A multi-classification diagnosis system for Alzheimer's disease based on deep learning

Abstract

The present invention relates to a multi-classification diagnostic system for Alzheimer's disease based on deep learning, comprising: an image feature extraction module, which is used to extract the feature vectors of three orthogonal plane MRI images of the brain according to a neural network model; an index feature selection module , which is used to select the inspection index to form the index feature vector according to the relevant medical literature; the vector linear fusion module is used to fuse the feature vector of the image and the index feature vector by using the multivariate data linear fusion method based on canonical correlation analysis; the disease classification diagnosis module, Used to feed the fused vectors into a multi-class classifier to distinguish the three stages of Alzheimer's disease. The invention can assist the multi-classification diagnosis of Alzheimer's disease.

Description

technical field [0001] The invention relates to the field of intelligent medical technology, in particular to a multi-classification diagnosis system for Alzheimer's disease based on deep learning. Background technique [0002] Alzheimer's disease (AD), also known as senile dementia, is a neurodegenerative disease characterized by progressive memory loss and loss of acquired knowledge until complete loss of daily life ability, which will not only cause Seriously affect the quality of life of patients themselves, but also bring a heavy burden to the patient's family and the whole society. Alzheimer's disease is an important cause of disease that threatens the health of the elderly after cardiovascular disease, cerebrovascular disease and tumors. [0003] Since the famous German neuroanatomist Alzheimer first mentioned the disease in 1906, Alzheimer's disease has been included in the history of medicine for more than 110 years. The clinical diagnosis of Alzheimer's disease i...

AI Technical Summary

Problems solved by technology

[0005] (1) 3D imaging images are often difficult to represent and model due to their high dimensionality, noise, and sparseness, and the use of regions of interest and image segmentation requires certain prior knowledge, which is a challenging task

[0006] (2) Only using imaging images as the basis for the diagnosis of Alzheimer's disease without reference to other medical examinations, such as demographic information, neuropsychological assessment, biological testing, etc., does not conform to clinical practice

Images