Front Comput Neurosci [JOURNAL]
Sun
200 papers
Arbor-TVB: a novel multi-scale co-simulation framework with a case study on neural-level seizure generation and whole-brain propagation.
Hater T, Courson J, Lu H … +2 more , Diaz-Pier S, Manos T
Front Comput Neurosci · 2025 · PMID 41704907 · Full text
Computational neuroscience has traditionally focused on isolated scales, limiting understanding of brain function across multiple levels. While microscopic models capture biophysical details of neurons, macroscopic model...
Computational neuroscience has traditionally focused on isolated scales, limiting understanding of brain function across multiple levels. While microscopic models capture biophysical details of neurons, macroscopic models describe large-scale network dynamics. Integrating these scales, however, remains a significant challenge. In this study, we present a novel co-simulation framework that bridges these levels by integrating the neural simulator Arbor with The Virtual Brain (TVB) platform. Arbor enables detailed simulations from single-compartment neurons to populations of such cells, while TVB models whole-brain dynamics based on anatomical features and the mean neural activity of a brain region. By linking these simulators for the first time, we provide an example of how to model and investigate the onset of seizures in specific areas and their propagation to the whole brain. This framework employs an MPI intercommunicator for real-time bidirectional interaction, translating between discrete spikes from Arbor and continuous TVB activity. Its fully modular design enables independent model selection for each scale, requiring minimal effort to translate activity across simulators. The novel Arbor-TVB co-simulator allows replacement of TVB nodes with biologically realistic neuron populations, offering insights into seizure propagation and potential intervention strategies. The integration of Arbor and TVB marks a significant advancement in multi-scale modeling, providing a comprehensive computational framework for studying neural disorders and optimizing treatments.
Symmetry breaking and avalanche shapes in modular neural networks.
de Candia A, Conte D, Golpayegan HA … +1 more , Scarpetta S
Front Comput Neurosci · 2026 · PMID 41696533 · Full text
Modularity is as a key characteristic of structural and functional brain networks across species and spatial scales. We investigate the stochastic Wilson-Cowan model on a modular network in which synaptic strengths diffe...
Modularity is as a key characteristic of structural and functional brain networks across species and spatial scales. We investigate the stochastic Wilson-Cowan model on a modular network in which synaptic strengths differ between intra-module and inter-module connections. The system exhibits a rich phase diagram comprising symmetric (with low and high activity) and "broken symmetry" phases. Symmetric phases are characterized by the same low or high activity in all the modules, while the broken symmetry phases are characterized by a high activity in a subset of the modules and low activity in the remaining ones. There are two lines of critical points, the first between the low activity symmetric phase and the high activity symmetric phase, and the second between the low activity symmetric phase and a broken symmetry phase with one active module. At those lines the system shows a critical behavior, with power law distributions in the avalanches. Avalanche shapes differ systematically along the two lines: they are symmetric or right-skewed at the transition with the symmetric phase, but become left-skewed over intermediate durations along critical line with the broken symmetry phase. These results provide a theoretical framework that accounts for both symmetric and left-skewed neural avalanche shapes observed experimentally, linking modular organization to critical brain dynamics.
AI-driven audience clustering in sport media: a human-computer interaction approach using 'CoPE-DEC'.
Jang YS
Front Comput Neurosci · 2026 · PMID 41696532 · Full text
This study investigates the characteristics and underlying patterns of sports media audiences from a human-computer interaction (HCI) perspective using artificial intelligence-based deep learning analysis, with the aim o...
