Autism detection method, device and system based on magnetic resonance image

Abstract

The invention discloses an autism detection method, device and system based on a graph theory, and belongs to the technical field of medical image processing. The method comprises the following steps:constructing a brain function network topological graph corresponding to each magnetic resonance image by taking a threshold value with the lowest network consumption as a binarization threshold value; determining an abnormal brain region based on the difference statistical information of the node degree information of the autistic patient and the normal person, and extracting the feature information of the abnormal brain region, namely the node degree information of the node corresponding to the brain region; and performing model training and detection of an autism dichotomy classifier basedon the extracted feature information, and providing auxiliary diagnosis help for autism diagnosis. According to the autism detection system in the multi-feature fusion mode, another auxiliary diagnosis help is provided for autism diagnosis, and the autism detection recognition rate is improved to a certain extent. The detection system can also be used for automatic detection in the health fieldsof smoking addiction, network addiction, network game addiction, knowledge and the like.

Description

technical field [0001] The invention belongs to the technical field of medical image processing, and in particular relates to a classification processing technology for autism based on magnetic resonance image processing. Background technique [0002] Autism is a relatively common mental disorder, which is a subtype of pervasive developmental disorder. The symptoms of this disease are mainly manifested in different degrees of language development disorders, interpersonal communication obstacles, narrow interests and rigid behaviors, and Intellectual disability, etc. The incidence of the disease is not uncommon in our country, but until now, there is still no good way to diagnose autism. At present, most of the diagnosis of autism is through the doctor's usual growth and development history, medical history and mental examination of the child, and referring to the currently internationally recognized autism diagnostic standard DSM-5 for disease diagnosis. This requires part...

AI Technical Summary

Problems solved by technology

The incidence of the disease is not uncommon in our country, but until now, there is still no good way for the diagnosis of autism

Images