arXiv subjects

Vince D. Calhoun

Publications and source records attributed to Vince D. Calhoun.

At least 37 records · Page 2Linked to original sources

arXiv2026

Complex-valued Phase Synchrony Reveals Directional Coupling in FMRI and Tracks Medication Effects

Understanding interactions in complex systems requires capturing the relative timing of coupling, not only its strength. Phase synchronization captures this timing, yet most methods either reduce the phase to its cosine or collapse it into scalar indices such as the phase-locking value, discarding relative timing. We propose a complex-valued phase synchrony (CVPS) framework that estimates phase with an adaptive Gabor wavelet and preserves both cosine and sine components. Simulations confirm that CVPS recovers true phase offsets and tracks non-stationary dynamics more faithfully than Hilbert-based methods. Because antipsychotics are known to modulate the timing of cortical interactions, they provide a rigorous context to evaluate whether CVPS can capture such pharmacological effects. CVPS further reveals cortical neuro-hemodynamic drivers, with occipital-to-parietal and prefrontal-to-striatal lead--lag flows consistent with known receptor targets, confirming its ability to capture pharmacological timing. CVPS, therefore, offers a robust, generalizable framework for detecting relative timing in complex systems such as the brain.

q-bio.NC↗

arXiv2026

Warp Quantification Analysis: A Framework For Path-based Signal Alignment Metrics

Dynamic time warping (DTW) is widely used to align time series evolving on mismatched timescales, yet most applications reduce alignment to a scalar distance. We introduce warp quantification analysis (WQA), a framework that derives interpretable geometric and structural descriptors from DTW paths. Controlled simulations showed that each metric selectively tracked its intended driver with minimal crosstalk. Applied to large-scale fMRI, WQA revealed distinct network signatures and complementary associations with schizophrenia negative symptom severity, capturing clinically meaningful variability beyond DTW distance. WQA transforms DTW from a single-score method into a family of alignment descriptors, offering a principled and generalizable extension for richer characterization of temporal coupling across domains where nonlinear normalization is essential.

cs.CE↗

arXiv2025

Deep Deterministic Nonlinear ICA via Total Correlation Minimization with Matrix-Based Entropy Functional

Blind source separation, particularly through independent component analysis (ICA), is widely utilized across various signal processing domains for disentangling underlying components from observed mixed signals, owing to its fully data-driven nature that minimizes reliance on prior assumptions. However, conventional ICA methods rely on an assumption of linear mixing, limiting their ability to capture complex nonlinear relationships and to maintain robustness in noisy environments. In this work, we present deep deterministic nonlinear independent component analysis (DDICA), a novel deep neural network-based framework designed to address these limitations. DDICA leverages a matrix-based entropy function to directly optimize the independence criterion via stochastic gradient descent, bypassing the need for variational approximations or adversarial schemes. This results in a streamlined training process and improved resilience to noise. We validated the effectiveness and generalizability of DDICA across a range of applications, including simulated signal mixtures, hyperspectral image unmixing, modeling of primary visual receptive fields, and resting-state functional magnetic resonance imaging (fMRI) data analysis. Experimental results demonstrate that DDICA effectively separates independent components with high accuracy across a range of applications. These findings suggest that DDICA offers a robust and versatile solution for blind source separation in diverse signal processing tasks.

stat.ME↗

arXiv2025

MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding

Decoding visual experiences from fMRI offers a powerful avenue to understand human perception and develop advanced brain-computer interfaces. However, current progress often prioritizes maximizing reconstruction fidelity while overlooking interpretability, an essential aspect for deriving neuroscientific insight. To address this gap, we propose MoRE-Brain, a neuro-inspired framework designed for high-fidelity, adaptable, and interpretable visual reconstruction. MoRE-Brain uniquely employs a hierarchical Mixture-of-Experts architecture where distinct experts process fMRI signals from functionally related voxel groups, mimicking specialized brain networks. The experts are first trained to encode fMRI into the frozen CLIP space. A finetuned diffusion model then synthesizes images, guided by expert outputs through a novel dual-stage routing mechanism that dynamically weighs expert contributions across the diffusion process. MoRE-Brain offers three main advancements: First, it introduces a novel Mixture-of-Experts architecture grounded in brain network principles for neuro-decoding. Second, it achieves efficient cross-subject generalization by sharing core expert networks while adapting only subject-specific routers. Third, it provides enhanced mechanistic insight, as the explicit routing reveals precisely how different modeled brain regions shape the semantic and spatial attributes of the reconstructed image. Extensive experiments validate MoRE-Brain's high reconstruction fidelity, with bottleneck analyses further demonstrating its effective utilization of fMRI signals, distinguishing genuine neural decoding from over-reliance on generative priors. Consequently, MoRE-Brain marks a substantial advance towards more generalizable and interpretable fMRI-based visual decoding. Code will be publicly available soon: https://github.com/yuxiangwei0808/MoRE-Brain.

