Frontiers in Neuroinformatics最新文献

Introduction: Brain tumors are a leading cause of mortality worldwide, with early and accurate diagnosis being essential for effective treatment. Although Deep Learning (DL) models offer strong performance in tumor detection and segmentation using MRI, their black-box nature hinders clinical adoption due to a lack of interpretability.

Methods: We present a hybrid AI framework that integrates a 3D U-Net Convolutional Neural Network for MRI-based tumor segmentation with radiomic feature extraction. Dimensionality reduction is performed using machine learning, and an Adaptive Neuro-Fuzzy Inference System (ANFIS) is employed to produce interpretable decision rules. Each experiment is constrained to a small set of high-impact radiomic features to enhance clarity and reduce complexity.

Results: The framework was validated on the BraTS2020 dataset, achieving an average DICE Score of 82.94% for tumor core segmentation and 76.06% for edema segmentation. Classification tasks yielded accuracies of 95.43% for binary (healthy vs. tumor) and 92.14% for multi-class (healthy vs. tumor core vs. edema) problems. A concise set of 18 fuzzy rules was generated to provide clinically interpretable outputs.

Discussion: Our approach balances high diagnostic accuracy with enhanced interpretability, addressing a critical barrier in applying DL models in clinical settings. Integrating of ANFIS and radiomics supports transparent decision-making, facilitating greater trust and applicability in real-world medical diagnostics assistance.

Introduction: Autism spectrum disorder (ASD) encompasses a diverse range of neurodevelopmental disorders with complex etiologies, including genetic, environmental, and neuroanatomical factors. While the exact mechanisms underlying ASD remain unclear, structural abnormalities in the brain offer valuable insights into its pathophysiology. The corpus callosum, the largest white matter tract in the brain, plays a crucial role in interhemispheric communication, and its structural abnormalities may contribute to ASD-related phenotypes.

Methods: To investigate the ultrastructural alterations in the corpus callosum associated with ASD, we utilized serial scanning electron microscopy (sSEM) in mice. A dataset of the entire sagittal sections of the corpus callosum from wild-type and Shank3B mutant mice was acquired at 4 nm resolution, enabling precise comparisons of myelinated axon properties. Leveraging a fine-tuned EM-SAM model for automated segmentation, we quantitatively analyzed key metrics, including G-ratio, myelin thickness, and axonal density.

Results: In the corpus callosum of Shank3B autism model mouse, we observed a significant increase in myelinated axon density, accompanied by thinner myelin sheaths compared to wild-type. Additionally, we identified abnormalities in the diameter distribution of myelinated axons and deviations in G-ratio. Notably, these ultrastructural alterations were widespread across the corpus callosum, suggesting a global disruption of myelinated axon integrity.

Discussion: This study provides novel insights into the microstructural abnormalities of the corpus callosum in ASD mouse, supporting the hypothesis that myelination deficits contribute to ASD-related communication impairments between brain hemispheres. However, given the structural focus of this study, further research integrating functional assessments is necessary to establish a direct link between these morphological changes and ASD-related neural dysfunction.

Introduction: Motor imagery electroencephalographic (MI-EEG) signal recognition is used in various brain-computer interface (BCI) systems. In most existing BCI systems, this identification relies on classification algorithms. However, generally, a large amount of subject-specific labeled training data is required to reliably calibrate the classification algorithm for each new subject. To address this challenge, an effective strategy is to integrate transfer learning into the construction of intelligent models, allowing knowledge to be transferred from the source domain to enhance the performance of models trained in the target domain. Although transfer learning has been implemented in EEG signal recognition, many existing methods are designed specifically for certain intelligent models, limiting their application and generalization.

Methods: To broaden application and generalization, an extended-LSR-based inductive transfer learning method is proposed to facilitate transfer learning across various classical intelligent models, including neural networks, Takagi-SugenoKang (TSK) fuzzy systems, and kernel methods.

Results and discussion: The proposed method not only promotes the transfer of valuable knowledge from the source domain to improve learning performance in the target domain when target domain training data are insufficient but also enhances application and generalization by incorporating multiple classic base models. The experimental results demonstrate the effectiveness of the proposed method in MI-EEG signal recognition.

