A Human-Machine Coupled System for Efficient Sleep Spindle Detection by Iterative Revision

Abstract

Sleep spindles are characteristic events in EEG signals during non-REM sleep, and are known to be important biological markers. Manually labeling spindles by visual inspection, however, proves to be a tedious task. Here, a novel system of \"Selection-Revision\" is introduced to aid in efficient detection of spindles. By coupling low-threshold automatic detection of spindle events based on selected parameters with manual \"Revision,\" the human task is effectively simplified from searching across signal traces to binary verification. After iterative application of this Selection-Revision process, convergence was observed between resulting spindle sets, largely independent of their initial manual or machine labeling, demonstrating the robustness of the method. This approach allows for fast labeling to obtain consistent spindle sets, which can also be used to train machine-learning models in the future.