This study investigates the characteristics and underlying patterns of sports media audiences from a human-computer interaction (HCI) perspective using artificial intelligence-based deep learning analysis, with the aim of providing foundational data for the sports media industry. To this end, a novel unsupervised clustering framework, the Column-conditioned Prototype-Enhanced Deep Embedded Clustering (CoPE-DEC) technique, was employed to model and analyze multidimensional viewer experience data derived from sports media consumption contexts. The analysis identified three distinct audience clusters with differentiated behavioral, attitudinal, and value-oriented characteristics. The first cluster, labeled "Sports Value Orientation," was characterized by enhanced concentration during sports viewing, promotion of cooperative skills, motivation for health and exercise, vicarious satisfaction, aesthetic appreciation of sports movements, and admiration for athletes' professional and economic success. The second cluster, termed "Sports Consumption Culture Orientation," exhibited a strong preference for sports broadcasts over entertainment content, frequent consumption of online sports media, active engagement with preferred sports, participation in sports-related tourism and activities, acquisition of sports skills through media, and consumption of sports-related products. The third cluster, identified as "Sports Attitude Orientation," reflected predominantly social and emotional dimensions of sports viewing, including improved social adaptation, relationship formation, group cohesion, stress relief, psychological stabilization, healthy competitive attitudes, and enhanced overall wellbeing. These findings demonstrate that AI-driven deep learning approaches, particularly the CoPE-DEC framework, are effective in uncovering latent audience typologies and preference structures in sports media consumption environments. By integrating HCI principles with advanced clustering techniques, this study offers a methodological contribution to audience analysis research and provides practical implications for audience segmentation, personalized content design, and strategic decision-making in the sports media industry. Future research is encouraged to extend this approach by incorporating diverse AI methodologies and multimodal data sources to further advance interdisciplinary insights at the intersection of HCI, artificial intelligence, and sports media studies.
MS-DASPNet: Multiple Sclerosis lesion segmentation from brain MRI using dual attention and spatial pyramid pooling with transfer learning.
Jain S, Rajpal N, Soni PK
Front Comput Neurosci · 2025 · PMID 41694140 · Full text
Accurate detection and segmentation of multiple sclerosis (MS) lesions in brain Magnetic Resonance Imaging (MRI) is a challenging task due to their small size, irregular shape, and variability in different imaging modali...
Accurate detection and segmentation of multiple sclerosis (MS) lesions in brain Magnetic Resonance Imaging (MRI) is a challenging task due to their small size, irregular shape, and variability in different imaging modalities. Precise segmentation of MS lesions from brain MRI is vital for early diagnosis, disease progression monitoring, and treatment planning. We introduce MS-DASPNet, a Dual Attention Guided Deep Neural Network specifically designed to address the challenges of MS lesion detection, including small lesion sizes, low contrast, and heterogeneous appearance. MS-DASPNet employs a VGG-16-based encoder, an Atrous Spatial Pyramid Pooling (ASPP) bottleneck for multi-scale context learning, and dual attention modules in each skip connection to simultaneously refine spatial details and enhance channel-wise feature representation. Evaluations on four publicly available datasets, namely ISBI-2015, Mendeley, MICCAI-2016, and MICCAI-2021, demonstrate that MS-DASPNet achieves superior Precision, Dice, Sensitivity, and Jaccard scores compared to state-of-the-art methods. MS-DASPNet attains a Dice score of 0.8736 on the MICCAI-2016 dataset and 0.8706 on the MICCAI-2021 dataset, both outperforming existing segmentation techniques, highlighting its robustness and effectiveness in accurate MS lesion segmentation.
An entropic explanation of insistence on sameness in autism.
Śliwiński P
Front Comput Neurosci · 2025 · PMID 41675406 · Full text
PURPOSE: An information theory-based framework is proposed in attempt to explain as an instance of a general behavior pattern in which an individual tries to reduce surprise and uncertainty. It offers a new definition o...
PURPOSE: An information theory-based framework is proposed in attempt to explain as an instance of a general behavior pattern in which an individual tries to reduce surprise and uncertainty. It offers a new definition of autism as . METHODS: An analogy between and of the is observed and examined for a set of assumptions that describe cognitive limitations of a person with autism. The metric is given by the formula () = (|)+(|), where represents sequences of random stimuli, is a memory that stores and retrieves them, and where (·|·) denotes their interpreted as and , respectively. RESULTS: It is first inferred that to minimize the metric an individual can learn about (and store that knowledge in ) or can restrict to the already known . Then, it is concluded that is a manifestation of the latter. Moreover, it is shown that the proposed framework: (1) Helps to quantify the concepts of or . (2) Leads to a list of guidelines for learning therapies and daily care routines, and allows them to be defined as optimization algorithms and implemented as programs for . (3) Can be validated with the help of a -like approach that requires no experiments involving individuals with autism. CONCLUSION: The framework-if positively validated-will provide advantages of both theoretical and practical importance: it explains the insistent on sameness as a consequence of cognitive restrictions and offers formal foundations and design guidelines for therapies aimed at improving of individuals with autism in .
