Spindle Detection Research Articles

Enhancing acetone detection of In2O3-decorated MOF-derived Fe2O3 spindles with Pt nanoparticles functionalization

Designsensing materials with core-shell structure is an excellent strategy to achieve high sensing performance toward acetone detection. Herein, MIL-88A(Fe) was fabricated via a hydrothermal route, which renders as a template to fabricate Fe2O3@In2O3 core-shell spindles structure. Gas sensing results show that the sensor based on Fe2O3@In2O3 exhibit enhanced response of 193–200 ppm acetone than that of 36 for pristine Fe2O3 at 200 °C. After Pt functionalization, the response of Fe2O3@In2O3/Pt to 200 ppm acetone is up to 839 at a reducing working temperature of 180 °C with a good selectivity and long-term stability. A synergistic mechanism originated from the intrinsic merits of Fe2O3 and In2O3, the 1D core-shell structure, the creation of heterojunction at the interface of Fe2O3 and In2O3 and the creation of Shottky junction at In2O3 and Pt nanoparticles, and the catalytic reaction of Pt holds accountable for the significant improvement in acetone sensing.

Unveil sleep spindles with concentration of frequency and time (ConceFT)

Objective. Sleep spindles contain crucial brain dynamics information. We introduce the novel non-linear time-frequency (TF) analysis tool ‘Concentration of Frequency and Time’ (ConceFT) to create an interpretable automated algorithm for sleep spindle annotation in EEG data and to measure spindle instantaneous frequencies (IFs). Approach. ConceFT effectively reduces stochastic EEG influence, enhancing spindle visibility in the TF representation. Our automated spindle detection algorithm, ConceFT-Spindle (ConceFT-S), is compared to A7 (non-deep learning) and SUMO (deep learning) using Dream and Montreal Archive of Sleep Studies (MASS) benchmark databases. We also quantify spindle IF dynamics. Main results. ConceFT-S achieves F1 scores of 0.765 in Dream and 0.791 in MASS, which surpass A7 and SUMO. We reveal that spindle IF is generally nonlinear. Significance. ConceFT offers an accurate, interpretable EEG-based sleep spindle detection algorithm and enables spindle IF quantification.

Spindle Detection Based on Elastic Time Window and Spatial Pyramid Pooling.

Sleep spindles have emerged as valuable biomarkers for assessing cognitive abilities and related disorders, underscoring the importance of their detection in clinical research. However, template matching-based algorithms using fixed templates may not be able to fully adapt to spindles of different durations. Moreover, inspired by the multiscale feature extraction of images, the use of multiscale feature extraction methods can be used to better adapt to spindles of different frequencies and durations. Therefore, this study proposes a novel automatic spindle detection algorithm based on elastic time windows and spatial pyramid pooling (SPP) for extracting multiscale features. The algorithm utilizes elastic time windows to segment electroencephalogram (EEG) signals, enabling the extraction of features across multiple scales. This approach accommodates significant variations in spindle duration and polarization positioning during different EEG epochs. Additionally, spatial pyramid pooling is integrated into a depthwise separable convolutional (DSC) network to perform multiscale pooling on the segmented spindle signal features at different scales. Compared with existing template matching algorithms, this algorithm's spindle wave polarization positioning is more consistent with the real situation. Experimental results conducted on the public dataset DREAMS show that the average accuracy of this algorithm reaches 95.75%, with an average negative predictive value (NPV) of 96.55%, indicating its advanced performance. The effectiveness of each module was verified through thorough ablation experiments. More importantly, the algorithm shows strong robustness when faced with changes in different experimental subjects. This feature makes the algorithm more accurate at identifying sleep spindles and is expected to help experts automatically detect spindles in sleep EEG signals, reduce the workload and time of manual detection, and improve efficiency.

