Frontiers in Computational Neuroscience最新文献

{"title":"Privacy-preserving dementia classification from EEG via hybrid-fusion EEGNetv4 and federated learning.","authors":"Muhammad Umair, Muhammad Shahbaz Khan, Muhammad Hanif, Wad Ghaban, Ibtehal Nafea, Sultan Noman Qasem, Faisal Saeed","doi":"10.3389/fncom.2025.1617883","DOIUrl":"10.3389/fncom.2025.1617883","url":null,"abstract":"<p><p>As global life expectancy rises, a growing proportion of the population is affected by dementia, particularly Alzheimer's disease (AD) and Frontotemporal dementia (FTD). Electroencephalography (EEG) based diagnosis presents a non-invasive, cost effective alternative for early detection, yet existing methods are challenged by data scarcity, inter-subject variability, and privacy concerns. This study proposes lightweight and privacy-preserving EEG classification framework combining deep learning and Federated Learning (FL). Five convolutional neural networks (EEGNetv1, EEGNetv4, EEGITNet, EEGInception, EEGInceptionERP) have been evaluated on resting-state EEG dataset comprising 88 subjects. EEG signals are preprocessed using band-pass (1-45 Hz) and notch filtering, followed by exponential standardization and 4-second windowing. EEGNetv4 outperformed among other EEG tailored models, and upon utilizing the hybrid fusion techniques it achieves 97.1% accuracy using only 1,609 parameters and less than 1 MB of memory, demonstrating high efficiency. Moreover, FL using FedAvg is implemented across five stratified clients, achieving 96.9% accuracy on the hybrid fused EEGNetV4 model while preserving data privacy. This work establishes a scalable, resource-efficient, and privacy-compliant framework for EEG-based dementia diagnosis, suitable for deployment in real-world clinical and edge-device settings.</p>","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"19 ","pages":"1617883"},"PeriodicalIF":2.3,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12399531/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144992064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Multi-label remote sensing classification with self-supervised gated multi-modal transformers.","authors":"Na Liu, Ye Yuan, Guodong Wu, Sai Zhang, Jie Leng, Lihong Wan","doi":"10.3389/fncom.2025.1665406","DOIUrl":"10.3389/fncom.2025.1665406","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.3389/fncom.2024.1404623.].</p>","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"19 ","pages":"1665406"},"PeriodicalIF":2.3,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12400118/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144991983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Transformer-based multimodal precision intervention model for enhancing diaphragm function in elderly patients.","authors":"Ma Xinli, Zhao Jie, Yan Ming, Zhang Yanping, Li Fan, Jia Jing, Ding Lu","doi":"10.3389/fncom.2025.1615576","DOIUrl":"10.3389/fncom.2025.1615576","url":null,"abstract":"<p><p>Diaphragm dysfunction represents a significant complication in elderly patients undergoing mechanical ventilation, often resulting in extended intensive care stays, unsuccessful weaning attempts, and increased healthcare expenditures. To address the deficiency of precise, real-time decision support in this context, a novel artificial intelligence framework is proposed, integrating imaging, physiological signals, and ventilator parameters. Initially, a hierarchical Transformer encoder is employed to extract modality-specific embeddings, followed by an attention-guided cross-modal fusion module and a temporal network for dynamic trend prediction. The framework was assessed using three public datasets, which are, the MIMIC-IV, eICU, and Chest X-ray. The proposed model achieved the highest accuracy (92.3% on MIMIC-IV, 91.8% on eICU, 92.0% on Chest X-ray) and surpassed all baselines in precision, recall, F1-score, and Matthews correlation coefficient. Additionally, the model's probability estimates were well-calibrated, and its SHAP-based explainability analysis identified ventilator volume and key imaging features as primary predictors. The clinical implications of this study are significant. By providing precise and interpretable predictions, the proposed model has the potential to transform critical care practices by offering a pathway to more effective and personalized interventions for high-risk patients.</p>","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"19 ","pages":"1615576"},"PeriodicalIF":2.3,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12399574/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144992073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Super special relativity.","authors":"Nicholas Jordan Wagter","doi":"10.3389/fncom.2025.1597914","DOIUrl":"10.3389/fncom.2025.1597914","url":null,"abstract":"<p><p>This paper proposes a new theoretical framework for understanding time perception centered on information processing in the brain. We introduce the concept of \"perceptual time\" as distinct from inertial clock time and develop a model relating perceptual time experience to the brain's computational capacity and information processing rate. This framework explains phenomena like time dilation and compression during intense experiences in terms of neural information processing, bridging perceptual time with physical theories of time.</p>","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"19 ","pages":"1597914"},"PeriodicalIF":2.3,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12380679/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144948339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The improved thalamo-cortical spiking network model of deep brain stimulation.","authors":"AmirAli Farokhniaee, Siavash Amiri","doi":"10.3389/fncom.2025.1662598","DOIUrl":"10.3389/fncom.2025.1662598","url":null,"abstract":"","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"19 ","pages":"1662598"},"PeriodicalIF":2.3,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12380790/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144948349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Maximum likelihood estimation of spatially dependent interactions in large populations of cortical neurons.","authors":"Camille Godin, J P Thivierge","doi":"10.3389/fncom.2025.1639829","DOIUrl":"10.3389/fncom.2025.1639829","url":null,"abstract":"<p><p>Understanding how functional connectivity between cortical neurons varies with spatial distance is crucial for characterizing large-scale neural dynamics. However, inferring these spatial patterns is challenging when spike trains are collected from large populations of neurons. Here, we present a maximum likelihood estimation (MLE) framework to quantify distance-dependent functional interactions directly from observed spiking activity. We validate this method using both synthetic spike trains generated from a linear Poisson model and biologically realistic simulations performed with Izhikevich neurons. We then apply the approach to large-scale electrophysiological recordings from V1 cortical neurons. Our results show that the proposed MLE approach robustly captures spatial decay in functional connectivity, providing insights into the spatial structure of population-level neural interactions.