Predicting brain structural network using functional connectivity

Uncovering the non-trivial brain structure-function relationship is fundamentally important for revealing organizational principles of human brain. However, it is challenging to infer a reliable relationship between individual brain structure and function, e.g., the relations between individual brain structural connectivity (SC) and functional connectivity (FC). Brain structure-function displays a distributed and heterogeneous pattern, that is, many functional relationships arise from non-overlapping sets of anatomical connections. This complex relation can be interwoven with widely existed individual structural and functional variations. Motivated by the advances of generative adversarial network (GAN) and graph convolutional network (GCN) in the deep learning field, in this work, we proposed a multi-GCN based GAN (MGCN-GAN) to infer individual SC based on corresponding FC by automatically learning the complex associations between individual brain structural and functional networks. The generator of MGCN-GAN is composed of multiple multi-layer GCNs which are designed to model complex indirect connections in brain network. The discriminator of MGCN-GAN is a single multi-layer GCN which aims to distinguish the predicted SC from real SC. To overcome the inherent unstable behavior of GAN, we designed a new structure-preserving (SP) loss function to guide the generator to learn the intrinsic SC patterns more effectively. Using Human Connectome Project (HCP) dataset and Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset as test beds, our MGCN-GAN model can generate reliable individual SC from FC. This result implies that there may exist a common regulation between specific brain structural and functional architectures across different individuals.

D-STGCNT: A Dense Spatio-Temporal Graph Conv-GRU Network based on transformer for assessment of patient physical rehabilitation

This paper tackles the challenge of automatically assessing physical rehabilitation exercises for patients who perform the exercises without clinician supervision. The objective is to provide a quality score to ensure correct performance and achieve desired results. To achieve this goal, a new graph-based model, the Dense Spatio-Temporal Graph Conv-GRU Network with Transformer, is introduced. This model combines a modified version of STGCN and transformer architectures for efficient handling of spatio-temporal data. The key idea is to consider skeleton data respecting its non-linear structure as a graph and detecting joints playing the main role in each rehabilitation exercise. Dense connections and GRU mechanisms are used to rapidly process large 3D skeleton inputs and effectively model temporal dynamics. The transformer encoder's attention mechanism focuses on relevant parts of the input sequence, making it useful for evaluating rehabilitation exercises. The evaluation of our proposed approach on the KIMORE and UI-PRMD datasets highlighted its potential, surpassing state-of-the-art methods in terms of accuracy and computational time. This resulted in faster and more accurate learning and assessment of rehabilitation exercises. Additionally, our model provides valuable feedback through qualitative illustrations, effectively highlighting the significance of joints in specific exercises.

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.

Multiview hyperedge-aware hypergraph embedding learning for multisite, multiatlas fMRI based functional connectivity network analysis

Recently, functional magnetic resonance imaging (fMRI) based functional connectivity network (FCN) analysis via graph convolutional networks (GCNs) has shown promise for automated diagnosis of brain diseases by regarding the FCNs as irregular graph-structured data. However, multiview information and site influences of the FCNs in a multisite, multiatlas fMRI scenario have been understudied. In this paper, we propose a Class-consistency and Site-independence Multiview Hyperedge-Aware HyperGraph Embedding Learning (CcSi-MHAHGEL) framework to integrate FCNs constructed on multiple brain atlases in a multisite fMRI study. Specifically, for each subject, we first model brain network as a hypergraph for every brain atlas to characterize high-order relations among multiple vertexes, and then introduce a multiview hyperedge-aware hypergraph convolutional network (HGCN) to extract a multiatlas-based FCN embedding where hyperedge weights are adaptively learned rather than employing the fixed weights precalculated in traditional HGCNs. In addition, we formulate two modules to jointly learn the multiatlas-based FCN embeddings by considering the between-subject associations across classes and sites, respectively, i.e., a class-consistency module to encourage both compactness within every class and separation between classes for promoting discrimination in the embedding space, and a site-independence module to minimize the site dependence of the embeddings for mitigating undesired site influences due to differences in scanning platforms and/or protocols at multiple sites. Finally, the multiatlas-based FCN embeddings are fed into a few fully connected layers followed by the soft-max classifier for diagnosis decision. Extensive experiments on the ABIDE demonstrate the effectiveness of our method for autism spectrum disorder (ASD) identification. Furthermore, our method is interpretable by revealing ASD-relevant brain regions that are biologically significant.

