Search Results (1,054)

Deep learning models have achieved high accuracy in forecasting problems, but at the cost of large computational energy demand. Brain-inspired spiking neural networks (SNNs) offer a promising, low-power alternative, yet their adoption for time-series forecasting has been limited by information loss from binary spikes and degraded performance in deeper networks. This paper proposes a fully spiking framework that bridges this gap by improving both the encoding and propagation of information in SNNs. The framework introduces a hybrid Delta-Rate encoding mechanism that captures both abrupt changes and gradual trends in time-series data, and a Mem-Spike mechanism that transmits analog membrane potential values to preserve fine-grained information between spiking layers. We further employ residual membrane connections to maintain signal flow in deep spiking networks. Using two public energy load datasets, our enhanced SNNs consistently outperform conventional spiking models, improving prediction accuracy by up to 61.6% and mitigating degradation in multi-layer networks. Notably, it narrows the gap to the selected deep learning baseline (LSTM), achieving comparable accuracy in some settings while requiring only about 10% of the estimated inference energy of that baseline under a common operation-level model. These results show that, within the empirical scope considered here, enhanced conventional SNNs can improve time-series forecasting accuracy while retaining favorable estimated efficiency. Full article

Background: Glioblastoma is an extremely aggressive brain tumor that diffusely infiltrates white matter and alters large-scale brain connectivity. Most prognostic models focus on localized tumor features and clinical variables, overlooking broader effects on the brain’s structural connectome. This study addressed this limitation by integrating graph-theoretical analysis of preoperative diffusion tensor imaging (DTI)-derived structural connectomes with machine learning (ML) to improve prediction of overall survival (OS) in newly diagnosed glioblastoma. Methods: Preoperative DTI data from 871 glioblastoma patients from the UPenn-GBM and UCSF-PDGM cohorts were processed to construct whole-brain structural connectomes weighted by tract count and quantitative anisotropy (QA). Global and nodal graph-theoretical network metrics were extracted and combined with demographic and clinical information. Ten ML models were trained and validated on 784 patients (90% of the cohort). The three best-performing algorithms were tested on a held-out cohort of 87 patients (10%). Results: Random forest, adaptive boosting, and KStar showed the strongest validation performance. In held-out internal testing, random forest models using degree and QA-weighted strength achieved accuracies of 0.862 and 0.874, with AUROCs of 0.929 and 0.909, for predicting OS beyond one year. Strength and clustering coefficient were key predictors, with over two-thirds of significant nodes localized in the temporal lobe, particularly the parahippocampal, and superior, middle, and inferior temporal gyri. Conclusions: Graph-theoretical quantification of structural brain network disruption combined with ML allows accurate prediction of OS in glioblastoma. These results support a network-based conceptualization of the disease and indicate that connectome-derived metrics may complement established prognostic frameworks. Full article

Background/Objectives: Autophagy is an evolutionarily conserved degradation and recycling pathway through which cells deliver cytoplasmic components, including toxic or damaged proteins and organelles, to lysosomes for clearance. In neurons, which are largely post-mitotic, degradative pathways are essential to prevent the accumulation of cellular waste and to maintain nutrient and energy homeostasis. Increasing evidence suggests that autophagy plays a critical role during early brain development, when neuronal circuits are established, synaptic connections are refined, and activity-dependent mechanisms shape network architecture. However, the developmental regulation of autophagy-related genes and the composition of the autophagic machinery at synapses remain poorly understood. This study aimed to characterize the maturation-dependent dynamics of autophagy–lysosomal genes and to investigate the synaptic autophagy-associated proteome during cortical development. Methods: Genome-wide transcriptomic analyses were performed in the cortical brain region across developmental stages to assess changes in the expression of autophagy–lysosomal genes. In parallel, synaptosomes were isolated and subjected to proteomic analysis to identify autophagy-related proteins associated with synaptic compartments. Results: Transcriptomic profiling revealed stage-dependent regulation of autophagy–lysosomal genes during cortical maturation. Proteomic analysis of synaptosomes identified multiple autophagy-associated proteins enriched at synaptic sites, suggesting that components of the autophagic machinery are present at synapses and may participate in synaptic remodeling and function during key phases of neuronal network formation. Conclusions: These findings provide new insights into the developmental regulation of autophagy in the brain and highlight the potential contribution of synaptic autophagy to neuronal circuit maturation. Understanding these mechanisms may help identify novel therapeutic targets for neurological disorders associated with impaired synaptic and cellular homeostasis. Full article

