Rapid eye movement sleep analysis method, system and equipment

Abstract

The invention discloses a rapid eye movement sleep analysis method, a system and equipment. The method includes: classifying video polysomnography data in a fast eye movement period and a non-rapid eye movement period, and storing the classification results and the video data according to a corresponding relationship; preprocessing the video data, and dividing the preprocessed video data and the corresponding classification results into a training set and a test set; performing feature learning on the video data in the training set, classifying with reference to the corresponding classification results given, and making certain adjustments to a deep neural network on the test set; preprocessing and slicing the video information to be classified to obtain input data matching the input of the deep neural network; and inputting the deep neural network to obtain an output result of the network. According to the method, a video monitoring mode is used for carrying out automatic analysis onrapid eye movement sleep, so that complexity of a video polysomnography monitoring system is reduced, contact influence on patients is reduced, and comfort and accuracy of polysomnography monitoring patients are improved.

Description

technical field [0001] The present application belongs to the technical field of medical signal processing, and in particular relates to a rapid eye movement sleep analysis method, system and equipment. Background technique [0002] The analysis of night sleep structure is of great significance to understand the sleep conditions of sleep patients. In the analysis of sleep structure, REM sleep and non-rapid eye movement sleep are two important components of sleep structure. Among them, in the non-rapid eye movement period, slow eye movement occasionally occurs. However, the rapid eye movement period has obvious conjugation, irregular, sharp eye movements, and is accompanied by phasic muscle twitching. Due to these characteristics, the analysis of rapid eye movement and non-rapid eye movement is mainly performed clinically by using oculoelectric signals, mental myoelectric signals and EEG signals in polysomnography. [0003] At present, automated REM sleep analysis methods a...

AI Technical Summary

Problems solved by technology

These devices will bring additional burden to patients, and affect the sleep of patients, resulting in a decrease in sleep quality

Images