Predicting full-scale and verbal intelligence scores from functional Connectomic data in individuals with autism Spectrum disorder

Prediction of individual performance and verbal intelligence scores from resting-state fMRI in children and adolescents

The neuroimaging basis of intelligence remains elusive; however, there is a growing body of research employing connectome-based predictive modeling to estimate individual intelligence scores, aiming to identify the optimal set of neuroimaging features for accurately predicting an individual's cognitive abilities. Compared to adults, the disparities in cognitive performance among children and adolescents are more likely to captivate individuals' interest and attention. Limited research has been dedicated to exploring neuroimaging markers of intelligence specifically in the pediatric population. In this study, we utilized resting-state functional magnetic resonance imaging (fMRI) and intelligence quotient (IQ) scores of 170 healthy children and adolescents obtained from a public database to identify brain functional connectivity markers associated with individual intellectual behavior. Initially, we extracted and summarized relevant resting-state features from whole-brain or functional network connectivity that were most pertinent to IQ scores. Subsequently, these features were employed to establish prediction models for both performance and verbal IQ scores. Within a 10-fold cross-validation framework, our findings revealed that prediction models based on whole-brain functional connectivity effectively predicted performance IQ scores( R = 0.35 , P = 2.2 × 10 - 4 ) but not verbal IQ scores( R = 0.12 , P = 0.20 ). Results of prediction models based on brain functional network connectivity further demonstrated the exceptional predictive ability of the default mode network (DMN) and fronto-parietal task control network (FTPN) for performance IQ scores ( R = 0.71 , P = 2.2 × 10 - 18 ). The above findings have also been validated using an independent dataset. Our findings suggest that the performance IQ of children and adolescents primarily relies on the connectivity of brain regions associated with DMN and FTPN. Moreover, variations in intellectual performance during childhood and adolescences are closely linked to alterations in brain functional network connectivity.

Dynamic graph transformer network via dual-view connectivity for autism spectrum disorder identification

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that requires objective and accurate identification methods for effective early intervention. Previous population-based methods via functional connectivity (FC) analysis ignore the differences between positive and negative FCs, which provide the potential information complementarity. And they also require additional information to construct a pre-defined graph. Meanwhile, two challenging demand attentions are the imbalance of performance caused by the class distribution and the inherent heterogeneity of multi-site data. In this paper, we propose a novel dynamic graph Transformer network based on dual-view connectivity for ASD Identification. It is based on the Autoencoders, which regard the input feature as individual feature and without any inductive bias. First, a dual-view feature extractor is designed to extract individual and complementary information from positive and negative connectivity. Then Graph Transformer network is innovated with a hot plugging K-Nearest Neighbor (KNN) algorithm module which constructs a dynamic population graph without any additional information. Additionally, we introduce the PolyLoss function and the Vrex method to address the class imbalance and improve the model's generalizability. The evaluation experiment on 1102 subjects from the ABIDE I dataset demonstrates our method can achieve superior performance over several state-of-the-art methods and satisfying generalizability for ASD identification.

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.

Using modular connectome-based predictive modeling to reveal brain-behavior relationships of individual differences in working memory

Working memory plays a crucial role in our daily lives, and brain imaging has been used to predict working memory performance. Here, we present an improved connectome-based predictive modeling approach for building a predictive model of individual working memory performance from whole-brain functional connectivity. The model was built using n-back task-based fMRI and resting-state fMRI data from the Human Connectome Project. Compared to prior models, our model was more interpretable, demonstrated a closer connection to the known anatomical and functional network. The model also demonstrates strong generalization on nine other cognitive behaviors from the HCP database and can well predict the working memory performance of healthy individuals in external datasets. By comparing the differences in prediction effects of different brain networks and anatomical feature analysis on n-back tasks, we found the essential role of some networks in differentiating between high and low working memory loads conditions.