Background/Objectives: Tobacco use is a leading cause of preventable death worldwide and is linked to major health and economic burden. Many smokers attempt to quit, yet long-term success rates with current medicines and counseling are still modest. Long-term nicotine exposure distorts brain systems involved in reward, craving, and self-control. These changes weaken inhibitory control and strengthen responses to smoking cues, which increases the risk of relapse. Transcranial magnetic stimulation (TMS) is a non-invasive technique that delivers magnetic pulses to specific cortical regions, most commonly the dorsolateral prefrontal cortex, to influence neural activity. This narrative review explored how transcranial magnetic stimulation may aid smoking cessation by acting on neural circuits linked to nicotine dependence. Methods: Five major databases were searched for studies published between 2015 and 2026. After removal of duplicates and screening, a total of 34 studies were included in this narrative synthesis. Randomized controlled trials, clinical studies, and neuroimaging investigations involving adults with nicotine dependence were included. A thematic narrative method was employed to synthesize findings due to the differences in study designs, protocols, and outcome measures. Results: TMS has been shown to attenuate cravings, decrease daily cigarette consumption, and decrease nicotine dependence in various studies. Several trials reported higher abstinence rates with active stimulation compared with sham treatment. Meta-analytic findings indicate stronger effects with 10 Hz stimulation and treatment courses of 20 sessions or more. Neuroimaging studies report changes in functional connectivity within reward, executive control, and salience networks, suggesting partial restoration of disrupted circuits. Treatment response varies according to age, educational level, baseline dependence, and stimulation parameters. Conclusions: These findings support transcranial magnetic stimulation as a promising brain-based approach for smoking cessation, while further well-designed trials with longer follow-up are still needed. Full article

Objective: The classic excitation/inhibition dichotomy may be insufficient to describe rTMS mechanisms in the aging brain. This study investigated immediate whole-brain resting-state functional connectivity effects of 10 Hz (high-frequency) and 1 Hz (low-frequency) rTMS over the left dorsolateral prefrontal cortex (DLPFC) in healthy older adults. Methods: Thirty healthy older adults (aged 60–75 years) participated in a randomized, single-blind, crossover study, and underwent 20-min 10 Hz and 1 Hz rTMS in separate visits. A 106-channel fNIRS system was used to record resting-state activity before and immediately after each intervention. Functional connectivity was analyzed at the channel, region-of-interest (ROI) and network summary levels, including graph-theoretic metrics and distance-stratified connectivity summaries. Results: At the network summary level, 10 Hz stimulation was associated with relatively more positive changes in global topology and spatially distributed connectivity summaries, whereas 1 Hz stimulation showed the opposite overall trend. In the graph-theoretic analyses, stimulation frequency × time interaction effects were observed for global efficiency, local efficiency, clustering coefficient, and mean node strength. At the edge level, only a small number of effects survived FDR correction, and the broader connection-wise patterns were therefore interpreted as exploratory. Uncorrected analyses suggested widespread enhancement after 10 Hz stimulation and widespread reduction after 1 Hz stimulation, together with localized paradoxical effects, including selective decreases after 10 Hz and selective increases after 1 Hz (e.g., bilateral primary motor cortex connectivity). Conclusions: These findings suggest that 10 Hz and 1 Hz rTMS over the left DLPFC are associated with different patterns of immediate whole-brain network reconfiguration in healthy older adults. The presence of localized paradoxical effects further suggests that rTMS responses in the aging brain may involve more complex forms of reorganization than a simple excitatory/inhibitory dichotomy would predict. Significance: The present study provides preliminary support for a network-level perspective on neuromodulation in older adults and highlights the value of whole-brain fNIRS for characterizing distributed responses to rTMS. Larger, sham-controlled, behavior-linked, and longitudinal studies are needed to determine the robustness and functional significance of these effects. Full article

