Sleep spindles, an oscillatory brain activity occurring during light non-rapid eye movement (NREM) sleep, are important for memory consolidation and cognitive functions. Accurate detection is important for understanding the role of spindles in sleep state physiology and brain health and for better understanding sleep and neurological disorders. However, manual spindle labeling of electroencephalography (EEG) data is time-consuming and impractical for most clinical and research settings and intracranial EEG (iEEG) presents additional challenges for spindle identification due to its unique signal characteristics and recording environment. This study introduces a novel, precise, and automatic spindle detection method for iEEG using a dual-head architecture to enhance performance, robustness, and ease of use. Our approach achieves a detection F1 score of 0.67 on a challenging iEEG dataset and 0.69 on the publicly available scalp EEG DREAMS dataset. Compared to existing methods such as SUMO, A7, and YASA, our model demonstrates superior performance in detecting, segmenting, and characterizing sleep spindles. This model contributes to open science and advances automated sleep spindle classification in iEEG. This will advance the development of more precise diagnostic and research tools and facilitate a deeper understanding of the role of sleep spindles in cognitive processes and neurological health.

Center for Sleep Medicine Division of Pulmonary and Critical Care Medicine Department of Medicine Mayo Clinic Rochester MN USA

Department of Neurology Mayo Clinic Rochester MN USA

Department of Neurology Mayo Clinic Rochester MN USA; Center for Sleep Medicine Division of Pulmonary and Critical Care Medicine Department of Medicine Mayo Clinic Rochester MN USA

Department of Neurology Mayo Clinic Rochester MN USA; Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Prague Prague Czech Republic

Department of Neurology Mayo Clinic Rochester MN USA; Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Prague Prague Czech Republic; Faculty of Biomedical Engineering Czech Technical University Prague Kladno Czech Republic

Department of Neurology Mayo Clinic Rochester MN USA; Department of Physiology and Biomedical Engineering Mayo Clinic Rochester MN USA

Faculty of Applied Sciences University of West Bohemia Plzen Czech Republic; Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Prague Prague Czech Republic

International Clinical Research Center and Neurology Department St Anne's Hospital Brno Czech Republic

Zobrazit více v PubMed

Akiba Takuya et al. “Optuna: A next-generation hyperparameter optimization framework”. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining. 2019, pp. 2623–2631.

Andrillon Thomas et al. “Sleep spindles in humans: insights from intracranial EEG and unit recordings”. In: Journal of Neuroscience 31.49 (2011), pp. 17821–17834. PubMed PMC

Bódizs Róbert et al. “The individual adjustment method of sleep spindle analysis: methodological improvements and roots in the fingerprint paradigm”. In: Journal of neuroscience methods 178.1 (2009), pp. 205–213. PubMed

Bower MR et al. “Evidence for Consolidation of Neuronal Assemblies after Seizures in Humans”. In: Journal of Neuroscience 35 (2015), pp. 999–1010. PubMed PMC

Brinkmann BH et al. “Large-scale electrophysiology: acquisition, compression, encryption, and storage of big data”. In: Journal of Neuroscience Methods 180 (2009), pp. 185– 192. PubMed PMC

Carvalho Diego Z et al. “Loss of sleep spindle frequency deceleration in obstructive sleep apnea”. In: Clinical Neurophysiology 125.2 (2014), pp. 306–312. PubMed

Castelnovo Anna et al. “Sleep spindle deficit in schizophrenia: contextualization of recent findings”. In: Current psychiatry reports 18 (2016), pp. 1–10. PubMed

Chen Peilu et al. “Automated sleep spindle detection with mixed EEG features”. In: Biomedical Signal Processing and Control 70 (2021), p. 103026.

Cheng Lei et al. “Classification of long sequential data using circular dilated convolutional neural networks”. In: Neurocomputing 518 (2023), pp. 50–59.

Clawson Brittany C, Durkin Jaclyn, and Aton Sara J. “Form and function of sleep spindles across the lifespan”. In: Neural plasticity 2016.1 (2016), p. 6936381. PubMed PMC

Devuyst Stephanie, Dutoit T, and Kerkhofs M. “The DREAMS databases and assessment algorithm”. In: Zenodo: Geneva, Switzerland: (2005).

Devuyst Stéphanie et al. “Automatic K-complexes detection in sleep EEG recordings using likelihood thresholds”. In: 2010 Annual international conference of the ieee engineering in medicine and biology. IEEE. 2010, pp. 4658–4661. PubMed

Djonlagic Ina et al. “Macro and micro sleep architecture and cognitive performance in older adults”. en. In: Nature Human Behaviour 5.1 (Nov. 2020), pp. 123–145. PubMed PMC

Fernandez Laura MJ and Lüthi Anita. “Sleep spindles: mechanisms and functions”. In: Physiological reviews 100.2 (2020), pp. 805–868. PubMed

Gais Steffen et al. “Learning-dependent increases in sleep spindle density”. In: Journal of Neuroscience 22.15 (2002), pp. 6830–6834. PubMed PMC

Hassan Umair, Feld Gordon B, and Bergmann Til Ole. “Automated real-time EEG sleep spindle detection for brain-state-dependent brain stimulation”. In: Journal of sleep research 31.6 (2022), e13733. PubMed

Helfrich Randolph F et al. “Old Brains Come Uncoupled in Sleep: Slow Wave-Spindle Synchrony, Brain Atrophy, and Forgetting”. In: Neuron 97.1 (2018), 221–230.e4. PubMed PMC

Huupponen Eero et al. “Development and comparison of four sleep spindle detection methods”. In: Artificial intelligence in medicine 40.3 (2007), pp. 157–170. PubMed

Kaulen Lars et al. “Advanced sleep spindle identification with neural networks”. In: Scientific reports 12.1 (2022), p. 7686. PubMed PMC

Klinzing Jens G, Niethard Niels, and Born Jan. “Mechanisms of systems memory consolidation during sleep”. In: Nature neuroscience 22.10 (2019), pp. 1598–1610. PubMed

Kremen V. et al. “Automated unsupervised behavioral state classification using intracranial electrophysiology”. In: Journal of Neural Engineering 16.2 (2019), p. 026004. PubMed

Kremen V. et al. “Behavioral state classification in epileptic brain using intracranial electrophysiology”. In: Journal of Neural Engineering 14.2 (2017), p. 026001. PubMed PMC

Kremen Vaclav et al. “Integrating Brain Implants With Local and Distributed Computing Devices: A Next Generation Epilepsy Management System”. In: IEEE Journal of Translational Engineering in Health and Medicine 6 (2018), pp. 1–12. PubMed PMC

Kvavilashvili Andrew Tomaz. “Employing Intracranial EEG Data to Decipher Sleep Neural Dynamics”. PhD thesis. Virginia Tech, 2023.

Lachaux J Ph, Rudrauf D, and Kahane P. “Intracranial EEG and human brain mapping”. In: Journal of Physiology-Paris 97.4–6 (2003), pp. 613–628. PubMed

Lachner-Piza Daniel et al. “A single channel sleep-spindle detector based on multivariate classification of EEG epochs: MUSSDET”. In: Journal of neuroscience methods 297 (2018), pp. 31–43. PubMed

Lacourse Karine et al. “A sleep spindle detection algorithm that emulates human expert spindle scoring”. In: Journal of neuroscience methods 316 (2019), pp. 3–11. PubMed PMC

Markovic Andjela et al. “Sleep spindle activity in childhood onset schizophrenia: diminished and associated with clinical symptoms”. In: Schizophrenia research 223 (2020), pp. 327–336. PubMed PMC

Martin Nicolas et al. “Topography of age-related changes in sleep spindles”. In: Neurobiology of aging 34.2 (2013), pp. 468–476. PubMed

Ouichka Omaima, Echtioui Amira, and Hamam Habib. “Deep learning models for predicting epileptic seizures using iEEG signals”. In: Electronics 11.4 (2022), p. 605.

Pal Attia T. et al. “Epilepsy Personal Assistant Device - A Mobile Platform for Brain State, Dense Behavioral and Physiology Tracking and Controlling Adaptive Stimulation”. In: Frontiers in Neurology (2021). PubMed PMC

Parekh Ankit et al. “Detection of K-complexes and sleep spindles (DETOKS) using sparse optimization”. In: Journal of neuroscience methods 251 (2015), pp. 37–46. PubMed

Parekh Ankit et al. “Multichannel sleep spindle detection using sparse low-rank optimization”. In: Journal of neuroscience methods 288 (2017), pp. 1–16. PubMed

Piantoni Giovanni, Halgren Eric, and Cash Sydney S. “Spatiotemporal characteristics of sleep spindles depend on cortical location”. In: Neuroimage 146 (2017), pp. 236–245. PubMed PMC

Scafa Stefano et al. “Personalized Sleep Spindle Detection in Whole Night Polysomnography”. In: 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE. 2020, pp. 1047–1050. PubMed

Shiao Han-Tai et al. “SVM-based system for prediction of epileptic seizures from iEEG signal”. In: IEEE Transactions on Biomedical Engineering 64.5 (2016), pp. 1011–1022. PubMed PMC

Silber MH. “Staging sleep”. In: Sleep Medicine Clinics 7 (2012), pp. 487–496.

Sladky Vladimir et al. “Distributed brain co-processor for tracking spikes, seizures and behaviour during electrical brain stimulation”. In: Brain Communications 4.3 (June 2022), fcac115. PubMed PMC

Vallat Raphael and Walker Matthew P. “An open-source, high-performance tool for automated sleep staging”. In: Elife 10 (2021), e70092. PubMed PMC

Wamsley Erin J et al. “Reduced sleep spindles and spindle coherence in schizophrenia: mechanisms of impaired memory consolidation?” In: Biological psychiatry 71.2 (2012), pp. 154–161. PubMed PMC

Watanabe Shuhei. “Tree-structured parzen estimator: Understanding its algorithm components and their roles for better empirical performance”. In: arXiv:2304.11127 (2023).

Wendt Sabrina L et al. “Inter-expert and intra-expert reliability in sleep spindle scoring”. In: Clinical Neurophysiology 126.8 (2015), pp. 1548–1556. PubMed PMC

Wendt Sabrina L et al. “Validation of a novel automatic sleep spindle detector with high performance during sleep in middle aged subjects”. In: 2012 Annual international conference of the IEEE engineering in medicine and biology society. IEEE. 2012, pp. 4250–4253. PubMed

Zhang Zisheng and Parhi Keshab K. “Low-complexity seizure prediction from iEEG/sEEG using spectral power and ratios of spectral power”. In: IEEE transactions on biomedical circuits and systems 10.3 (2015), pp. 693–706. PubMed