Automated scoring of pre-REM sleep in mice with deep learning

Grieger, Niklas; Schwabedal, Justus T. C.; Wendel, Stefanie; Ritze, Yvonne; Bialonski, Stephan

doi:10.1038/s41598-021-91286-0

Cited by 18 publications

(22 citation statements)

References 49 publications

(80 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TS is visually distinguishable from REM sleep due to the irregular shape of the continuous oscillation that also has a higher frequency than REM theta. It is challenging for an automatic algorithm to distinguish TS from REM due to the brief duration of TS (1.8% of the total sleep as reported by Grieger et al (2021)). However, the current consensus would be that TS would be part of NREM due to the spindle dominance. The detection of TS might alter our understanding of sleep in the rodents.…”

Section: Different Potential Light Nrem Sleep Stages In Rodentsmentioning

confidence: 99%

Sleep scoring in rodents: Criteria, automatic approaches and outstanding issues

Rayan

Agarwal

Samanta

et al. 2022

Eur J of Neuroscience

View full text Add to dashboard Cite

There is nothing we spend as much time on in our lives as we do sleeping, which makes it even more surprising that we currently do not know why we need to sleep. Most of the research addressing this question is performed in rodents to allow for invasive, mechanistic approaches. However, in contrast to human sleep, we currently do not have shared and agreed upon standards on sleep states in rodents. In this article, we present an overview on sleep stages in humans and rodents and a historical perspective on the development of automatic sleep scoring systems in rodents. Further, we highlight specific issues in rodent sleep that also call into question some of the standards used in human sleep research.

show abstract

Section: Different Potential Light Nrem Sleep Stages In Rodentsmentioning

confidence: 99%

Sleep scoring in rodents: Criteria, automatic approaches and outstanding issues

Rayan

Agarwal

Samanta

et al. 2022

Eur J of Neuroscience

View full text Add to dashboard Cite

show abstract

“…We present the successful creation of a machine-learning-based classifier for the automated, accurate, and rapid scoring of sleep-wake states, seizures, and post-ictal states in mice with epilepsy. While previously reported classifiers effectively classified sleep in various populations of mice (Exarchos et al, 2020;Grieger et al, 2021;Lampert et al, 2015;Yamabe et al, 2019), none have demonstrated scoring proficiency in any rodent models of epilepsy. To our knowledge, our classifier is the first to achieve this goal.…”

Section: Discussionmentioning

confidence: 99%

Classifier for the Rapid Simultaneous Determination of Sleep-Wake States and Seizures in Mice

Harvey

Oláh

Aiani

et al. 2023

Preprint

View full text Add to dashboard Cite

Independent automated scoring of sleep-wake and seizures have recently been achieved; however, the combined scoring of both states has yet to be reported. Mouse models of epilepsy typically demonstrate an abnormal electroencephalographic (EEG) background with significant variability between mice, making combined scoring a more difficult classification problem for manual and automated scoring. Given the extensive EEG variability between epileptic mice, large group sizes are needed for most studies. As large datasets are unwieldy and impractical to score manually, automatic seizure and sleep-wake classification are warranted. To this end, we developed an accurate automated classifier of sleep-wake states, seizures, and the post-ictal state. Our benchmark was a classification accuracy at or above the 93% level of human inter-rater agreement. Given the failure of parametric scoring in the setting of altered baseline EEGs, we adopted a machine-learning approach. We created several multi-layer neural network architectures that were trained on human-scored training data from an extensive repository of continuous recordings of electrocorticogram (ECoG), left and right hippocampal local field potential (HPC-L and HPC-R), and electromyogram (EMG) in the murine intra-amygdala kainic acid model of medial temporal lobe epilepsy. We then compared different network models, finding a bidirectional long short-term memory (BiLSTM) design to show the best performance with validation and test portions of the dataset. The SWISC (sleep-wake and the ictal state classifier) achieved >93% scoring accuracy in all categories for epileptic and non-epileptic mice. Classification performance was principally dependent on hippocampal signals and performed well without EMG. Additionally, performance is within desirable limits for recording montages featuring only ECoG channels, expanding its potential scope. This accurate classifier will allow for rapid combined sleep-wake and seizure scoring in mouse models of epilepsy and other neurologic diseases with varying EEG abnormalities, thereby facilitating rigorous experiments with larger numbers of mice.

