Frontiers in Neuroinformatics最新文献

Introduction: This paper describes an experimental work using machine learning (ML) as a "decoding for interpretation" to understand the brain's physiology better.

Methods: Multivariate pattern analysis (MVPA) was used to decode the patterns of event-related potentials (ERPs, brain responses to stimuli) in a visual oddball task. The ERPs were measured before (run 1) and after (30 min-run 2, 90 min-run 3) a single dose of an energy dietary supplement with only a small amount of caffeine.

Results: Its effect on ERPs was successfully decoded. Above-chance decoding accuracies were obtained between ∼350 and 450 ms (corresponds to P3 peak) after stimulus onset for both the placebo and study groups, whereas between ∼200 and 260 ms (corresponds to P2 waveform) only in the placebo group. Moreover, the decoding accuracies were significantly higher in the placebo than in the study group in the 200-250 ms and 450-500 ms time bins. Our previously reported findings showed an increase in P3 amplitude among the runs only in the placebo group, indicating a reduction of mental fatigue caused by the supplementation.

Discussion: Thus, this paper extends these results, showing that the dietary supplement affected the brain's neural activity related to the attention-related processing of the visual stimuli in the oddball task already at the early processing stage. This implies that inhibiting the fatigue-related brain changes after only a single dose of a dietary neurostimulant acts on early and late processing stages. This emphasizes the value of decoding for interpretation in ERP research. The results also point out the necessity of controlling the uptake of dietary supplements before the neurophysiological examinations.

Introduction: Computational models are valuable tools for understanding and studying a wide range of characteristics and mechanisms of the brain. Furthermore, they can also be exploited to explore biological neural networks from neuronal cultures. However, few of the current in silico approaches consider the energetic demand of neurons to sustain their electrophysiological functions, specifically their well-known oxygen-dependent firing.

Methods: In this work, we introduce Digitoids, a computational platform which integrates a Hodgkin-Huxley-like model to describe the time-dependent oscillations of the neuronal membrane potential with oxygen dynamics in the culture environment. In Digitoids, neurons are connected to each other according to Small-World topologies observed in cell cultures, and oxygen consumption by cells is modeled as limited by diffusion through the culture medium. The oxygen consumed is used to fuel their basal metabolism and the activity of Na⁺-K⁺-ATP membrane pumps, thus it modulates neuronal firing.

Results: Our simulations show that the characteristics of neuronal firing predicted throughout the network are related to oxygen availability. In addition, the average firing rate predicted by Digitoids is statistically similar to that measured in neuronal networks in vitro, further proving the relevance of this platform.

Dicussion: Digitoids paves the way for a new generation of in silico models of neuronal networks, establishing the oxygen dependence of electrophysiological dynamics as a fundamental requirement to improve their physiological relevance.

Introduction: Imagined speech decoding using EEG holds promising applications for individuals with motor neuron diseases, although its performance remains limited due to small dataset sizes and the absence of sensory feedback. Here, we investigated whether incorporating EEG data from overt (pronounced) speech could enhance imagined speech classification.

Methods: Our approach systematically compares four classification scenarios by modifying the training dataset: intra-subject (using only imagined speech, combining overt and imagined speech, and using only overt speech) and multi-subject (combining overt speech data from different participants with the imagined speech of the target participant). We implemented all scenarios using the convolutional neural network EEGNet. To this end, twenty-four healthy participants pronounced and imagined five Spanish words.

Results: In binary word-pair classifications, combining overt and imagined speech data in the intra-subject scenario led to accuracy improvements of 3%-5.17% in four out of 10 word pairs, compared to training with imagined speech only. Although the highest individual accuracy (95%) was achieved with imagined speech alone, the inclusion of overt speech data allowed more participants to surpass 70% accuracy, increasing from 10 (imagined only) to 15 participants. In the intra-subject multi-class scenario, combining overt and imagined speech did not yield statistically significant improvements over using imagined speech exclusively.