Retraction Note: Automatic detection of sleep spindles with the use of STFT, EMD and DWT methods

Retraction Note: Automatic detection of sleep spindles with the use of STFT, EMD and DWT methods

0204 Spindle Detection in Polysomnography of Toddlers: Comparing Manual Feature Detection and an Automated Algorithm

0204 Spindle Detection in Polysomnography of Toddlers: Comparing Manual Feature Detection and an Automated Algorithm

Method and system for automated detection of sleep spindles using a single EEG channels based TEO and EMD

As a hallmark of N2 sleep stage, sleep spindle detection based on electroencephalogram (EEG) recordings plays a crucial role in analyzing sleep. Hence, how to effectively automatically detect sleep spindle is crucially important. However, many automatic detection methods assume that the signal is stationary, which is inconsistent with the observation that spindle signals have a significant change in amplitude. Thus, some important non-stationary information and the presented evident dynamic characteristics has been ignored.To overcome the aforementioned shortcoming, we propose a novel methodology based on Teager Energy Operator (TEO) and Empirical Mode Decomposition (EMD) to determine the exact location of sleep spindles using single-channel EEG signals. Because the TEO is sensitive to amplitude variations and energy features, our proposed method is suitable for capturing sleep spindles. We conduct plenty of experiments to evaluate our method. The experiments are conducted to validate the effectiveness of our method. On the DREAMS Sleep Spindles Database, our method achieves 91.83% ± 1.1%, 94.12% ± 3.46%, and 83.38% ± 9.32% for accuracy, specificity, and sensitivity, respectively. Experimental results show that the performance of the proposed methodology presented herein achieves better performance as compared to other methods. Moreover, owing to its usage of a single channel of EEG signal, the proposed method will be suitable for edge-device implementation to expedite sleep disorder diagnosis.

A personalized semi-automatic sleep spindle detection (PSASD) framework

BackgroundSleep spindles are distinct electroencephalogram (EEG) patterns of brain activity that have been posited to play a critical role in development, learning, and neurological disorders. Manual scoring for sleep spindles is labor-intensive and tedious but could supplement automated algorithms to resolve challenges posed with either approaches alone. New methodsA Personalized Semi-Automatic Sleep Spindle Detection (PSASD) framework was developed to combine the strength of automated detection algorithms and visual expertise of human scorers. The underlying model in the PSASD framework assumes a generative model for EEG sleep spindles as oscillatory components, optimized to EEG amplitude, with remaining signals distributed into transient and low-frequency components. ResultsA single graphical user interface (GUI) allows both manual scoring of sleep spindles (model training data) and verification of automatically detected spindles. A grid search approach allows optimization of parameters to balance tradeoffs between precision and recall measures. Comparison with existing methodsPSASD outperformed DETOKS in F1-score by 19% and 4% on the DREAMS and P-DROWS-E datasets, respectively. It also outperformed YASA in F1-score by 25% in the P-DROWS-E dataset. Further benchmarking analysis showed that PSASD outperformed four additional widely used sleep spindle detectors in F1-score in the P-DROWS-E dataset. Titration analysis revealed that four 30-second epochs are sufficient to fine-tune the model parameters of PSASD. Associations of frequency, duration, and amplitude of detected sleep spindles matched those previously reported with automated approaches. ConclusionsOverall, PSASD improves detection of sleep spindles in EEG data acquired from both younger healthy and older adult patient populations.

An examination of sleep spindle metrics in the Sleep Heart Health Study: superiority of automated spindle detection over total sigma power in assessing age-related spindle decline

BackgroundSleep spindle activity is commonly estimated by measuring sigma power during stage 2 non-rapid eye movement (NREM2) sleep. However, spindles account for little of the total NREM2 interval and therefore sigma power over the entire interval may be misleading. This study compares derived spindle measures from direct automated spindle detection with those from gross power spectral analyses for the purposes of clinical trial design.MethodsWe estimated spindle activity in a set of 8,440 overnight electroencephalogram (EEG) recordings from 5,793 patients from the Sleep Heart Health Study using both sigma power and direct automated spindle detection. Performance of the two methods was evaluated by determining the sample size required to detect decline in age-related spindle coherence with each method in a simulated clinical trial.ResultsIn a simulated clinical trial, sigma power required a sample size of 115 to achieve 95% power to identify age-related changes in sigma coherence, while automated spindle detection required a sample size of only 60.ConclusionsMeasurements of spindle activity utilizing automated spindle detection outperformed conventional sigma power analysis by a wide margin, suggesting that many studies would benefit from incorporation of automated spindle detection. These results further suggest that some previous studies which have failed to detect changes in sigma power or coherence may have failed simply because they were underpowered.

