International journal of neural systems最新文献

{"title":"Self-Supervised Image Segmentation Using Meta-Learning and Multi-Backbone Feature Fusion.","authors":"Muhammad Shahroz Ajmal, Guohua Geng, Xiaofeng Wang, Mohsin Ashraf","doi":"10.1142/S0129065725500121","DOIUrl":"10.1142/S0129065725500121","url":null,"abstract":"<p><p>Few-shot segmentation (FSS) aims to reduce the need for manual annotation, which is both expensive and time-consuming. While FSS enhances model generalization to new concepts with only limited test samples, it still relies on a substantial amount of labeled training data for base classes. To address these issues, we propose a multi-backbone few shot segmentation (MBFSS) method. This self-supervised FSS technique utilizes unsupervised saliency for pseudo-labeling, allowing the model to be trained on unlabeled data. In addition, it integrates features from multiple backbones (ResNet, ResNeXt, and PVT v2) to generate a richer feature representation than a single backbone. Through extensive experimentation on PASCAL-5i and COCO-20i, our method achieves 54.3% and 25.1% on one-shot segmentation, exceeding the baseline methods by 13.5% and 4%, respectively. These improvements significantly enhance the model's performance in real-world applications with negligible labeling effort.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2550012"},"PeriodicalIF":0.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143191645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Coherence-Based Graph Convolution Network to Assess Brain Reorganization in Spinal Cord Injury Patients.","authors":"Jiancai Leng, Jiaqi Zhao, Yongjian Wu, Chengyan Lv, Zhixiao Lun, Yanzi Li, Chao Zhang, Bin Zhang, Yang Zhang, Fangzhou Xu, Changsong Yi, Tzyy-Ping Jung","doi":"10.1142/S0129065725500212","DOIUrl":"10.1142/S0129065725500212","url":null,"abstract":"<p><p>Motor imagery (MI) engages a broad network of brain regions to imagine a specific action. Investigating the mechanism of brain network reorganization during MI after spinal cord injury (SCI) is crucial because it reflects overall brain activity. Using electroencephalogram (EEG) data from SCI patients, we conducted EEG-based coherence analysis to examine different brain network reorganizations across different frequency bands, from resting to MI. Furthermore, we introduced a consistency calculation-based residual graph convolution (C-ResGCN) classification algorithm. The results show that the [Formula: see text]- and [Formula: see text]-band connectivity weakens, and brain activity decreases during the MI task compared to the resting state. In contrast, the [Formula: see text]-band connectivity increases in motor regions while the default mode network activity declines during MI. Our C-ResGCN algorithm showed excellent performance, achieving a maximum classification accuracy of 96.25%, highlighting its reliability and stability. These findings suggest that brain reorganization in SCI patients reallocates relevant brain resources from the resting state to MI, and effective network reorganization correlates with improved MI performance. This study offers new insights into the mechanisms of MI and potential biomarkers for evaluating rehabilitation outcomes in patients with SCI.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2550021"},"PeriodicalIF":0.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143639865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Understanding the Spatio-Temporal Coupling of Spikes and Spindles in Focal Epilepsy Through a Network-Level Computational Model.","authors":"Min Pan, Qiang Li, Jiangling Song, Bo Wang, Wenhua Wang, Rui Zhang","doi":"10.1142/S0129065725500182","DOIUrl":"10.1142/S0129065725500182","url":null,"abstract":"<p><p>The electrophysiological findings have shown that epileptiform spikes triggering sleep spindles within 1[Formula: see text]s across multiple channels are commonly observed during sleep in focal epilepsy (FE). Such spatio-temporal couplings of spikes and spindles (STCSSs) are defined as a kind of pathological waves, and frequent emergence of them may cause the degradation of cognitive function for FE patients. However, the neural mechanisms underlying STCSSs are not well understood. To this end, this work first develops a neural mass network model for focal epilepsy (FE-NMNM) with multiple thalamocortical columns being its nodes and the long-range synaptic interactions of thalamocortical columns being its edges, where each thalamocortical column is extended on the basis of Costa model and then they are connected through excitatory synapses between pyramidal cells. Then, how the cortico-cortical connectivity affects the evolution of STCSSs across the network is especially discussed by simulations in two cases, where the inter-ictal state and the ictal state are considered separately. Simulation results demonstrate that: (1) the more STCSSs occur in a more extensive area when the cortico-cortical connectivity becomes stronger, and the significant increase of coupling discharges is attributed to the presence of abundant spikes; (2) when the connectivity is excessively strong, the cortical hyperexcitability will happen, thereby inducing massive spike discharges which may further inhibit the occurrence of spindles, and hence, resulting in the disappearance of STCSSs. The obtained results provide a mechanistic insight into STCSSs, and suggest that such coupling patterns could reflect widespread network dysfunction in FE, thereby potentially advancing therapeutic strategies for FE.