Multichannel sleep spindle detection using sparse low-rank optimization

A robust deep learning detector for sleep spindles and K-complexes: towards population norms

Sleep spindles (SSs) and K-complexes (KCs) are brain patterns involved in cognitive functions that appear during sleep. Large-scale sleep studies would benefit from precise and robust automatic sleep event detectors, capable of adapting the variability in both electroencephalography (EEG) signals and expert annotation rules. We introduce the Sleep EEG Event Detector (SEED), a deep learning system that outperforms existing approaches in SS and KC detection, reaching an F1-score of 80.5% and 83.7%, respectively, on the MASS2 dataset. SEED transfers well and requires minimal fine-tuning for new datasets and annotation styles. Remarkably, SEED substantially reduces the required amount of annotated data by using a novel pretraining approach that leverages the rule-based detector A7. An analysis of 11,224 subjects revealed that SEED's detections provide better estimates of SS population statistics than existing approaches. SEED is a powerful resource for obtaining sleep-event statistics that could be useful for establishing population norms.

Sleep and circadian rhythm disruption by NPTX2 loss of function

Sleep and circadian rhythm disruption (SCRD) is commonly observed in aging, especially in individuals who experience progressive cognitive decline to mild cognitive impairment (MCI) and Alzheimer's disease (AD). However, precise molecular mechanisms underlying the association between SCRD and aging are not fully understood. Orexin A is a well-characterized "sleep neuropeptide" that is expressed in hypothalamic neurons and evokes wake behavior. The importance of Orexin is exemplified in narcolepsy where it is profoundly down-regulated. Interestingly, the synaptic immediate early gene NPTX2 is co-expressed in Orexin neurons and is similarly reduced in narcolepsy. NPTX2 is also down-regulated in CSF of some cognitively normal older individuals and predicts the time of transition from normal cognition to MCI. The association between Orexin and NPTX2 is further evinced here where we observe that Orexin A and NPTX2 are highly correlated in CSF of cognitively normal aged individuals and raises the question of whether SCRD that are typically attributed to Orexin A loss of function may be modified by concomitant NPTX2 down-regulation. Is NPTX2 an effector of sleep or simply a reporter of orexin-dependent SCRD? To address this question, we examined NPTX2 KO mice and found they retain Orexin expression in the brain and so provide an opportunity to examine the specific contribution of NPTX2 to SCRD. Our results reveal that NPTX2 KO mice exhibit a disrupted circadian onset time, coupled with increased activity during the sleep phase, suggesting difficulties in maintaining states. Sleep EEG indicates distinct temporal allocation shifts across vigilance states, characterized by reduced wake and increased NREM time. Evident sleep fragmentation manifests through alterations of event occurrences during Wake and NREM, notably during light transition periods, in conjunction with an increased frequency of sleep transitions in NPTX2 KO mice, particularly between Wake and NREM. EEG spectral analysis indicated significant shifts in power across various frequency bands in the wake, NREM, and REM states, suggestive of disrupted neuronal synchronicity. An intriguing observation is the diminished occurrence of sleep spindles, one of the earliest measures of human sleep disruption, in NPTX2 KO mice. These findings highlight the effector role of NPTX2 loss of function as an instigator of SCRD and a potential mediator of sleep disruption in aging.

Effect of Aging and a Dual Orexin Receptor Antagonist on Sleep Architecture and Non-REM Oscillations Including an REM Behavior Disorder Phenotype in the PS19 Mouse Model of Tauopathy