</p>","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"19 ","pages":"1639829"},"PeriodicalIF":2.3,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12380633/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144948372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Editorial: Cardio-respiratory-brain integrative physiology: interactions, mechanisms, and methods for assessment.","authors":"Tijana Bojić, Luca Faes, Steffen Schulz, Tomislav Stankovski","doi":"10.3389/fncom.2025.1664088","DOIUrl":"10.3389/fncom.2025.1664088","url":null,"abstract":"","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"19 ","pages":"1664088"},"PeriodicalIF":2.3,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12378168/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144948380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Editorial: Interdisciplinary synergies in neuroinformatics, cognitive computing, and computational neuroscience.","authors":"Nabamita Deb, Zardad Khan, Muhammad Sulaiman, Maharani Abu Bakar","doi":"10.3389/fncom.2025.1657167","DOIUrl":"10.3389/fncom.2025.1657167","url":null,"abstract":"","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"19 ","pages":"1657167"},"PeriodicalIF":2.3,"publicationDate":"2025-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12364901/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144948344","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dentate gyrus granule cell activation following extracellular electrical stimulation: a multi-scale computational model to guide hippocampal neurostimulation strategies.","authors":"Shayan Farzad, Tianyuan Wei, Jean-Marie C Bouteiller, Gianluca Lazzi","doi":"10.3389/fncom.2025.1638002","DOIUrl":"10.3389/fncom.2025.1638002","url":null,"abstract":"<p><strong>Introduction: </strong>The effectiveness of neural interfacing devices depends on the anatomical and physiological properties of the target region. Multielectrode arrays, used for neural recording and stimulation, are influenced by electrode placement and stimulation parameters, which critically impact tissue response. This study presents a multiscale computational model that predicts responses of neurons in the hippocampus-a key brain structure primarily involved in memory formation, especially the conversion of short-term memories into long-term storage-to extracellular electrical stimulation, providing insights into the effects of electrode positioning and stimulation strategies on neuronal response.</p><p><strong>Methods: </strong>We modeled the rat hippocampus with highly detailed axonal projections, integrating the Admittance Method to model propagation of the electric field in the tissue with the NEURON simulation platform. The resulting model simulates electric fields generated by virtual electrodes in the perforant path of entorhinal cortical (EC) axons projecting to the dentate gyrus (DG) and predicts DG granule cell activation via synaptic inputs.</p><p><strong>Results: </strong>We determined stimulation amplitude thresholds required for granule cell activation at different electrode placements along the perforant path. Membrane potential changes during synaptic activation were validated against experimental recordings. Additionally, we assessed the effects of bipolar electrode placements and stimulation amplitudes on direct and indirect activation.</p><p><strong>Conclusion: </strong>Stimulation amplitudes above 750 μA consistently activate DG granule cells. Lower stimulation amplitudes are required for axonal activation and downstream synaptic transmission when electrodes are placed in the molecular layer, infra-pyramidal region, and DG crest.</p><p><strong>Significance: </strong>The study and underlying methodology provide useful insights to guide the stimulation protocol required to activate DG granule cells following the stimulation of EC axons; the complete realistic 3D model presented constitutes an invaluable tool to strengthen our understanding of hippocampal response to electrical stimulation and guide the development and placement of prospective stimulation devices and strategies.</p>","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"19 ","pages":"1638002"},"PeriodicalIF":2.3,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12354454/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144872268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring subthreshold processing for next-generation TinyAI.","authors":"Farid Nakhle, Antoine H Harfouche, Hani Karam, Vasileios Tserolas","doi":"10.3389/fncom.2025.1638782","DOIUrl":"10.3389/fncom.2025.1638782","url":null,"abstract":"<p><p>The energy demands of modern AI systems have reached unprecedented levels, driven by the rapid scaling of deep learning models, including large language models, and the inefficiencies of current computational architectures. In contrast, biological neural systems operate with remarkable energy efficiency, achieving complex computations while consuming orders of magnitude less power. A key mechanism enabling this efficiency is subthreshold processing, where neurons perform computations through graded, continuous signals below the spiking threshold, reducing energy costs. Despite its significance in biological systems, subthreshold processing remains largely overlooked in AI design. This perspective explores how principles of subthreshold dynamics can inspire the design of novel AI architectures and computational methods as a step toward advancing TinyAI. We propose pathways such as algorithmic analogs of subthreshold integration, including graded activation functions, dendritic-inspired hierarchical processing, and hybrid analog-digital systems to emulate the energy-efficient operations of biological neurons. We further explore neuromorphic and compute-in-memory hardware platforms that could support these operations, and propose a design stack aligned with the efficiency and adaptability of the brain. By integrating subthreshold dynamics into AI architecture, this work provides a roadmap toward sustainable, responsive, and accessible intelligence for resource-constrained environments.</p>","PeriodicalId":12363,"journal":{"name":"Frontiers in Computational Neuroscience","volume":"19 ","pages":"1638782"},"PeriodicalIF":2.3,"publicationDate":"2025-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12351320/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144872269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}