The increasing prevalence of Autism Spectrum Disorder (ASD) has intensified research efforts aimed at clarifying its neurobiological underpinnings. Electroencephalography (EEG) has enabled the identification of functional alterations in neuronal networks, contributing to the characterization of ASD-related brain dynamics and supporting the investigation of links between neural processes and behavioral impairments. In recent years, Artificial Intelligence (AI) methods have been increasingly applied to EEG analysis, allowing the extraction of complex, high-dimensional features. However, the limited interpretability of many AI-based models represents a major barrier to their clinical translation. To address this issue, Explainable Artificial Intelligence (XAI) approaches have emerged as promising tools to enhance model transparency and neurobiological interpretability. This systematic review examined studies explicitly applying XAI techniques to EEG or event-related potential data from individuals with ASD. A comprehensive literature search was conducted across multiple electronic databases up to November 2025. Studies were included if they involved ASD populations, electrophysiological data, and AI-based analytical approaches with explicit explainability components. Due to substantial methodological heterogeneity, a qualitative narrative synthesis was performed. Eleven studies met the inclusion criteria. Overall, included articles highlighted partially overlapping electrophysiological patterns involving spectral alterations, functional connectivity, and network organization; however, some studies also revealed marked heterogeneity in study design and limited clinical characterization. Consequently, they should be interpreted with caution, as the field remains at a preliminary stage. This review outlines current trends, methodological limitations, and key gaps in XAI-driven EEG research in ASD, and discusses future directions toward clinically meaningful and interpretable neurophysiological biomarkers. The review protocol was registered in PROSPERO (CRD420251231630). Full article

Background: The recognition of autism spectrum disorder (ASD) has been a challenge due to the heterogeneity in symptoms and complex variations in brain function. Resting-state functional magnetic resonance imaging (rs-fMRI) has become instrumental in studying these disorders by accessing underlying abnormal neural activity and connectivity. Recently, deep learning approaches have shifted the analysis of brain networks by capturing spatiotemporal information from fMRI sequences. Nonetheless, most existing studies are limited by relying on a single representational scale, typically restricting analysis to either voxel-level spatiotemporal patterns or static connectivity matrices. Additionally, the dynamic reconfiguration of functional coupling and its variations across different anatomical parcellations are often ignored, which obscures neurobiologically meaningful dynamics. Methods: In this regard, we propose a multi-atlas dynamic connectivity transformer fused with 4D spatiotemporal modeling for ASD recognition (MADCT-4D). Specifically, the framework comprises two complementary branches. The 4D spatiotemporal branch encodes raw rs-fMRI volumes to learn hierarchical representations of evolving neural activity, while the dynamic-connectivity branch models time-resolved functional connectivity sequences constructed from multiple atlases, enabling the network to capture dynamic reconfiguration at the connectome level under different parcellation granularities. Moreover, we perform late fusion by combining the branch-specific decision scores with a learnable gate, allowing the model to adaptively weight voxel-level dynamics and multi-atlas connectivity evidence for each subject. Results: Extensive experiments on the publicly available ABIDE dataset demonstrate that the proposed method achieves 90.2% accuracy for ASD recognition, outperforming multiple competitive baselines. Conclusions: The proposed framework yields interpretable biomarkers based on learned dynamic connectivity patterns that are consistent with altered functional coupling in ASD. Full article

