Improving Between-Group Effect Size for Multi-Site Functional Connectivity Data via Site-Wise De-Meaning

The status of MRI databases across the world focused on psychiatric and neurological disorders

Neuroimaging databases for neuro-psychiatric disorders enable researchers to implement data-driven research approaches by providing access to rich data that can be used to study disease, build and validate machine learning models, and even redefine disease spectra. The importance of sharing large, multi-center, multi-disorder databases has gradually been recognized in order to truly translate brain imaging knowledge into real-world clinical practice. Here, we review MRI databases that share data globally to serve multiple psychiatric or neurological disorders. We found 42 datasets consisting of 23,293 samples from patients with psychiatry and neurological disorders and healthy controls; 1245 samples from mood disorders (major depressive disorder and bipolar disorder), 2015 samples from developmental disorders (autism spectrum disorder, attention-deficit hyperactivity disorder), 675 samples from schizophrenia, 1194 samples from Parkinson's disease, 5865 samples from dementia (including Alzheimer's disease), We recognize that large, multi-center databases should include governance processes that allow data to be shared across national boundaries. Addressing technical and regulatory issues of existing databases can lead to better design and implementation and improve data access for the research community. The current trend toward the development of shareable MRI databases will contribute to a better understanding of the pathophysiology, diagnosis and assessment, and development of early interventions for neuropsychiatric disorders.

Modeling the impact of MRI acquisition bias on structural connectomes: Harmonizing structural connectomes

One way to increase the statistical power and generalizability of neuroimaging studies is to collect data at multiple sites or merge multiple cohorts. However, this usually comes with site-related biases due to the heterogeneity of scanners and acquisition parameters, negatively impacting sensitivity. Brain structural connectomes are not an exception: Being derived from T1-weighted and diffusion-weighted magnetic resonance images, structural connectivity is impacted by differences in imaging protocol. Beyond minimizing acquisition parameter differences, removing bias with postprocessing is essential. In this work we create, from the exhaustive Human Connectome Project Young Adult dataset, a resampled dataset of different b-values and spatial resolutions, modeling a cohort scanned across multiple sites. After demonstrating the statistical impact of acquisition parameters on connectivity, we propose a linear regression with explicit modeling of b-value and spatial resolution, and validate its performance on separate datasets. We show that b-value and spatial resolution affect connectivity in different ways and that acquisition bias can be reduced using a linear regression informed by the acquisition parameters while retaining interindividual differences and hence boosting fingerprinting performance. We also demonstrate the generative potential of our model, and its generalization capability in an independent dataset reflective of typical acquisition practices in clinical settings.

Heritability estimation of subcortical volumes in a multi-ethnic multi-site cohort study

Heritability of regional subcortical brain volumes (rSBVs) describes the role of genetics in middle and inner brain development. rSBVs are highly heritable in adults but are not characterized well in adolescents. The Adolescent Brain Cognitive Development study (ABCD), taken over 22 US sites, provides data to characterize the heritability of subcortical structures in adolescence. In ABCD, site-specific effects co-occur with genetic effects which can bias heritability estimates. Existing methods adjusting for site effects require additional steps to adjust for site effects and can lead to inconsistent estimation. We propose a random-effect model-based method of moments approach that is a single step estimator and is a theoretically consistent estimator even when sites are imbalanced and performs well under simulations. We compare methods on rSBVs from ABCD. The proposed approach yielded heritability estimates similar to previous results derived from single-site studies. The cerebellum cortex and hippocampus were the most heritable regions (> 50%).

Deep learning based joint fusion approach to exploit anatomical and functional brain information in autism spectrum disorders

BACKGROUND

The integration of the information encoded in multiparametric MRI images can enhance the performance of machine-learning classifiers. In this study, we investigate whether the combination of structural and functional MRI might improve the performances of a deep learning (DL) model trained to discriminate subjects with Autism Spectrum Disorders (ASD) with respect to typically developing controls (TD).

MATERIAL AND METHODS

We analyzed both structural and functional MRI brain scans publicly available within the ABIDE I and II data collections. We considered 1383 male subjects with age between 5 and 40 years, including 680 subjects with ASD and 703 TD from 35 different acquisition sites. We extracted morphometric and functional brain features from MRI scans with the Freesurfer and the CPAC analysis packages, respectively. Then, due to the multisite nature of the dataset, we implemented a data harmonization protocol. The ASD vs. TD classification was carried out with a multiple-input DL model, consisting in a neural network which generates a fixed-length feature representation of the data of each modality (FR-NN), and a Dense Neural Network for classification (C-NN). Specifically, we implemented a joint fusion approach to multiple source data integration. The main advantage of the latter is that the loss is propagated back to the FR-NN during the training, thus creating informative feature representations for each data modality. Then, a C-NN, with a number of layers and neurons per layer to be optimized during the model training, performs the ASD-TD discrimination. The performance was evaluated by computing the Area under the Receiver Operating Characteristic curve within a nested 10-fold cross-validation. The brain features that drive the DL classification were identified by the SHAP explainability framework.

