Search Results (439)

Traumatic brain injury (TBI) remains a major global health problem, contributing significantly to morbidity and mortality worldwide. Despite advances in understanding its complex pathophysiology, current therapeutic strategies are insufficient in addressing the long-term cognitive, emotional, and neurological impairments. While the primary mechanical injury is immediate and unavoidable, the secondary phase involves a cascade of biological processes leading to neuroinflammation, blood–brain barrier (BBB) disruption, and systemic immune activation. The heterogeneity of patient responses underscores the urgent need for reliable biomarkers and targeted interventions. Emerging evidence highlights the gut–brain axis as a critical modulator of the secondary phase, with microbiota-derived extracellular vesicles (MEVs) representing a promising avenue for both diagnosis and therapy. MEVs can cross the intestinal barrier and BBB, carrying biomolecules that influence neuronal survival, synaptic plasticity, and inflammatory signaling. These properties make MEVs promising biomarkers for early detection, severity classification, and prognosis in TBI, while also offering therapeutic potential through modulation of neuroinflammation and promotion of neural repair. MEV-based strategies could enable tailored interventions based on the individual’s microbiome profile, immune status, and injury characteristics. The integration of multi-omics with artificial intelligence is expected to fully unlock the diagnostic and therapeutic potential of MEVs. These approaches can identify molecular subtypes, predict outcomes, and facilitate real-time clinical decision-making. By bridging microbiology, neuroscience, and precision medicine, MEVs hold transformative potential to advance TBI diagnosis, monitoring, and treatment. This review also identifies key research gaps and proposes future directions for MEVs in precision diagnostics and gut microbiota-based therapeutics in neurotrauma care. Full article

This paper proposes and evaluates two neural network-based approaches for object classification in automotive radar systems, comparing the performance impact of grid search and genetic algorithm (GA) hyperparameter optimization strategies. The task involves classifying cars, pedestrians, and cyclists using radar-derived features. The grid search–optimized model employs a compact architecture with two hidden layers and 10 neurons per layer, leveraging kinematic correlations and motion descriptors to achieve mean accuracies of 90.06% (validation) and 90.00% (test). In contrast, the GA-optimized model adopts a deeper architecture with nine hidden layers and 30 neurons per layer, integrating an expanded feature set that includes object dimensions, signal-to-noise ratio (SNR), radar cross-section (RCS), and Kalman filter–based motion descriptors, resulting in substantially higher performance at approximately 97.40% mean accuracy on both validation and test datasets. Principal Component Analysis (PCA) and SHapley Additive exPlanations (SHAP) highlight the enhanced discriminative power of the new set of features, while parallelized GA execution enables efficient exploration of a broader hyperparameter space. Although currently optimized for urban traffic scenarios, the proposed approach can be extended to highway and extra-urban environments through targeted dataset expansion and developing additional features that are less sensitive to object kinematics, thereby improving robustness across diverse motion patterns and operational contexts. Full article

Organismal biosensing leverages the olfactory acuity of living systems to detect volatile organic compounds (VOCs) associated with cancer, offering a low-cost and non-invasive complement to conventional diagnostics. Early studies demonstrate its feasibility across diverse platforms. In C. elegans, chemotaxis assays on urine samples achieved sensitivities of 87–96% and specificities of 90–95% in case–control cohorts (n up to 242), while calcium imaging of AWC neurons distinguished breast cancer urine with ~97% accuracy in a small pilot cohort (n ≈ 40). Trained canines have identified prostate cancer from urine with sensitivities of ~71% and specificities of 70–76% (n ≈ 50), and AI-augmented canine breath platforms have reported accuracies of ~94–95% across ~1400 participants. Insects such as locusts and honeybees enable ultrafast neural decoding of VOCs, achieving 82–100% classification accuracy within 250 ms in pilot studies (n ≈ 20–30). Collectively, these platforms validate the principle that organismal behavior and neural activity encode cancer-related VOC signatures. However, limitations remain, including small cohorts, methodological heterogeneity, and reliance on binary outputs. This review proposes a Dual-Pathway Framework, where Pathway 1 leverages validated indices (e.g., the Chemotaxis Index) for high-throughput screening, and Pathway 2 applies machine learning to high-dimensional behavioral vectors for cancer subtyping, staging, and monitoring. By integrating these approaches, organismal biosensing could evolve from proof-of-concept assays into clinically scalable precision diagnostics. Full article