Continuous representations in brain navigation system are manifested as spatially structured patterns of population activity, such as a single-peaked bump moving along a ring manifold in head-direction system and hexagonal lattice patterns underlying spatial representation in grid-cell systems. These phenomena are commonly modelled within the framework of continuous attractor networks (neural dynamical field), yet the mechanisms by which activation-function nonlinearities interact with connectivity structure to determine pattern selection and dynamics remain incompletely understood. This paper separately analyses the interactions between non-resonant and resonant modes using a multiscale unfolding approach. We show that, when the critical modes satisfy a resonance condition, the quadratic nonlinearity of the activation function induces a three-mode coupling that fundamentally alters the structure of the amplitude equations and becomes the dominant mechanism governing spatial pattern selection. Building on this analysis, we introduce a weak asymmetric component in the connectivity and analytically derive the resulting pattern drift velocity, which is subsequently confirmed by numerical simulations. Finally, we apply these dynamical mechanisms to input-driven scenarios, illustrating that similar dynamical mechanisms can account for activity-bump tracking in head-direction models and lattice translations in grid-cell models. Overall, this work provides an analytically tractable framework for studying pattern dynamics in neural field models relevant to spatial representations, and may inform biomimetic approaches to spatial representation and navigation. Full article

Visual mental imagery, the ability to generate and manipulate internal visual experiences without direct sensory input, links perception with memory, planning, and higher cognition. In this targeted narrative review, we synthesize neuroimaging and lesion evidence on the brain basis of visual imagery, with a focus on neuroradiological correlates of the ventral and dorsal visual pathways. Unlike prior cognitive neuroscience reviews that primarily emphasize functional mechanisms, this review is neuroradiology-oriented and integrates lesion patterns and white-matter disconnection to support clinico-radiological interpretation of imagery complaints. Using a dual-stream framework, we contrast ventral occipito-temporal systems that preferentially support object imagery (appearance-based features such as form, faces/objects, and color, with texture remaining under-studied) with dorsal occipito-parietal systems that preferentially support spatial imagery (relations, transformations, and navigation). Across studies, imagery recruitment is strongly task- and stage-dependent: ventral regions are most often engaged during object-focused imagery, whereas parietal regions are prominent during spatial transformation tasks, with evidence for interaction between pathways when demands require both content and spatial operations. Structural and clinico-radiological findings indicate that imagery impairment can arise from focal posterior lesions and posterior neurodegenerative syndromes but also from network disruption affecting long-range connections that support top-down access to posterior representations. Finally, emerging work on aphantasia and hyperphantasia supports a network-level view in which imagery vividness relates to how effectively higher-order systems engage visual representations. We conclude that standardized, stream-sensitive tasks and multimodal approaches combining functional and structural imaging with lesion-based evidence are key to discovering clinically actionable biomarkers of imagery dysfunction. Full article

Background: Against the backdrop of global population aging, understanding the mechanisms of age-related cognitive decline has become crucial for improving the health and quality of life in older adults. Methods: This study employed a multimodal approach to investigate the neural modulations induced by a motor cognitive dual task and their relationship with age-related decline. By integrating behavioral assessments, electroencephalography (EEG), and body composition analysis, we comprehensively evaluated performance and neural correlates in 19 younger and 18 older adults. Specifically, EEG analyses focused on comparing pre-task and post-task resting-state recordings to investigate the immediate impact of a single acute cognitive-motor dual-task session on neural oscillations and brain network organization. Results: Key findings include: (1) older adults exhibited significantly inferior performance in task accuracy, reaction time, and composite performance score compared to younger adults (p < 0.001); (2) neural oscillatory analysis of resting-state data revealed a localized increase in gamma-band power at posterior-temporal sites (PO4/T6) in older adults following the dual-task, while younger adults exhibited widespread multi-band (delta to beta) power modulation across frontal, central, and temporal regions in younger adults; (3) brain network analysis demonstrated synergistic enhancement of multi-band (Theta, Alpha, Beta, Gamma) connectivity and optimized topological organization in younger adults post-task, contrasting with network rigidity and localized compensatory patterns in older adults; (4) correlation analyses indicated significant associations between dual-task performance and MoCA-B scores in older adults (r = 0.861, p < 0.001). Conclusions: This study innovatively elucidates the neurophysiological characteristics of brain aging. The motor-cognitive dual-task paradigm proves to be a sensitive tool for capturing early cognitive changes, holding significant promise for clinical screening. Full article

