Brain multiplexes reveal morphological connectional biomarkers fingerprinting late brain dementia states

Cortical morphological networks for profiling autism spectrum disorder using tensor component analysis

Atypical neurodevelopmental disorders such as Autism Spectrum Disorder (ASD) can alter the cortex morphology at different levels: (i) a low-order level where cortical regions are examined individually, (ii) a high-order level where the relationship between two cortical regions is considered, and (iii) a multi-view high-order level where the relationship between regions is examined across multiple brain views. In this study, we propose to use the emerging multi-view cortical morphological network (CMN), which is derived from T1-w magnetic resonance imaging (MRI), to profile autistic and typical brains and pursue new ways of fingerprinting 'cortical morphology' at the intersection of 'network neuroscience'. Each CMN view models the pairwise morphological dissimilarity at the connection level using a specific cortical attribute (e.g., thickness). Specifically, we set out to identify the inherently most representative morphological connectivities shared across different views of the cortex in both autistic and normal control (NC) populations using tensor component analysis. We thus discover the connectional profiles of both populations shared across different CMNs of the left and right hemispheres, respectively. One of the most representative morphological cortical attributes for assessing the abnormal brain structures in patients with ASD is cortical thickness. The most representative morphological connectivities in multi-view CMN population of normal control and ASD subjects, respectively, and in both left and right hemispheres within the temporal, frontal, and insular lobes of individuals with ASD. These representative connectivities are corresponded to specific clinical features observed in individuals with ASD.

Toward individualized connectomes of brain morphology

The morphological brain connectome (MBC) delineates the coordinated patterns of local morphological features (such as cortical thickness) across brain regions. While classically constructed using population-based approaches, there is a growing trend toward individualized modeling. Currently, the methods for individualized MBCs are varied, posing challenges for method selection and cross-study comparisons. Here, we summarize how individualized MBCs are modeled through low-order methods (correlation-, divergence-, distance-, and deviation-based methods) describing relations in brain morphology, as well as high-order methods capturing similarities in these low-order relations. We discuss the merits and limitations of different methods, examining them in the context of robustness, reproducibility, and reliability. We highlight the importance of elucidating the cellular and molecular mechanisms underlying the individualized connectome, and establishing normative benchmarks to assess individual variation in development, aging, and neuropsychiatric disorders.

Multiple sclerosis clinical forms classification with graph convolutional networks based on brain morphological connectivity

Multiple Sclerosis (MS) is an autoimmune disease that combines chronic inflammatory and neurodegenerative processes underlying different clinical forms of evolution, such as relapsing-remitting, secondary progressive, or primary progressive MS. This identification is usually performed by clinical evaluation at the diagnosis or during the course of the disease for the secondary progressive phase. In parallel, magnetic resonance imaging (MRI) analysis is a mandatory diagnostic complement. Identifying the clinical form from MR images is therefore a helpful and challenging task. Here, we propose a new approach for the automatic classification of MS forms based on conventional MRI (i.e., T1-weighted images) that are commonly used in clinical context. For this purpose, we investigated the morphological connectome features using graph based convolutional neural network. Our results obtained from the longitudinal study of 91 MS patients highlight the performance (F1-score) of this approach that is better than state-of-the-art as 3D convolutional neural networks. These results open the way for clinical applications such as disability correlation only using T1-weighted images.

Single-subject cortical morphological brain networks: Phenotypic associations and neurobiological substrates

Although single-subject morphological brain networks provide an important way for human connectome studies, their roles and origins are poorly understood. Combining cross-sectional and repeated structural magnetic resonance imaging scans from adults, children and twins with behavioral and cognitive measures and brain-wide transcriptomic, cytoarchitectonic and chemoarchitectonic data, this study examined phenotypic associations and neurobiological substrates of single-subject morphological brain networks. We found that single-subject morphological brain networks explained inter-individual variance and predicted individual outcomes in Motor and Cognition domains, and distinguished individuals from each other. The performance can be further improved by integrating different morphological indices for network construction. Low-moderate heritability was observed for single-subject morphological brain networks with the highest heritability for sulcal depth-derived networks and higher heritability for inter-module connections. Furthermore, differential roles of genetic, cytoarchitectonic and chemoarchitectonic factors were observed for single-subject morphological brain networks. Cortical thickness-derived networks were related to the three factors with contributions from genes enriched in membrane and transport related functions, genes preferentially located in supragranular and granular layers, overall thickness in the molecular layer and thickness of wall in the infragranular layers, and metabotropic glutamate receptor 5 and dopamine transporter; fractal dimension-, gyrification index- and sulcal depth-derived networks were only associated with the chemoarchitectonic factor with contributions from different sets of neurotransmitter receptors. Most results were reproducible across different parcellation schemes and datasets. Altogether, this study demonstrates phenotypic associations and neurobiological substrates of single-subject morphological brain networks, which provide intermediate endophenotypes to link molecular and cellular architecture and behavior and cognition.

Graph neural network based unsupervised influential sample selection for brain multigraph population fusion

Graph neural networks (GNNs) have witnessed remarkable proliferation due to the increasing number of applications where data is represented as graphs. GNN-based multigraph population fusion methods for estimating population representative connectional brain templates (CBT) have recently led to improvements, especially in network neuroscience. However, prior studies do not consider how an individual training brain multigraph influences the quality of GNN training for brain multigraph population fusion. To address this issue, we propose two major sample selection methods to quantify the influence of a training brain multigraph on the brain multigraph population fusion task using GNNs, in a fully unsupervised manner: (1) GraphGradIn, in which we use gradients w.r.t GNN weights to trace changes in the centeredness loss of connectional brain template during the training phase; (2) GraphTestIn, in which we exclude a training brain multigraph of interest during the refinement process in the test phase to infer its influence on the CBT centeredness loss. Next, we select the most influential multigraphs to build the training set for brain multigraph population fusion into a CBT. We conducted extensive experiments on brain multigraph datasets to show that using a dataset of influential training samples improves the learned connectional brain template in terms of centeredness, discriminativeness, and topological soundness. Finally, we demonstrate the use of our methods by discovering the connectional fingerprints of healthy and neurologically disordered brain multigraph populations including Alzheimer's disease and Autism spectrum disorder patients. Our source code is available at https://github.com/basiralab/GraphGradIn.