cs.LG↗

arXiv2025

BrainIB++: Leveraging Graph Neural Networks and Information Bottleneck for Functional Brain Biomarkers in Schizophrenia

The development of diagnostic models is gaining traction in the field of psychiatric disorders. Recently, machine learning classifiers based on resting-state functional magnetic resonance imaging (rs-fMRI) have been developed to identify brain biomarkers that differentiate psychiatric disorders from healthy controls. However, conventional machine learning-based diagnostic models often depend on extensive feature engineering, which introduces bias through manual intervention. While deep learning models are expected to operate without manual involvement, their lack of interpretability poses significant challenges in obtaining explainable and reliable brain biomarkers to support diagnostic decisions, ultimately limiting their clinical applicability. In this study, we introduce an end-to-end innovative graph neural network framework named BrainIB++, which applies the information bottleneck (IB) principle to identify the most informative data-driven brain regions as subgraphs during model training for interpretation. We evaluate the performance of our model against nine established brain network classification methods across three multi-cohort schizophrenia datasets. It consistently demonstrates superior diagnostic accuracy and exhibits generalizability to unseen data. Furthermore, the subgraphs identified by our model also correspond with established clinical biomarkers in schizophrenia, particularly emphasizing abnormalities in the visual, sensorimotor, and higher cognition brain functional network. This alignment enhances the model's interpretability and underscores its relevance for real-world diagnostic applications.

cs.LG↗

arXiv2025

Efficient Brain Network Estimation with Sparse ICA in Non-Human Primate Neuroimaging

Independent component analysis (ICA) is widely used to separate mixed signals and recover statistically independent components. However, in non-human primate neuroimaging studies, most ICA-recovered spatial maps are often dense. To extract the most relevant brain activation patterns, post-hoc thresholding is typically applied-though this approach is often imprecise and arbitrary. To address this limitation, we employed the Sparse ICA method, which enforces both sparsity and statistical independence, allowing it to extract the most relevant activation maps without requiring additional post-processing. Simulation experiments demonstrate that Sparse ICA performs competitively against 11 classical linear ICA methods. We further applied Sparse ICA to real non-human primate neuroimaging data, identifying several independent component networks spanning different brain networks. These spatial maps revealed clearly defined activation areas, providing further evidence that Sparse ICA is effective and reliable in practical applications.

stat.AP↗

arXiv2025

A Generative Imputation Method for Multimodal Alzheimer's Disease Diagnosis

Multimodal data analysis can lead to more accurate diagnoses of brain disorders due to the complementary information that each modality adds. However, a major challenge of using multimodal datasets in the neuroimaging field is incomplete data, where some of the modalities are missing for certain subjects. Hence, effective strategies are needed for completing the data. Traditional methods, such as subsampling or zero-filling, may reduce the accuracy of predictions or introduce unintended biases. In contrast, advanced methods such as generative models have emerged as promising solutions without these limitations. In this study, we proposed a generative adversarial network method designed to reconstruct missing modalities from existing ones while preserving the disease patterns. We used T1-weighted structural magnetic resonance imaging and functional network connectivity as two modalities. Our findings showed a 9% improvement in the classification accuracy for Alzheimer's disease versus cognitive normal groups when using our generative imputation method compared to the traditional approaches.

eess.IV↗

arXiv2025

Functional Correspondences in the Human and Marmoset Visual Cortex During Movie Watching: Insights from Correlation, Redundancy, and Synergy

The world of beauty is deeply connected to the visual cortex, as perception often begins with vision in both humans and marmosets. In this study, to investigate their functional correspondences, we used 13 healthy human volunteers (9 males and 4 females, aged 22-56 years) and 8 common marmosets (6 males and 2 females, aged 20-42 months). We then measured pairwise and beyond-pairwise correlations, redundancy, and synergy in movie-driven fMRI data across species. First, we consistently observed a high degree of functional similarity in visual processing within and between species, suggesting that integrative processing mechanisms are preserved in both humans and marmosets, despite potential differences in their specific activity patterns. Second, we found that the strongest functional correspondences during movie watching occurred between the human peri-entorhinal and entorhinal cortex (PeEc) and the occipitotemporal high-level visual regions in the marmoset, reflecting a synergistic functional relationship. This suggests that these regions share complementary and integrated patterns of information processing across species. Third, redundancy measures maintained stable high-order hubs, indicating a steady core of shared information processing, while synergy measures revealed a dynamic shift from low- to high-level visual regions as interaction increased, reflecting adaptive integration. This highlights distinct patterns of information processing across the visual hierarchy. Ultimately, our results reveal the marmoset as a compelling model for investigating visual perception, distinguished by its remarkable functional parallels to the human visual cortex.