Switching state-space modeling of neural signal dynamics.

Linear parametric state-space models are a ubiquitous tool for analyzing neural time series data, providing a way to characterize the underlying brain dynamics with much greater statistical efficiency than non-parametric data analysis approaches. However, neural time series data are frequently time-varying, exhibiting rapid changes in dynamics, with transient activity that is often the key feature of interest in the data. Stationary methods can be adapted to time-varying scenarios by employing fixed-duration windows under an assumption of quasi-stationarity. But time-varying dynamics can be explicitly modeled by switching state-space models, i.e., by using a pool of state-space models with different dynamics selected by a probabilistic switching process. Unfortunately, exact solutions for state inference and parameter learning with switching state-space models are intractable. Here we revisit a switching state-space model inference approach first proposed by Ghahramani and Hinton. We provide explicit derivations for solving the inference problem iteratively after applying a variational approximation on the joint posterior of the hidden states and the switching process. We introduce a novel initialization procedure using an efficient leave-one-out strategy to compare among candidate models, which significantly improves performance compared to the existing method that relies on deterministic annealing. We then utilize this state inference solution within a generalized expectation-maximization algorithm to estimate model parameters of the switching process and the linear state-space models with dynamics potentially shared among candidate models. We perform extensive simulations under different settings to benchmark performance against existing switching inference methods and further validate the robustness of our switching inference solution outside the generative switching model class. Finally, we demonstrate the utility of our method for sleep spindle detection in real recordings, showing how switching state-space models can be used to detect and extract transient spindles from human sleep electroencephalograms in an unsupervised manner.

SpindlesTracker: An Automatic and Low-cost Labeled Workflow for Spindle Analysis.

Quantitative analysis of spindle dynamics in mitosis through fluorescence microscopy requires tracking spindle elongation in noisy image sequences. Deterministic methods, which use typical microtubule detection and tracking methods, perform poorly in the sophisticated background of spindles. In addition, the expensive data labeling cost also limits the application of machine learning in this field. Here we present a fully automatic and low-cost labeled workflow that efficiently analyzes the dynamic spindle mechanism of time-lapse images, called SpindlesTracker. In this workflow, we design a network named YOLOX-SP which can accurately detect the location and endpoint of each spindle under box-level data supervision. We then optimize the algorithm SORT and MCP for spindle's tracking and skeletonization. As there was no publicly available dataset, we annotated a S.pombe dataset that was entirely acquired from the real world for both training and evaluation. Extensive experiments demonstrate that SpindlesTracker achieves excellent performance in all aspects, while reducing label costs by 60%. Specifically, it achieves 84.1% mAP in spindle detection and over 90% accuracy in endpoint detection. Furthermore, the improved algorithm enhances tracking accuracy by 1.3% and tracking precision by 6.5%. Statistical results also indicate that the mean error of spindle length is within 1 μm. In summary, SpindlesTracker holds significant implications for the study of mitotic dynamic mechanisms and can be readily extended to the analysis of other filamentous objects. The code and the dataset are both released on https://github.com/lizhogn/SpindlesTrackerGitHub.

