Alzheimer's disease SVM classification model construction method based on nuclear magnetic resonance spectrum

Abstract

The invention provides an Alzheimer's disease SVM classification model construction method based on a nuclear magnetic resonance spectrum. The method comprises the following steps: acquiring and processing MRS data of a patient, marking multiple voxels in a hippocampus region, and extracting specific multi-voxel MRS metabolite concentrations; calculating the multi-voxel MRS metabolite concentration ratios of all the markers, and respectively calculating four characteristics of the multi-voxel MRS metabolite concentration ratios of the left hippocampus and the right hippocampus to form an input characteristic vector; normalizing all the feature vectors; inputting the obtained feature vectors into an SVM function to establish an SVM classification model; and obtaining a prediction category of an input sample. An extracted 48-dimensional characteristic value of brain hippocampus tissue metabolism data observed based on a multi-voxel MRS technology is used for establishing a support vector machine automatic classification model for three classifications of AD patients, MCI patients and normal old people, and hippocampus multi-voxel magnetic resonance spectrum data of the three types of people can be classified and identified through the model. Therefore, the type of the subject can be quickly classified, and the method is practical and effective.

Description

technical field [0001] The invention relates to the technical field of Alzheimer's disease diagnosis, in particular to a method for constructing an SVM classification model of Alzheimer's disease based on nuclear magnetic resonance spectroscopy. Background technique [0002] Alzheimer's disease (AD) is a neurodegenerative disease with insidious onset and progressive development. Clinically, it is characterized by comprehensive dementia such as memory impairment, aphasia, apraxia, agnosia, impairment of visuospatial skills, executive dysfunction, and personality and behavior changes. The etiology is still unknown. Those with onset before the age of 65 are called Alzheimer's disease; those with onset after the age of 65 are called senile dementia; the disease may be a group of heterogeneous diseases that develop under the influence of multiple factors (including biological and psychosocial factors); Judging from the current research, there are more than 30 possible factors an...

AI Technical Summary

Problems solved by technology

[0003] MRS is a non-invasive neuroimaging technique that can be used for the qualitative and quantitative determination of metabolite concentrations in living brain tissue of various neurodegenerative diseases; the use of multi-voxel MRS technology to observe changes in the concentration of metabolites in hippocampus tissue is the key to Alzheimer's disease. It is an important tool for the differential diagnosis of Alzheimer's disease (AD) and mild cognitive impairment (MCI). Compared with MR structural image data, MRS is not intuitive, and its application in medical clinical analysis is limited due to the threshold of signal processing. Auxiliary diagnostic tool for Alzheimer's disease prediction

Images