q-bio.NC↗

arXiv2025

4D Multimodal Co-attention Fusion Network with Latent Contrastive Alignment for Alzheimer's Diagnosis

Multimodal neuroimaging provides complementary structural and functional insights into both human brain organization and disease-related dynamics. Recent studies demonstrate enhanced diagnostic sensitivity for Alzheimer's disease (AD) through synergistic integration of neuroimaging data (e.g., sMRI, fMRI) with behavioral cognitive scores tabular data biomarkers. However, the intrinsic heterogeneity across modalities (e.g., 4D spatiotemporal fMRI dynamics vs. 3D anatomical sMRI structure) presents critical challenges for discriminative feature fusion. To bridge this gap, we propose M2M-AlignNet: a geometry-aware multimodal co-attention network with latent alignment for early AD diagnosis using sMRI and fMRI. At the core of our approach is a multi-patch-to-multi-patch (M2M) contrastive loss function that quantifies and reduces representational discrepancies via geometry-weighted patch correspondence, explicitly aligning fMRI components across brain regions with their sMRI structural substrates without one-to-one constraints. Additionally, we propose a latent-as-query co-attention module to autonomously discover fusion patterns, circumventing modality prioritization biases while minimizing feature redundancy. We conduct extensive experiments to confirm the effectiveness of our method and highlight the correspondance between fMRI and sMRI as AD biomarkers.

cs.MM↗

arXiv2025

Integrated Brain Connectivity Analysis with fMRI, DTI, and sMRI Powered by Interpretable Graph Neural Networks

Multimodal neuroimaging modeling has becomes a widely used approach but confronts considerable challenges due to heterogeneity, which encompasses variability in data types, scales, and formats across modalities. This variability necessitates the deployment of advanced computational methods to integrate and interpret these diverse datasets within a cohesive analytical framework. In our research, we amalgamate functional magnetic resonance imaging, diffusion tensor imaging, and structural MRI into a cohesive framework. This integration capitalizes on the unique strengths of each modality and their inherent interconnections, aiming for a comprehensive understanding of the brain's connectivity and anatomical characteristics. Utilizing the Glasser atlas for parcellation, we integrate imaging derived features from various modalities: functional connectivity from fMRI, structural connectivity from DTI, and anatomical features from sMRI within consistent regions. Our approach incorporates a masking strategy to differentially weight neural connections, thereby facilitating a holistic amalgamation of multimodal imaging data. This technique enhances interpretability at connectivity level, transcending traditional analyses centered on singular regional attributes. The model is applied to the Human Connectome Project's Development study to elucidate the associations between multimodal imaging and cognitive functions throughout youth. The analysis demonstrates improved predictive accuracy and uncovers crucial anatomical features and essential neural connections, deepening our understanding of brain structure and function.

q-bio.NC↗

arXiv2025

An interpretable generative multimodal neuroimaging-genomics framework for decoding Alzheimer's disease

\textbf{Objective:} Alzheimer's disease (AD) is the most prevalent form of dementia worldwide, encompassing a prodromal stage known as Mild Cognitive Impairment (MCI), where patients may either progress to AD or remain stable. The objective of the work was to capture structural and functional modulations of brain structure and function relying on multimodal MRI data and Single Nucleotide Polymorphisms, also in case of missing views, with the twofold goal of classifying AD patients versus healthy controls and detecting MCI converters. % in two distinct tasks, dealing with also missing data.\\ \textbf{Approach:} We propose a multimodal DL-based classification framework where a generative module employing Cycle Generative Adversarial Networks was introduced in the latent space for imputing missing data (a common issue of multimodal approaches). Explainable AI method was then used to extract input features' relevance allowing for post-hoc validation and enhancing the interpretability of the learned representations. \textbf{Main results:} Experimental results on two tasks, AD detection and MCI conversion, showed that our framework reached competitive performance in the state-of-the-art with an accuracy of $0.926\pm0.02$ and $0.711\pm0.01$ in the two tasks, respectively. The interpretability analysis revealed gray matter modulations in cortical and subcortical brain areas typically associated with AD. Moreover, impairments in sensory-motor and visual resting state networks along the disease continuum, as well as genetic mutations defining biological processes linked to endocytosis, amyloid-beta, and cholesterol, were identified. \textbf{Significance:} Our integrative and interpretable DL approach shows promising performance for AD detection and MCI prediction while shedding light on important biological insights.

