Epilepsy focus positioning method and system

Abstract

The invention discloses an epilepsy focus positioning method and system, and the method comprises the steps: firstly carrying out the segmentation of a T1 structural image of an image clearly displaying a brain region structure, obtaining a to-be-detected tissue set, manufacturing a corresponding mask, extracting all tissue regions of tested gradient weighted MRI data through the mask, estimatinga DKI parameter graph, and inputting the DKI parameter graph into a neural network, extracting features to obtain feature vectors, further inputting the feature vectors into a classifier for classification, and judging whether the epilepsy focus exists or not. According to the method, the epilepsy focus analysis accuracy is higher on the basis of the DKI parameter graph with higher nerve tissue representation sensitivity and specificity; the whole brain is replaced by the brain division organization structure for parameter graph estimation, so that the calculation amount is reduced; the neuralnetwork constructed by transfer learning is used for feature extraction, the problem that features extracted by directly training and extracting the feature network are not comprehensive due to smallmedical data volume is solved, the method and system are applied to conventional MRI negative epilepsy, and the illness state of a patient can be effectively controlled through timely and accurate focus positioning diagnosis.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and system for locating an epileptic focus. Background technique [0002] Epilepsy, commonly known as "shorn horn" or "epilepsy", is a chronic disease in which the sudden abnormal discharge of brain neurons leads to transient brain dysfunction. It is estimated that there are about 9 million epilepsy patients in China, of which 5 to 6 million are active epilepsy patients. At the same time, about 400,000 new epilepsy patients are added every year. In China, epilepsy has become the second most common disease in neurology after headache. . In the routine MRI examination, the pathogenic focus directly related to the seizure cannot be found, which is called conventional MRI-negative epilepsy (MRI-Negative Epilepsy), and it is considered to be a subtype of epilepsy, which may be at the starting point of the seizure, and its tissue microstructure Already changed, with...

AI Technical Summary

Problems solved by technology

[0004] Therefore, the present invention aims to solve the problems of large differences and error-prone manual diagnosis of epilepsy in the prior art, thereby providing a method and system for locating epileptic focus, which can automatically learn features and patterns from data, and objectively and accurately locate epileptic focus. Carry out positioning diagnosis

Images