Parkinson's disease auxiliary recognition method for constructing brain network modeling based on fMRI and DTI

Abstract

The invention provides a Parkinson's disease auxiliary identification method for constructing brain network modeling based on fMRI and DTI. The method comprises the steps: extracting an fMRI image ofthe brain of a user, and preprocessing the fMRI image; performing calculating based on the region of interest to obtain an fMRI function connection matrix, and identifying brain function connection related to PD motion symptoms; extracting a DTI image of the brain of the user, preprocessing the DTI image, and then performing calculating based on the region of interest to obtain a DTI probability fiber connection matrix; preprocessing the fMRI image and preprocessing the DTI image respectively; identifying brain function connection and probability fiber connection with high representativeness in the fMRI function connection matrix and the DTI probability fiber connection matrix; performing machine learning on the brain function connection and the probability fiber connection with high characterization to obtain PD related connection characteristics, and obtaining characterization parameters most similar to the brain region of a PD patient through the high characterization connection characteristics of the fMRI function connection matrix and the DTI probability connection matrix so as to compare and judge the state of the PD patient.

Description

technical field [0001] The invention relates to the technical field of computer analysis of medical images, in particular to a Parkinson's-aided recognition method for constructing brain network modeling based on fMRI and DTI. Background technique [0002] Parkinson's disease (PD) is a common degenerative disease of the nervous system. So far unknown. At present, the clinical diagnosis of Parkinson's disease mainly depends on physical examination, medical history and clinical manifestations of patients. However, when most patients are diagnosed, they are already in the middle and advanced stages, which makes most Parkinson's patients miss the best treatment period. Therefore, the development of Parkinson's early diagnosis technology and the search for Parkinson's biological markers are urgent problems to be solved; in particular, the search for individualized neuroimaging markers that improve motor symptoms has a more intuitive effect on subsequent treatment and judgment o...

AI Technical Summary

Problems solved by technology

However, due to the atypical clinical symptoms in the early stage of the disease, it is difficult to diagnose, and the conventional MRI examination also has certain limitations in its diagnosis, so the treatment is often delayed

Images