The impact of tau pathology on sleep microarchitecture features, including slow oscillations, spindles, and their coupling, has been understudied, despite the proposed importance of these electrophysiological features toward learning and memory. Dual orexin receptor antagonists (DORAs) are known to promote sleep, but whether and how they affect sleep microarchitecture in the setting of tauopathy is unknown. In the PS19 mouse model of tauopathy MAPT (microtubule-associated protein tau) P301S (both male and female), young PS19 mice 2-3 months old show a sleep electrophysiology signature with markedly reduced spindle duration and power and elevated slow oscillation (SO) density compared with littermate controls, although there is no significant tau hyperphosphorylation, tangle formation, or neurodegeneration at this age. With aging, there is evidence for sleep disruption in PS19 mice, characterized by reduced REM duration, increased non-REM and REM fragmentation, and more frequent brief arousals at the macrolevel and reduced spindle density, SO density, and spindle-SO coupling at the microlevel. In ∼33% of aged PS19 mice, we unexpectedly observed abnormal goal-directed behaviors in REM, including mastication, paw grasp, and forelimb/hindlimb extension, seemingly consistent with REM behavior disorder (RBD). Oral administration of DORA-12 in aged PS19 mice increased non-REM and REM duration, albeit with shorter bout lengths, and increased spindle density, spindle duration, and SO density without change to spindle-SO coupling, power in either the SO or spindle bands, or the arousal index. We observed a significant effect of DORA-12 on objective measures of RBD, thereby encouraging future exploration of DORA effects on sleep-mediated cognition and RBD treatment.SIGNIFICANCE STATEMENT The specific effect of tauopathy on sleep macroarchitecture and microarchitecture throughout aging remains unknown. Our key findings include the following: (1) the identification of a sleep EEG signature constituting an early biomarker of impending tauopathy; (2) sleep physiology deteriorates with aging that are also markers of off-line cognitive processing; (3) the novel observation that dream enactment behaviors reminiscent of RBD occur, likely the first such observation in a tauopathy model; and (4) a dual orexin receptor antagonist is capable of restoring several of the sleep macroarchitecture and microarchitecture abnormalities.

Hierarchical fusion detection algorithm for sleep spindle detection

Background

Sleep spindles are a vital sign implying that human beings have entered the second stage of sleep. In addition, they can effectively reflect a person’s learning and memory ability, and clinical research has shown that their quantity and density are crucial markers of brain function. The “gold standard” of spindle detection is based on expert experience; however, the detection cost is high, and the detection time is long. Additionally, the accuracy of detection is influenced by subjectivity.

Methods

To improve detection accuracy and speed, reduce the cost, and improve efficiency, this paper proposes a layered spindle detection algorithm. The first layer used the Morlet wavelet and RMS method to detect spindles, and the second layer employed an improved k-means algorithm to improve spindle detection efficiency. The fusion algorithm was compared with other spindle detection algorithms to prove its effectiveness.

Results

The hierarchical fusion spindle detection algorithm showed good performance stability, and the fluctuation range of detection accuracy was minimal. The average value of precision was 91.6%, at least five percentage points higher than other methods. The average value of recall could reach 89.1%, and the average value of specificity was close to 95%. The mean values of accuracy and F1-score in the subject sample data were 90.4 and 90.3%, respectively. Compared with other methods, the method proposed in this paper achieved significant improvement in terms of precision, recall, specificity, accuracy, and F1-score.

Conclusion

A spindle detection method with high steady-state accuracy and fast detection speed is proposed, which combines the Morlet wavelet with window RMS and an improved k-means algorithm. This method provides a powerful tool for the automatic detection of spindles and improves the efficiency of spindle detection. Through simulation experiments, the sampled data were analyzed and verified to prove the feasibility and effectiveness of this method.

Automated real-time EEG sleep spindle detection for brain-state-dependent brain stimulation

Sleep spindles are a hallmark electroencephalographic feature of non-rapid eye movement sleep, and are believed to be instrumental for sleep-dependent memory reactivation and consolidation. However, direct proof of their causal relevance is hard to obtain, and our understanding of their immediate neurophysiological consequences is limited. To investigate their causal role, spindles need to be targeted in real-time with sensory or non-invasive brain-stimulation techniques. While fully automated offline detection algorithms are well established, spindle detection in real-time is highly challenging due to their spontaneous and transient nature. Here, we present the real-time spindle detector, a robust multi-channel electroencephalographic signal-processing algorithm that enables the automated triggering of stimulation during sleep spindles in a phase-specific manner. We validated the real-time spindle detection method by streaming pre-recorded sleep electroencephalographic datasets to a real-time computer system running a Simulink® Real-Time™ implementation of the algorithm. Sleep spindles were detected with high levels of Sensitivity (~83%), Precision (~78%) and a convincing F1-Score (~81%) in reference to state-of-the-art offline algorithms (which reached similar or lower levels when compared with each other), for both naps and full nights, and largely independent of sleep scoring information. Detected spindles were comparable in frequency, duration, amplitude and symmetry, and showed the typical time-frequency characteristics as well as a centroparietal topography. Spindles were detected close to their centre and reliably at the predefined target phase. The real-time spindle detection algorithm therefore empowers researchers to target spindles during human sleep, and apply the stimulation method and experimental paradigm of their choice.