Measurement effects on critical scaling in neural systems.
Li MS, Liu B, van Antwerp KW … +2 more , Abdelaleem E, Sederberg AJ
Front Comput Neurosci · 2025 · PMID 41658372 · Full text
The recently developed phenomenological renormalization group (pRG) analysis has uncovered scale-free properties in large-scale neural population recordings across recording modalities, including extracellular electrophy...
The recently developed phenomenological renormalization group (pRG) analysis has uncovered scale-free properties in large-scale neural population recordings across recording modalities, including extracellular electrophysiology and calcium imaging. The convergence of these properties across the datasets hints at universal neural behavior. Yet, it is unknown how differences in temporal resolution and measurement details affect pRG scaling. Here, we use a network model known to produce scaling under pRG analysis as a testbed to assess how recording and analysis choices shape inferred scaling exponents. We show that scaling properties depend on the choices of temporal binning, measurement nonlinearities, and deconvolution, and that the quality of scaling for cluster covariance eigenvalues is particularly sensitive to measurement effects. Moreover, all scaling exponents shift substantially with these transformations, even when the underlying neural dynamics are identical. Together, these results show how experimental choices can change pRG scaling and provide a framework for separating scaling driven by neural dynamics from that introduced by the recording method.
Causal links between serotonin dynamics and cued fear learning: evidence from experimental studies.
Badripour A, Kim T
Front Comput Neurosci · 2026 · PMID 41657916 · Full text
Serotonin is thought to regulate emotional learning and memory, but there remains much to be explored regarding its causal role in cued fear conditioning and extinction (CFC-E). Recent recording of dorsal raphe nucleus...
Serotonin is thought to regulate emotional learning and memory, but there remains much to be explored regarding its causal role in cued fear conditioning and extinction (CFC-E). Recent recording of dorsal raphe nucleus serotonin neuronal activity during CFC-E paradigm showed that the time course of serotonin level includes both rapid responses to conditioned and unconditioned stimuli and a slowly accumulating component that spans inter-trial intervals and reverses during extinction. By reviewing the studies that directly link the fear expression during CFC-E to the acute or chronic perturbations of serotonin dynamics at the organism level or within specific brain areas via pharmacological, genetic, and projection-specific manipulations, we argue that theoretical models defining the causal role of serotonin must incorporate continuous-time serotonin dynamics.
Towards robust probabilistic maps in Deep Brain Stimulation: exploring the impact of patient number, stimulation counts, and statistical approaches.
Bucciarelli V, Vogel D, Wårdell K … +6 more , Coste J, Blomstedt P, Lemaire JJ, Guzman R, Hemm S, Nordin T
Front Comput Neurosci · 2025 · PMID 41647526 · Full text
INTRODUCTION: Probabilistic Stimulation Maps (PSMs) are increasingly employed to identify brain regions associated with optimal therapeutic outcomes in Deep Brain Stimulation (DBS). However, their reliability and general...