Motor recovery after stroke, spinal cord injury, or traumatic brain injury reflects relearning rather than simple restitution, as surviving circuits retain plastic potential that can be re-engaged through temporally precise stimulation. This review synthesizes convergent findings demonstrating that Hebbian and spike-timing-dependent mechanisms govern reorganization across cortical, striatal, and spinal levels. Leveraging these timing rules to shape excitability during receptive network states enables durable changes in connectivity and behavior. This effect depends on temporal precision, physiological state, and reinforcement—not stimulus intensity alone—within plasticity windows regulated by metaplastic mechanisms that determine whether Hebbian processes are expressed. Together, these principles define a translational framework for neurorehabilitation, emphasizing biomarker-guided, adaptive, and scalable strategies aligned with intrinsic rules of experience-dependent reorganization. Full article

The development of the human brain starts with the orchestrated expression of our genes during embryogenesis. Non-protein-coding DNA sequences (gene promoters and enhancers) dynamically interact to form a three-dimensional (3D) network, orchestrating gene expression. We discuss novel perspectives on how DNA sequence variants within regulatory DNA, identified by whole-genome sequencing (WGS), contribute to the development of neurodevelopmental disorders (NDDs), including autism spectrum disorders (ASDs). We discuss two recent models explaining the evolution of a subset of regulatory sequences, Human Accelerated DNA Regions (HARs), proposed to be involved in the evolution of uniquely human brain features through their participation in the 3D interactions network. We connect this with the recent proposal that rare, recessive inherited sequence variants within HARs, interacting with distant target genes in neural cells, represent risk factors for the development of ASDs. The SOX2 transcription factor, whose heterozygous mutation causes NDDs, shapes the noncoding-DNA interaction network in neural cells, and binds DNA together with FOS, whose recognition sequence is enriched within HARs carrying human-specific substitutions modulating enhancer activity. SOX2 also binds regulatory regions (including HARs) carrying ASD-associated mutations. We highlight research directions based on these findings, which will hopefully improve our understanding of the connection between SOX2-dependent gene regulatory networks, NDDs, and brain evolution. Full article

Background/Objectives: Young adulthood is a critical developmental period during which lifestyle behaviors may shape intrinsic brain network dynamics that support cognition. This pilot longitudinal intervention study examined whether variability in physical activity and sedentary behavior during an 8-week exercise and/or cognitive intervention protocol was associated with changes in intrinsic brain dynamics and cognitive and mood outcomes in undergraduate young adults. Methods: Participants (n = 32) completed resting-state functional magnetic resonance imaging (rs-fMRI) at baseline (T1) and post-intervention (T2). Dynamic functional network connectivity (dFNC) was estimated from 53 intrinsic connectivity networks derived using spatially constrained independent component analysis (ICA). Ten recurring dynamic connectivity states were identified and individualized using constrained dynamic double functional independent primitives (c-ddFIPs). State occupancy and dynamic convergence and divergence metrics were computed to characterize network flexibility. Results: Greater moderate-to-vigorous physical activity was modestly but consistently associated with increased occupancy of integrative higher-order states, particularly States 6 and 7, and reduced occupancy of more segregated configurations. More physically active individuals also demonstrated greater divergence between integrative and low-engagement states, whereas greater sedentary time corresponded to increased similarity among segregated configurations. Working memory performance showed parallel associations with more integrative and better-differentiated dynamic patterns. Conclusions: These findings suggest that dynamic functional network reconfiguration may represent a neurobiological mechanism linking lifestyle behaviors and cognitive health in young adulthood. Furthermore, they highlight the translational promise of engagement-driven, low-burden programs for college-aged young adults, showing that even modest variability in habitual physical activity corresponds to greater engagement and differentiation of integrative connectivity states linked to executive and broader cognitive functions. Full article