Molecular and network-level mechanisms explaining individual differences in autism spectrum disorder

The mechanisms underlying phenotypic heterogeneity in autism spectrum disorder (ASD) are not well understood. Using a large neuroimaging dataset, we identified three latent dimensions of functional brain network connectivity that predicted individual differences in ASD behaviors and were stable in cross-validation. Clustering along these three dimensions revealed four reproducible ASD subgroups with distinct functional connectivity alterations in ASD-related networks and clinical symptom profiles that were reproducible in an independent sample. By integrating neuroimaging data with normative gene expression data from two independent transcriptomic atlases, we found that within each subgroup, ASD-related functional connectivity was explained by regional differences in the expression of distinct ASD-related gene sets. These gene sets were differentially associated with distinct molecular signaling pathways involving immune and synapse function, G-protein-coupled receptor signaling, protein synthesis and other processes. Collectively, our findings delineate atypical connectivity patterns underlying different forms of ASD that implicate distinct molecular signaling mechanisms.

Default mode and fronto-parietal network associations with IQ development across childhood in autism

Background

Intellectual disability affects approximately one third of individuals with autism spectrum disorder (autism). Yet, a major unresolved neurobiological question is what differentiates autistic individuals with and without intellectual disability. Intelligence quotients (IQs) are highly variable during childhood. We previously identified three subgroups of autistic children with different trajectories of intellectual development from early (2–3½ years) to middle childhood (9–12 years): (a) persistently high: individuals whose IQs remained in the normal range; (b) persistently low: individuals whose IQs remained in the range of intellectual disability (IQ < 70); and (c) changers: individuals whose IQs began in the range of intellectual disability but increased to the normal IQ range. The frontoparietal (FPN) and default mode (DMN) networks have established links to intellectual functioning. Here, we tested whether brain regions within the FPN and DMN differed volumetrically between these IQ trajectory groups in early childhood.

Methods

We conducted multivariate distance matrix regression to examine the brain regions within the FPN (11 regions x 2 hemispheres) and the DMN (12 regions x 2 hemispheres) in 48 persistently high (18 female), 108 persistently low (32 female), and 109 changers (39 female) using structural MRI acquired at baseline. FPN and DMN regions were defined using networks identified in Smith et al. (Proc Natl Acad Sci U S A 106:13040–5, 2009). IQ trajectory groups were defined by IQ measurements from up to three time points spanning early to middle childhood (mean age time 1: 3.2 years; time 2: 5.4 years; time 3: 11.3 years).

Results

The changers group exhibited volumetric differences in the DMN compared to both the persistently low and persistently high groups at time 1. However, the persistently high group did not differ from the persistently low group, suggesting that DMN structure may be an early predictor for change in IQ trajectory. In contrast, the persistently high group exhibited differences in the FPN compared to both the persistently low and changers groups, suggesting differences related more to concurrent IQ and the absence of intellectual disability.

Conclusions

Within autism, volumetric differences of brain regions within the DMN in early childhood may differentiate individuals with persistently low IQ from those with low IQ that improves through childhood. Structural differences in brain networks between these three IQ-based subgroups highlight distinct neural underpinnings of these autism sub-phenotypes.

Supplementary Information

The online version contains supplementary material available at 10.1186/s11689-022-09460-y.

Predicting cognitive scores with graph neural networks through sample selection learning

Analyzing the relation between intelligence and neural activity is of the utmost importance in understanding the working principles of the human brain in health and disease. In existing literature, functional brain connectomes have been used successfully to predict cognitive measures such as intelligence quotient (IQ) scores in both healthy and disordered cohorts using machine learning models. However, existing methods resort to flattening the brain connectome (i.e., graph) through vectorization which overlooks its topological properties. To address this limitation and inspired from the emerging graph neural networks (GNNs), we design a novel regression GNN model (namely RegGNN) for predicting IQ scores from brain connectivity. On top of that, we introduce a novel, fully modular sample selection method to select the best samples to learn from for our target prediction task. However, since such deep learning architectures are computationally expensive to train, we further propose a learning-based sample selection method that learns how to choose the training samples with the highest expected predictive power on unseen samples. For this, we capitalize on the fact that connectomes (i.e., their adjacency matrices) lie in the symmetric positive definite (SPD) matrix cone. Our results on full-scale and verbal IQ prediction outperforms comparison methods in autism spectrum disorder cohorts and achieves a competitive performance for neurotypical subjects using 3-fold cross-validation. Furthermore, we show that our sample selection approach generalizes to other learning-based methods, which shows its usefulness beyond our GNN architecture.