Frequency Detection and Change Point Estimation for Time Series of Complex Oscillation

We consider detecting the evolutionary oscillatory pattern of a signal when it is contaminated by nonstationary noises with complexly time-varying data generating mechanism. A high-dimensional dense progressive periodogram test is proposed to accurately detect all oscillatory frequencies. A further phase-adjusted local change point detection algorithm is applied in the frequency domain to detect the locations at which the oscillatory pattern changes. Our method is shown to be able to detect all oscillatory frequencies and the corresponding change points within an accurate range with a prescribed probability asymptotically. A Gaussian approximation scheme and an overlapping-block multiplier bootstrap methodology for sums of complex-valued high dimensional nonstationary time series without variance lower bounds are established, which could be of independent interest. This study is motivated by oscillatory frequency estimation and change point detection problems encountered in physiological time series analysis. An application to spindle detection and estimation in electroencephalogram recorded during sleep is used to illustrate the usefulness of the proposed methodology. Supplementary materials for this article are available online including a standardized description of the materials available for reproducing the work.

Differences in the topographical distribution of sleep spindles among adult epilepsy with cognitive impairment.

Cognitive comorbidities are common in epilepsy; however, symptomatic treatment is currently the only available effective therapy. Sleep, cognition, and epilepsy are closely associated. Therefore, many studies on epilepsy and cognition have focused on sleep structures, such as sleep spindles, which are considered windows to understanding the sleeping brain. This study aimed to investigate the relationship between sleep spindles and the severity of cognitive impairment in adult epilepsy. Fifty-seven adults with epilepsy underwent overnight sleep electroencephalogram recordings and cognitive testing. Slow (9-12 Hz) and fast (12-15 Hz) spindle characteristics during N2 sleep were calculated using a convolutional neural network-based sleep staging system and automatic spindle detection algorithm. Repeated-measures analysis of variance was used to analyze differences in fast and slow spindle densities among subgroups of patients based on cognitive impairment severity. A significant between-group effect was observed for both slow and fast spindle densities. Multiple comparisons showed that slow and fast spindle densities of the severe cognitive impairment subgroup were lower than those of the noncognitive impairment subgroup (P < 0.05). Simple-effect analysis revealed differences in slow spindle density distributed among the EEG channels Fp1, Fp2, F3, C3, P4, O1, O2, F8, T4, T5, T6, Fz, and Cz (P < 0.05). Differences in fast spindle density were distributed among the channels Fp1, Fp2, F3, C3, O1, O2, F7, F8, T4, T5, T6, and Fz (P < 0.05). Significant differences in topographical distribution of fast and slow spindle densities were observed at the scalp level among patients with different cognitive statuses. Compared with patients with no cognitive impairment, those with severe cognitive impairment had lower slow and fast spindle densities over multiple scalp regions during N2 sleep. This study provides a reference for objective assessment of cognitive dysfunction in epilepsy patients.

0263 Feasibility of Measuring Sleep Spindles Using a Wearable EEG Headband in Adolescents with Neurodevelopmental Disorders

Abstract Introduction There is compelling evidence that sleep spindles, electroencephalogram (EEG) signatures of non-rapid eye movement sleep, are reliable markers of thalamocortical dysfunction in Schizophrenia. While promising, this research is limited by traditional sleep EEG methods, which cultivate small, non-representative samples. Wearable EEG headbands could be used to study naturalistic sleep across several nights in individuals who cannot tolerate standard sleep assessments, but this has yet to be tested. We aim to test feasibility of using a dry-EEG headband to measure sleep spindles in adolescents with a neurodevelopmental disorder, 22q11.2 Deletion Syndrome (22q11DS). Methods Adolescents with 22q11DS (n=7; 3 Females; Age: 15-28 years) were asked to sleep in their own bed wearing a dry-EEG headband (Dreem 3). Feasibility of data acquisition was determined by the ability of the participants to record at least 3 consecutive nights. We performed visual artifact detection and examined the ability to detect sleep spindles using the well-validated Ferrarelli Spindle Detection Algorithm on the F7-O2 electrode. Results All subjects completed at least 3 nights of recording (range: 3-5 nights), suggesting the device was well-tolerated. The data contained minimal artifact; 17 out of the 22 nights available for analysis contained artifact in &amp;lt; 20% of sleep epochs. The best night contained artifact in only 6% of sleep epochs. Sleep spindles were successfully detected using an automatic detector (M= 1.92 spindles/minute). Conclusion This pilot study suggests dry-EEG headbands offer a feasible method to measure sleep spindles in individuals with neurodevelopmental disorders. This new technology could allow for scalable biomarkers of atypical neurodevelopment associated with psychiatric disorders. Support (if any) RO1 MH085953; U01MH10171; UCLA Center for Autism Research Pilot Grant; Dreem Coup de Coeur Award

