Papers › DOSED: a deep learning approach to detect multiple sleep micro-events in EEG signal

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

7 Dec 2018arXiv:1812.04079archive 2025-07-28

Stanislas Chambon, Valentin Thorey, Pierrick J. Arnal, Emmanuel Mignot, Alexandre Gramfort

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 architecure 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.

PaperPDFCode

Code

Dreem-Organization/dosed mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

EEGElectroencephalogram (EEG)K-complex detectionSleep Arousal DetectionSleep Micro-event detectionSleep QualitySleep apnea detectionSpindle DetectionTime Series Analysis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
K-complex detection MASS SS2 DOSED F1-score (@IoU = 0.3) 0.6 #3 of 4 Archive leaderboard report
Sleep Arousal Detection MESA DOSED (3 EEG + 2 EOG) F1-score (@IoU = 0.3) 0.71 #1 of 3 Archive leaderboard report
Sleep Arousal Detection MESA DOSED (1 EEG) F1-score (@IoU = 0.3) 0.61 #2 of 3 Archive leaderboard report
Sleep apnea detection Dreem_NCT03657329 DOSED Accuracy 81% #1 of 1 Archive leaderboard report
Sleep apnea detection Dreem_NCT03657329 DOSED F1-score (@IoU = 0.3) 0.57 ± 0.23 #1 of 1 Archive leaderboard report
Sleep apnea detection Dreem_NCT03657329 DOSED Mean AHI Error 4.69 ± 4.25 #1 of 1 Archive leaderboard report
Spindle Detection MASS SS2 DOSED F1-score (@IoU = 0.3) 0.75 #3 of 6 Archive leaderboard report
Spindle Detection Stanford Sleep Cohort (SSC) DOSED F1-score (@IoU = 0.3) 0.48 #1 of 1 Archive leaderboard report
Spindle Detection Wisconsin Sleep Cohort (WSC) DOSED F1-score (@IoU = 0.3) 0.46 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionConvolutionNon Maximum SuppressionSSD

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections