홈 › Papers

Desynchronization Index: a New Approach for Exploring Complex Epileptogenic Networks in Stereoelectroencephalography

In this work, we propose a new computational framework to assist neurophysiologists in Stereoelectroencephalography (SEEG) analysis, with the final aim of improving the definition of the Epileptogenic Zone (EZ) in patients with drug-resistant epilepsy. We design a new algorithm, named Desynchronization Index (DI), that classifies as most epileptogenic those SEEG channels that show independent behavior during the seconds preceding the seizure propagation. We test the proposed DI algorithm against the Epileptogenic Index (EI) algorithm on a clinical dataset of 11 patients, considering the neurophysiological evaluation of the EZ as the clinical ground truth. Our results denote that DI overcomes EI in terms of area under the ROC curve (AUC=0.81 vs AUC=0.74) while combining the two algorithms as a unique tool leads to the best performance (AUC=0.87). The DI algorithm underscores connectivity dynamics that can hardly be identified with a pure visual analysis, increasing the accuracy of the EZ definition compared to traditional methods. This technique can lead to the definition of a new effective biomarker of the EZ, reducing the burden required by the SEEG review in the case of extensive implants and improving our understanding of the dynamics leading to the generation of seizures.

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반