Effect of a Recliner Chair with Rocking Motions on Sleep Efficiency

In this study, we analyze the effect of a recliner chair with rocking motions on sleep quality of naps using automated sleep scoring and spindle detection models. The quality of sleep corresponding to the two rocking motions was measured quantitatively and qualitatively. For the quantitative evaluation, we conducted a sleep parameter analysis based on the results of the estimated sleep stages obtained on the brainwave and spindle estimation, and a sleep survey assessment from the participants was analyzed for the qualitative evaluation. The analysis showed that sleep in the recliner chair with rocking motions positively increased the duration of the spindles and deep sleep stage, resulting in improved sleep quality.

A deep learning approach for real-time detection of sleep spindles

OBJECTIVE

Sleep spindles have been implicated in memory consolidation and synaptic plasticity during NREM sleep. Detection accuracy and latency in automatic spindle detection are critical for real-time applications.

APPROACH

Here we propose a novel deep learning strategy (SpindleNet) to detect sleep spindles based on a single EEG channel. While the majority of spindle detection methods are used for off-line applications, our method is well suited for online applications.

MAIN RESULTS

Compared with other spindle detection methods, SpindleNet achieves superior detection accuracy and speed, as demonstrated in two publicly available expert-validated EEG sleep spindle datasets. Our real-time detection of spindle onset achieves detection latencies of 150-350 ms (~two-three spindle cycles) and retains excellent performance under low EEG sampling frequencies and low signal-to-noise ratios. SpindleNet has good generalization across different sleep datasets from various subject groups of different ages and species.

SIGNIFICANCE

SpindleNet is ultra-fast and scalable to multichannel EEG recordings, with an accuracy level comparable to human experts, making it appealing for long-term sleep monitoring and closed-loop neuroscience experiments.

DOSED: A deep learning approach to detect multiple sleep micro-events in EEG signal

BACKGROUND

Electroencephalography (EEG) monitors brain activity during sleep and is used to identify sleep disorders. In sleep medicine, clinicians interpret raw EEG signals in so-called sleep stages, which are assigned by experts to every 30s window of signal. For diagnosis, they also rely on shorter prototypical micro-architecture events which exhibit variable durations and shapes, such as spindles, K-complexes or arousals. Annotating such events is traditionally performed by a trained sleep expert, making the process time consuming, tedious and subject to inter-scorer variability. To automate this procedure, various methods have been developed, yet these are event-specific and rely on the extraction of hand-crafted features.

NEW METHOD

We propose a novel deep learning architecture called Dreem One Shot Event Detector (DOSED). DOSED jointly predicts locations, durations and types of events in EEG time series. The proposed approach, applied here on sleep related micro-architecture events, is inspired by object detectors developed for computer vision such as YOLO and SSD. It relies on a convolutional neural network that builds a feature representation from raw EEG signals, as well as two modules performing localization and classification respectively.

RESULTS AND COMPARISON WITH OTHER METHODS

The proposed approach is tested on 4 datasets and 3 types of events (spindles, K-complexes, arousals) and compared to the current state-of-the-art detection algorithms.

CONCLUSIONS

Results demonstrate the versatility of this new approach and improved performance compared to the current state-of-the-art detection methods.

Spindler: a framework for parametric analysis and detection of spindles in EEG with application to sleep spindles

OBJECTIVE

EEG spindles, narrow-band oscillatory signal bursts, are widely-studied biomarkers of subject state and neurological function. Most existing methods for spindle detection select algorithm parameters by optimizing agreement with expert labels. We propose a new framework for selecting algorithm parameters based on stability of spindle properties and elucidate the dependence of these properties on parameter selection for several algorithms.

APPROACH

To demonstrate this approach we developed a new algorithm (Spindler) that decomposes the signal using matching pursuit with Gabor atoms and computes the spindles for each point in a fine grid of parameter values. After computing characteristic surfaces as a function of parameters, Spindler selects algorithm parameters based on the stability of characteristic surface geometry.

MAIN RESULTS

Spindler performs well relative to several common supervised and unsupervised EEG sleep spindle detection methods. Spindler is available as an open-source MATLAB toolbox (https://github.com/VisLab/EEG-Spindles). In addition to Spindler, the toolbox provides implementations of several other spindle detection algorithms as well as standardized methods for matching ground truth to predictions and a framework for understanding algorithm parameter surfaces.

SIGNIFICANCE

This work demonstrates that parameter selection based on physical constraints rather than labelled data can provide effective, fully-automated, unsupervised spindle detection. This work also exposes the dangers of applying cross-validation without considering the dependence of spindle properties on parameters. Parameters selected to optimize one performance metric or matching method are not optimized for others. Furthermore, elucidation of the stability of predicted indicators with respect to algorithm parameter selection is critical to practical application of these algorithms.