Background/Objectives: Understanding the diverse neuron types within the hippocampal formation is essential for advancing our knowledge of its fundamental roles in learning and memory. Hippocampome.org serves as a comprehensive, evidence-based knowledge repository that integrates morphological, electrophysiological, and molecular features of neurons across the rodent dentate gyrus, CA3, CA2, CA1, subiculum, and entorhinal cortex. In addition to these core properties, this open access resource includes detailed information on synaptic connectivity, signal propagation, and plasticity, facilitating sophisticated modeling of hippocampal circuits. A distinguishing feature of Hippocampome.org is its emphasis on quantitative, literature-backed data that can help constrain and validate spiking neural network simulations via an interactive web interface. Methods: To assess and enhance its utility to the neuroscience community, we integrated Google Analytics (GA) into the platform to monitor user behavior, identify high-impact content, and evaluate geographic reach. Results: GA data provided valuable page view metrics, revealing usage trends, frequently accessed neuron properties, and the progressive adoption of new functionalities. Conclusions: These insights directly inform iterative development, particularly in the design of a robust Application Programming Interface (API) to support programmatic access. Ultimately, the integration of GA empowers data-driven optimization of this public resource to better serve the global neuroscience community. Full article

This study presents a novel hybrid approach combining grammatical evolution with constrained genetic algorithms to overcome key limitations in automated neural network design. The proposed method addresses two critical challenges: the tendency of grammatical evolution to converge to suboptimal architectures due to local optima, and the common overfitting problems in evolved networks. Our solution employs grammatical evolution for initial architecture generation while implementing a specialized genetic algorithm that simultaneously optimizes network parameters within dynamically adjusted bounds. The genetic component incorporates innovative penalty mechanisms in its fitness function to control neuron activation patterns and prevent overfitting. Comprehensive testing across 53 diverse datasets shows our method achieves superior performance compared to traditional optimization techniques, with an average classification error of 21.18% vs. 36.45% for ADAM, while maintaining better generalization capabilities. The constrained optimization approach proves particularly effective in preventing premature convergence, and the penalty system successfully mitigates overfitting even in complex, high-dimensional problems. Statistical validation confirms these improvements are significant (p < $1.1\times {10}^{-8}$) and consistent across multiple domains, including medical diagnosis, financial prediction, and physical system modeling. This work provides a robust framework for automated neural network construction that balances architectural innovation with parameter optimization while addressing fundamental challenges in evolutionary machine learning. Full article

Prototype-Based Networks (PBNs) are inherently interpretable architectures that facilitate understanding of model outputs by analyzing the activation of specific neurons—referred to as prototypes—during the forward pass. The learned prototypes serve as transformations of the input space into a latent representation that more effectively encapsulates the main characteristics shared across data samples, thereby enhancing classification performance. Crucially, these prototypes can be decoded and projected back into the original input space, providing direct interpretability of the features learned by the network. While this characteristic marks a meaningful advancement toward the realization of fully interpretable artificial intelligence systems, our findings reveal that prototype representations can be deliberately or inadvertently manipulated without compromising the superficial appearance of explainability. In this study, we conduct a series of empirical investigations that demonstrate this phenomenon, framing it as a structural paradox potentially intrinsic to the architecture or its design, which may represent a significant robustness challenge for explainable AI methodologies. Full article

