The relationships between dynamic resting-state networks and social behavior in autism spectrum disorder revealed by fuzzy entropy-based temporal variability analysis of large-scale network

Association among internalizing problems, white matter integrity, and social difficulties in children with autism spectrum disorder

Autism spectrum disorder (ASD) is characterized by social difficulties and often accompanied by internalizing and externalizing problems, which are frequently overlooked. Here, we examined and compared fractional anisotropy (FA) between 79 children with ASD (aged 4-7.8 years) and 70 age-, gender-, and handedness- matched typically developing controls (TDCs, aged 3-7.2 years). We aimed to explore the relationship among social difficulties, internalizing and externalizing problems, and brain structural foundation (characterized by white matter integrity). Compared with the TDCs, the children with ASD exhibited more severe internalizing and externalizing problems, which were positively correlated with social difficulties. Reduced FA values were observed in specific white matter tracts that integrate a fronto-temporal-occipital circuit. In particular, the FA values within this circuit were negatively correlated with internalizing problems and SRS-TOTAL scores. Mediation analysis revealed that internalizing problems mediated the relationship between the FA values in the left middle longitudinal fasciculus (L-MdLF) and corpus callosum forceps major (CCM) and social difficulties in children with ASD. These findings contribute to our understanding of social difficulties, internalizing and externalizing problems, and white matter integrity in children with ASD and highlight internalizing problems as a mediator between social difficulties and white matter integrity.

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.

Alteration of the large-scale white-matter functional networks in autism spectrum disorder

Autism spectrum disorder is a neurodevelopmental disorder whose core deficit is social dysfunction. Previous studies have indicated that structural changes in white matter are associated with autism spectrum disorder. However, few studies have explored the alteration of the large-scale white-matter functional networks in autism spectrum disorder. Here, we identified ten white-matter functional networks on resting-state functional magnetic resonance imaging data using the K-means clustering algorithm. Compared with the white matter and white-matter functional network connectivity of the healthy controls group, we found significantly decreased white matter and white-matter functional network connectivity mainly located within the Occipital network, Middle temporo-frontal network, and Deep network in autism spectrum disorder. Compared with healthy controls, findings from white-matter gray-matter functional network connectivity showed the decreased white-matter gray-matter functional network connectivity mainly distributing in the Occipital network and Deep network. Moreover, we compared the spontaneous activity of white-matter functional networks between the two groups. We found that the spontaneous activity of Middle temporo-frontal and Deep network was significantly decreased in autism spectrum disorder. Finally, the correlation analysis showed that the white matter and white-matter functional network connectivity between the Middle temporo-frontal network and others networks and the spontaneous activity of the Deep network were significantly correlated with the Social Responsiveness Scale scores of autism spectrum disorder. Together, our findings indicate that changes in the white-matter functional networks are associated behavioral deficits in autism spectrum disorder.

Disease-specific resting-state EEG network variations in schizophrenia revealed by the contrastive machine learning

Given a multitude of genetic and environmental factors, when investigating the variability in schizophrenia (SCZ) and the first-degree relatives (R-SCZ), latent disease-specific variation is usually hidden. To reliably investigate the mechanism underlying the brain deficits from the aspect of functional networks, we newly iterated a framework of contrastive variational autoencoders (cVAEs) applied in the contrasts among three groups, to disentangle the latent resting-state network patterns specified for the SCZ and R-SCZ. We demonstrated that the comparison in reconstructed resting-state networks among SCZ, R-SCZ, and healthy controls (HC) revealed network distortions of the inner-frontal hypoconnectivity and frontal-occipital hyperconnectivity, while the original ones illustrated no differences. And only the classification by adopting the reconstructed network metrics achieved satisfying performances, as the highest accuracy of 96.80% ± 2.87%, along with the precision of 95.05% ± 4.28%, recall of 98.18% ± 3.83%, and F1-score of 96.51% ± 2.83%, was obtained. These findings consistently verified the validity of the newly proposed framework for the contrasts among the three groups and provided related resting-state network evidence for illustrating the pathological mechanism underlying the brain deficits in SCZ, as well as facilitating the diagnosis of SCZ.

Multi-Scale Dynamic Graph Learning for Brain Disorder Detection With Functional MRI

Resting-state functional magnetic resonance imaging (rs-fMRI) has been widely used in the detection of brain disorders such as autism spectrum disorder based on various machine/deep learning techniques. Learning-based methods typically rely on functional connectivity networks (FCNs) derived from blood-oxygen-level-dependent time series of rs-fMRI data to capture interactions between brain regions-of-interest (ROIs). Graph neural networks have been recently used to extract fMRI features from graph-structured FCNs, but cannot effectively characterize spatiotemporal dynamics of FCNs, e.g., the functional connectivity of brain ROIs is dynamically changing in a short period of time. Also, many studies usually focus on single-scale topology of FCN, thereby ignoring the potential complementary topological information of FCN at different spatial resolutions. To this end, in this paper, we propose a multi-scale dynamic graph learning (MDGL) framework to capture multi-scale spatiotemporal dynamic representations of rs-fMRI data for automated brain disorder diagnosis. The MDGL framework consists of three major components: 1) multi-scale dynamic FCN construction using multiple brain atlases to model multi-scale topological information, 2) multi-scale dynamic graph representation learning to capture spatiotemporal information conveyed in fMRI data, and 3) multi-scale feature fusion and classification. Experimental results on two datasets show that MDGL outperforms several state-of-the-art methods.

Identification and analysis of autism spectrum disorder via large-scale dynamic functional network connectivity

Autism spectrum disorder (ASD) is a prevalent neurodevelopmental disorder with severe cognitive impairment. Several studies have reported that brain functional network connectivity (FNC) has great potential for identifying ASD from healthy control (HC) and revealing the relationships between the brain and behaviors of ASD. However, few studies have explored dynamic large-scale FNC as a feature to identify individuals with ASD. This study used a time-sliding window method to study the dynamic FNC (dFNC) on the resting-state fMRI. To avoid arbitrarily determining the window length, we set a window length range of 10-75 TRs (TR = 2 s). We constructed linear support vector machine classifiers for all window length conditions. Using a nested 10-fold cross-validation framework, we obtained a grand average accuracy of 94.88% across window length conditions, which is higher than those reported in previous studies. In addition, we determined the optimal window length using the highest classification accuracy of 97.77%. Based on the optimal window length, we found that the dFNCs were located mainly in dorsal and ventral attention networks (DAN and VAN) and exhibited the highest weight in classification. Specifically, we found that the dFNC between DAN and temporal orbitofrontal network (TOFN) was significantly negatively correlated with social scores of ASD. Finally, using the dFNCs with high classification weights as features, we construct a model to predict the clinical score of ASD. Overall, our findings demonstrated that the dFNC could be a potential biomarker to identify ASD and provide new perspectives to detect cognitive changes in ASD.