2020
DOI: 10.1038/s41597-020-0533-4
|View full text |Cite
|
Sign up to set email alerts
|

Massive online data annotation, crowdsourcing to generate high quality sleep spindle annotations from EEG data

Abstract: Spindle event detection is a key component in analyzing human sleep. However, detection of these oscillatory patterns by experts is time consuming and costly. automated detection algorithms are cost efficient and reproducible but require robust datasets to be trained and validated. Using the MODa (Massive Online Data annotation) platform, we used crowdsourcing to produce a large opensource dataset of high quality, human-scored sleep spindles (5342 spindles, from 180 subjects). We evaluated the performance of t… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
69
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
7
3

Relationship

0
10

Authors

Journals

citations
Cited by 31 publications
(69 citation statements)
references
References 45 publications
0
69
0
Order By: Relevance
“…Together, these results may explain, at least in part, the association between abnormal spindle activity during sleep and neurodegenerative diseases such as Alzheimer's disease (Gorgoni et al, 2016) and Parkinson's diseases (Christensen et al, 2015). However, spindle detection is still a challenge and algorithm refinements on public benchmark datasets remain warranted (Warby et al, 2014;Lacourse et al, 2020). Furthermore, recent evidence suggests that the current definition of sleep spindles may be too restrictive and traditionally defined spindles may only be a small subset of a more generalized class of sigma oscillations during sleep (Dimitrov et al, 2021).…”
Section: Sleep Spindlesmentioning
confidence: 99%
“…Together, these results may explain, at least in part, the association between abnormal spindle activity during sleep and neurodegenerative diseases such as Alzheimer's disease (Gorgoni et al, 2016) and Parkinson's diseases (Christensen et al, 2015). However, spindle detection is still a challenge and algorithm refinements on public benchmark datasets remain warranted (Warby et al, 2014;Lacourse et al, 2020). Furthermore, recent evidence suggests that the current definition of sleep spindles may be too restrictive and traditionally defined spindles may only be a small subset of a more generalized class of sigma oscillations during sleep (Dimitrov et al, 2021).…”
Section: Sleep Spindlesmentioning
confidence: 99%
“…Labels by a group of experts would establish a gold standard and would allow for an assessment of inter-rater variability, even for pre-REM sleep. Such approaches have been successfully pursued in other areas of sleep research, for instance for the challenge of sleep spindle detection 62 .…”
Section: Discussionmentioning
confidence: 99%
“…Since the A7 spindle detection algorithm is designed to analyze empirical data, e.g., EEG, MEG, ECoG, or LFP (cf. [58, 59]), we made adjustments to the algorithm parameters. For detecting spindles on the cortical model output, we lowered the threshold for the duration from 0.5 to 0.3 seconds and for the relative power in the σ -band from 0.2 to 0.15.…”
Section: Methodsmentioning
confidence: 99%