Graph Neural Networks in Network Neuroscience

Noninvasive medical neuroimaging has yielded many discoveries about the brain connectivity. Several substantial techniques mapping morphological, structural and functional brain connectivities were developed to create a comprehensive road map of neuronal activities in the human brain -namely brain graph. Relying on its non-euclidean data type, graph neural network (GNN) provides a clever way of learning the deep graph structure and it is rapidly becoming the state-of-the-art leading to enhanced performance in various network neuroscience tasks. Here we review current GNN-based methods, highlighting the ways that they have been used in several applications related to brain graphs such as missing brain graph synthesis and disease classification. We conclude by charting a path toward a better application of GNN models in network neuroscience field for neurological disorder diagnosis and population graph integration. The list of papers cited in our work is available at https://github.com/basiralab/GNNs-in-Network-Neuroscience.

Comparative survey of multigraph integration methods for holistic brain connectivity mapping

One of the greatest scientific challenges in network neuroscience is to create a representative map of a population of heterogeneous brain networks, which acts as a connectional fingerprint. The connectional brain template (CBT), also named network atlas, presents a powerful tool for capturing the most representative and discriminative traits of a given population while preserving its topological patterns. The idea of a CBT is to integrate a population of heterogeneous brain connectivity networks, derived from different neuroimaging modalities or brain views (e.g., structural and functional), into a unified holistic representation. Here we review current state-of-the-art methods designed to estimate well-centered and representative CBT for populations of single-view and multi-view brain networks. We start by reviewing each CBT learning method, then we introduce the evaluation measures to compare CBT representativeness of populations generated by single-view and multigraph integration methods, separately, based on the following criteria: Centeredness, biomarker-reproducibility, node-level similarity, global-level similarity, and distance-based similarity. We demonstrate that the deep graph normalizer (DGN) method significantly outperforms other multi-graph and all single-view integration methods for estimating CBTs using a variety of healthy and disordered datasets in terms of centeredness, reproducibility (i.e., graph-derived biomarkers reproducibility that disentangle the typical from the atypical connectivity variability), and preserving the topological traits at both local and global graph-levels.

Towards better interpretable and generalizable AD detection using collective artificial intelligence

Alzheimer's Disease is the most common cause of dementia. Accurate diagnosis and prognosis of this disease are essential to design an appropriate treatment plan, increasing the life expectancy of the patient. Intense research has been conducted on the use of machine learning to identify Alzheimer's Disease from neuroimaging data, such as structural magnetic resonance imaging. In recent years, advances of deep learning in computer vision suggest a new research direction for this problem. Current deep learning-based approaches in this field, however, have a number of drawbacks, including the interpretability of model decisions, a lack of generalizability information and a lower performance compared to traditional machine learning techniques. In this paper, we design a two-stage framework to overcome these limitations. In the first stage, an ensemble of 125 U-Nets is used to grade the input image, producing a 3D map that reflects the disease severity at voxel-level. This map can help to localize abnormal brain areas caused by the disease. In the second stage, we model a graph per individual using the generated grading map and other information about the subject. We propose to use a graph convolutional neural network classifier for the final classification. As a result, our framework demonstrates comparative performance to the state-of-the-art methods in different datasets for both diagnosis and prognosis. We also demonstrate that the use of a large ensemble of U-Nets offers a better generalization capacity for our framework.

Template-based graph registration network for boosting the diagnosis of brain connectivity disorders

Brain graphs are powerful representations to explore the biological roadmaps of the human brain in its healthy and disordered states. Recently, a few graph neural networks (GNNs) have been designed for brain connectivity synthesis and diagnosis. However, such non-Euclidean deep learning architectures might fail to capture the neural interactions between different brain regions as they are trained without guidance from any prior biological template-i.e., template-free learning. Here we assume that using a population-driven brain connectional template (CBT) that captures well the connectivity patterns fingerprinting a given brain state (e.g., healthy) can better guide the GNN training in its downstream learning task such as classification or regression. To this aim we design a plug-in graph registration network (GRN) that can be coupled with any conventional graph neural network (GNN) so as to boost its learning accuracy and generalizability to unseen samples. Our GRN is a graph generative adversarial network (gGAN), which registers brain graphs to a prior CBT. Next, the registered brain graphs are used to train typical GNN models. Our GRN can be integrated into any GNN working in an end-to-end fashion to boost its prediction accuracy. Our experiments showed that GRN remarkably boosted the prediction accuracy of four conventional GNN models across four neurological datasets.

Imputing Brain Measurements Across Data Sets via Graph Neural Networks

Publicly available data sets of structural MRIs might not contain specific measurements of brain Regions of Interests (ROIs) that are important for training machine learning models. For example, the curvature scores computed by Freesurfer are not released by the Adolescent Brain Cognitive Development (ABCD) Study. One can address this issue by simply reapplying Freesurfer to the data set. However, this approach is generally computationally and labor intensive (e.g., requiring quality control). An alternative is to impute the missing measurements via a deep learning approach. However, the state-of-the-art is designed to estimate randomly missing values rather than entire measurements. We therefore propose to re-frame the imputation problem as a prediction task on another (public) data set that contains the missing measurements and shares some ROI measurements with the data sets of interest. A deep learning model is then trained to predict the missing measurements from the shared ones and afterwards is applied to the other data sets. Our proposed algorithm models the dependencies between ROI measurements via a graph neural network (GNN) and accounts for demographic differences in brain measurements (e.g. sex) by feeding the graph encoding into a parallel architecture. The architecture simultaneously optimizes a graph decoder to impute values and a classifier in predicting demographic factors. We test the approach, called Demographic Aware Graph-based Imputation (DAGI), on imputing those missing Freesurfer measurements of ABCD (N=3760; minimum age 12 years) by training the predictor on those publicly released by the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA, N=540). 5-fold cross-validation on NCANDA reveals that the imputed scores are more accurate than those generated by linear regressors and deep learning models. Adding them also to a classifier trained in identifying sex results in higher accuracy than only using those Freesurfer scores provided by ABCD.

Predicting the evolution trajectory of population-driven connectional brain templates using recurrent multigraph neural networks

The mapping of the time-dependent evolution of the human brain connectivity using longitudinal and multimodal neuroimaging datasets provides insights into the development of neurological disorders and the way they alter the brain morphology, structure and function over time. Recently, the connectional brain template (CBT) was introduced as a compact representation integrating a population of brain multigraphs, where two brain regions can have multiple connections, into a single graph. Given a population of brain multigraphs observed at a baseline timepoint t₁, we aim to learn how to predict the evolution of the population CBT at follow-up timepoints t>t₁. Such model will allow us to foresee the evolution of the connectivity patterns of healthy and disordered individuals at the population level. Here we present recurrent multigraph integrator network (ReMI-Net^⋆) to forecast population templates at consecutive timepoints from a given single timepoint. In particular, we unprecedentedly design a graph neural network architecture to model the changes in the brain multigraph and identify the biomarkers that differentiate between the typical and atypical populations. Addressing such issues is of paramount importance in diagnosing neurodegenerative disorders at early stages and promoting new clinical studies based on the pinned-down biomarker brain regions or connectivities. In this paper, we demonstrate the design and use of the ReMI-Net^⋆ model, which learns both the multigraph node level and time level dependencies concurrently. Thanks to its novel graph convolutional design and normalization layers, ReMI-Net^⋆ predicts well-centered, discriminative, and topologically sound connectional templates over time. Additionally, the results show that our model outperforms all benchmarks and state-of-the-art methods by comparing and discovering the atypical connectivity alterations over time. Our ReMI-Net^⋆ code is available on GitHub at https://github.com/basiralab/ReMI-Net-Star.

Emerging Materials, Wearables, and Diagnostic Advancements in Therapeutic Treatment of Brain Diseases

Among the most critical health issues, brain illnesses, such as neurodegenerative conditions and tumors, lower quality of life and have a significant economic impact. Implantable technology and nano-drug carriers have enormous promise for cerebral brain activity sensing and regulated therapeutic application in the treatment and detection of brain illnesses. Flexible materials are chosen for implantable devices because they help reduce biomechanical mismatch between the implanted device and brain tissue. Additionally, implanted biodegradable devices might lessen any autoimmune negative effects. The onerous subsequent operation for removing the implanted device is further lessened with biodegradability. This review expands on current developments in diagnostic technologies such as magnetic resonance imaging, computed tomography, mass spectroscopy, infrared spectroscopy, angiography, and electroencephalogram while providing an overview of prevalent brain diseases. As far as we are aware, there hasn't been a single review article that addresses all the prevalent brain illnesses. The reviewer also looks into the prospects for the future and offers suggestions for the direction of future developments in the treatment of brain diseases.

Estimating High-Order Brain Functional Networks in Bayesian View for Autism Spectrum Disorder Identification

Brain functional network (BFN) has become an increasingly important tool to understand the inherent organization of the brain and explore informative biomarkers of neurological disorders. Pearson’s correlation (PC) is the most widely accepted method for constructing BFNs and provides a basis for designing new BFN estimation schemes. Particularly, a recent study proposes to use two sequential PC operations, namely, correlation’s correlation (CC), for constructing the high-order BFN. Despite its empirical effectiveness in identifying neurological disorders and detecting subtle changes of connections in different subject groups, CC is defined intuitively without a solid and sustainable theoretical foundation. For understanding CC more rigorously and providing a systematic BFN learning framework, in this paper, we reformulate it in the Bayesian view with a prior of matrix-variate normal distribution. As a result, we obtain a probabilistic explanation of CC. In addition, we develop a Bayesian high-order method (BHM) to automatically and simultaneously estimate the high- and low-order BFN based on the probabilistic framework. An efficient optimization algorithm is also proposed. Finally, we evaluate BHM in identifying subjects with autism spectrum disorder (ASD) from typical controls based on the estimated BFNs. Experimental results suggest that the automatically learned high- and low-order BFNs yield a superior performance over the artificially defined BFNs via conventional CC and PC.

Multigraph classification using learnable integration network with application to gender fingerprinting

Multigraphs with heterogeneous views present one of the most challenging obstacles to classification tasks due to their complexity. Several works based on feature selection have been recently proposed to disentangle the problem of multigraph heterogeneity. However, such techniques have major drawbacks. First, the bulk of such works lies in the vectorization and the flattening operations, failing to preserve and exploit the rich topological properties of the multigraph. Second, they learn the classification process in a dichotomized manner where the cascaded learning steps are pieced in together independently. Hence, such architectures are inherently agnostic to the cumulative estimation error from step to step. To overcome these drawbacks, we introduce MICNet (multigraph integration and classifier network), the first end-to-end graph neural network based model for multigraph classification. First, we learn a single-view graph representation of a heterogeneous multigraph using a GNN based integration model. The integration process in our model helps tease apart the heterogeneity across the different views of the multigraph by generating a subject-specific graph template while preserving its geometrical and topological properties conserving the node-wise information while reducing the size of the graph (i.e., number of views). Second, we classify each integrated template using a geometric deep learning block which enables us to grasp the salient graph features. We train, in end-to-end fashion, these two blocks using a single objective function to optimize the classification performance. We evaluate our MICNet in gender classification using brain multigraphs derived from different cortical measures. We demonstrate that our MICNet significantly outperformed its variants thereby showing its great potential in multigraph classification.

A comparative study of machine learning methods for predicting the evolution of brain connectivity from a baseline timepoint

BACKGROUND

Predicting the evolution of the brain network, also called connectome, by foreseeing changes in the connectivity weights linking pairs of anatomical regions makes it possible to spot connectivity-related neurological disorders in earlier stages and detect the development of potential connectomic anomalies. Remarkably, such a challenging prediction problem remains least explored in the predictive connectomics literature. It is a known fact that machine learning (ML) methods have proven their predictive abilities in a wide variety of computer vision problems. However, ML techniques specifically tailored for the prediction of brain connectivity evolution trajectory from a single timepoint are almost absent.

NEW METHOD

To fill this gap, we organized a Kaggle competition where 20 competing teams designed advanced machine learning pipelines for predicting the brain connectivity evolution from a single timepoint. The teams developed their ML pipelines with combination of data pre-processing, dimensionality reduction and learning methods. Each ML framework inputs a baseline brain connectivity matrix observed at baseline timepoint t₀ and outputs the brain connectivity map at a follow-up timepoint t₁. The longitudinal OASIS-2 dataset was used for model training and evaluation. Both random data split and 5-fold cross-validation strategies were used for ranking and evaluating the generalizability and scalability of each competing ML pipeline.

RESULTS

Utilizing an inclusive approach, we ranked the methods based on two complementary evaluation metrics (mean absolute error (MAE) and Pearson Correlation Coefficient (PCC)) and their performances using different training and testing data perturbation strategies (single random split and cross-validation). The final rank was calculated using the rank product for each competing team across all evaluation measures and validation strategies. Furthermore, we added statistical significance values to each proposed pipeline.

CONCLUSION

In support of open science, the developed 20 ML pipelines along with the connectomic dataset are made available on GitHub (https://github.com/basiralab/Kaggle-BrainNetPrediction-Toolbox). The outcomes of this competition are anticipated to lead the further development of predictive models that can foresee the evolution of the brain connectivity over time, as well as other types of networks (e.g., genetic networks).

Estimation of gender-specific connectional brain templates using joint multi-view cortical morphological network integration

The estimation of a connectional brain template (CBT) integrating a population of brain networks while capturing shared and differential connectional patterns across individuals remains unexplored in gender fingerprinting. This paper presents the first study to estimate gender-specific CBTs using multi-view cortical morphological networks (CMNs) estimated from conventional T1-weighted magnetic resonance imaging (MRI). Specifically, each CMN view is derived from a specific cortical attribute (e.g. thickness), encoded in a network quantifying the dissimilarity in morphology between pairs of cortical brain regions. To this aim, we propose Multi-View Clustering and Fusion Network (MVCF-Net), a novel multi-view network fusion method, which can jointly identify consistent and differential clusters of multi-view datasets in order to capture simultaneously similar and distinct connectional traits of samples. Our MVCF-Net method estimates a representative and well-centered CBTs for male and female populations, independently, to eventually identify their fingerprinting regions of interest (ROIs) in four main steps. First, we perform multi-view network clustering model based on manifold optimization which groups CMNs into shared and differential clusters while preserving their alignment across views. Second, for each view, we linearly fuse CMNs belonging to each cluster, producing local CBTs. Third, for each cluster, we non-linearly integrate the local CBTs across views, producing a cluster-specific CBT. Finally, by linearly fusing the cluster-specific centers we estimate a final CBT of the input population. MVCF-Net produced the most centered and representative CBTs for male and female populations and identified the most discriminative ROIs marking gender differences. The most two gender-discriminative ROIs involved the lateral occipital cortex and pars opercularis in the left hemisphere and the middle temporal gyrus and lingual gyrus in the right hemisphere.

Brain multigraph prediction using topology-aware adversarial graph neural network

Brain graphs (i.e, connectomes) constructed from medical scans such as magnetic resonance imaging (MRI) have become increasingly important tools to characterize the abnormal changes in the human brain. Due to the high acquisition cost and processing time of multimodal MRI, existing deep learning frameworks based on Generative Adversarial Network (GAN) focused on predicting the missing multimodal medical images from a few existing modalities. While brain graphs help better understand how a particular disorder can change the connectional facets of the brain, synthesizing a target brain multigraph (i.e, multiple brain graphs) from a single source brain graph is strikingly lacking. Additionally, existing graph generation works mainly learn one model for each target domain which limits their scalability in jointly predicting multiple target domains. Besides, while they consider the global topological scale of a graph (i.e., graph connectivity structure), they overlook the local topology at the node scale (e.g., how central a node is in the graph). To address these limitations, we introduce topology-aware graph GAN architecture (topoGAN), which jointly predicts multiple brain graphs from a single brain graph while preserving the topological structure of each target graph. Its three key innovations are: (i) designing a novel graph adversarial auto-encoder for predicting multiple brain graphs from a single one, (ii) clustering the encoded source graphs in order to handle the mode collapse issue of GAN and proposing a cluster-specific decoder, (iii) introducing a topological loss to force the prediction of topologically sound target brain graphs. The experimental results using five target domains demonstrated the outperformance of our method in brain multigraph prediction from a single graph in comparison with baseline approaches.

Brain graph super-resolution using adversarial graph neural network with application to functional brain connectivity

Brain image analysis has advanced substantially in recent years with the proliferation of neuroimaging datasets acquired at different resolutions. While research on brain image super-resolution has undergone a rapid development in the recent years, brain graph super-resolution is still poorly investigated because of the complex nature of non-Euclidean graph data. In this paper, we propose the first-ever deep graph super-resolution (GSR) framework that attempts to automatically generate high-resolution (HR) brain graphs with N^' nodes (i.e., anatomical regions of interest (ROIs)) from low-resolution (LR) graphs with N nodes where N<N^'. First, we formalize our GSR problem as a node feature embedding learning task. Once the HR nodes' embeddings are learned, the pairwise connectivity strength between brain ROIs can be derived through an aggregation rule based on a novel Graph U-Net architecture. While typically the Graph U-Net is a node-focused architecture where graph embedding depends mainly on node attributes, we propose a graph-focused architecture where the node feature embedding is based on the graph topology. Second, inspired by graph spectral theory, we break the symmetry of the U-Net architecture by super-resolving the low-resolution brain graph structure and node content with a GSR layer and two graph convolutional network layers to further learn the node embeddings in the HR graph. Third, to handle the domain shift between the ground-truth and the predicted HR brain graphs, we incorporate adversarial regularization to align their respective distributions. Our proposed AGSR-Net framework outperformed its variants for predicting high-resolution functional brain graphs from low-resolution ones. Our AGSR-Net code is available on GitHub at https://github.com/basiralab/AGSR-Net.

MGN-Net: A multi-view graph normalizer for integrating heterogeneous biological network populations

With the recent technological advances, biological datasets, often represented by networks (i.e., graphs) of interacting entities, proliferate with unprecedented complexity and heterogeneity. Although modern network science opens new frontiers of analyzing connectivity patterns in such datasets, we still lack data-driven methods for extracting an integral connectional fingerprint of a multi-view graph population, let alone disentangling the typical from the atypical variations across the population samples. We present the multi-view graph normalizer network (MGN-Net²), a graph neural network based method to normalize and integrate a set of multi-view biological networks into a single connectional template that is centered, representative, and topologically sound. We demonstrate the use of MGN-Net by discovering the connectional fingerprints of healthy and neurologically disordered brain network populations including Alzheimer's disease and Autism spectrum disorder patients. Additionally, by comparing the learned templates of healthy and disordered populations, we show that MGN-Net significantly outperforms conventional network integration methods across extensive experiments in terms of producing the most centered templates, recapitulating unique traits of populations, and preserving the complex topology of biological networks. Our evaluations showed that MGN-Net is powerfully generic and easily adaptable in design to different graph-based problems such as identification of relevant connections, normalization and integration.

Gender differences in cortical morphological networks

Cortical morphological networks (CMN), where each network models the relationship in morphology between different cortical brain regions quantified using a specific measurement (e.g., cortical thickness), have not been investigated with respect to gender differences in the human brain. Cortical processes are expected to involve complex interactions between different brain regions, univariate methods thus might overlook informative gender markers. Hence, by leveraging machine learning techniques with the potential to highlight multivariate interacting effects, we found that the most discriminative CMN connections between males and females were derived from the left hemisphere using the mean sulcal depth as measurement. However, for both left and right hemispheres, the first most discriminative morphological connection revealed across all cortical attributes involved (entorhinal cortex ↔ caudal anterior cingulate cortex) and (entorhinal cortex ↔ transverse temporal cortex) respectively, which gives us new insights into behavioral gender differences from an omics perspective and might explain why males and females learn differently.

Sex effects on cortical morphological networks in healthy young adults

Understanding sex-related differences across the human cerebral cortex is an important step in elucidating the basis of psychological, behavioural and clinical differences between the sexes. Prior structural neuroimaging studies primarily focused on regional sex differences using univariate analyses. Here we focus on sex differences in cortical morphological networks (CMNs) derived using multivariate modelling of regional cortical measures of volume and surface from high-quality structural MRI scans from healthy participants in the Human Connectome Project (HCP) (n = 1,063) and the Southwest University Longitudinal Imaging Multimodal (SLIM) study (n = 549). The functional relevance of the CMNs was inferred using the NeuroSynth decoding function. Sex differences were widespread but not uniform. In general, females had higher volume, thickness and cortical folding in networks that involve prefrontal (both ventral and dorsal regions including the anterior cingulate) and parietal regions while males had higher volume, thickness and cortical folding in networks that primarily include temporal and posterior cortical regions. CMN loading coefficients were used as input features to linear discriminant analyses that were performed separately in the HCP and SLIM; sex was predicted with a high degree of accuracy (81%-85%) across datasets. The availability of behavioral data in the HCP enabled us to show that male-biased surface-based CMNs were associated with externalizing behaviors. These results extend previous literature on regional sex-differences by identifying CMNs that can reliably predict sex, are relevant to the expression of psychopathology and provide the foundation for the future investigation of their functional significance in clinical populations.

A diagnostic unified classification model for classifying multi-sized and multi-modal brain graphs using graph alignment

BACKGROUND

Presence of multimodal brain graphs derived from different neuroimaging modalities is inarguably one of the most critical challenges in building unified classification models that can be trained and tested on any brain graph regardless of its size and the modality it was derived from.

EXISTING METHODS

One solution is to learn a model for each modality independently, which is cumbersome and becomes more time-consuming as the number of modalities increases. Another traditional solution is to build a model inputting multimodal brain graphs for the target prediction task; however, this is only applicable to datasets where all samples have joint neuro-modalities.

NEW METHOD

In this paper, we propose to build a unified brain graph classification model trained on unpaired multimodal brain graphs, which can classify any brain graph of any size. This is enabled by incorporating a graph alignment step where all multi-modal graphs of different sizes and heterogeneous distributions are mapped to a common template graph. Next, we design a graph alignment strategy to the target fixed-size template and further apply linear discriminant analysis (LDA) to the aligned graphs as a supervised dimensionality reduction technique for the target classification task.

RESULTS

We tested our method on unpaired autistic and healthy brain connectomes derived from functional and morphological MRI datasets (two modalities).