Assessment of Cognitive Function with Sleep Spindle Characteristics in Adults with Epilepsy.

Epilepsy may cause chronic cognitive impairment by disturbing sleep plasticity. Sleep spindles play a crucial role in sleep maintenance and brain plasticity. This study explored the relationship between cognition and spindle characteristics in adult epilepsy. Participants underwent one-night sleep electroencephalogram recording and neuropsychological tests on the same day. Spindle characteristics during N2 sleep were extracted using a learning-based system for sleep staging and an automated spindle detection algorithm. We investigated the difference between cognitive subgroups in spindle characteristics. Multiple linear regressions were applied to analyze associations between cognition and spindle characteristics. Compared with no/mild cognitive impairment, epilepsy patients who developed severe cognitive impairment had lower sleep spindle density, the differences mainly distributed in central, occipital, parietal, middle temporal, and posterior temporal (P < 0.05), and had relatively long spindle duration in occipital and posterior temporal (P < 0.05). Mini-Mental State Examination (MMSE) was associated with spindle density (pars triangularis of the inferior frontal gyrus (IFGtri): β = 0.253, P = 0.015, and P.adjust = 0.074) and spindle duration (IFGtri: β = -0.262, P = 0.004, and P.adjust = 0.030). Montreal Cognitive Assessment (MoCA) was associated with spindle duration (IFGtri: β = -0.246, P = 0.010, and P.adjust = 0.055). Executive Index Score (MoCA-EIS) was associated with spindle density (IFGtri: β = 0.238, P = 0.019, and P.adjust = 0.087; parietal: β = 0.227, P = 0.017, and P.adjust = 0.082) and spindle duration (parietal: β = -0.230, P = 0.013, and P.adjust = 0.065). Attention Index Score (MoCA-AIS) was associated with spindle duration (IFGtri: β = -0.233, P = 0.017, and P.adjust = 0.081). The findings suggested that the altered spindle activity in epilepsy with severe cognitive impairment, the associations between the global cognitive status of adult epilepsy and spindle characteristics, and specific cognitive domains may relate to spindle characteristics in particular brain regions.

Hierarchical fusion detection algorithm for sleep spindle detection.

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. 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. 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. 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.

Convolutional Multiple Instance Learning for Sleep Spindle Detection With Label Refinement

Sleep spindles are closely associated with cognitive functions and neurological disorders; thus, spindle detection has been an important topic in sleep medicine. Recently, machine learning approaches have shown the potential in automatic sleep spindle detection by learning optimized features in a data-driven way, while they highly rely on labeled data, and the performance can be degraded when labels are inaccurate. However, accurate annotation of the spindle is usually difficult to obtain and high intraexpert and interexpert variance exist. In this work, we propose a convolutional neural network (CNN) with a label refinement component to learn an effective spindle detector with imperfect labels. Our approach consists of two stages: 1) a feature learning stage and 2) a label refinement stage. In the feature learning stage, a CNN-based multiple instance learning framework (CNN-MIL) is built for spindle feature learning. By assuming only parts of each labeled spindle segment contain true spindle patterns, the CNN-MIL model can learn most-likely spindle-related features from ambiguous labels. In the label refinement stage, we adjust the spindle labels by merging the original labels and labels predicted by CNN-MIL, and the modified labels are then used in the next round CNN-MIL feature learning. The two stages perform alternately for detector optimization. Extensive experiments demonstrated that our approach achieved the state-of-the-art performance.