Discussion: Finally, we observed that features such as word length, phonological complexity, and frequency of use contributed to higher discriminability between certain imagined word pairs. These findings suggest that incorporating overt speech data can improve imagined speech decoding in individualized models, offering a feasible strategy to support the early adoption of brain-computer interfaces before speech deterioration occurs in individuals with motor neuron diseases.

Electroencephalogram (EEG) signal analysis is important for the diagnosis of various neurological conditions. Traditional deep neural networks, such as convolutional networks, sequence-to-sequence networks, and hybrids of such neural networks were proven to be effective for a wide range of neurological disease classifications. However, these are limited by the requirement of a large dataset, extensive training, and hyperparameter tuning, which require expert-level machine learning knowledge. This survey paper aims to explore the ability of Large Language Models (LLMs) to transform existing systems of EEG-based disease diagnostics. LLMs have a vast background knowledge in neuroscience, disease diagnostics, and EEG signal processing techniques. Thus, these models are capable of achieving expert-level performance with minimal training data, nominal fine-tuning, and less computational overhead, leading to a shorter time to find effective solutions for diagnostics. Further, in comparison with traditional methods, LLM's capability to generate intermediate results and meaningful reasoning makes it more reliable and transparent. This paper delves into several use cases of LLM in EEG signal analysis and attempts to provide a comprehensive understanding of techniques in the domain that can be applied to different disease diagnostics. The study also strives to highlight challenges in the deployment of LLM models, ethical considerations, and bottlenecks in optimizing models due to requirements of specialized methods such as Low-Rank Adapation. In general, this survey aims to stimulate research in the area of EEG disease diagnostics by effectively using LLMs and associated techniques in machine learning pipelines.

Advancements in machine learning hold great promise for the analysis of multimodal neuroimaging data. They can help identify biomarkers and improve diagnosis for various neurological disorders. However, the application of such techniques for rare and heterogeneous diseases remains challenging due to small-cohorts available for acquiring data. Efforts are therefore commonly directed toward improving the classification models, in an effort to optimize outcomes given the limited data. In this study, we systematically evaluated the impact of various machine learning pipeline configurations, including scaling methods, feature selection, dimensionality reduction, and hyperparameter optimization. The efficacy of such components in the pipeline was evaluated on classification performance using multimodal MRI data from a cohort of 16 ALS patients and 14 healthy controls. Our findings reveal that, while certain pipeline components, such as subject-wise feature normalization, help improve classification outcomes, the overall influence of pipeline refinements on performance is modest. Feature selection and dimensionality reduction steps were found to have limited utility, and the choice of hyperparameter optimization strategies produced only marginal gains. Our results suggest that, for small-cohort studies, the emphasis should shift from extensive tuning of these pipelines to addressing data-related limitations, such as progressively expanding cohort size, integrating additional modalities, and maximizing the information extracted from existing datasets. This study provides a methodological framework to guide future research and emphasizes the need for dataset enrichment to improve clinical utility.

With increasing model complexity, models are typically re-used and evolved rather than starting from scratch. There is also a growing challenge in ensuring that these models can seamlessly work across various simulation backends and hardware platforms. This underscores the need to ensure that models are easily findable, accessible, interoperable, and reusable-adhering to the FAIR principles. NESTML addresses these requirements by providing a domain-specific language for describing neuron and synapse models that covers a wide range of neuroscientific use cases. The language is supported by a code generation toolchain that automatically generates low-level simulation code for a given target platform (for example, C++ code targeting NEST Simulator). Code generation allows an accessible and easy-to-use language syntax to be combined with good runtime simulation performance and scalability. With an intuitive and highly generic language, combined with the generation of efficient, optimized simulation code supporting large-scale simulations, it opens up neuronal network model development and simulation as a research tool to a much wider community. While originally developed in the context of NEST Simulator, NESTML has been extended to target other simulation platforms, such as the SpiNNaker neuromorphic hardware platform. The processing toolchain is written in Python and is lightweight and easily customizable, making it easy to add support for new simulation platforms.