CONCLUSION

Our results showed that our unified model method not only has great promise in solving such a challenging problem but achieves comparable performance to models trained on each modality independently.

Brain graph synthesis by dual adversarial domain alignment and target graph prediction from a source graph

Developing predictive intelligence in neuroscience for learning how to generate multimodal medical data from a single modality can improve neurological disorder diagnosis with minimal data acquisition resources. Existing deep learning frameworks are mainly tailored for images, which might fail in handling geometric data (e.g., brain graphs). Specifically, predicting a target brain graph from a single source brain graph remains largely unexplored. Solving such problem is generally challenged with domain fracturecaused by the difference in distribution between source and target domains. Besides, solving the prediction and domain fracture independently might not be optimal for both tasks. To address these challenges, we unprecedentedly propose a Learning-guided Graph Dual Adversarial Domain Alignment (LG-DADA) framework for predicting a target brain graph from a source brain graph. The proposed LG-DADA is grounded in three fundamental contributions: (1) a source data pre-clustering step using manifold learning to firstly handle source data heterogeneity and secondly circumvent mode collapse in generative adversarial learning, (2) a domain alignment of source domain to the target domain by adversarially learning their latent representations, and (3) a dual adversarial regularization that jointly learns a source embedding of training and testing brain graphs using two discriminators and predict the training target graphs. Results on morphological brain graphs synthesis showed that our method produces better prediction accuracy and visual quality as compared to other graph synthesis methods.

Topology-guided cyclic brain connectivity generation using geometric deep learning

BACKGROUND

There is a growing need for analyzing medical data such as brain connectomes. However, the unavailability of large-scale training samples increases risks of model over-fitting. Recently, deep learning (DL) architectures quickly gained momentum in synthesizing medical data. However, such frameworks are primarily designed for Euclidean data (e.g., images), overlooking geometric data (e.g., brain connectomes). A few existing geometric DL works that aimed to predict a target brain connectome from a source one primarily focused on domain alignment and were agnostic to preserving the connectome topology.

NEW METHOD

To address the above limitations, firstly, we adapt the graph translation generative adversarial network (GT GAN) architecture to brain connectomic data. Secondly, we extend the baseline GT GAN to a cyclic graph translation (CGT) GAN, allowing bidirectional brain network translation between the source and target views. Finally, to preserve the topological strength of brain regions of interest (ROIs), we impose a topological strength constraint on the CGT GAN learning, thereby introducing CGTS GAN architecture.

COMPARISON WITH EXISTING METHODS

We compared CGTS with graph translation methods and its ablated versions.

RESULTS

Our deep graph network outperformed the baseline comparison method and its ablated versions in mean squared error (MSE) using multiview autism spectrum disorder connectomic dataset.

CONCLUSION

We designed a topology-aware bidirectional brain connectome synthesis framework rooted in geometric deep learning, which can be used for data augmentation in clinical diagnosis.

Multi-Regression based supervised sample selection for predicting baby connectome evolution trajectory from neonatal timepoint

The connectional map of the baby brain undergoes dramatic changes over the first year of postnatal development, which makes its mapping a challenging task, let alone learning how to predict its evolution. Currently, learning models for predicting brain connectomic developmental trajectories remain broadly absent despite their great potential in spotting atypical neurodevelopmental disorders early. This is most likely due to the scarcity and often incompleteness of longitudinal infant neuroimaging studies for training such models. In this paper, we propose the first approach for progressively predicting longitudinal development of brain networks during the postnatal period solely from a baseline connectome around birth. To this end, a supervised multi-regression sample selection strategy is designed to learn how to identify the best set of neighbors of a testing baseline connectome to eventually predict its evolution trajectory at follow-up timepoints. However, given that the training dataset may have missing samples (connectomes) at certain timepoints, this may affect the training of the predictive model. To overcome this problem, we perform a low-rank tensor completion based on a robust principal component analysis to impute the missing training connectomes by linearly approximating similar complete training networks. In the prediction step, our sample selection strategy aims to preserve spatiotemporal relationships between consecutive timepoints. Therefore, the proposed method learns how to identify the set of the local closest neighbors to a target network by training an ensemble of bidirectional regressors leveraging temporal dependency between consecutive timepoints with a recall to the baseline observations to progressively predict the evolution of a testing network over time. Our method achieves the best prediction results and better captures the dynamic changes of each brain connectome over time in comparison to its ablated versions using leave-one-out cross-validation strategy.

Adversarial brain multiplex prediction from a single brain network with application to gender fingerprinting

Brain connectivity networks, derived from magnetic resonance imaging (MRI), non-invasively quantify the relationship in function, structure, and morphology between two brain regions of interest (ROIs) and give insights into gender-related connectional differences. However, to the best of our knowledge, studies on gender differences in brain connectivity were limited to investigating pairwise (i.e., low-order) relationships across ROIs, overlooking the complex high-order interconnectedness of the brain as a network. A few recent works on neurological disorders addressed this limitation by introducing the brain multiplex which is composed of a source network intra-layer, a target intra-layer, and a convolutional interlayer capturing the high-level relationship between both intra-layers. However, brain multiplexes are built from at least two different brain networks hindering their application to connectomic datasets with single brain networks (e.g., functional networks). To fill this gap, we propose Adversarial Brain Multiplex Translator (ABMT), the first work for predicting brain multiplexes from a source network using geometric adversarial learning to investigate gender differences in the human brain. Our framework comprises: (i) a geometric source to target network translator mimicking a U-Net architecture with skip connections, (ii) a conditional discriminator which distinguishes between predicted and ground truth target intra-layers, and finally (iii) a multi-layer perceptron (MLP) classifier which supervises the prediction of the target multiplex using the subject class label (e.g., gender). Our experiments on a large dataset demonstrated that predicted multiplexes significantly boost gender classification accuracy compared with source networks and unprecedentedly identify both low and high-order gender-specific brain multiplex connections. Our ABMT source code is available on GitHub at https://github.com/basiralab/ABMT.

