Depression tendency evaluation system based on residual convolutional neural network

Abstract

The invention discloses a depression tendency evaluation system based on a residual convolutional neural network. The depression tendency evaluation system comprises an acquisition unit, a preprocessing unit, an extraction unit and an evaluation unit; in a depression evaluation experiment, the acquisition unit acquires a multi-lead electroencephalogram signal of a subject; the preprocessing unit preprocesses the electroencephalogram signals; the extraction unit is used for extracting features of the preprocessed electroencephalogram signals based on the residual convolutional neural network; and the evaluation unit is used for calculating the depression evaluation scores of the subjects by training and verifying the extracted electroencephalogram signal features of the leads through a regression model so as to evaluate depression tendencies of the subjects. According to the method, the features are directly extracted from the original electroencephalogram signals through the convolutional residual neural network, the depth of the convolutional network is increased, and the features of the electroencephalogram signals are extracted to the maximum extent. The regression model training is performed on the electroencephalogram information of each lead, so that the model can fully consider the correlation of each region of the brain, and the model can process electroencephalogram signals of different brain regions at the same time.

Description

technical field [0001] The invention belongs to the technical field of depression assessment, and relates to a depression tendency assessment system based on a residual convolutional neural network. Background technique [0002] Major depressive disorder (Major Depression) is a typical disease among depressive disorders. It is characterized by well-defined episodes of at least 2 weeks involving marked changes in affective, cognitive, and autonomic function. Studies have shown that the 12-month prevalence of major depressive disorder is about 7%, making it one of the most common mental illnesses. [0003] Major depressive disorder has long been a hot issue in the field of mental health, and a lot of research has been carried out on the etiology, treatment and prognosis of major depressive disorder. In these studies, the early identification of depressive tendencies is considered to play a very important role in the prevention and treatment of the disease. However, since ma...

AI Technical Summary

Problems solved by technology

[0005] EEG data contains rich physiological information of the brain, but due to low signal-to-noise ratio and large data volume, it is difficult to effectively process and analyze EEG data.

Images