An Efficient Sleep Spindle Detection Algorithm Based on MP and LSBoost

An Efficient Sleep Spindle Detection Algorithm Based on MP and LSBoost

Networks of cortical activity in infants with epilepsy.

Epilepsy in infancy links to a significant risk of neurodevelopmental delay, calling for a better understanding of its underlying mechanisms. Here, we studied cortical activity networks in infants with early-onset epilepsy to identify network properties that could pre-empt infants' neurodevelopmental course. We studied high-density (64 channel) electroencephalogram during non-rapid eye movement (N2) sleep in n = 49 infants at 1 year of age after being diagnosed with epilepsy during their first year of life. We computed frequency-specific networks in the cortical source space for two intrinsic brain modes: amplitude-amplitude and phase-phase correlations. Cortical activity networks of all frequency bands and connectivity modes were compared between the syndrome groups as well as between the three categories of neurocognitive development. The group differences were studied at three spatial levels: global, regional, and individual connections. Cortical mechanisms related to infant epilepsy were further compared with physiological networks using an automatic spindle detection algorithm. Our results show that global connectivity does not significantly differ between epilepsy syndromes; however, it co-varies with neurocognitive development. The largest network differences were observed at the lowest (<1 Hz) and mid-range (10-15 Hz) frequency bands. An algorithmic removal of sleep spindles from the data partially reduced the mid-range frequency network's strength. The centrocentral and frontocentral networks at the spindle frequencies were found to be strongest in infants with a persistent age-typical neurocognitive performance, while their low-frequency (< 1 Hz) networks were weaker for both amplitude-amplitude [P = 0.008, effect size = 0.61] and phase-phase correlations (P = 0.02, effect size = 0.54) at low (< 1 Hz). However, subjects with persistent mild neurocognitive delay from 1 to 2 years of age had higher amplitude-amplitude (P = 0.02, effect size = 0.73) and phase-phase (P = 0.06, effect size = 0.59) at low frequencies than those that deteriorated from mild to severely delayed from 1 to 2 years of age. Our findings suggest that cortical activity networks reflect the underlying clinical course of infants' epilepsy, and measures of spectrally and spatially resolved networks might become useful in better understanding infantile epilepsy as a network disease.

Effects of pleasant sound on overnight sleep condition: A crossover randomized study

It is desirable to improve sleep quality since poor sleep results in decreases in work productivity and increases in risks of lifestyle-related diseases. Sleep spindles in sleep EEG are waveforms that characterize non-REM sleep Stage 2 (Stage N2). Music therapy has been adopted as a non-pharmacological therapy for sleep quality improvement; however, few studies mention the relationship between music during sleep and spindles. We conducted a crossover randomized study to investigate music's effects on spindles and sleep parameters. Polysomnography (PSG) was performed on 12 adult males with sleep difficulties over three nights, during which they were exposed to three different acoustic environments–silent, white noise, and pleasant sounds–throughout the night, in a crossover randomized setting. Half of the participants with large WASO were defined as the sleep maintenance difficulty group. We investigated whether pleasant sounds shortened sleep onset latency (SOL) and increased the number of spindles (SN) and spindle density (SD) compared to white noise, using silent as the reference. The spindles were detected using the previously reported automatic spindle detection algorithm. After one patient was excluded due to data corruption, a total of 11 participants, including the sleep maintenance difficulty group (n = 5), were analyzed. For all participants, SOL was not significantly shorter with pleasant sound than with white noise (p = 0.683); for the sleep maintenance difficulty group, SOL tended to be shorter with pleasant sound than with white noise (p = 0.060). Compared to white noise, the SN increased in pleasant sound for 7 of 11 (4 of 5 in the sleep maintenance difficulty group), and SD increased for 5 of 11 (3 of 5 in the sleep maintenance difficulty group). The results suggest that all-night background sound exposure may affect SN and SD. Future research should investigate whether background sound exposure reduces sleep-related distress, achieves sound sleep, or improves daytime psychomotor function.

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.