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2550018"},"PeriodicalIF":0.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143625844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Heterogeneous Attractor Model for Neural Dynamical Mechanism of Movement Preparation.","authors":"Lining Yin, Lanyun Cui, Ying Yu, Qingyun Wang","doi":"10.1142/S0129065725500194","DOIUrl":"https://doi.org/10.1142/S0129065725500194","url":null,"abstract":"<p><p>Preparatory activity is crucial for voluntary motor control, reducing reaction time and enhancing precision. To understand the neurodynamic mechanisms behind this, we construct a dynamical model within the motor cortex, which comprises coupled heterogeneous attractors to simulate delayed reaching tasks. This model replicates the neural activity patterns observed in the macaque motor cortex, within distinct attractor spaces for preparatory and executive activities. It can capture the transition from preparation to execution through shifts in an orthogonal subspace combined with a thresholding mechanism. Results show that the preparation duration modulates behavioral accuracy, with optimal preparation intervals enhancing performance. External inputs primarily shape the preparatory activity, while synaptic connections dominate execution. Our analysis of the network's multi-stable dynamics reveals that external inputs reshape the stable points of the heterogeneous attractor modules both before and after preparation, while synaptic strength affects dynamical stability and input sensitivity, allowing rapid and precise actions. Additionally, sensitivity to external perturbations decreases as preparatory time increases, emphasizing the importance of external inputs during preparation. Overall, this study provides insights into the neurodynamic mechanisms underlying the transition from motor preparation to execution and underscores the significance of preparatory activity for accurate motor control.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":"35 5","pages":"2550019"},"PeriodicalIF":0.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143766249","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Minimal Neural Network Conditions for Encoding Future Interactions.","authors":"Sergio Diez-Hermano, Gonzalo Aparicio-Rodriguez, Paloma Manubens, Abel Sanchez-Jimenez, Carlos Calvo-Tapia, David Levcik, José Antonio Villacorta-Atienza","doi":"10.1142/S0129065725500169","DOIUrl":"10.1142/S0129065725500169","url":null,"abstract":"<p><p>Space and time are fundamental attributes of the external world. Deciphering the brain mechanisms involved in processing the surrounding environment is one of the main challenges in neuroscience. This is particularly defiant when situations change rapidly over time because of the intertwining of spatial and temporal information. However, understanding the cognitive processes that allow coping with dynamic environments is critical, as the nervous system evolved in them due to the pressure for survival. Recent experiments have revealed a new cognitive mechanism called time compaction. According to it, a dynamic situation is represented internally by a static map of the future interactions between the perceived elements (including the subject itself). The salience of predicted interactions (e.g. collisions) over other spatiotemporal and dynamic attributes during the processing of time-changing situations has been shown in humans, rats, and bats. Motivated by this ubiquity, we study an artificial neural network to explore its minimal conditions necessary to represent a dynamic stimulus through the future interactions present in it. We show that, under general and simple conditions, the neural activity linked to the predicted interactions emerges to encode the perceived dynamic stimulus. Our results show that this encoding improves learning, memorization and decision making when dealing with stimuli with impending interactions compared to no-interaction stimuli. These findings are in agreement with theoretical and experimental results that have supported time compaction as a novel and ubiquitous cognitive process.