Data sharing in scientific research is widely acknowledged as crucial for accelerating progress and innovation. Mandates from funders, such as the NIH's updated Data Sharing Policy, have been beneficial in promoting data sharing. However, the effectiveness of such mandates relies heavily on the motivation of data providers. Despite policy-imposed requirements, many researchers may only comply minimally, resulting in data that is inadequately reusable. Here, we discuss the multifaceted challenges of incentivizing data sharing and the complex interplay of factors involved. Our paper delves into the motivations of various stakeholders, including funders, investigators, and data users, highlighting the differences in perspectives and concerns. We discuss the role of guidelines, such as the FAIR principles, in promoting good data management practices but acknowledge the practical and ethical challenges in implementation. We also examine the impact of infrastructure on data sharing effectiveness, emphasizing the need for systems that support efficient data discovery, access, and analysis. We address disparities in resources and expertise among researchers and concerns related to data misuse and misinterpretation. Here, we advocate for a holistic approach to incentivizing data sharing beyond mere compliance with mandates. It calls for the development of reward systems, financial incentives, and supportive infrastructure to encourage researchers to share data enthusiastically and effectively. By addressing these challenges collaboratively, the scientific community can realize the full potential of data sharing to advance knowledge and innovation.

The Stimulating Peripheral Activity to Relieve Conditions (SPARC) program is a U.S. National Institutes of Health (NIH) funded effort to enhance our understanding of the neural circuitry responsible for visceral control. SPARC's mission is to identify, extract, and compile our overall existing knowledge and understanding of the autonomic nervous system (ANS) connectivity between the central nervous system and end organs. A major goal of SPARC is to use this knowledge to promote the development of the next generation of neuromodulation devices and bioelectronic medicine for nervous system diseases. As part of the SPARC program, we have been developing the SPARC Connectivity Knowledge Base of the Autonomic Nervous System (SCKAN), a dynamic resource containing information about the origins, terminations, and routing of ANS projections. The distillation of SPARC's connectivity knowledge into this knowledge base involves a rigorous curation process to capture connectivity information provided by experts, published literature, textbooks, and SPARC scientific data. SCKAN is used to automatically generate anatomical and functional connectivity maps on the SPARC portal. In this article, we present the design and functionality of SCKAN, including the detailed knowledge engineering process developed to populate the resource with high quality and accurate data. We discuss the process from both the perspective of SCKAN's ontological representation as well as its practical applications in developing information systems. We share our techniques, strategies, tools and insights for developing a practical knowledgebase of ANS connectivity that supports continual enhancement.

Introduction: The effectiveness of research and innovation often relies on the diversity or heterogeneity of datasets that are Findable, Accessible, Interoperable and Reusable (FAIR). However, the global landscape of brain data is yet to achieve desired levels of diversity that can facilitate generalisable outputs. Brain datasets from low-and middle-income countries of Africa are still missing in the global open science ecosystem. This can mean that decades of brain research and innovation may not be generalisable to populations in Africa.

Methods: This research combined experiential learning or experiential research with a survey questionnaire. The experiential research involved deriving insights from direct, hands-on experiences of collecting African Brain data in view of making it FAIR. This was a critical process of action, reflection, and learning from doing data collection. A questionnaire was then used to validate the findings from the experiential research and provide wider contexts for these findings.

Results: The experiential research revealed major challenges to FAIR African brain data that can be categorised as socio-cultural, economic, technical, ethical and legal challenges. It also highlighted opportunities for growth that include capacity development, development of technical infrastructure, funding as well as policy and regulatory changes. The questionnaire then showed that the wider African neuroscience community believes that these challenges can be ranked in order of priority as follows: Technical, economic, socio-cultural and ethical and legal challenges.

Conclusion: We conclude that African researchers need to work together as a community to address these challenges in a way to maximise efforts and to build a thriving FAIR brain data ecosystem that is socially acceptable, ethically responsible, technically robust and legally compliant.

Introduction: Multiple sclerosis (MS) is an intricate neurological condition that affects many individuals worldwide, and there is a considerable amount of research into understanding the pathology and treatment development. Nonlinear analysis has been increasingly utilized in analyzing electroencephalography (EEG) signals from patients with various neurological disorders, including MS, and it has been proven to be an effective tool for comprehending the complex nature exhibited by the brain.

Methods: This study seeks to investigate the impact of Interferon-β (IFN-β) and dimethyl fumarate (DMF) on MS patients using sample entropy (SampEn) and Higuchi's fractal dimension (HFD) on collected EEG signals. The data were collected at Jagiellonian University in Krakow, Poland. In this study, a total of 175 subjects were included across the groups: IFN-β (n = 39), DMF (n = 53), and healthy controls (n = 83).

Results: The analysis indicated that each treatment group exhibited more complex EEG signals than the control group. SampEn had demonstrated significant sensitivity to the effects of each treatment compared to HFD, while HFD showed more sensitivity to changes over time, particularly in the DMF group.