show abstract

“…In humans, NREMS can be further divided into 3 stages, N1 to N3, ranging from the lightest sleep in N1 to the deepest sleep in N3. Human-like sleep stages have been revealed in mice in a few studies [16,17], but whether these stages have a physiological relevance remains to be explored. NREMS in mice, equivalent to human deep NREMS, is also termed as slow-wave sleep (SWS), with high-amplitude, lowfrequency oscillations as the dominant spectral power state.…”

Section: Nrem and Rem Sleepmentioning

confidence: 99%

Sleep control by TFAP2a and TFAP2b transcription factors in mice

Yang¹

View full text Add to dashboard Cite

Sleep is a universal behavior that exists across species. We previously found that deletion of transcription factor APTF-1 induces sleep loss in C. elegans and Drosophila. In mammals, sleep has two states: rapid eye movement sleep (REMS) and non-REM sleep (NREMS), which can be distinguished by EEG spectral power. There are five homologs of APTF-1 in mammals, from Tfap2a to e. However, little is known about whether these homologs, Tfap2a and b, have a conserved role of regulating sleep in animals with a more complex brain. Therefore, I characterized the sleep and wakefulness of Tfap2a and b mutants in mice. Consistent with our previous finding, paralogs of Tfap2a and b control sleep in mice. However, Tfap2a and b control sleep in a bidirectional manner. EEG results showed that Tfap2a +/mice exhibited higher sleep drive, whereas Tfap2b +/mice showed a reduced sleep quality with shortened NREMS amount during baseline recording. As expected, sleep deprivation induced a stronger delta and theta power rebound in Tfap2a mutants, but a weaker response in Tfap2b mutants. This functional divergence was also observed in behaviors beyond sleep. Tfap2b +/mice displayed depression-like behavior while Tfap2a +/mice were hyperactive and showed more resistance to the stressful environment. With the decreased sleep quality, learning and memory were impaired in Tfap2b mutants. In addition, Tfap2b mutants exhibited a slightly shortened circadian period. In summary, Tfap2a and b control sleep in mice as well, but in a bidirectional way. It might support the hypothesis that, as nervous system evolved, the function of Tfap2a and b genes also diverged.GABAergic neurons play a key role promoting sleep. The development of GABAergic neurons is regulated by various transcription factors. However, it is not clear whether or how Tfap2a and b are involved in the expression and function of GABAergic neurons. Here I measured the expression of the genes that control GABA synthesis and transportation in Tfap2a +/and Tfap2b +/mice. Results from qPCR has confirmed a role of Tfap2b, but not TFap2a, in regulating the GABAergic gene expression.However, the role of Tfap2b was complex. The expression of GAD65, GAD67, Vgat was decreased in cortex, brainstem, cerebellum, but increased in striatum. Further, using ISH, a decrease number of the GAD67 expressing GABAergic cells was detected in the parafacial zone, a sleep-promoting center located in the lower brainstem. Since the expression of Tfap2b in brain starts early at developmental stages, E14.5 brains were extracted and analyzed using RNA-seq. Results have revealed various differentially regulated genes from homeobox, Slc family and those related to neurotransmission function. Together with qPCR and ISH results, they provided molecular evidences implying a functional role of GABAergic neurons expressing Tfap2b gene. Next, I characterized the function of GABAergic neurons expressing Tfap2b in sleep in Vgat-Tfap2b -/mice. EEG analysis showed that sleep quantity and intensity were reduced in female Vgat-T...

show abstract

Automated scoring of pre-REM sleep in mice with deep learning

Cited by 18 publications

References 49 publications

Sleep scoring in rodents: Criteria, automatic approaches and outstanding issues

Sleep scoring in rodents: Criteria, automatic approaches and outstanding issues

Classifier for the Rapid Simultaneous Determination of Sleep-Wake States and Seizures in Mice

Sleep control by TFAP2a and TFAP2b transcription factors in mice

Contact Info

Product

Resources

About