INTRODUCTION: Probabilistic Stimulation Maps (PSMs) are increasingly employed to identify brain regions associated with optimal therapeutic outcomes in Deep Brain Stimulation (DBS). However, their reliability and generalizability are challenged by the limited size of most patient cohorts and the inherent variability introduced by different statistical methods and input data configurations. This study aimed to investigate the geometrical variability of Probabilistic Sweet Spots (PSS) as a function of both the number of patients (nPat) and the number of stimulations per patient (nStim), and to model a stability boundary defining the minimum data requirements for obtaining geometrically stable PSS. METHODS: Three statistical approaches-Bayesian -test, Wilcoxon test with False Discovery Rate (FDR) correction, and Wilcoxon test with nonparametric permutation correction-were applied to two patient cohorts: a primary cohort of 36 patients undergoing DBS for Parkinson's Disease (PD), and a secondary cohort of 61 patients treated for Essential Tremor (ET), used to assess generalizability. Stimulation test data was collected intra-operatively for the first cohort and post-operatively for the second one. Geometric stability was evaluated based on variability in PSS volume extent and centroid location. RESULTS: The analysis revealed a non-linear trade-off between nPat and nStim to yield stable PSS. A stability boundary was defined, representing the minimum combinations of nPat-nStim required for anatomically robust PSS. Among the tested methods, the Bayesian -test achieved stability with smaller sample sizes (∼15 patients) and demonstrated a consistent performance across both cohorts. In contrast, the Wilcoxon-based methods showed variable behavior between cohorts, which differed in symptom type and testing phase (intra-operative testing vs. post-operative screening). DISCUSSION: The proposed PSS stability boundary provides a practical reference for designing DBS studies and stimulation screening protocols aimed at probabilistic mapping. The Bayesian -test emerged as a reliable method across both cohorts, supporting its potential in studies with limited sample sizes and scenarios where the method needs to be readily generalized to varying symptoms. These findings underscore the importance of considering both cohort size and stimulation count in probabilistic DBS mapping and call for further investigation into method-specific sensitivities to clinical and procedural factors.
F-CommNet: Fourier-Fractional neural networks with Lyapunov stability guarantees for hallucination-resistant community detection.
Qu D, Ma Y
Front Comput Neurosci · 2025 · PMID 41647525 · Full text
Community detection is a crucial task in network research, applicable to social systems, biology, cybersecurity, and knowledge graphs. Recent advancements in graph neural networks (GNNs) have exhibited significant repres...
Community detection is a crucial task in network research, applicable to social systems, biology, cybersecurity, and knowledge graphs. Recent advancements in graph neural networks (GNNs) have exhibited significant representational capability; yet, they frequently experience instability and erroneous clustering, often referred to as "hallucinations." These artifacts stem from sensitivity to high-frequency eigenmodes, over-parameterization, and noise amplification, undermining the robustness of learned communities. To mitigate these constraints, we present F-CommNet, a Fourier-Fractional neural framework that incorporates fractional-order dynamics, spectrum filtering, and Lyapunov-based stability analysis. The fractional operator implements long-memory dampening that mitigates oscillations, whereas Fourier spectral projections selectively attenuate eigenmodes susceptible to hallucination. Theoretical analysis delineates certain stability criteria under Lipschitz non-linearities and constrained disturbances, resulting in a demonstrable expansion of the Lyapunov margin. Experimental validation on synthetic and actual networks indicates that F-CommNet reliably diminishes hallucination indices, enhances stability margins, and produces interpretable communities in comparison to integer-order GNN baselines. This study integrates fractional calculus, spectral graph theory, and neural network dynamics, providing a systematic method for hallucination-resistant community discovery.
OASIS-SB: a sex-balanced, distribution-preserving, synthetic phenotypic dataset for bias-resilient clinical prediction.
Dhariwal N
Front Comput Neurosci · 2025 · PMID 41625991 · Full text
Abstract loading — click title to view on PubMed.
Dynamic mode decomposition of resting-state fMRI revealing abnormal brain region features in schizophrenia.
Wang Y, Wang Y, Xu X … +1 more , Pan X
Front Comput Neurosci · 2025 · PMID 41613385 · Full text
Extracting features from abnormal brain regions in schizophrenia patients' brain images holds significant importance for aiding diagnosis. However, existing methods remained limited in simultaneously capturing spatiotemp...