Identification of Pathogenetic Brain Regions via Neuroimaging Data for Diagnosis of Autism Spectrum Disorders

Autism spectrum disorder (ASD) is a kind of neurodevelopmental disorder that often occurs in children and has a hidden onset. Patients usually have lagged development of communication ability and social behavior and thus suffer an unhealthy physical and mental state. Evidence has indicated that diseases related to ASD have commonalities in brain imaging characteristics. This study aims to study the pathogenesis of ASD based on brain imaging data to locate the ASD-related brain regions. Specifically, we collected the functional magnetic resonance image data of 479 patients with ASD and 478 normal subjects matched in age and gender and used a machine-learning framework named random support vector machine cluster to extract distinctive brain regions from the preprocessed data. According to the experimental results, compared with other existing approaches, the method used in this study can more accurately distinguish patients from normal individuals based on brain imaging data. At the same time, this study found that the development of ASD was highly correlated with certain brain regions, e.g., lingual gyrus, superior frontal gyrus, medial gyrus, insular lobe, and olfactory cortex. This study explores the effectiveness of a novel machine-learning approach in the study of ASD brain imaging and provides a reference brain area for the medical research and clinical treatment of ASD.

A structural enriched functional network: An application to predict brain cognitive performance

The structure-function coupling in brain networks has emerged as an important research topic in modern neuroscience. The structural network could provide the backbone of the functional network. The integration of the functional network with structural information can help us better understand functional communication in the brain. This paper proposed a method to accurately estimate the brain functional network enriched by the structural network from diffusion magnetic resonance imaging. First, we adopted a simplex regression model with graph-constrained Elastic Net to construct the functional networks enriched by the structural network. Then, we compared the constructed network characteristics of this approach with several state-of-the-art competing functional network models. Furthermore, we evaluated whether the structural enriched functional network model improves the performance for predicting the cognitive-behavioral outcomes. The experiments have been performed on 218 participants from the Human Connectome Project database. The results demonstrated that our network model improves network consistency and its predictive performance compared with several state-of-the-art competing functional network models.

Good neighbors, bad neighbors: the frequent network neighborhood mapping of the hippocampus enlightens several structural factors of the human intelligence on a 414-subject cohort

The human connectome has become the very frequent subject of study of brain-scientists, psychologists and imaging experts in the last decade. With diffusion magnetic resonance imaging techniques, united with advanced data processing algorithms, today we are able to compute braingraphs with several hundred, anatomically identified nodes and thousands of edges, corresponding to the anatomical connections of the brain. The analysis of these graphs without refined mathematical tools is hopeless. These tools need to address the high error rate of the MRI processing workflow, and need to find structural causes or at least correlations of psychological properties and cerebral connections. Until now, structural connectomics was only rarely able of identifying such causes or correlations. In the present work we study the frequent neighbor sets of the most deeply investigated brain area, the hippocampus. By applying the Frequent Network Neighborhood mapping method, we identified frequent neighbor-sets of the hippocampus, which may influence numerous psychological parameters, including intelligence-related ones. We have found "Good Neighbor" sets, which correlate with better test results and also "Bad Neighbor" sets, which correlate with worse test results. Our study utilizes the braingraphs, computed from the imaging data of the Human Connectome Project's 414 subjects, each with 463 anatomically identified nodes.