Background: The generation of synthetic CT images from MRI scans represents a crucial step toward enabling MRI-only clinical workflows and supporting multi-modal integration in medical imaging, particularly in radiotherapy planning. Despite significant advancements in deep learning models, many current methods still struggle to reconstruct high-density structures, especially bone, and exhibit limited accuracy in density values. This shortcoming is largely attributed to the passage of excessive or noisy features through skip connections in the traditional U-Net architecture, which degrade the quality of information transmitted to the decoder, negatively impacting the clarity of anatomical boundaries and the pixel-wise accuracy of the resulting synthetic image. Methods: In this work, we propose an enhanced 3D U-Net architecture in which the Convolutional Block Attention Module (CBAM) is systematically integrated within each skip connection. The CBAM sequentially applies channel and spatial attention to adaptively reweight encoder feature maps before fusion with the decoder, thereby emphasizing anatomically relevant structures while suppressing irrelevant feature propagation. The model was trained and evaluated on the SynthRAD2023 (Task 1—Brain) MRI–CT dataset. To rigorously assess the contribution of the attention mechanism, a dedicated ablation study was conducted comparing three variants: 3D U-Net with Squeeze-and-Excitation (SE), Coordinate Attention (CA), and the proposed CBAM module. Performance was evaluated using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Normalized Cross-Correlation (NCC). Results: The ablation study demonstrated that the CBAM-enhanced model consistently outperformed both SE- and CA-based variants across all quantitative metrics. Specifically, the proposed method achieved an MAE of $38.2\pm 5.4$ HU and an RMSE of $51.0\pm 12.0$ HU, representing the lowest reconstruction errors among the evaluated models. In addition, it obtained a PSNR of $29.45\pm 2.10$ dB, SSIM of $0.940\pm 0.031$, and NCC of $0.967\pm 0.015$, indicating superior structural preservation and strong voxel-wise correspondence between synthesized and reference CT volumes. These results confirm that the sequential integration of channel and spatial attention provides a statistically and practically meaningful improvement for high-fidelity MRI-to-CT synthesis. Conclusions: Generating high-resolution brain CT images from brain MRI scans using a 3D U-Net network enhanced with a CBAM module can contribute to supporting the clinical workflow by providing additional diagnostic data without the need for extra radiological examinations, thereby enhancing diagnostic efficiency and reducing radiation exposure. This technique helps reduce patient exposure to radiation and improves accessibility in resource-limited settings. Furthermore, this method is valuable for retrospective studies, surgical planning, and image-guided therapy, where complete multi-modal data may not always be available. Full article

Functional near-infrared spectroscopy (fNIRS) is a valuable non-invasive modality for brain-computer interfaces (BCIs), but robust signal interpretation is challenged by the significant temporal variability of the hemodynamic response. Standard linear methods, such as Pearson correlation, often fail to capture functional connectivity when signals exhibit temporal jitter. This study validates an unsupervised Dynamic Time Warping (DTW) clustering framework to robustly identify motor networks from fNIRS data by accommodating non-linear temporal shifts. We analyzed a public fNIRS dataset (N = 30) across right-hand (RHT), left-hand (LHT), and foot tapping (FT) tasks. A robust preprocessing pipeline was implemented, including Wavelet Motion Correction and Common Average Referencing (CAR) to remove artifacts and global systemic noise. The core method involved computing Z-score normalized DTW distance matrices, followed by hierarchical clustering. To validate the framework, we benchmarked it against a standard Pearson Correlation method. Results show that the unsupervised DTW framework achieved a network identification accuracy of 53.17%, significantly outperforming the standard Pearson correlation benchmark (48.06%) with a statistically significant difference (p < 0.05). The framework successfully detected distinct, somatotopically correct modulations: superior-medial activation during foot tapping and lateralized activation during hand tapping. These findings demonstrate that unsupervised DTW clustering is a robust, data-driven approach that outperforms conventional linear methods in capturing functional networks during motor tasks, showing significant potential for next-generation asynchronous BCIs. Full article