Auxiliary decision-making system for diagnosis of attention deficit hyperactivity disorder (ADHD) disease based on deep convolutional spiking neural network

Abstract

The present invention discloses an auxiliary decision-making system for diagnosis of attention deficit hyperactivity disorder (ADHD) disease based on a deep convolutional spiking neural network. The auxiliary decision-making system comprises a preprocessing device, an encoding device and a diagnosis prediction output device; the preprocessing device is used for preprocessing functional magnetic resonance imaging data through a signal-to-noise ratio feature selection method; the encoding device is used for encoding the preprocessed functional magnetic resonance imaging data by adopting a forward algorithm to generate a pulse sequence; and the diagnosis prediction output device is used for conducting diagnosis prediction according to the pulse sequence by using the deep convolution pulse neural network and outputting a diagnosis prediction result. The auxiliary decision-making system does not need manual labeling features, adjusts weights for different distribution of medical cases, optimizes a prediction model, and improves reliability of the diagnosis prediction result.

Description

technical field [0001] The embodiment of the present invention relates to the technical field of diagnostic equipment, and in particular to an auxiliary decision system for ADHD disease diagnosis based on a deep convolutional pulse neural network. Background technique [0002] In recent years, with the ultra-high-speed development of social economy, people's pressure in all aspects is gradually increasing, and the number of patients with neurological diseases is increasing day by day. According to the statistics of the World Health Organization, brain-related diseases, including various neurological and mental diseases, are the largest social burden of all diseases, accounting for more than 20%, surpassing cardiovascular diseases, and also exceeding cancer. Therefore, the diagnosis and intervention of severe brain diseases such as autism or ADHD and mental retardation in childhood, depression and addiction in middle age, degenerative brain diseases such as Alzheimer's disea...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the embodiments of the present invention is to provide an auxiliary decision-making system for ADHD disease diagnosis based on a deep convolutional pulse neural network, which is used to solve the problem that certain data information will be lost when the existing classifier performs feature extraction, thereby reducing the classification accuracy and affecting Problems with the accuracy of diagnostic results

Images