Multiscale neural dynamics in sleep transition volatility across age scales: a multimodal EEG-EMG-EOG analysis of temazepam effects.

Recent advances in computational modeling techniques have facilitated a more nuanced understanding of sleep neural dynamics across the lifespan. In this study, we tensorize multiscale multimodal electroencephalogram (EEG), electromyogram (EMG), and electrooculogram (EOG) signals and apply Generalized Autoregressive Conditional Heteroskedasticity (GARCH) modeling to quantify interactions between age scales and the use of pharmacological sleep aids on sleep stage transitions. Our cohort consists of 22 subjects in a crossover design study, where each subject received both a sleep aid and a placebo in different sessions. To understand these effects across the lifespan, three evenly distributed age groups were formed: 18-29, 30-49, and 50-66 years. The methodological framework implemented here employs tensor-based machine learning techniques to compute continuous wavelet transform time-frequency features and utilizes a GARCH model to quantify sleep signal volatility across age scales. Support Vector Machines are used for feature ranking, and our analysis captures interactions between signal entropy, age, and sleep aid status across frequency bands, sleep transitions, and sleep stages. GARCH model results reveal statistically significant volatility clustering in EEG, EMG, and EOG signals, particularly during transitions between REM and non-REM sleep. Notably, volatility was higher in the 50-66 age group compared to the 18-29 age group, with marked fluctuations during transitions from deep sleep to REM sleep (standard deviation of 0.35 in the older group vs. 0.30 in the 18-29 age group, p < 0.05). Statistical comparisons of volatility across frequency bands, age scales, and sleep stages highlight significant differences attributable to sleep aid use. Mean conditional volatility parameterization of the GARCH model reveals directional influences, with a causality index of 0.75 from frontal to occipital regions during REM sleep transition periods. Our methodological framework identifies distinct neural behavior patterns across age groups associated with each sleep stage and transition, offering insights into the development of targeted interventions for sleep regularity across the lifespan.

Autonomous optimization of neuroprosthetic stimulation parameters that drive the motor cortex and spinal cord outputs in rats and monkeys.

Neural stimulation can alleviate paralysis and sensory deficits. Novel high-density neural interfaces can enable refined and multipronged neurostimulation interventions. To achieve this, it is essential to develop algorithmic frameworks capable of handling optimization in large parameter spaces. Here, we leveraged an algorithmic class, Gaussian-process (GP)-based Bayesian optimization (BO), to solve this problem. We show that GP-BO efficiently explores the neurostimulation space, outperforming other search strategies after testing only a fraction of the possible combinations. Through a series of real-time multi-dimensional neurostimulation experiments, we demonstrate optimization across diverse biological targets (brain, spinal cord), animal models (rats, non-human primates), in healthy subjects, and in neuroprosthetic intervention after injury, for both immediate and continual learning over multiple sessions. GP-BO can embed and improve "prior" expert/clinical knowledge to dramatically enhance its performance. These results advocate for broader establishment of learning agents as structural elements of neuroprosthetic design, enabling personalization and maximization of therapeutic effectiveness.

Multimodal Autoencoder Predicts fNIRS Resting State From EEG Signals.

In this work, we introduce a deep learning architecture for evaluation on multimodal electroencephalographic (EEG) and functional near-infrared spectroscopy (fNIRS) recordings from 40 epileptic patients. Long short-term memory units and convolutional neural networks are integrated within a multimodal sequence-to-sequence autoencoder. The trained neural network predicts fNIRS signals from EEG, sans a priori, by hierarchically extracting deep features from EEG full spectra and specific EEG frequency bands. Results show that higher frequency EEG ranges are predictive of fNIRS signals with the gamma band inputs dominating fNIRS prediction as compared to other frequency envelopes. Seed based functional connectivity validates similar patterns between experimental fNIRS and our model's fNIRS reconstructions. This is the first study that shows it is possible to predict brain hemodynamics (fNIRS) from encoded neural data (EEG) in the resting human epileptic brain based on power spectrum amplitude modulation of frequency oscillations in the context of specific hypotheses about how EEG frequency bands decode fNIRS signals.

Automated Analysis of Brain Microvasculature: From Segmentation to Anatomical Modeling.

Two-photon microscopy (TPM) can provide a detailed microscopic information of cerebrovascular structures. Extracting anatomical vascular models from TPM angiograms remains a tedious task due to image degeneration associated with TPM acquisitions and the complexity of microvascular networks. Here, we propose a fully automated pipeline capable of providing useful anatomical models of vascular structures captured with TPM. In the proposed method, we segment blood vessels using a fully convolutional neural network and employ the resulting binary labels to create an initial geometric graph enclosed within vessels boundaries. The initial geometry is then decimated and refined to form graphed curve skeletons that can retain both the vascular shape and its topology. We validate the proposed method on 3D realistic TPM angiographies and compare our results with that obtained through manual annotations.

fNIRS improves seizure detection in multimodal EEG-fNIRS recordings.

In the context of epilepsy monitoring, electroencephalography (EEG) remains the modality of choice. Functional near-infrared spectroscopy (fNIRS) is a relatively innovative modality that cannot only characterize hemodynamic profiles of seizures but also allow for long-term recordings. We employ deep learning methods to investigate the benefits of integrating fNIRS measures for seizure detection. We designed a deep recurrent neural network with long short-term memory units and subsequently validated it using the CHBMIT scalp EEG database-a compendium of 896 h of surface EEG seizure recordings. After validating our network using EEG, fNIRS, and multimodal data comprising a corpus of 89 seizures from 40 refractory epileptic patients was used as model input to evaluate the integration of fNIRS measures. Following heuristic hyperparameter optimization, multimodal EEG-fNIRS data provide superior performance metrics (sensitivity and specificity of 89.7% and 95.5%, respectively) in a seizure detection task, with low generalization errors and loss. False detection rates are generally low, with 11.8% and 5.6% for EEG and multimodal data, respectively. Employing multimodal neuroimaging, particularly EEG-fNIRS, in epileptic patients, can enhance seizure detection performance. Furthermore, the neural network model proposed and characterized herein offers a promising framework for future multimodal investigations in seizure detection and prediction.