Beyond homophily in spatial-temporal traffic flow forecasting

Traffic flow forecasting is a crucial yet complex task due to the intricate spatial-temporal correlations arising from road interactions. Recent methods model these interactions using message-passing Graph Convolution Networks (GCNs), which work for homophily graphs where connected nodes primarily exhibit close observations. However, relying solely on homophily graphs presents inherent limitations in traffic modeling, as road interactions can yield not only close but also distant observations over time, revealing diverse and dynamic node-wise correlations. We designate this phenomenon as homophily-heterophily dynamics, which has been largely overlooked in previous works. To address this gap, we propose a homophily-heterophily Spatial-Temporal Graph Convolution Network (H2STGCN) that exploits both homophily and heterophily components in the spatial-temporal domain. Specifically, we first adopt time-related node attributes to disentangle the diverse and dynamic node-wise relations across time, thereby obtaining homophily and heterophily Spatial-Temporal Graphs (STGs), which provide comprehensive insights into road interactions. Subsequently, we construct dual information propagation branches, each outfitted with a specific type of STG, to exploit multiple ranges of spatial-temporal correlations from distinct perspectives through dilated causal spatial-temporal graph convolution operations on STGs. Additionally, we introduce a Graph Collaborative Learning Module (GCLM) to capture the complementary information of these two branches via mutual information transfer. Experimental evaluation on four real-world traffic datasets reveals that our model outperforms state-of-the-art methods.

A transformer model for learning spatiotemporal contextual representation in fMRI data

Representation learning is a core component in data-driven modeling of various complex phenomena. Learning a contextually informative representation can especially benefit the analysis of fMRI data because of the complexities and dynamic dependencies present in such datasets. In this work, we propose a framework based on transformer models to learn an embedding of the fMRI data by taking the spatiotemporal contextual information in the data into account. This approach takes the multivariate BOLD time series of the regions of the brain as well as their functional connectivity network simultaneously as the input to create a set of meaningful features that can in turn be used in various downstream tasks such as classification, feature extraction, and statistical analysis. The proposed spatiotemporal framework uses the attention mechanism as well as the graph convolution neural network to jointly inject the contextual information regarding the dynamics in time series data and their connectivity into the representation. We demonstrate the benefits of this framework by applying it to two resting-state fMRI datasets, and provide further discussion on various aspects and advantages of it over a number of other commonly adopted architectures.

FIT-graph: A multi-grained evolutionary graph based framework for disease diagnosis

Early assessment, with the help of machine learning methods, can aid clinicians in optimizing the diagnosis and treatment process, allowing patients to receive critical treatment time. Due to the advantages of effective information organization and interpretable reasoning, knowledge graph-based methods have become one of the most widely used machine learning algorithms for this task. However, due to a lack of effective organization and use of multi-granularity and temporal information, current knowledge graph-based approaches are hard to fully and comprehensively exploit the information contained in medical records, restricting their capacity to make superior quality diagnoses. To address these challenges, we examine and study disease diagnosis applications in-depth, and propose a novel disease diagnosis framework named FIT-Graph. With novel medical multi-grained evolutionary graphs, FIT-Graph efficiently organizes the extracted information from various granularities and time stages, maximizing the retention of valuable information for disease inference and ensuring the comprehensiveness and validity of the final disease inference. We compare FIT-Graph with two real-world clinical datasets from cardiology and respiratory departments with the baseline. The experimental results show that its effect is better than the baseline model, and the baseline performance of the task is improved by about 5% in multiple indices.

Graph convolution networks model identifies and quantifies gene and cancer specific transcriptome signatures of cancer driver events

BACKGROUND

The identification and drug targeting of cancer causing (driver) genetic alterations has seen immense improvement in recent years, with many new targeted therapies developed. However, identifying, prioritizing, and treating genetic alterations is insufficient for most cancer patients. Current clinical practices rely mainly on DNA level mutational analyses, which in many cases fail to identify treatable driver events. Arguably, signal strength may determine cell fate more than the mutational status that initiated it. The use of transcriptomics, a complex and highly informative representation of cellular and tumor state, had been suggested to enhance diagnostics and treatment successes. A gene-expression based model trained over known genetic alterations could improve identification and quantification of cancer related biological aberrations' signal strength.

METHODS

We present STAMP (Signatures in Transcriptome Associated with Mutated Protein), a Graph Convolution Networks (GCN) based framework for the identification of gene expression signatures related to cancer driver events. STAMP was trained to identify the p53 dysfunction of cancer samples from gene expression, utilizing comprehensive curated graph structures of gene interactions. Predictions were modified for generating a quantitative score to rank the severity of a driver event in each sample. STAMP was then extended to almost 300 tumor type-specific predictive models for important cancer genes/pathways, by training to identify well-established driver events' annotations from the literature.

RESULTS

STAMP achieved very high AUC on unseen data across several tumor types and on an independent cohort. The framework was validated on p53 related genetic and clinical characteristics, including the effect of Variants of Unknown Significance, and showed strong correlation with protein function. For genes and tumor types where targeted therapy is available, STAMP showed correlation with drugs sensitivity (IC50) in an independent cell line database. It managed to stratify drug effect on samples with similar mutational profiles. STAMP was validated for drug-response prediction in clinical patients' cohorts, improving over a state-of-the-art method and suggesting potential biomarkers for cancer treatments.

CONCLUSIONS

The STAMP models provide a learning framework that successfully identifies and quantifies driver events' signal strength, showing utility in portraying the molecular landscape of tumors based on transcriptomics. Importantly, STAMP manifested the ability to improve targeted therapy selection and hence can contribute to better treatment.