Extracting features from abnormal brain regions in schizophrenia patients' brain images holds significant importance for aiding diagnosis. However, existing methods remained limited in simultaneously capturing spatiotemporal information. Dynamic mode decomposition (DMD) effectively extracts spatiotemporal features from dynamic systems, making it suitable for time-series signals such as functional magnetic resonance imaging (fMRI) and electrocorticography (ECoG). This study utilized resting-state fMRI data from 68 healthy subjects and 68 schizophrenia patients. The DMD method was employed to extract the mean amplitude of dynamic patterns as features, with feature selection conducted via Least Absolute Shrinkage and Selection Operator (LASSO) regression. A support vector machine (SVM) was further employed to validate the predictive capability of the selected features across subject groups. Based on the LASSO screening, we identified brain regions exhibiting significant inter-group differences in mean amplitude, designated these as abnormal regions, and subsequently analyzed their functional deviations. The DMD method not only provided explicit temporal dynamic representations of brain activity but also supported signal reconstruction and prediction, thereby enhancing feature interpretability. Results demonstrated that DMD effectively extracted mean amplitude features from fMRI data. Combined with LASSO and SVM, it enabled the identification of abnormal brain regions and functional abnormalities in schizophrenia patients. Furthermore, this method captured frequency-dependent signal patterns, with extracted features correlating with both regional activation intensity and functional connectivity. This approach provides novel insights for exploring potential biomarkers of psychiatric disorders.
Computational modeling of resistance to hormone-mediated remission in childhood absence epilepsy.
Ahmed M, Campbell SA
Front Comput Neurosci · 2025 · PMID 41602213 · Full text
Childhood absence epilepsy (CAE) often resolves during adolescence, a period marked by hormonal and neurosteroid changes associated with puberty. However, remission does not occur in all individuals. To investigate this...
Childhood absence epilepsy (CAE) often resolves during adolescence, a period marked by hormonal and neurosteroid changes associated with puberty. However, remission does not occur in all individuals. To investigate this clinical heterogeneity, we developed a simplified thalamocortical model with a layered cortical structure, using deep-layer intrinsically bursting (IB) neurons to represent frontal cortex and regular spiking (RS) neurons modeling the parietal cortex. By simulating two cortical configurations, we explored how variations in neuronal composition and frontocortical connectivity influence seizure dynamics and the effectiveness of allopregnanolone (ALLO) in resolving pathological spike-wave discharges (SWDs) associated with CAE. While both models exhibited similar physiological and pathological oscillations, only the parietal-dominant network (with a higher proportion of RS neurons in layer 5) recovered from SWDs under increased frontocortical connectivity following ALLO administration. These findings suggest that neuronal composition critically modulates ALLO-mediated resolution of SWDs, providing a mechanistic link between structural connectivity and clinical outcomes in CAE, and highlighting the potential for personalized treatment strategies based on underlying network architecture.
The impact of dynamic reversal potential on the evolution of action potential attributes during spike trains.
Aldohbeyb AA, Vigh J, Lear KL
Front Comput Neurosci · 2025 · PMID 41585348 · Full text
Action potentials (AP) are the basic elements of information processing in the nervous system. Understanding AP generation mechanisms is a critical step to understand how neurons encode information. However, an individua...
Action potentials (AP) are the basic elements of information processing in the nervous system. Understanding AP generation mechanisms is a critical step to understand how neurons encode information. However, an individual neuron might fire APs with various shapes even in response to the same stimulus, and the mechanisms responsible for this variability remain unclear. Therefore, we analyzed four AP attributes including AP rapidity and threshold during consecutive bursts from three neuron types using intracellular electrophysiological recordings. In response to consecutive current steps, the AP attributes in evoked spike trains show two distinctive patterns across different neurons: (1) The first APs from each train always have comparable properties regardless of the stimulus strength; (2) The attributes of the subsequent APs during each pulse monotonically change during the burst, where the magnitude of AP attribute change during each pulse increases with increasing stimulation strength. Various conductance-based models were explored to determine if they replicated the observed AP bursts. The observed patterns could not be replicated using the classical HH-type models, or modified HH model with cooperative Na gating. However, adding ion concentration dynamics to the model reproduced the AP attribute variation, and the magnitude of change during a pulse correlated with change in dynamic reversal potential (DRP), but failed to replicate the first AP attributes pattern. Then, the role of cooperative Na gating on neuronal firing dynamics was investigated. Inclusion of cooperative gating restored the first APs' attributes and enhanced the magnitude of modeled variation of some AP attributes to better agree with observed data. We conclude that changes in local ion concentrations could be responsible for the monotonic change in APs attributes during neuronal bursts, and cooperative gating of Na channels can enhance the effect. Thus, the two mechanisms could contribute to the observed variability in neuronal response.