RESULTS

The AUC values of 0.66±0.05 and of 0.76±0.04 were obtained in the ASD vs. TD discrimination when only structural or functional features are considered, respectively. The joint fusion approach led to an AUC of 0.78±0.04. The set of structural and functional connectivity features identified as the most important for the two-class discrimination supports the idea that brain changes tend to occur in individuals with ASD in regions belonging to the Default Mode Network and to the Social Brain.

CONCLUSIONS

Our results demonstrate that the multimodal joint fusion approach outperforms the classification results obtained with data acquired by a single MRI modality as it efficiently exploits the complementarity of structural and functional brain information.

Left Frontoparietal Control Network Connectivity Moderates the Effect of Amyloid on Cognitive Decline in Preclinical Alzheimer's Disease: The A4 Study

BACKGROUND

Stronger resting-state functional connectivity of the default mode and frontoparietal control networks has been associated with cognitive resilience to Alzheimer's disease related pathology and neurodegeneration in smaller cohort studies.

OBJECTIVES

We investigated whether these networks are associated with longitudinal CR to AD biomarkers of beta-amyloid (Aβ).

DESIGN

Longitudinal mixed.

SETTING

The Anti-Amyloid Treatment in Asymptomatic Alzheimer's Disease (A4) study and its natural history observation arm, the Longitudinal Evaluation of Amyloid Risk and Neurodegeneration (LEARN) study.

PARTICIPANTS

A sample of 1,021 cognitively unimpaired older adults (mean age = 71.2 years [SD = 4.7 years], 61% women, 42% APOEε4 carriers, 52% Aβ positive).

MEASUREMENTS

Global cognitive performance (Preclinical Alzheimer's Cognitive Composite) was assessed over an average 5.4 year follow-up period (SD = 2 years). Cortical Aβ and functional connectivity (left and right frontoparietal control and default mode networks) were estimated from fMRI and PET, respectively, at baseline. Covariates included baseline age, APOEε4 carrier status, years of education, adjusted gray matter volume, head motion, study group, cumulative treatment exposure, and cognitive test version.

RESULTS

Mixed effects models revealed that functional connectivity of the left frontoparietal control network moderated the negative effect of Aβ on cognitive change (p = .025) such that stronger connectivity was associated with reduced Aβ-related cognitive decline.

CONCLUSIONS

Our results demonstrate a potential protective effect of functional connectivity in preclinical AD, such that stronger connectivity in this network is associated with slower Aβ-related cognitive decline.

Effect of data harmonization of multicentric dataset in ASD/TD classification

Machine Learning (ML) is nowadays an essential tool in the analysis of Magnetic Resonance Imaging (MRI) data, in particular in the identification of brain correlates in neurological and neurodevelopmental disorders. ML requires datasets of appropriate size for training, which in neuroimaging are typically obtained collecting data from multiple acquisition centers. However, analyzing large multicentric datasets can introduce bias due to differences between acquisition centers. ComBat harmonization is commonly used to address batch effects, but it can lead to data leakage when the entire dataset is used to estimate model parameters. In this study, structural and functional MRI data from the Autism Brain Imaging Data Exchange (ABIDE) collection were used to classify subjects with Autism Spectrum Disorders (ASD) compared to Typical Developing controls (TD). We compared the classical approach (external harmonization) in which harmonization is performed before train/test split, with an harmonization calculated only on the train set (internal harmonization), and with the dataset with no harmonization. The results showed that harmonization using the whole dataset achieved higher discrimination performance, while non-harmonized data and harmonization using only the train set showed similar results, for both structural and connectivity features. We also showed that the higher performances of the external harmonization are not due to larger size of the sample for the estimation of the model and hence these improved performance with the entire dataset may be ascribed to data leakage. In order to prevent this leakage, it is recommended to define the harmonization model solely using the train set.

Exploring the correlation between genetic transcription and multi-temporal developmental autism spectrum disorder using resting-state functional magnetic resonance imaging

Introduction

The present investigation aimed to explore the neurodevelopmental trajectory of autism spectrum disorder (ASD) by identifying the changes in brain function and gene expression associated with the disorder. Previous studies have indicated that ASD is a highly inherited neurodevelopmental disorder of the brain that displays symptom heterogeneity across different developmental periods. However, the transcriptomic changes underlying these developmental differences remain largely unknown.