Deep neural networks (DNNs) are highly effective across many domains but are sensitive to noisy or corrupted training data. Existing noise mitigation strategies often rely on strong assumptions about noise distributions or require costly retraining, limiting their scalability. Inspired by machine unlearning, we propose a novel framework that integrates attribution-guided data partitioning, neuron pruning, and targeted fine-tuning to enhance robustness. Our method uses gradient-based attribution to probabilistically identify clean samples without assuming specific noise characteristics. It then applies sensitivity-based neuron pruning to remove components most susceptible to noise, followed by fine-tuning on the retained high-quality subset. This approach jointly addresses data and model-level noise, offering a practical alternative to full retraining or explicit noise modeling. We evaluate our method on CIFAR-10 image classification and keyword spotting tasks under varying levels of label corruption. On CIFAR-10, our framework improves accuracy by up to 10% (F-FT vs. retrain) and reduces retraining time by 47% (L-FT vs. retrain), highlighting both accuracy and efficiency gains. These results highlight its effectiveness and efficiency in noisy settings, making it a scalable solution for robust generalization. Full article

Histone deacetylases (HDACs) are key epigenetic regulators that influence chromatin remodeling, gene expression, and cellular plasticity in the central nervous system (CNS). This review provides a comprehensive overview of the classification and functional diversity of HDACs, with particular emphasis on their roles in neural progenitor cells, mature neurons, and glial populations. In neural stem and progenitor cells, HDACs modulate neurogenesis, fate specification, and lineage commitment. In differentiated neurons, HDACs govern synaptic plasticity, memory formation, and survival. In glial cells, including astrocytes and microglia, HDACs orchestrate inflammatory responses, redox balance, and metabolic adaptations. We further examine the dysregulation of HDAC expression and activity in major neurodegenerative diseases, including Alzheimer’s disease and Parkinson’s disease. Evidence from human post-mortem brain studies reveals region- and isoform-specific alterations in HDAC expression, which are closely associated with cognitive decline, mitochondrial dysfunction, and neuroinflammation. Preclinical studies support the use of HDAC inhibitors (HDACi) as neuroprotective agents, capable of restoring acetylation homeostasis, reducing neuroinflammation, and improving neuronal function. Given the relevance of HDACi, we summarize current clinical studies assessing the safety of these compounds in the context of tumor biology, as well as their potential future applications in neurodegenerative diseases. Together, this review underscores the dual significance of HDACs as biomarkers and therapeutic targets in the context of CNS disorders. Full article

The precise identification, classification, sorting, and rapid and accurate quality assessment of soybean seeds are extremely important in terms of the continuity of agricultural production, varietal purity, seed processing, protein extraction, and food safety. Currently, commonly used methods for the identification and quality assessment of soybean seeds include morphological analysis, chemical analysis, protein electrophoresis, liquid chromatography, spectral analysis, and image analysis. The use of image analysis and artificial intelligence is the aim of the presented research, in which a method for the automatic classification of soybean varieties, the assessment of the degree of damage, and the identification of geometric features of soybean seeds based on numerical models obtained using a 3D scanner has been proposed. Unlike traditional two-dimensional images, which only represent height and width, 3D imaging adds a third dimension, allowing for a more realistic representation of the shape of the seeds. The research was conducted on soybean seeds with a moisture content of 13%, and the seeds were stored in a room with a temperature of 20–23 °C and air humidity of 60%. Individual soybean seeds were scanned to create 3D models, allowing for the measurement of their geometric parameters, assessment of texture, evaluation of damage, and identification of characteristic varietal features. The developed 3D-CNN network model comprised an architecture consisting of an input layer, three hidden layers, and one output layer with a single neuron. The aim of the conducted research is to design a new, three-dimensional 3D-CNN architecture, the main task of which is the classification of soybean seeds. For the purposes of network analysis and testing, 22 input criteria were defined, with a hierarchy of their importance. The training, testing, and validation database of the SB3D-NET network consisted of 3D models obtained as a result of scanning individual soybean seeds, 100 for each variety. The accuracy of the training process of the proposed SB3D-NET model for the qualitative classification of 3D models of soybean seeds, based on the adopted criteria, was 95.54%, and the accuracy of its validation was 90.74%. The relative loss value during the training process of the SB3D-NET model was 18.53%, and during its validation process, it was 37.76%. The proposed SB3D-NET neural network model for all twenty-two criteria achieves values of global error (GE) of prediction and classification of seeds at the level of 0.0992. Full article