This study presents a general trainable network of Hopf oscillators to model high-dimensional electroencephalogram (EEG) signals across different sleep stages. The proposed architecture consists of two main components: a layer of interconnected oscillators and a complex-valued feed-forward network designed with and without a hidden layer. Incorporating a hidden layer in the feed-forward network leads to lower reconstruction errors than the simpler version without it. Our model reconstructs EEG signals across all five sleep stages and predicts the subsequent 5 s of EEG activity. The predicted data closely aligns with the empirical EEG regarding mean absolute error, power spectral similarity, and complexity measures. We propose three models, each representing a stage of increasing complexity from initial training to architectures with and without hidden layers. In these models, the oscillators initially lack spatial localization. However, we introduce spatial constraints in the final two models by superimposing spherical shells and rectangular geometries onto the oscillator network. Overall, the proposed model represents a step toward constructing a large-scale, biologically inspired model of brain dynamics.

In cognitive neuroscience, the integration of deep neural networks (DNNs) with traditional neuroscientific analyses has significantly advanced our understanding of both biological neural processes and the functioning of DNNs. However, challenges remain in effectively comparing the representational spaces of artificial models and brain data, particularly due to the growing variety of models and the specific demands of neuroimaging research. To address these challenges, we present Net2Brain, a Python-based toolbox that provides an end-to-end pipeline for incorporating DNNs into neuroscience research, encompassing dataset download, a large selection of models, feature extraction, evaluation, and visualization. Net2Brain provides functionalities in four key areas. First, it offers access to over 600 DNNs trained on diverse tasks across multiple modalities, including vision, language, audio, and multimodal data, organized through a carefully structured taxonomy. Second, it provides a streamlined API for downloading and handling popular neuroscience datasets, such as the NSD and THINGS dataset, allowing researchers to easily access corresponding brain data. Third, Net2Brain facilitates a wide range of analysis options, including feature extraction, representational similarity analysis (RSA), and linear encoding, while also supporting advanced techniques like variance partitioning and searchlight analysis. Finally, the toolbox integrates seamlessly with other established open source libraries, enhancing interoperability and promoting collaborative research. By simplifying model selection, data processing, and evaluation, Net2Brain empowers researchers to conduct more robust, flexible, and reproducible investigations of the relationships between artificial and biological neural representations.

Introduction: Alzheimer's disease is a progressive neurodegenerative disorder challenging early diagnosis and treatment. Recent advancements in deep learning algorithms applied to multimodal brain imaging offer promising solutions for improving diagnostic accuracy and predicting disease progression.

Method: This narrative review synthesizes current literature on deep learning applications in Alzheimer's disease diagnosis using multimodal neuroimaging. The review process involved a comprehensive search of relevant databases (PubMed, Embase, Google Scholar and ClinicalTrials.gov), selection of pertinent studies, and critical analysis of findings. We employed a best-evidence approach, prioritizing high-quality studies and identifying consistent patterns across the literature.

Results: Deep learning architectures, including convolutional neural networks, recurrent neural networks, and transformer-based models, have shown remarkable potential in analyzing multimodal neuroimaging data. These models can effectively process structural and functional imaging modalities, extracting relevant features and patterns associated with Alzheimer's pathology. Integration of multiple imaging modalities has demonstrated improved diagnostic accuracy compared to single-modality approaches. Deep learning models have also shown promise in predictive modeling, identifying potential biomarkers and forecasting disease progression.

Discussion: While deep learning approaches show great potential, several challenges remain. Data heterogeneity, small sample sizes, and limited generalizability across diverse populations are significant hurdles. The clinical translation of these models requires careful consideration of interpretability, transparency, and ethical implications. The future of AI in neurodiagnostics for Alzheimer's disease looks promising, with potential applications in personalized treatment strategies.