Bridging neuromorphic computing and deep learning for next-generation neural data interpretation.
Zhang M, Wang T, Zhu Z
Front Comput Neurosci · 2025 · PMID 41585347 · Full text
Abstract loading — click title to view on PubMed.
Transferable CNN-based data mining approaches for medical imaging: application to spine DXA scans for osteoporosis detection.
Naeem AB, Osman O, Alsubai S … +4 more , Çevik N, Zaidi AT, Seyyedabbasi A, Rasheed J
Front Comput Neurosci · 2025 · PMID 41536415 · Full text
INTRODUCTION: Osteoporosis is the leading cause of sudden bone fractures. This is a silent and deadly disease that can affect any part of the body, such as the spine, hips, and knee bones. AIM: To measure bone mineral de...
INTRODUCTION: Osteoporosis is the leading cause of sudden bone fractures. This is a silent and deadly disease that can affect any part of the body, such as the spine, hips, and knee bones. AIM: To measure bone mineral density, dual-energy X-ray absorptiometry (DXA) scans help radiologists and other medical professionals identify early signs of osteoporosis in the spine. METHODS: A proposed 21-layer convolutional neural network (CNN) model is implemented and validated to automatically detect osteoporosis in spine DXA images. The dataset contains 174 spine DXA images, including 114 affected by osteoporosis and the rest normal or non-fractured. To improve training, the dataset is expanded using various data augmentation techniques. RESULTS: The classification performance of the proposed model is compared with that of four popular pre-trained models: ResNet-50, Visual Geometry Group 16 (VGG-16), VGG-19, and InceptionV3. With an F1-score of 97.16%, recall of 95.41%, classification accuracy of 97.14%, and precision of 99.04%, the proposed model consistently outperforms competing approaches. CONCLUSION: The proposed paradigm would therefore be very valuable to radiologists and other medical professionals. The proposed approach's capacity to detect, monitor, and diagnose osteoporosis may reduce the risk of developing the condition.
Fractal memory structure in the spatiotemporal learning rule.
Orima T, Tsuda I, Tsukada M … +2 more , Tsukada H, Horio Y
Front Comput Neurosci · 2025 · PMID 41477451 · Full text
The spatiotemporal learning rule (STLR) can reproduce synaptic plasticity in the hippocampus. Analysis of the synaptic weights in the network with the STLR is challenging. Consequently, our previous research only focused...
The spatiotemporal learning rule (STLR) can reproduce synaptic plasticity in the hippocampus. Analysis of the synaptic weights in the network with the STLR is challenging. Consequently, our previous research only focused on the network's outputs. However, a detailed analysis of the STLR requires focusing on the synaptic weights themselves. To address this issue, we mapped the synaptic weights to a distance space and analyzed the characteristics of the STLR. The results indicate that the synaptic weights form a fractal-like structure in Euclidean distance space. Furthermore, three analytical approaches-multi-dimensional scaling, estimating fractal dimension, and modeling with an iterated function system-demonstrate that the STLR forms a fractal structure in the synaptic weights through fractal coding. These findings contribute to clarifying the learning mechanisms in the hippocampus.
State-dependent filtering as a mechanism toward visual robustness.
Yan J, Feng Y, Dai WP … +1 more , Zhang Y
Front Comput Neurosci · 2025 · PMID 41450784 · Full text
Robustness, defined as a system's ability to maintain functional reliability in the face of perturbations, is achieved through its capacity to filter external disturbances using internal priors encoded in its structure a...
