Method for automatically identifying and positioning focal cortex dysplasia epilepsy focus

Abstract

The invention discloses a method for automatically identifying and positioning focal cortex dysplasia epilepsy focus. The method comprises the following steps: acquiring multi-modal nerve image data including MRI and PET; forming a large number of data sets with labels through manual labeling; from the angles of brain structure, brain metabolism and the like, deeply excavating a multi-modal biomarker of FCD epilepsy; and establishing and training a CNN focus identification segmentation model based on the original features of the multi-modal data for automatic positioning diagnosis of FCD. According to the invention, aiming at the common pathology FCD of the epilepsy surgery, a part of cases are negative in magnetic resonance and cannot be visually distinguished, intelligent identification is carried out aiming at the FCD epileptic focus, the experience dependence of subjective film reading is greatly reduced, the time cost and the labor cost are reduced, and finally, the diagnosis and treatment efficiency of the epileptic focus is improved, and the operation prognosis is improved.

Description

technical field [0001] The invention relates to the technical field of EEG detection, in particular to a method for automatically identifying and locating focal cortical dysplasia epilepsy lesions. Background technique [0002] Epilepsy is a recurrent neurological chronic disease that seriously threatens human health. WHO statistics show that the prevalence of epilepsy is between 5‰ and 11.2‰. There are about 50 million epilepsy patients in the world, and about 9 million epilepsy patients in my country, including 6 million active epilepsy, and about 400,000 new cases every year . About 20-30% of all epilepsy patients are drug-resistant epilepsy, which requires preoperative evaluation and surgical treatment. [0003] From a pathological point of view, malformation of cortical development (MCD) is the most common pathological basis of drug-refractory focal epilepsy. The pathological manifestations of MCD are the migration, layering and structural abnormalities of cerebral co...

AI Technical Summary

Problems solved by technology

[0013] The previous work was semi-automatic. Firstly, the post-processing of the software took a long time. Secondly, there were many steps, which required manual monitoring, operation and quality control, and there was a possibility of accumulation of errors and errors that could not be traced.

Images