 2, we find that the attention network model defined in dataset 1 generalizes to predict in-scan attention in a separate sample of neurotypical participants performing the same attention task. In datasets 3-5, we use connectome-based identification and longitudinal scans to probe the stability of the attention network across months to years in individual participants. Our results help elucidate the brain correlates of attentional state in youth and support the further development of predictive dimensional models of other clinically relevant phenotypes.

An anatomical and connectivity atlas of the marmoset cerebellum

The cerebellum is essential for motor control and cognitive functioning, engaging in bidirectional communication with the cerebral cortex. The common marmoset, a small non-human primate, offers unique advantages for studying cerebello-cerebral circuits. However, the marmoset cerebellum is not well described in published resources. In this study, we present a comprehensive atlas of the marmoset cerebellum comprising (1) fine-detailed anatomical atlases and surface-analysis tools of the cerebellar cortex based on ultra-high-resolution ex vivo MRI, (2) functional connectivity and gradient patterns of the cerebellar cortex revealed by awake resting-state fMRI, and (3) structural-connectivity mapping of cerebellar nuclei using high-resolution diffusion MRI tractography. The atlas elucidates the anatomical details of the marmoset cerebellum, reveals distinct gradient patterns of intra-cerebellar and cerebello-cerebral functional connectivity, and maps the topological relationship of cerebellar nuclei in cerebello-cerebral circuits. As version 5 of the Marmoset Brain Mapping project, this atlas is publicly available at https://marmosetbrainmapping.org/MBMv5.html.

Comprehensive evaluation of harmonization on functional brain imaging for multisite data-fusion

To embrace big-data neuroimaging, harmonizing the site effect in resting-state functional magnetic resonance imaging (R-fMRI) data fusion is a fundamental challenge. A comprehensive evaluation of potentially effective harmonization strategies, particularly with specifically collected data, has been scarce, especially for R-fMRI metrics. Here, we comprehensively assess harmonization strategies from multiple perspectives, including tests on residual site effect, individual identification, test-retest reliability, and replicability of group-level statistical results, on widely used R-fMRI metrics across various datasets, including data obtained from participants with repetitive measures at different scanners. For individual identifiability (i.e., whether the same subject could be identified across R-fMRI data scanned across different sites), we found that, while most methods decreased site effects, the Subsampling Maximum-mean-distance based distribution shift correction Algorithm (SMA) and parametric unadjusted CovBat outperformed linear regression models, linear mixed models, ComBat series and invariant conditional variational auto-encoder in clustering accuracy. Test-retest reliability was better for SMA and parametric adjusted CovBat than unadjusted ComBat series and parametric unadjusted CovBat in the number of overlapped voxels. At the same time, SMA was superior to the latter in replicability in terms of the Dice coefficient and the scale of brain areas showing sex differences reproducibly observed across datasets. Furthermore, SMA better detected reproducible sex differences of ALFF under the site-sex confounded situation. Moreover, we designed experiments to identify the best target site features to optimize SMA identifiability, test-retest reliability, and stability. We noted both sample size and distribution of the target site matter and introduced a heuristic formula for selecting the target site. In addition to providing practical guidelines, this work can inform continuing improvements and innovations in harmonizing methodologies for big R-fMRI data.

uRP: An integrated research platform for one-stop analysis of medical images

Introduction

Medical image analysis is of tremendous importance in serving clinical diagnosis, treatment planning, as well as prognosis assessment. However, the image analysis process usually involves multiple modality-specific software and relies on rigorous manual operations, which is time-consuming and potentially low reproducible.

Methods

We present an integrated platform - uAI Research Portal (uRP), to achieve one-stop analyses of multimodal images such as CT, MRI, and PET for clinical research applications. The proposed uRP adopts a modularized architecture to be multifunctional, extensible, and customizable.