Contemporary visual assistive devices often lack immersive user experience due to passive control systems. This study introduces a neuronally controlled visual assistive device (NCVAD) that aims to assist visually impaired users in performing reach tasks with active, intuitive control. The developed NCVAD integrates computer vision, electroencephalogram (EEG) signal processing, and robotic manipulation to facilitate object detection, selection, and assistive guidance. The monocular vision-based subsystem implements the YOLOv8n algorithm to detect objects of daily use. Then, audio prompting conveys the detected objects’ information to the user, who selects their targeted object using a voluntary trigger decoded through real-time EEG classification. The target’s physical coordinates are extracted using ArUco markers, and a gradient descent-based path optimization algorithm (POA) guides a 3-DoF robotic arm to reach the target. The classification algorithm achieves over 85% precision and recall in decoding EEG data, even with coexisting physiological artifacts. Similarly, the POA achieves approximately 650 ms of actuation time with a 0.001 learning rate and 0.1 cm² error threshold settings. In conclusion, the study also validates the preliminary analysis results on a working physical model and benchmarks the robotic arm’s performance against human users, establishing the proof-of-concept for future assistive technologies integrating EEG and computer vision paradigms. Full article

Glioblastoma (GBM) remains one of the most aggressive and treatment-resistant brain tumors, largely due to its profound intratumoral heterogeneity and immunosuppressive microenvironment. Various classifications of GBM subtypes were created based on transcriptional and methylation profiles. This effort, followed by the development of new technology such as single-nuclei sequencing (snRNAseq) and spatial transcriptomics, led to a better understanding of the glioma cells’ plasticity and their ability to transition between diverse cellular states. GBM cells can mimic neurodevelopmental programs to resemble oligodendrocyte or neural progenitor behavior and hitchhike the local neuronal network to support their growth. The tumor microenvironment, especially under hypoxic conditions, drives the tumor cell clonal selection, which then reshapes the immune cells’ functions. These adaptations contribute to immune evasion by progressively disabling T cell and myeloid cell functions, ultimately establishing a highly immunosuppressive tumor milieu. This complex and metabolically constrained environment poses a major barrier to effective antitumor immunity and limits the success of conventional therapies. Understanding the dynamic interactions between glioma cells and their microenvironment is essential for the development of more effective immunotherapies and rational combination strategies aimed at overcoming resistance and improving patient outcomes. Full article

This study aims to characterize short-wave infrared (SWIR) reflectance spectra at cranial (at the scalp overlying the frontal cortex and the temporal bone window) and extracranial (biceps and triceps) sites in patients with multiple sclerosis (MS) and age-/sex-matched controls. We sought to identify the diagnostic accuracy of wavelength-specific patterns in distinguishing MS from normal controls and spectral markers associated with disability (e.g., Expanded Disability Status Scale scores). To achieve these objectives, we employed a multi-site SWIR spectroscopy acquisition protocol that included measurements from traditional cranial locations as well as extracranial reference sites. Advanced spectral analysis techniques, including wavelength-dependent absorption modeling and machine learning-based classification, were applied to differentiate MS-related hemodynamic changes from normal physiological variability. Classification models achieved perfect performance (accuracy = 1.00), and cortical site regression models showed strong predictive power (EDSS: R²_CV = 0.980; FSS: R²_CV = 0.939). Variable Importance in Projection (VIP) analysis highlighted key wavelengths as potential spectral biomarkers. This approach allowed us to explore novel biomarkers of neural and systemic impairment in MS, paving the way for potential clinical applications of SWIR spectroscopy in disease monitoring and management. In conclusion, spectral analysis revealed distinct wavelength-specific patterns collected from cranial and extracranial sites reflecting biochemical and structural differences between patients with MS and normal subjects. These differences are driven by underlying physiological changes, including myelin integrity, neuronal density, oxidative stress, and water content fluctuations in the brain or muscles. This study shows that portable spectral devices may contribute to bedside individuation and monitoring of neural diseases, offering a cost-effective alternative to repeated imaging. Full article