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2550016"},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143525553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Architecture Knowledge Distillation for Evolutionary Generative Adversarial Network.","authors":"Yu Xue, Yan Lin, Ferrante Neri","doi":"10.1142/S0129065725500133","DOIUrl":"10.1142/S0129065725500133","url":null,"abstract":"<p><p>Generative Adversarial Networks (GANs) are effective for image generation, but their unstable training limits broader applications. Additionally, neural architecture search (NAS) for GANs with one-shot models often leads to insufficient subnet training, where subnets inherit weights from a supernet without proper optimization, further degrading performance. To address both issues, we propose Architecture Knowledge Distillation for Evolutionary GAN (AKD-EGAN). AKD-EGAN operates in two stages. First, architecture knowledge distillation (AKD) is used during supernet training to efficiently optimize subnetworks and accelerate learning. Second, a multi-objective evolutionary algorithm (MOEA) searches for optimal subnet architectures, ensuring efficiency by considering multiple performance metrics. This approach, combined with a strategy for architecture inheritance, enhances GAN stability and image quality. Experiments show that AKD-EGAN surpasses state-of-the-art methods, achieving a Fréchet Inception Distance (FID) of 7.91 and an Inception Score (IS) of 8.97 on CIFAR-10, along with competitive results on STL-10 (FID: 20.32, IS: 10.06). Code and models will be available at https://github.com/njit-ly/AKD-EGAN.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2550013"},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143451188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Online and Cross-User Finger Movement Pattern Recognition by Decoding Neural Drive Information from Surface Electromyogram.","authors":"Haowen Zhao, Yunfei Liu, Xinhui Li, Xiang Chen, Xu Zhang","doi":"10.1142/S0129065725500145","DOIUrl":"10.1142/S0129065725500145","url":null,"abstract":"<p><p>Cross-user variability is a well-known challenge that leads to severe performance degradation and impacts the robustness of practical myoelectric control systems. To address this issue, a novel method for myoelectric recognition of finger movement patterns is proposed by incorporating a neural decoding approach with unsupervised domain adaption (UDA) learning. In our method, the neural decoding approach is implemented by extracting microscopic features characterizing individual motor unit (MU) activities obtained from a two-stage online surface electromyogram (SEMG) decomposition. A specific deep learning model is designed and initially trained using labeled data from a set of existing users. The model can update adaptively when recognizing the movement patterns of a new user. The final movement pattern was determined by a fuzzy weighted decision strategy. SEMG signals were collected from the finger extensor muscles of 15 subjects to detect seven dexterous finger-movement patterns. The proposed method achieved a movement pattern recognition accuracy of ([Formula: see text])% over seven movements under cross-user testing scenarios, much higher than that of the conventional methods using global SEMG features. Our study presents a novel robust myoelectric pattern recognition approach at a fine-grained MU level, with wide applications in neural interface and prosthesis control.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2550014"},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143191644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Frequency-Assisted Local Attention in Lower Layers of Visual Transformers.","authors":"Xin Zhou, Zeyu Jiang, Shihua Zhou, Zhaohui Ren, Yongchao Zhang, Tianzhuang Yu, Yulin Liu","doi":"10.1142/S0129065725500157","DOIUrl":"10.1142/S0129065725500157","url":null,"abstract":"<p><p>Since vision transformers excel at establishing global relationships between features, they play an important role in current vision tasks. However, the global attention mechanism restricts the capture of local features, making convolutional assistance necessary. This paper indicates that transformer-based models can attend to local information without using convolutional blocks, similar to convolutional kernels, by employing a special initialization method. Therefore, this paper proposes a novel hybrid multi-scale model called Frequency-Assisted Local Attention Transformer (FALAT). FALAT introduces a Frequency-Assisted Window-based Positional Self-Attention (FWPSA) module that limits the attention distance of query tokens, enabling the capture of local contents in the early stage. The information from value tokens in the frequency domain enhances information diversity during self-attention computation. Additionally, the traditional convolutional method is replaced with a depth-wise separable convolution to downsample in the spatial reduction attention module for long-distance contents in the later stages. Experimental results demonstrate that FALAT-S achieves 83.0% accuracy on IN-1k with an input size of [Formula: see text] using 29.9[Formula: see text]M parameters and 5.6[Formula: see text]G FLOPs. This model outperforms the Next-ViT-S by 0.9[Formula: see text]AP^<i>b</i>/0.8[Formula: see text]AP^<i>m</i> with Mask-R-CNN [Formula: see text] on COCO and surpasses the recent FastViT-SA36 by 3.1% mIoU with FPN on ADE20k.