Dynamic GNNs, which integrate temporal and spatial features in Electroencephalography (EEG) data, have shown great potential in automating seizure detection. However, fully capturing the underlying dynamics necessary to represent brain states, such as seizure and non-seizure, remains a non-trivial task and presents two fundamental challenges. First, most existing dynamic GNN methods are built on temporally fixed static graphs, which fail to reflect the evolving nature of brain connectivity during seizure progression. Second, current efforts to jointly model temporal signals and graph structures and, more importantly, their interactions remain nascent, often resulting in inconsistent performance. To address these challenges, we present the first theoretical analysis of these two problems, demonstrating the effectiveness and necessity of explicit dynamic modeling and time-then-graph dynamic GNN method. Building on these insights, we propose EvoBrain, a novel seizure detection model that integrates a two-stream Mamba architecture with a GCN enhanced by Laplacian Positional Encoding, following neurological insights. Moreover, EvoBrain incorporates explicitly dynamic graph structures, allowing both nodes and edges to evolve over time. Our contributions include (a) a theoretical analysis proving the expressivity advantage of explicit dynamic modeling and time-then-graph over other approaches, (b) a novel and efficient model that significantly improves AUROC by 23\% and F1 score by 30\%, compared with the dynamic GNN baseline, and (c) broad evaluation of our method on the challenging early seizure prediction task.

While end-to-end multi-channel electroencephalography (EEG) learning approaches have shown significant promise, their applicability is often constrained in neurological diagnostics, such as intracranial EEG resources. When provided with a single-channel EEG, how can we learn representations that are robust to multi-channels and scalable across varied tasks, such as seizure prediction? In this paper, we present SplitSEE, a structurally splittable framework designed for effective temporal-frequency representation learning in single-channel EEG. The key concept of SplitSEE is a self-supervised framework incorporating a deep clustering task. Given an EEG, we argue that the time and frequency domains are two distinct perspectives, and hence, learned representations should share the same cluster assignment. To this end, we first propose two domain-specific modules that independently learn domain-specific representation and address the temporal-frequency tradeoff issue in conventional spectrogram-based methods. Then, we introduce a novel clustering loss to measure the information similarity. This encourages representations from both domains to coherently describe the same input by assigning them a consistent cluster. SplitSEE leverages a pretraining-to-fine-tuning framework within a splittable architecture and has following properties: (a) Effectiveness: it learns representations solely from single-channel EEG but has even outperformed multi-channel baselines. (b) Robustness: it shows the capacity to adapt across different channels with low performance variance. Superior performance is also achieved with our collected clinical dataset. (c) Scalability: With just one fine-tuning epoch, SplitSEE achieves high and stable performance using partial model layers.

Dementia and mild cognitive impairment (MCI) represent significant health challenges in an aging population. As the search for noninvasive, precise and accessible diagnostic methods continues, the efficacy of electroencephalography (EEG) combined with deep convolutional neural networks (DCNNs) in varied clinical settings remains unverified, particularly for pathologies underlying MCI such as Alzheimer's disease (AD), dementia with Lewy bodies (DLB) and idiopathic normal-pressure hydrocephalus (iNPH). Addressing this gap, our study evaluates the generalizability of a DCNN trained on EEG data from a single hospital (Hospital #1). For data from Hospital #1, the DCNN achieved a balanced accuracy (bACC) of 0.927 in classifying individuals as healthy (n = 69) or as having AD, DLB, or iNPH (n = 188). The model demonstrated robustness across institutions, maintaining bACCs of 0.805 for data from Hospital #2 (n = 73) and 0.920 at Hospital #3 (n = 139). Additionally, the model could differentiate AD, DLB, and iNPH cases with bACCs of 0.572 for data from Hospital #1 (n = 188), 0.619 for Hospital #2 (n = 70), and 0.508 for Hospital #3 (n = 139). Notably, it also identified MCI pathologies with a bACC of 0.715 for Hospital #1 (n = 83), despite being trained on overt dementia cases instead of MCI cases. These outcomes confirm the DCNN's adaptability and scalability, representing a significant stride toward its clinical application. Additionally, our findings suggest a potential for identifying shared EEG signatures between MCI and dementia, contributing to the field's understanding of their common pathophysiological mechanisms.

Magnetoencephalography (MEG) is a useful tool for clinically evaluating the localization of interictal spikes. Neurophysiologists visually identify spikes from the MEG waveforms and estimate the equivalent current dipoles (ECD). However, presently, these analyses are manually performed by neurophysiologists and are time-consuming. Another problem is that spike identification from MEG waveforms largely depends on neurophysiologists' skills and experiences. These problems cause poor cost-effectiveness in clinical MEG examination. To overcome these problems, we fully automated spike identification and ECD estimation using a deep learning approach fully automated AI-based MEG interictal epileptiform discharge identification and ECD estimation (FAMED). We applied a semantic segmentation method, which is an image processing technique, to identify the appropriate times between spike onset and peak and to select appropriate sensors for ECD estimation. FAMED was trained and evaluated using clinical MEG data acquired from 375 patients. FAMED training was performed in two stages: in the first stage, a classification network was learned, and in the second stage, a segmentation network that extended the classification network was learned. The classification network had a mean AUC of 0.9868 (10-fold patient-wise cross-validation); the sensitivity and specificity were 0.7952 and 0.9971, respectively. The median distance between the ECDs estimated by the neurophysiologists and those using FAMED was 0.63 cm. Thus, the performance of FAMED is comparable to that of neurophysiologists, and it can contribute to the efficiency and consistency of MEG ECD analysis.

To realize a brain-machine interface to assist swallowing, neural signal decoding is indispensable. Eight participants with temporal-lobe intracranial electrode implants for epilepsy were asked to swallow during electrocorticogram (ECoG) recording. Raw ECoG signals or certain frequency bands of the ECoG power were converted into images whose vertical axis was electrode number and whose horizontal axis was time in milliseconds, which were used as training data. These data were classified with four labels (Rest, Mouth open, Water injection, and Swallowing). Deep transfer learning was carried out using AlexNet, and power in the high-[Formula: see text] band (75-150[Formula: see text]Hz) was the training set. Accuracy reached 74.01%, sensitivity reached 82.51%, and specificity reached 95.38%. However, using the raw ECoG signals, the accuracy obtained was 76.95%, comparable to that of the high-[Formula: see text] power. We demonstrated that a version of AlexNet pre-trained with visually meaningful images can be used for transfer learning of visually meaningless images made up of ECoG signals. Moreover, we could achieve high decoding accuracy using the raw ECoG signals, allowing us to dispense with the conventional extraction of high-[Formula: see text] power. Thus, the images derived from the raw ECoG signals were equivalent to those derived from the high-[Formula: see text] band for transfer deep learning.

Recent studies using functional magnetic resonance imaging (fMRI) have enabled quantitative evaluation of the semantic space during processing of visual stimuli. In the semantic space of the natural language processing model, called a skip-gram, decoders were shown to generalize to natural scenes of a movie that was not included in the training data of the decoders. Combined with electrocorticography (ECoG), which has a higher sampling rate than fMRI, this approach is expected to aid the development of a practical brain-machine interface. Here, we decoded vector representations of scenes within the semantic space of a skip-gram model to assess whether a decoder trained using ECoG features still generalizes to scenes new to the decoder.