q-bio.QM↗

arXiv2025

A Privacy-Preserving Domain Adversarial Federated learning for multi-site brain functional connectivity analysis

Resting-state functional magnetic resonance imaging (rs-fMRI) and its derived functional connectivity networks (FCNs) have become critical for understanding neurological disorders. However, collaborative analyses and the generalizability of models still face significant challenges due to privacy regulations and the non-IID (non-independent and identically distributed) property of multiple data sources. To mitigate these difficulties, we propose Domain Adversarial Federated Learning (DAFed), a novel federated deep learning framework specifically designed for non-IID fMRI data analysis in multi-site settings. DAFed addresses these challenges through feature disentanglement, decomposing the latent feature space into domain-invariant and domain-specific components, to ensure robust global learning while preserving local data specificity. Furthermore, adversarial training facilitates effective knowledge transfer between labeled and unlabeled datasets, while a contrastive learning module enhances the global representation of domain-invariant features. We evaluated DAFed on the diagnosis of ASD and further validated its generalizability in the classification of AD, demonstrating its superior classification accuracy compared to state-of-the-art methods. Additionally, an enhanced Score-CAM module identifies key brain regions and functional connectivity significantly associated with ASD and MCI, respectively, uncovering shared neurobiological patterns across sites. These findings highlight the potential of DAFed to advance multi-site collaborative research in neuroimaging while protecting data confidentiality.

cs.LG↗

arXiv2025

A Deep Spatio-Temporal Architecture for Dynamic Effective Connectivity Network Analysis Based on Dynamic Causal Discovery

Dynamic effective connectivity networks (dECNs) reveal the changing directed brain activity and the dynamic causal influences among brain regions, which facilitate the identification of individual differences and enhance the understanding of human brain. Although the existing causal discovery methods have shown promising results in effective connectivity network analysis, they often overlook the dynamics of causality, in addition to the incorporation of spatio-temporal information in brain activity data. To address these issues, we propose a deep spatio-temporal fusion architecture, which employs a dynamic causal deep encoder to incorporate spatio-temporal information into dynamic causality modeling, and a dynamic causal deep decoder to verify the discovered causality. The effectiveness of the proposed method is first illustrated with simulated data. Then, experimental results from Philadelphia Neurodevelopmental Cohort (PNC) demonstrate the superiority of the proposed method in inferring dECNs, which reveal the dynamic evolution of directed flow between brain regions. The analysis shows the difference of dECNs between young adults and children. Specifically, the directed brain functional networks transit from fluctuating undifferentiated systems to more stable specialized networks as one grows. This observation provides further evidence on the modularization and adaptation of brain networks during development, leading to higher cognitive abilities observed in young adults.

cs.LG↗

arXiv2025

Deep P-Spline: Theory, Fast Tuning, and Application

Deep neural networks (DNNs) have been widely applied to solve real-world regression problems. However, selecting optimal network structures remains a significant challenge. This study addresses this issue by linking neuron selection in DNNs to knot placement in basis expansion techniques. We introduce a difference penalty that automates knot selection, thereby simplifying the complexities of neuron selection. We name this method Deep P-Spline (DPS). This approach extends the class of models considered in conventional DNN modeling and forms the basis for a latent variable modeling framework using the Expectation-Conditional Maximization (ECM) algorithm for efficient network structure tuning with theoretical guarantees. From a nonparametric regression perspective, DPS is proven to overcome the curse of dimensionality, enabling the effective handling of datasets with a large number of input variable, a scenario where conventional nonparametric regression methods typically underperform. This capability motivates the application of the proposed methodology to computer experiments and image data analyses, where the associated regression problems involving numerous inputs are common. Numerical results validate the effectiveness of the model, underscoring its potential for advanced nonlinear regression tasks.