Robustness, defined as a system's ability to maintain functional reliability in the face of perturbations, is achieved through its capacity to filter external disturbances using internal priors encoded in its structure and states. While biophysical neural networks are widely recognized for their robustness, the precise mechanisms underlying this resilience remain poorly understood. In this study, we explore how orientation-selective neurons arranged in a one-dimensional ring network respond to perturbations, with the aim of uncovering insights into the robustness of visual subsystems in the brain. By analyzing the steady-state dynamics of a rate-based network, we characterize how the activation state of neurons influences the network's response to disturbances. Our results demonstrate that the activation state of neurons, rather than their firing rates alone, governs the network's sensitivity to perturbations. We further show that lateral connectivity modulates this effect by shaping the response profile across spatial frequency components. These findings suggest a state-dependent filtering mechanism that contributes to the robustness of visual circuits, offering theoretical insight into how different components of perturbations are selectively modulated within the network.
Neurocognition, cerebellar functions and psychiatric features in spinocerebellar ataxia type 34: a case series.
Cundari M, Kirchhoff L, Vestberg S … +9 more , van Westen D, Dobloug S, Markenroth Bloch K, Nilsson M, Wennberg L, Hansson B, Priovoulos N, Rasmussen A, Gorcenco S
Front Comput Neurosci · 2025 · PMID 41445982 · Full text
OBJECTIVE: This study primarily aimed to comprehensively characterize the neurological, neuroradiological and neurocognitive profiles, as well psychiatric features of individuals with Spinocerebellar Ataxia Type 34 (SCA3...
OBJECTIVE: This study primarily aimed to comprehensively characterize the neurological, neuroradiological and neurocognitive profiles, as well psychiatric features of individuals with Spinocerebellar Ataxia Type 34 (SCA34) associated with pathogenic variants in the gene. Secondarily, we investigated the relationship between neurocognitive functions and cerebellar morphology in individuals with SCA34 by correlating structural changes to cognitive performance. Given involvement of the cerebellum in SCA34, our findings will contribute to a broader understanding of the role of the cerebellum in cognition. METHODS: Four individuals (52 f, 72 m, 76 m, 76 f) underwent DNA testing using Next-Generation Sequencing and detailed assessment of neurocognitive functions. The test battery evaluated all six cognitive domains: verbal functions, executive functions, attention and processing speed, learning and memory, visuospatial perception and abilities, and social cognition. In addition, cerebellar and motor functions were evaluated using Finger Tapping, Prism Adaptation, and the Motor Speed subtest of the Delis-Kaplan executive function system (D-KEFS). Test results were compared with each individual's estimated premorbid cognitive level, determined from their highest educational attainment or occupational status prior to disease onset. Psychiatric symptoms related to anxiety, depression, and sleep were reported using clinical scales. The Scale for the Assessment and Rating of Ataxia (SARA) was used to assess ataxia severity. Two individuals and one matched control underwent high-resolution 7T MRI to characterize cerebellar morphology. RESULTS: Neurocognitive assessments identified cognitive and motor dysfunction across all individuals, including distinct neurocognitive impairments consistent with cerebellar cognitive-affective syndrome (CCAS), along with additional deficits in learning, visual and verbal episodic memory, emotion recognition-a component of social cognition. Anxiety and sleep disturbance, but not depression, were observed in both female participants. High-resolution 7 T MRI revealed structural cerebellar alterations, with moderate to severe bilateral cerebellar atrophy, including the vermis and multiple lobules (Crus II, VIIb, VIIIa, VIIIb, IX), as well as atrophy of the middle and superior cerebellar peduncles, accompanied by mild pontine atrophy. Genetic analyses confirmed the involvement of -related disruptions in long-chain fatty acid biosynthesis, offering insight into the molecular underpinnings of cerebellar degeneration in SCA34. CONCLUSION: Individuals with SCA34 show cerebellar degeneration accompanied by cognitive, motor, and social-affective impairments consistent with CCAS. Atrophy of the vermis, multiple lobules, and cerebellar peduncles align with these deficits, highlighting the cerebellum's key role in cognition. ELOVL4-related disruptions in fatty acid biosynthesis provides insight into the molecular basis of SCA34. Together, these findings advance our understanding of how cerebellar pathology contributes to complex neurocognitive and psychiatric symptoms in genetic ataxias.
GAME-Net: an ensemble deep learning framework integrating Generative Autoencoders and attention mechanisms for automated brain tumor segmentation in MRI.
Haq IU, Iqbal A, Anas M … +3 more , Masood F, Alzahrani AS, Al-Naeem M
Front Comput Neurosci · 2025 · PMID 41439240 · Full text
INTRODUCTION: Accurate and early identification of brain tumors is essential for improving therapeutic planning and clinical outcomes. Manual segmentation of Magnetic Resonance Imaging (MRI) remains time-consuming and su...
INTRODUCTION: Accurate and early identification of brain tumors is essential for improving therapeutic planning and clinical outcomes. Manual segmentation of Magnetic Resonance Imaging (MRI) remains time-consuming and subject to inter-observer variability. Computational models that combine Artificial Intelligence and biomedical imaging offer a pathway toward objective and efficient tumor delineation. The present study introduces a deep learning framework designed to enhance brain tumor segmentation performance. METHODS: A comprehensive ensemble architecture was developed by integrating Generative Autoencoders with Attention Mechanisms (GAME), Convolutional Neural Networks, and attention-augmented U-Net segmentation modules. The dataset comprised 5,880 MRI images sourced from the BraTS 2023 benchmark distribution accessed via Kaggle, partitioned into training, validation, and testing subsets. Preprocessing included intensity normalization, augmentation, and unsupervised feature extraction. Tumor segmentation employed an attention-based U-Net, while tumor classification utilized a CNN coupled with Transformer-style self-attention. The Generative Autoencoder performed unsupervised representation learning to refine feature separability and enhance robustness to MRI variability. RESULTS: The proposed framework achieved notable performance improvements across multiple evaluation metrics. The segmentation module produced a Dice Coefficient of 0.85 and a Jaccard Index of 0.78. The classification component yielded an accuracy of 87.18 percent, sensitivity of 88.3 percent, specificity of 86.5 percent, and an AUC-ROC of 0.91. The combined use of generative modeling, attention mechanisms, and ensemble learning improved tumor localization, boundary delineation, and false positive suppression compared with conventional architectures. DISCUSSION: The findings indicate that enriched representation learning and attention-driven feature refinement substantially elevate segmentation accuracy on heterogeneous MRI data. The integration of unsupervised learning within the pipeline supported improved generalization across variable imaging conditions. The demonstrated performance suggests strong potential for clinical utility, although broader validation across external datasets is recommended to further substantiate generalizability.
Simplex polynomial in complex networks and its applications to compute the Euler characteristic.
Wang Z, Fu X, Deng B … +2 more , Chen Y, Zhao H
Front Comput Neurosci · 2025 · PMID 41383550 · Full text
In algebraic topology, a -dimensional simplex is defined as a convex polytope consisting of + 1 vertices. If spatial dimensionality is not considered, it corresponds to the complete graph with + 1 vertices in graph the...
In algebraic topology, a -dimensional simplex is defined as a convex polytope consisting of + 1 vertices. If spatial dimensionality is not considered, it corresponds to the complete graph with + 1 vertices in graph theory. The alternating sum of the number of simplices across dimensions yields a topological invariant known as the Euler characteristic, which has gained significant attention due to its widespread application in fields such as topology, homology theory, complex systems, and biology. The most common method for calculating the Euler characteristic is through simplicial decomposition and the Euler-Poincaré formula. In this study, we introduce a new "subgraph" polynomial, termed the simplex polynomial, and explore some of its properties. Using those properties, we provide a new method for computing the Euler characteristic and prove the existence of the Euler characteristic as an arbitrary integer by constructing the corresponding simplicial complex structure. When the Euler characteristic is 1, we determined a class of corresponding simplicial complex structures. Moreover, for three common network structures, we present the recurrence relations for their simplex polynomials and their corresponding Euler characteristics. Finally, at the end of this study, three basic questions are raised for the interested readers to study deeply.
About
- Frequency
- Sun
- Papers found
- 200
- RSS feed
- Subscribe