Results and Discussion

The uRP shows 3 advantages, as it 1) spans a wealth of algorithms for image processing including semi-automatic delineation, automatic segmentation, registration, classification, quantitative analysis, and image visualization, to realize a one-stop analytic pipeline, 2) integrates a variety of functional modules, which can be directly applied, combined, or customized for specific application domains, such as brain, pneumonia, and knee joint analyses, 3) enables full-stack analysis of one disease, including diagnosis, treatment planning, and prognosis assessment, as well as full-spectrum coverage for multiple disease applications. With the continuous development and inclusion of advanced algorithms, we expect this platform to largely simplify the clinical scientific research process and promote more and better discoveries.

Brain-age prediction: A systematic comparison of machine learning workflows

The difference between age predicted using anatomical brain scans and chronological age, i.e., the brain-age delta, provides a proxy for atypical aging. Various data representations and machine learning (ML) algorithms have been used for brain-age estimation. However, how these choices compare on performance criteria important for real-world applications, such as; (1) within-dataset accuracy, (2) cross-dataset generalization, (3) test-retest reliability, and (4) longitudinal consistency, remains uncharacterized. We evaluated 128 workflows consisting of 16 feature representations derived from gray matter (GM) images and eight ML algorithms with diverse inductive biases. Using four large neuroimaging databases covering the adult lifespan (total N = 2953, 18-88 years), we followed a systematic model selection procedure by sequentially applying stringent criteria. The 128 workflows showed a within-dataset mean absolute error (MAE) between 4.73-8.38 years, from which 32 broadly sampled workflows showed a cross-dataset MAE between 5.23-8.98 years. The test-retest reliability and longitudinal consistency of the top 10 workflows were comparable. The choice of feature representation and the ML algorithm both affected the performance. Specifically, voxel-wise feature spaces (smoothed and resampled), with and without principal components analysis, with non-linear and kernel-based ML algorithms performed well. Strikingly, the correlation of brain-age delta with behavioral measures disagreed between within-dataset and cross-dataset predictions. Application of the best-performing workflow on the ADNI sample showed a significantly higher brain-age delta in Alzheimer's and mild cognitive impairment patients compared to healthy controls. However, in the presence of age bias, the delta estimates in the patients varied depending on the sample used for bias correction. Taken together, brain-age shows promise, but further evaluation and improvements are needed for its real-world application.

Systematic evaluation of head motion on resting-state functional connectivity MRI in the neonate

Reliability and robustness of resting state functional connectivity MRI (rs-fcMRI) relies, in part, on minimizing the influence of head motion on measured brain signals. The confounding effects of head motion on functional connectivity have been extensively studied in adults, but its impact on newborn brain connectivity remains unexplored. Here, using a large newborn data set consisting of 159 rs-fcMRI scans acquired in the Developing Brain Institute at Children's National Hospital and 416 scans from The Developing Human Connectome Project (dHCP), we systematically investigated associations between head motion and rs-fcMRI. Head motion during the scan significantly affected connectivity at sensory-related networks and default mode networks, and at the whole brain scale; the direction of motion effects varied across the whole brain. Comparing high- versus low-head motion groups suggested that head motion can impact connectivity estimates across the whole brain. Censoring of high-motion volumes using frame-wise displacement significantly reduced the confounding effects of head motion on neonatal rs-fcMRI. Lastly, in the dHCP data set, we demonstrated similar persistent associations between head motion and network connectivity despite implementing a standard denoising strategy. Collectively, our results highlight the importance of using rigorous head motion correction in preprocessing neonatal rs-fcMRI to yield reliable estimates of brain activity.

Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives

Transformer, one of the latest technological advances of deep learning, has gained prevalence in natural language processing or computer vision. Since medical imaging bear some resemblance to computer vision, it is natural to inquire about the status quo of Transformers in medical imaging and ask the question: can the Transformer models transform medical imaging? In this paper, we attempt to make a response to the inquiry. After a brief introduction of the fundamentals of Transformers, especially in comparison with convolutional neural networks (CNNs), and highlighting key defining properties that characterize the Transformers, we offer a comprehensive review of the state-of-the-art Transformer-based approaches for medical imaging and exhibit current research progresses made in the areas of medical image segmentation, recognition, detection, registration, reconstruction, enhancement, etc. In particular, what distinguishes our review lies in its organization based on the Transformer's key defining properties, which are mostly derived from comparing the Transformer and CNN, and its type of architecture, which specifies the manner in which the Transformer and CNN are combined, all helping the readers to best understand the rationale behind the reviewed approaches. We conclude with discussions of future perspectives.