Overfitting remains a major difficulty in training deep neural networks, especially when attempting to achieve good generalization in complex classification tasks. Standard dropout is often employed to address this issue; however, its uniform random inactivation of neurons typically leads to instability and insufficient performance increases. This paper proposes an upgraded regularization technique merging adaptive sigmoidal dropout with weight amplification, seeking to dynamically adjust neuron deactivation depending on weight statistics, activation patterns, and neuron history. The proposed dropout process uses a sigmoid function driven by a temperature parameter to determine deactivation likelihood and incorporates a “neuron recovery” step to restore important activations. Simultaneously, the method amplifies high-magnitude weights to select crucial traits during learning. The proposed method is tested on CIFAR-10, and CIFAR-100 datasets using four unique CNN architectures, including deep and residual-based models, to evaluate the approach. Results demonstrate that the suggested technique consistently outperforms both standard dropout and baseline models without dropout, yielding higher validation accuracy and lower, more stable validation loss across all datasets. In particular, it demonstrated superior convergence and generalization performance on challenging datasets such as CIFAR-100. These findings demonstrate the potential of the proposed technique to improve model robustness and training efficiency and provide an alternative in complex classification tasks. Full article

Investigating brain area functions requires advanced technologies, but meaningful insights depend on correlating neural signals with behavior. Traditional mice behavior annotation methods, including manual and semi-automated approaches, are limited by subjectivity and time constraints. To overcome these limitations, our study employs the YOLO neural network for precise mice tracking and composite RGB frames for behavioral scoring. Our model, trained on over 10,000 frames, accurately classifies sitting, running, and grooming behaviors. Additionally, we provide statistical metrics and data visualization tools. We further combined AI-powered behavior labeling to examine hippocampal neuronal activity using fluorescence microscopy. To analyze neuronal circuit dynamics, we utilized a manifold analysis approach, revealing distinct functional patterns corresponding to transgenic 5xFAD Alzheimer’s model mice. This open-source software enhances the accuracy and efficiency of behavioral and neural data interpretation, advancing neuroscience research. Full article

Alzheimer’s disease (AD) is the most prevalent neurodegenerative disorder and represents a major public health challenge. With increasing life expectancy, the incidence of AD has also increased, highlighting the need for early diagnosis and improved monitoring. Traditionally, diagnosis has relied on clinical symptoms and neuroimaging; however, the introduction of biomarkers has revolutionized disease assessment. Traditional biomarkers, including the Aβ42/Aβ40 ratio, phosphorylated tau (p-Tau181, p-Tau217, and p-Tau231), total tau (t-tau), and neurofilament light chain (NfL), are fundamental for staging AD progression. Updated guidelines introduced the ATX(N) model, which extends biomarker classification to include additional promising biomarkers, such as SNAP-25, YKL-40, GAP-43, VILIP-1, progranulin (PGRN), TREM2, IGF-1, hFABP, MCP-1, TDP-43, and BDNF. Recent advancements have allowed for the detection of these biomarkers not only in CSF but also in plasma and neuron-derived exosomes, offering less invasive and more accessible diagnostic options. This review explores established and emerging biomarkers and emphasizes their roles in early diagnosis, patient stratification, and precision medicine. Full article