Temporal lobe epilepsy auxiliary diagnosis method based on DTI technology and SVM

Abstract

The invention discloses a temporal lobe epilepsy auxiliary diagnosis method based on a DTI technology and SVM, and belongs to the technical field of epilepsy auxiliary diagnosis. At first, a diffusionmagnetic resonance imaging (MRI) map is preprocessed; diffusion MRI indexes of brain main white matter fibrous skeleton are extracted; multiple diffusion indexes of 50 core white matter regions divided according to a spectrum are calculated, then white matter region diffusion indexes having obvious difference are extracted; a machine learning method of SVM (support vector machine) is adopted to carry out classification; and the diffusion indexes of a white matter region having the strongest differentiating performance are taken as the input characteristics to carry out model training and testing. Finally, the left temporal lobe epilepsy patients, the right temporal lobe epilepsy patients and normal persons can be identified and classified. A novel MRI technology and machine learning are adopted to classify and identify temporal lobe epilepsy patients and novel thinking and approach are provided for the auxiliary diagnosis of temporal lobe epilepsy patients in clinic.

Description

technical field [0001] The invention belongs to the technical field of auxiliary diagnosis of epilepsy, and in particular relates to a method for identifying and classifying patients with temporal lobe epilepsy (TLE) based on diffusion tensor imaging (DTI) and support vector machine (SVM) method. Background technique [0002] Temporal lobe epilepsy is the most common drug-refractory epilepsy and focal epilepsy clinically. Seizure types include simple partial seizures, complex partial seizures, and secondary generalized seizures or a combination of these seizures, often with a history of febrile seizures and a family history of epilepsy. Simple partial seizures are typically characterized by autonomic and / or psychiatric symptoms, the most common being a rushing sensation in the upper abdomen. Surgical resection of the epileptogenic focus is an effective treatment for some TLE patients who cannot be controlled by drugs. Surgical treatment methods for TLE mainly include: ant...

AI Technical Summary

Problems solved by technology

The traditional analysis method is the two-sample t-test method based on the voxel hypothesis test of magnetic resonance images. However, this method can only find the difference between the patient group and the normal group at the group level, and cannot clinically analyze the individual Auxiliary diagnosis

Images