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

Decoding how intelligence is engrained in the human brain construct is vital in the understanding of particular neurological disorders. While the majority of existing studies focus on characterizing intelligence in neurotypical (NT) brains, investigating how neural correlates of intelligence scores are altered by atypical neurodevelopmental disorders, such as Autism Spectrum Disorders (ASD), is almost absent. To help fill this gap, we use a connectome-based predictive model (CPM) to predict intelligence scores from functional connectome data, derived from resting-state functional magnetic resonance imaging (rsfMRI). The utilized model learns how to select the most significant positive and negative brain connections, independently, to predict the target intelligence scores in NT and ASD populations, respectively. In the first step, using leave-one-out cross-validation we train a linear regressor robust to outliers to identify functional brain connections that best predict the target intelligence score (p - value < 0.01). Next, for each training subject, positive (respectively negative) connections are summed to produce single-subject positive (respectively negative) summary values. These are then paired with the target training scores to train two linear regressors: (a) a positive model which maps each positive summary value to the subject score, and (b) a negative model which maps each negative summary value to the target score. In the testing stage, by selecting the same connections for the left-out testing subject, we compute their positive and negative summary values, which are then fed to the trained negative and positive models for predicting the target score. This framework was applied to NT and ASD populations independently to identify significant functional connections coding for full-scale and verbal intelligence quotients in the brain.

Machine learning methods for brain network classification: Application to autism diagnosis using cortical morphological networks

BACKGROUND

Autism spectrum disorder (ASD) affects the brain connectivity at different levels. Nonetheless, non-invasively distinguishing such effects using magnetic resonance imaging (MRI) remains very challenging to machine learning diagnostic frameworks due to ASD heterogeneity. So far, existing network neuroscience works mainly focused on functional (derived from functional MRI) and structural (derived from diffusion MRI) brain connectivity, which might not directly capture relational morphological changes between brain regions. Indeed, machine learning (ML) studies for ASD diagnosis using morphological brain networks derived from conventional T1-weighted MRI are very scarce.

NEW METHOD

To fill this gap, we leverage crowdsourcing by organizing a Kaggle competition to build a pool of machine learning pipelines for neurological disorder diagnosis with application to ASD diagnosis using cortical morphological networks derived from T1-weighted MRI.

RESULTS

During the competition, participants were provided with a training dataset and only allowed to check their performance on a public test data. The final evaluation was performed on both public and hidden test datasets based on accuracy, sensitivity, and specificity metrics. Teams were ranked using each performance metric separately and the final ranking was determined based on the mean of all rankings. The first-ranked team achieved 70% accuracy, 72.5% sensitivity, and 67.5% specificity, where the second-ranked team achieved 63.8%, 62.5%, 65% respectively.

CONCLUSION

Leveraging participants to design ML diagnostic methods within a competitive machine learning setting has allowed the exploration and benchmarking of wide spectrum of ML methods for ASD diagnosis using cortical morphological networks.

Neonatal morphometric similarity mapping for predicting brain age and characterizing neuroanatomic variation associated with preterm birth

Multi-contrast MRI captures information about brain macro- and micro-structure which can be combined in an integrated model to obtain a detailed "fingerprint" of the anatomical properties of an individual's brain. Inter-regional similarities between features derived from structural and diffusion MRI, including regional volumes, diffusion tensor metrics, neurite orientation dispersion and density imaging measures, can be modelled as morphometric similarity networks (MSNs). Here, individual MSNs were derived from 105 neonates (59 preterm and 46 term) who were scanned between 38 and 45 weeks postmenstrual age (PMA). Inter-regional similarities were used as predictors in a regression model of age at the time of scanning and in a classification model to discriminate between preterm and term infant brains. When tested on unseen data, the regression model predicted PMA at scan with a mean absolute error of 0.70  ±  0.56 weeks, and the classification model achieved 92% accuracy. We conclude that MSNs predict chronological brain age accurately; and they provide a data-driven approach to identify networks that characterise typical maturation and those that contribute most to neuroanatomic variation associated with preterm birth.

No relationship between fornix and cingulum degradation and within-network decreases in functional connectivity in prodromal Alzheimer's disease

INTRODUCTION

The earliest changes in the brain due to Alzheimer's disease are associated with the neural networks related to memory function. We investigated changes in functional and structural connectivity among regions that support memory function in prodromal Alzheimer's disease, i.e., during the mild cognitive impairment (MCI) stage.

METHODS

Twenty-three older healthy controls and 25 adults with MCI underwent multimodal MRI scanning. Limbic white matter tracts-the fornix, parahippocampal cingulum, retrosplenial cingulum, subgenual cingulum and uncinate fasciculus-were reconstructed in ExploreDTI using constrained spherical deconvolution-based tractography. Using a network-of-interest approach, resting-state functional connectivity time-series correlations among sub-parcellations of the default mode and limbic networks, the hippocampus and the thalamus were calculated in Conn.

ANALYSIS

Controlling for age, education, and gender between group linear regressions of five diffusion-weighted measures and of resting state connectivity measures were performed per hemisphere. FDR-corrections were performed within each class of measures. Correlations of within-network Fisher Z-transformed correlation coefficients and the mean diffusivity per tract were performed. Whole-brain graph theory measures of cluster coefficient and average path length were inspecting using the resting state data.

RESULTS & CONCLUSION

MCI-related changes in white matter structure were found in the fornix, left parahippocampal cingulum, left retrosplenial cingulum and left subgenual cingulum. Functional connectivity decreases were observed in the MCI group within the DMN-a sub-network, between the hippocampus and sub-areas -a and -c of the DMN, between DMN-c and DMN-a, and, in the right hemisphere only between DMN-c and both the thalamus and limbic-a. No relationships between white matter tract 'integrity' (mean diffusivity) and within sub-network functional connectivity were found. Graph theory revealed that changes in the MCI group was mostly restricted to diminished between-neighbour connections of the hippocampi and of nodes within DMN-a and DMN-b.