stat.CO↗

arXiv2024

Generalized Dynamic Brain Functional Connectivity Based on Random Convolutions

Dynamic functional connectivity (DFC) analysis has been widely applied to functional magnetic resonance imaging (fMRI) data to reveal time-varying dynamic changes of brain states. The sliding window method is by far the most popular DFC analysis method due to its simplicity. However, the sliding window method comes with some assumptions, namely the typically approach uses a single window which captures dynamics only within a specific frequency range. In this study, we propose a generalized approach to dynamics via a multi-dimensional random convolution (RandCon) DFC method that is able to effectively capture time-varying DFC at arbitrary time scales by extracting different local features from fMRI time series using a number of multi-dimensional random convolution kernels without the need for learning kernel weights. Compared to a standard sliding window method, multiplication of temporal derivatives (MTD) and phase synchrony methods, RandCon with the smallest kernel size (3 time points) showed notable improvements in performance on simulated data, particularly in terms of DFC temporal and spatial estimation in very short window/kernel size under different noise levels. Results from real fMRI data indicated that RandCon was more sensitive to gender differences than competing methods. Furthermore, we show that the sliding window method can be considered a special case of the proposed multi-dimensional convolution framework. The proposed method is simple and efficient significantly broadens the scope of dynamic functional connectivity research and offer theoretical and practical potential.

cs.LG↗

arXiv2024

Correlation of Correlation Networks: High-Order Interactions in the Topology of Brain Networks

To understand collective network behavior in the complex human brain, pairwise correlation networks alone are insufficient for capturing the high-order interactions that extend beyond pairwise interactions and play a crucial role in brain network dynamics. These interactions often reveal intricate relationships among multiple brain networks, significantly influencing cognitive processes. In this study, we explored the correlation of correlation networks and topological network analysis with resting-state fMRI to gain deeper insights into these higher-order interactions and their impact on the topology of brain networks, ultimately enhancing our understanding of brain function. We observed that the correlation of correlation networks highlighted network connections while preserving the topological structure of correlation networks. Our findings suggested that the correlation of correlation networks surpassed traditional correlation networks, showcasing considerable potential for applications in various areas of network science. Moreover, after applying topological network analysis to the correlation of correlation networks, we observed that some high-order interaction hubs predominantly occurred in primary and high-level cognitive areas, such as the visual and fronto-parietal regions. These high-order hubs played a crucial role in information integration within the human brain.

q-bio.NC↗

arXiv2024

The Dynamics of Triple Interactions in Resting fMRI: Insights into Psychotic Disorders

The human brain dynamically integrated and configured information to adapt to the environment. To capture these changes over time, dynamic second-order functional connectivity was typically used to capture transient brain patterns. However, dynamic second-order functional connectivity typically ignored interactions beyond pairwise relationships. To address this limitation, we utilized dynamic triple interactions to investigate multiscale network interactions in the brain. In this study, we evaluated a resting-state fMRI dataset that included individuals with psychotic disorders (PD). We first estimated dynamic triple interactions using resting-state fMRI. After clustering, we estimated cohort-specific and cohort-common states for controls (CN), schizophrenia (SZ), and schizoaffective disorder (SAD). From the cohort-specific states, we observed significant triple interactions, particularly among visual, subcortical, and somatomotor networks, as well as temporal and higher cognitive networks in SZ. In SAD, key interactions involved temporal networks in the initial state and somatomotor networks in subsequent states. From the cohort-common states, we observed that high-cognitive networks were primarily involved in SZ and SAD compared to CN. Furthermore, the most significant differences between SZ and SAD also existed in high-cognitive networks. In summary, we studied PD using dynamic triple interaction, the first time such an approach has been used to study PD. Our findings highlighted the significant potential of dynamic high-order functional connectivity, paving the way for new avenues in the study of the healthy and disordered human brain.

q-bio.NC↗

arXiv2024

Generative forecasting of brain activity enhances Alzheimer's classification and interpretation

Understanding the relationship between cognition and intrinsic brain activity through purely data-driven approaches remains a significant challenge in neuroscience. Resting-state functional magnetic resonance imaging (rs-fMRI) offers a non-invasive method to monitor regional neural activity, providing a rich and complex spatiotemporal data structure. Deep learning has shown promise in capturing these intricate representations. However, the limited availability of large datasets, especially for disease-specific groups such as Alzheimer's Disease (AD), constrains the generalizability of deep learning models. In this study, we focus on multivariate time series forecasting of independent component networks derived from rs-fMRI as a form of data augmentation, using both a conventional LSTM-based model and the novel Transformer-based BrainLM model. We assess their utility in AD classification, demonstrating how generative forecasting enhances classification performance. Post-hoc interpretation of BrainLM reveals class-specific brain network sensitivities associated with AD.

cs.LG↗