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.

Multisite test-retest reliability and compatibility of brain metrics derived from FreeSurfer versions 7.1, 6.0, and 5.3

Automatic neuroimaging processing tools provide convenient and systematic methods for extracting features from brain magnetic resonance imaging scans. One tool, FreeSurfer, provides an easy-to-use pipeline to extract cortical and subcortical morphometric measures. There have been over 25 stable releases of FreeSurfer, with different versions used across published works. The reliability and compatibility of regional morphometric metrics derived from the most recent version releases have yet to be empirically assessed. Here, we used test-retest data from three public data sets to determine within-version reliability and between-version compatibility across 42 regional outputs from FreeSurfer versions 7.1, 6.0, and 5.3. Cortical thickness from v7.1 was less compatible with that of older versions, particularly along the cingulate gyrus, where the lowest version compatibility was observed (intraclass correlation coefficient 0.37-0.61). Surface area of the temporal pole, frontal pole, and medial orbitofrontal cortex, also showed low to moderate version compatibility. We confirm low compatibility between v6.0 and v5.3 of pallidum and putamen volumes, while those from v7.1 were compatible with v6.0. Replication in an independent sample showed largely similar results for measures of surface area and subcortical volumes, but had lower overall regional thickness reliability and compatibility. Batch effect correction may adjust for some inter-version effects when most sites are run with one version, but results vary when more sites are run with different versions. Age associations in a quality controlled independent sample (N = 106) revealed version differences in results of downstream statistical analysis. We provide a reference to highlight the regional metrics that may yield recent version-related inconsistencies in published findings. An interactive viewer is provided at http://data.brainescience.org/Freesurfer_Reliability/.

Normative model detects abnormal functional connectivity in psychiatric disorders

INTRODUCTION

The diagnosis of psychiatric disorders is mostly based on the clinical evaluation of the patient's signs and symptoms. Deep learning binary-based classification models have been developed to improve the diagnosis but have not yet reached clinical practice, in part due to the heterogeneity of such disorders. Here, we propose a normative model based on autoencoders.

METHODS

We trained our autoencoder on resting-state functional magnetic resonance imaging (rs-fMRI) data from healthy controls. The model was then tested on schizophrenia (SCZ), bipolar disorder (BD), and attention-deficit hyperactivity disorder (ADHD) patients to estimate how each patient deviated from the norm and associate it with abnormal functional brain networks' (FBNs) connectivity. Rs-fMRI data processing was conducted within the FMRIB Software Library (FSL), which included independent component analysis and dual regression. Pearson's correlation coefficients between the extracted blood oxygen level-dependent (BOLD) time series of all FBNs were calculated, and a correlation matrix was generated for each subject.

RESULTS AND DISCUSSION

We found that the functional connectivity related to the basal ganglia network seems to play an important role in the neuropathology of BD and SCZ, whereas in ADHD, its role is less evident. Moreover, the abnormal connectivity between the basal ganglia network and the language network is more specific to BD. The connectivity between the higher visual network and the right executive control and the connectivity between the anterior salience network and the precuneus networks are the most relevant in SCZ and ADHD, respectively. The results demonstrate that the proposed model could identify functional connectivity patterns that characterize different psychiatric disorders, in agreement with the literature. The abnormal connectivity patterns from the two independent SCZ groups of patients were similar, demonstrating that the presented normative model was also generalizable. However, the group-level differences did not withstand individual-level analysis implying that psychiatric disorders are highly heterogeneous. These findings suggest that a precision-based medical approach, focusing on each patient's specific functional network changes may be more beneficial than the traditional group-based diagnostic classification.