Discussion: These findings enhance our understanding of the complex nature of MS, support treatment development, and demonstrate the effectiveness of nonlinear analysis methods.

Analysis of electroencephalography (EEG) signals gathered by brain-computer interface (BCI) recently demonstrated that deep neural networks (DNNs) can be effectively used for investigation of time sequences for physical actions (PA) classification. In this study, the relatively simple DNN with fully connected network (FCN) components and convolutional neural network (CNN) components was considered to classify finger-palm-hand manipulations each from the grasp-and-lift (GAL) dataset. The main aim of this study was to imitate and investigate environmental influence by the proposed noise data augmentation (NDA) of two kinds: (i) natural NDA by inclusion of noise EEG data from neighboring regions by increasing the sampling size N and the different offset values for sample labeling and (ii) synthetic NDA by adding the generated Gaussian noise. The natural NDA by increasing N leads to the higher micro and macro area under the curve (AUC) for receiver operating curve values for the bigger N values than usage of synthetic NDA. The detrended fluctuation analysis (DFA) was applied to investigate the fluctuation properties and calculate the correspondent Hurst exponents H for the quantitative characterization of the fluctuation variability. H values for the low time window scales (< 2 s) are higher in comparison with ones for the bigger time window scales. For example, H more than 2-3 times higher for some PAs, i.e., it means that the shorter EEG fragments (< 2 s) demonstrate the scaling behavior of the higher complexity than the longer fragments. As far as these results were obtained by the relatively small DNN with the low resource requirements, this approach can be promising for porting such models to Edge Computing infrastructures on devices with the very limited computational resources.

Introduction: Recently, numerous studies have focused on the semantic decoding of perceived images based on functional magnetic resonance imaging (fMRI) activities. However, it remains unclear whether it is possible to establish relationships between brain activities and semantic features of human actions in video stimuli. Here we construct a framework for decoding action semantics by establishing relationships between brain activities and semantic features of human actions.

Methods: To effectively use a small amount of available brain activity data, our proposed method employs a pre-trained image action recognition network model based on an expanding three-dimensional (X3D) deep neural network framework (DNN). To apply brain activities to the image action recognition network, we train regression models that learn the relationship between brain activities and deep-layer image features. To improve decoding accuracy, we join by adding the nonlocal-attention mechanism module to the X3D model to capture long-range temporal and spatial dependence, proposing a multilayer perceptron (MLP) module of multi-task loss constraint to build a more accurate regression mapping approach and performing data enhancement through linear interpolation to expand the amount of data to reduce the impact of a small sample.

Results and discussion: Our findings indicate that the features in the X3D-DNN are biologically relevant, and capture information useful for perception. The proposed method enriches the semantic decoding model. We have also conducted several experiments with data from different subsets of brain regions known to process visual stimuli. The results suggest that semantic information for human actions is widespread across the entire visual cortex.

Introduction: Neurodegenerative diseases such as Alzheimer's disease (AD) or frontotemporal lobar degeneration (FTLD) involve specific loss of brain volume, detectable in vivo using T1-weighted MRI scans. Supervised machine learning approaches classifying neurodegenerative diseases require diagnostic-labels for each sample. However, it can be difficult to obtain expert labels for a large amount of data. Self-supervised learning (SSL) offers an alternative for training machine learning models without data-labels.

Methods: We investigated if the SSL models can be applied to distinguish between different neurodegenerative disorders in an interpretable manner. Our method comprises a feature extractor and a downstream classification head. A deep convolutional neural network, trained with a contrastive loss, serves as the feature extractor that learns latent representations. The classification head is a single-layer perceptron that is trained to perform diagnostic group separation. We used N = 2,694 T1-weighted MRI scans from four data cohorts: two ADNI datasets, AIBL and FTLDNI, including cognitively normal controls (CN), cases with prodromal and clinical AD, as well as FTLD cases differentiated into its phenotypes.

Results: Our results showed that the feature extractor trained in a self-supervised way provides generalizable and robust representations for the downstream classification. For AD vs. CN, our model achieves 82% balanced accuracy on the test subset and 80% on an independent holdout dataset. Similarly, the Behavioral variant of frontotemporal dementia (BV) vs. CN model attains an 88% balanced accuracy on the test subset. The average feature attribution heatmaps obtained by the Integrated Gradient method highlighted hallmark regions, i.e., temporal gray matter atrophy for AD, and insular atrophy for BV.

Conclusion: Our models perform comparably to state-of-the-art supervised deep learning approaches. This suggests that the SSL methodology can successfully make use of unannotated neuroimaging datasets as training data while remaining robust and interpretable.