Automated sleep spindle detection with mixed EEG features. (September 2021)

• Record Type: Journal Article
• Authors: Chen, Peilu; Chen, Dan; Zhang, Lei; Tang, Yunbo; Li, Xiaoli
• Is Part Of: Biomedical signal processing and control. Volume 70(2021)
• Publication Date: 2021-09
• Subjects: Spindle detection -- Sleep EEG -- Convolutional Neural Network -- Deep features -- Entropy; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.103026
• Languages: English
• ISSNs: 1746-8094

Abstract

Abstract: Detection of sleep spindles, a special type of burst brainwaves recordable with electroencephalography (EEG), is critical in examining sleep-related brain functions from memory consolidation to cortical development. It has long been an onerous and highly professional task to visually position individual sleep spindles and label their onset & offset. Automated spindle detection (template- and classifier-based) is experiencing performance bottleneck due to uncertain variances between spindles in both duration & formation. This study then develops a generic framework based on Deep Neural Network for accurate spindle detection by mixing the deep (micro-scale) features and the entropy (macro-scale) of sleep EEG. First, an "elastic" time window applies to adapt to the significantly varied durations of spindles in EEG, after which regulated deep features of EEG epochs with variable-lengths are obtained via a compact Convolutional Neural Network (CNN) with spatial pyramid pooling. Second, these deep features are mixed with the entropy of EEG epochs to support spindle classification. Focal loss applies to ease the severe imbalance between spindles and other epochs. Finally, elastic EEG epochs are set to capture the individual spindles. Experimental results on a public sleep EEG dataset (DREAMS) with the proposed framework against the state-of-the-art counterparts indicate that (1) it outperforms the counterparts with an F1-score of 0.66(0.11) while introducing entropy information gains 0.034(0.02) in this process; (2) it incurs less errors in identifying the onset & offset of spindles. Overall, the core design of the framework paves the way for detection of complicated EEG waveforms or time series in general. Highlights: Deep features mixed with entropy of EEG epochs enhance feature representation. "Elastic" time window applies to adapt to the variation of spindle duration. Focal loss eases the severe imbalance between spindles and other epochs. A DNN framework incurs a less error in identifying onset & offset of spindles.