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2550015"},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143525637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"End-User Confidence in Artificial Intelligence-Based Predictions Applied to Biomedical Data.","authors":"Zvi Kam, Lorenzo Peracchio, Giovanna Nicora","doi":"10.1142/S0129065725500170","DOIUrl":"https://doi.org/10.1142/S0129065725500170","url":null,"abstract":"<p><p>Applications of Artificial Intelligence (AI) are revolutionizing biomedical research and healthcare by offering data-driven predictions that assist in diagnoses. Supervised learning systems are trained on large datasets to predict outcomes for new test cases. However, they typically do not provide an indication of the reliability of these predictions, even though error estimates are integral to model development. Here, we introduce a novel method to identify regions in the feature space that diverge from training data, where an AI model may perform poorly. We utilize a compact precompiled structure that allows for fast and direct access to confidence scores in real time at the point of use without requiring access to the training data or model algorithms. As a result, users can determine when to trust the AI model's outputs, while developers can identify where the model's applicability is limited. We validate our approach using simulated data and several biomedical case studies, demonstrating that our approach provides fast confidence estimates ([Formula: see text] milliseconds per case), with high concordance to previously developed methods (<i>f</i>-[Formula: see text]). These estimates can be easily added to real-world AI applications. We argue that providing confidence estimates should be a standard practice for all AI applications in public use.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":"35 4","pages":"2550017"},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143568989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Efficient Seizure Detection by Complementary Integration of Convolutional Neural Network and Vision Transformer.","authors":"Jiaqi Wang, Haotian Li, Chuanyu Li, Weisen Lu, Haozhou Cui, Xiangwen Zhong, Shuhao Ren, Zhida Shang, Weidong Zhou","doi":"10.1142/S0129065725500236","DOIUrl":"https://doi.org/10.1142/S0129065725500236","url":null,"abstract":"<p><p>Epilepsy, as a prevalent neurological disorder, is characterized by its high incidence, sudden onset, and recurrent nature. The development of an accurate and real-time automatic seizure detection system is crucial for assisting clinicians in making precise diagnoses and providing timely treatment for epilepsy. However, conventional automatic seizure detection methods often face limitations in simultaneously capturing both local features and long-range correlations inherent in EEG signals, which constrains the accuracy of these existing detection systems. To address this challenge, we propose a novel end-to-end seizure detection framework, named CNN-ViT, which complementarily integrates a Convolutional Neural Network (CNN) for capturing local inductive bias of EEG and Vision Transformer (ViT) for further mining their long-range dependency. Initially, raw electroencephalogram (EEG) signals are filtered and segmented and then sent into the CNN-ViT model to learn their local and global feature representations and identify the seizure patterns. Meanwhile, we adopt a global max-pooling strategy to reduce the scale of the CNN-ViT model and make it focus on the most discriminative features. Given the occurrence of diverse artifacts in long-term EEG recordings, we further employ post-processing techniques to improve the seizure detection performance. The proposed CNN-ViT model, when evaluated using the publicly accessible CHB-MIT EEG dataset, reveals its outstanding performance with a sensitivity of 99.34% at a segment-based level and 99.70% at an event-based level. On the SH-SDU dataset we collected, our method yielded a segment-based sensitivity of 99.86%, specificity of 94.33%, and accuracy of 94.40%, along with an event-based sensitivity of 100%. The total processing time for 1[Formula: see text]h EEG data was only 3.07[Formula: see text]s. These exceptional results demonstrate the potential of our method as a reference for clinical real-time seizure detection applications.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2550023"},"PeriodicalIF":0.0,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143756812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}