Methods

To address this gap in knowledge, our study employed resting-state functional magnetic resonance imaging (rs-fMRI) data from a large sample of male participants across four representative age groups to stratify the abnormal changes in brain function associated with ASD. Partial least square regression (PLSr) was utilized to identify unique changes in gene expression in brain regions characterized by aberrant functioning in ASD.

Results

Our results revealed that ASD exhibits distinctive developmental trajectories in crucial brain regions such as the default mode network (DMN), temporal lobe, and prefrontal lobes during critical periods of neurodevelopment when compared to the control group. These changes were also associated with genes primarily located in synaptic tissues.

Discussion

The findings of this study suggest that the neurobiology of ASD is uniquely heterogeneous across different ages and may be accompanied by distinct molecular mechanisms related to gene expression.

Gender effects on autism spectrum disorder: a multi-site resting-state functional magnetic resonance imaging study of transcriptome-neuroimaging

Introduction

The gender disparity in autism spectrum disorder (ASD) has been one of the salient features of condition. However, its relationship between the pathogenesis and genetic transcription in patients of different genders has yet to reach a reliable conclusion.

Methods

To address this gap, this study aimed to establish a reliable potential neuro-marker in gender-specific patients, by employing multi-site functional magnetic resonance imaging (fMRI) data, and to further investigate the role of genetic transcription molecules in neurogenetic abnormalities and gender differences in autism at the neuro-transcriptional level. To this end, age was firstly used as a regression covariate, followed by the use of ComBat to remove the site effect from the fMRI data, and abnormal functional activity was subsequently identified. The resulting abnormal functional activity was then correlated by genetic transcription to explore underlying molecular functions and cellular molecular mechanisms.

Results

Abnormal brain functional activities were identified in autism patients of different genders, mainly located in the default model network (DMN) and precuneus-cingulate gyrus-frontal lobe. The correlation analysis of neuroimaging and genetic transcription further found that heterogeneous brain regions were highly correlated with genes involved in signal transmission between neurons' plasma membranes. Additionally, we further identified different weighted gene expression patterns and specific expression tissues of risk genes in ASD of different genders.

Discussion

Thus, this work not only identified the mechanism of abnormal brain functional activities caused by gender differences in ASD, but also explored the genetic and molecular characteristics caused by these related changes. Moreover, we further analyzed the genetic basis of sex differences in ASD from a neuro-transcriptional perspective.

Pre- and post-task resting-state differs in clinical populations

Resting-state functional connectivity has generated great hopes as a potential brain biomarker for improving prevention, diagnosis, and treatment in psychiatry. This neuroimaging protocol can routinely be performed by patients and does not depend on the specificities of a task. Thus, it seems ideal for big data approaches that require aggregating data across multiple studies and sites. However, technical variability, diverging data analysis approaches, and differences in data acquisition protocols introduce heterogeneity to the aggregated data. Besides these technical aspects, a prior task that changes the psychological state of participants might also contribute to heterogeneity. In healthy participants, studies have shown that behavioral tasks can influence resting-state measures, but such effects have not yet been reported in clinical populations. Here, we fill this knowledge gap by comparing resting-state functional connectivity before and after clinically relevant tasks in two clinical conditions, namely substance use disorders and phobias. The tasks consisted of viewing craving-inducing and spider anxiety provoking pictures that are frequently used in cue-reactivity studies and exposure therapy. We found distinct pre- vs post-task resting-state connectivity differences in each group, as well as decreased thalamo-cortical and increased intra-thalamic connectivity which might be associated with decreased vigilance in both groups. Our results confirm that resting-state measures can be strongly influenced by prior emotion-inducing tasks that need to be taken into account when pooling resting-state scans for clinical biomarker detection. This demands that resting-state datasets should include a complete description of the experimental design, especially when a task preceded data collection.

Assessing Multi-Site rs-fMRI-Based Connectomic Harmonization Using Information Theory

Several harmonization techniques have recently been proposed for connectomics/networks derived from resting-state functional magnetic resonance imaging (rs-fMRI) acquired at multiple sites. These techniques have the objective of mitigating site-specific biases that complicate its subsequent analysis and, therefore, compromise the quality of the results when these images are analyzed together. Thus, harmonization is indispensable when large cohorts are required in which the data obtained must be independent of the particular condition of each resonator, its make and model, its calibration, and other features or artifacts that may affect the significance of the acquisition. To date, no assessment of the actual efficacy of these harmonization techniques has been proposed. In this work, we apply recently introduced Information Theory tools to analyze the effectiveness of these techniques, developing a methodology that allows us to compare different harmonization models. We demonstrate the usefulness of this methodology by applying it to some of the most widespread harmonization frameworks and datasets. As a result, we are able to show that some of these techniques are indeed ineffective since the acquisition site can still be determined from the fMRI data after the processing.