Loading...
Send to Friend
 Bookmark
 Review List
  1. HFO Detection from iEEG Signals in Epilepsy using Time-Trained Graphs and Deep Graph Convolutional Neural Network
HFO Detection from iEEG Signals in Epilepsy using Time-Trained Graphs and Deep Graph Convolutional Neural Network
22 viewed

HFO Detection from iEEG Signals in Epilepsy using Time-Trained Graphs and Deep Graph Convolutional Neural Network

Gharebaghi, F

HFO Detection from iEEG Signals in Epilepsy using Time-Trained Graphs and Deep Graph Convolutional Neural Network

Gharebaghi, F ; Sharif University of Technology | 2024

22 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/ICEE63041.2024.10668007
  3. Publisher: 2024
  4. Abstract:
  5. Intracranial electroencephalography (iEEG) is a type of brain signal widely used to study neurological disorders. Typically, the iEEG signal exhibits frequency components reaching up to 80 Hz. Yet, recent research indicates that in specific circumstances, like epilepsy, the brain signal encompasses frequency components surpassing 80 Hz. These are identified as high-frequency oscillations (HFOs) and are regarded as biomarkers for epilepsy. This paper presents a novel methodology for the automated detection of HFOs based on time-domain features of signals and a deep graph convolutional neural network (DGCNN) algorithm. The proposed method was evaluated using the iEEG data of the Fedele's group from 20 patients with medically intractable epilepsy. The method assumes that the temporal data structure is a graph structure that differs between HFO and non-HFO intervals. By conceptualizing the sequence of time samples as nodes within a graph and training the adjacency matrix of this graph using temporal data, distinct graphs emerge for HFO and non-HFO intervals. Additionally, intervals are distinguished by other features such as RMS, STE, LL, and Teager energy. Therefore, these features are considered as node features that help to increase classification accuracy. The DGCNN network is used to classify the time-trained graphs with extracted node features. The proposed methodology has the following significant advantages: 1) it achieves a higher sensitivity than the recently reported HFO detectors using the DGCNN classifier, and 2) it can automatically extract the common features of HFO events from different patients and is more robust, unlike other automated methods in the literature where the features of HFOs were manually extracted based on researchers' knowledge, which may be subject to observer bias. The proposed method attained a sensitivity of 90.7% and a specificity of 93.3%, indicating a higher sensitivity compared to recently reported HFO detectors. © 2024 IEEE
  6. Keywords:
  7. Deep Graph Convolutional Neural Network (DGCNN) ; Epilepsy ; High Frequency Oscillations (HFOs) ; Intracranial Electroencephalography (iEEG) ; Deep neural networks ; Electroencephalography ; Electrotherapeutics ; Graph algorithms ; Graph neural networks ; Network theory (graphs) ; Neurons ; Time domain analysis ; Brain signals ; Frequency components ; Oscillation frequency ; Temporal Data ; Convolutional neural networks
  8. Source: Iranian Conference on Electrical Engineering, ICEE ; Issue 2024 , 2024 ; 21647054 (ISSN)
  9. URL: https://ieeexplore.ieee.org/document/10668007