Morphological Brain Age Prediction using Multi-View Brain Networks Derived from Cortical Morphology in Healthy and Disordered Participants

Brain development and aging are dynamic processes that unfold over years on multiple levels in both healthy and disordered individuals. Recent studies have revealed a disparity between the chronological brain age and the ‘data-driven’ brain age using functional MRI (fMRI) and diffusion MRI (dMRI). Particularly, predicting the ‘brain age’ from connectomic data might help identify relevant connectional biomarkers of neurological disorders that emerge early or late in the lifespan. While prior brain-age prediction studies have relied exclusively on either structural or functional connectomic data, here we unprecedentedly propose to predict the morphological age of the brain by solely using morphological brain networks (derived from T1-weighted images) in both healthy and disordered populations. Besides, although T1-weighted MRI was widely used for brain age prediction, it was leveraged from an image-based analysis perspective not from a connectomic perspective. Our method includes the following steps: (i) building multi-view morphological brain networks (M-MBN), (ii) feature extraction and selection, (iii) training a machine-learning regression model to predict age from M-MBN data, and (iv) utilizing our model to identify connectional brain features related to age in both autistic and healthy populations. We demonstrate that our method significantly outperforms existing approaches and discovered brain connectional morphological features that fingerprint the age of brain cortical morphology in both autistic and healthy individuals. In particular, we discovered that the connectional cortical thickness best predicts the morphological age of the autistic brain.

Joint Pairing and Structured Mapping of Convolutional Brain Morphological Multiplexes for Early Dementia Diagnosis

Diagnosis of brain dementia, particularly early mild cognitive impairment (eMCI), is critical for early intervention to prevent the onset of Alzheimer's disease, where cognitive decline is severe and irreversible. There is a large body of machine-learning-based research investigating how dementia alters brain connectivity, mainly using structural (derived from diffusion magnetic resonance imaging [MRI]) and functional (derived from resting-state functional MRI) brain connectomic data. However, how early dementia affects cortical brain connections in morphology remains largely unexplored. To fill this gap, we propose a joint morphological brain multiplexes pairing and mapping strategy for eMCI detection, where a brain multiplex not only encodes the relationship in morphology between pairs of brain regions but also a pair of brain morphological networks. Experimental results confirm that the proposed framework outperforms in classification accuracy several state-of-the-art methods. More importantly, we unprecedentedly identified most discriminative brain morphological networks between eMCI and normal control (NC), which included the paired views derived from maximum principal curvature and the sulcal depth for the left hemisphere, and sulcal depth and the average curvature for the right hemisphere. We also identified the most highly correlated morphological brain connections in our cohort, which included the pericalcarine cortex and insula cortex on the maximum principal curvature view, entorhinal cortex and insula cortex on the mean sulcal depth view, and entorhinal cortex and pericalcarine cortex on the mean average curvature view for both hemispheres. These highly correlated morphological connections might serve as biomarkers for eMCI diagnosis.

Unsupervised Manifold Learning Using High-Order Morphological Brain Networks Derived From T1-w MRI for Autism Diagnosis

Brain disorders, such as Autism Spectrum Disorder (ASD), alter brain functional (from fMRI) and structural (from diffusion MRI) connectivities at multiple levels and in varying degrees. While unraveling such alterations have been the focus of a large number of studies, morphological brain connectivity has been out of the research scope. In particular, shape-to-shape relationships across brain regions of interest (ROIs) were rarely investigated. As such, the use of networks based on morphological brain data in neurological disorder diagnosis, while leveraging the advent of machine learning, could complement our knowledge on brain wiring alterations in unprecedented ways. In this paper, we use conventional T1-weighted MRI to define morphological brain networks (MBNs), each quantifying shape relationship between different cortical regions for a specific cortical attribute at both low-order and high-order levels. While typical brain connectomes investigate the relationship between two ROIs, we propose high-order MBN which better captures brain complex interactions by modeling the morphological relationship between pairs of ROIs. For ASD identification, we present a connectomic manifold learning framework, which learns multiple kernels to estimate a similarity measure between ASD and normal controls (NC) connectional features, to perform dimensionality reduction for clustering ASD and NC subjects. We benchmark our ASD identification method against both supervised and unsupervised state-of-the-art methods, while depicting the most discriminative high- and low-order relationships between morphological regions in the left and right hemispheres.

Analysis of Progression Toward Alzheimer's Disease Based on Evolutionary Weighted Random Support Vector Machine Cluster

Alzheimer’s disease (AD) could be described into following four stages: healthy control (HC), early mild cognitive impairment (EMCI), late MCI (LMCI) and AD dementia. The discriminations between different stages of AD are considerably important issues for future pre-dementia treatment. However, it is still challenging to identify LMCI from EMCI because of the subtle changes in imaging which are not noticeable. In addition, there were relatively few studies to make inferences about the brain dynamic changes in the cognitive progression from EMCI to LMCI to AD. Inspired by the above problems, we proposed an advanced approach of evolutionary weighted random support vector machine cluster (EWRSVMC). Where the predictions of numerous weighted SVM classifiers are aggregated for improving the generalization performance. We validated our method in multiple binary classifications using Alzheimer’s Disease Neuroimaging Initiative dataset. As a result, the encouraging accuracy of 90% for EMCI/LMCI and 88.89% for LMCI/AD were achieved respectively, demonstrating the excellent discriminating ability. Furthermore, disease-related brain regions underlying the AD progression could be found out on the basis of the amount of discriminative information. The findings of this study provide considerable insight into the neurophysiological mechanisms in AD development.