FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3155364532> ?p ?o ?g. }

• W3155364532 abstract "Automated seizure detection and classification from electroencephalography (EEG) can greatly improve the diagnosis and treatment of seizures. While prior studies mainly used convolutional neural networks (CNNs) that assume image-like structure in EEG signals or spectrograms, this modeling choice does not reflect the natural geometry of or connectivity between EEG electrodes. In this study, we propose modeling EEGs as graphs and present a graph neural network for automated seizure detection and classification. In addition, we leverage unlabeled EEG data using a self-supervised pre-training strategy. Our graph model with self-supervised pre-training significantly outperforms previous state-of-the-art CNN and Long Short-Term Memory (LSTM) models by 6.3 points (7.8%) in Area Under the Receiver Operating Characteristic curve (AUROC) for seizure detection and 6.3 points (9.2%) in weighted F1-score for seizure type classification. Ablation studies show that our graph-based modeling approach significantly outperforms existing CNN or LSTM models, and that self-supervision helps further improve the model performance. Moreover, we find that self-supervised pre-training substantially improves model performance on combined tonic seizures, a low-prevalence seizure type. Furthermore, our model interpretability analysis suggests that our model is better at identifying seizure regions compared to an existing CNN. In summary, our graph-based modeling approach integrates domain knowledge about EEG, sets a new state-of-the-art for seizure detection and classification on a large public dataset (5,499 EEG files), and provides better ability to identify seizure regions." @default.
• W3155364532 created "2021-04-26" @default.
• W3155364532 creator A5004336107 @default.
• W3155364532 creator A5004965117 @default.
• W3155364532 creator A5016622484 @default.
• W3155364532 creator A5020160974 @default.
• W3155364532 creator A5023339664 @default.
• W3155364532 creator A5049093095 @default.
• W3155364532 creator A5061240205 @default.
• W3155364532 creator A5077447259 @default.
• W3155364532 date "2021-04-16" @default.
• W3155364532 modified "2023-09-23" @default.
• W3155364532 title "Automated Seizure Detection and Seizure Type Classification From Electroencephalography With a Graph Neural Network and Self-Supervised Pre-Training." @default.
• W3155364532 cites W1504660451 @default.
• W3155364532 cites W1866331913 @default.
• W3155364532 cites W1964875525 @default.
• W3155364532 cites W1974094402 @default.
• W3155364532 cites W1978437325 @default.
• W3155364532 cites W2056349259 @default.
• W3155364532 cites W2064675550 @default.
• W3155364532 cites W2069115302 @default.
• W3155364532 cites W2073135166 @default.
• W3155364532 cites W2101491865 @default.
• W3155364532 cites W2130942839 @default.
• W3155364532 cites W2138190513 @default.
• W3155364532 cites W2153120743 @default.
• W3155364532 cites W2155390087 @default.
• W3155364532 cites W2315878770 @default.
• W3155364532 cites W2318777845 @default.
• W3155364532 cites W2345279893 @default.
• W3155364532 cites W2592509339 @default.
• W3155364532 cites W2594644573 @default.
• W3155364532 cites W2749859392 @default.
• W3155364532 cites W2753247993 @default.
• W3155364532 cites W2756417987 @default.
• W3155364532 cites W2759483166 @default.
• W3155364532 cites W2768189107 @default.
• W3155364532 cites W2790404832 @default.
• W3155364532 cites W2805050064 @default.
• W3155364532 cites W2842511635 @default.
• W3155364532 cites W2888487581 @default.
• W3155364532 cites W2904559787 @default.
• W3155364532 cites W2911605208 @default.
• W3155364532 cites W2911632638 @default.
• W3155364532 cites W2948224565 @default.
• W3155364532 cites W2949095067 @default.
• W3155364532 cites W2963196092 @default.
• W3155364532 cites W2963290013 @default.
• W3155364532 cites W2963358464 @default.
• W3155364532 cites W2963861107 @default.
• W3155364532 cites W2964121744 @default.
• W3155364532 cites W2964199361 @default.
• W3155364532 cites W2964267916 @default.
• W3155364532 cites W2964321699 @default.
• W3155364532 cites W2966616847 @default.
• W3155364532 cites W2990430870 @default.
• W3155364532 cites W2991453460 @default.
• W3155364532 cites W2992314358 @default.
• W3155364532 cites W3003074332 @default.
• W3155364532 cites W3015198908 @default.
• W3155364532 cites W3016911444 @default.
• W3155364532 cites W3034978746 @default.
• W3155364532 cites W3036982689 @default.
• W3155364532 cites W3082319289 @default.
• W3155364532 cites W3087671240 @default.
• W3155364532 cites W3092787476 @default.
• W3155364532 cites W3098288266 @default.
• W3155364532 cites W3101658985 @default.
• W3155364532 cites W3106003888 @default.
• W3155364532 cites W3109789186 @default.
• W3155364532 cites W3119307757 @default.
• W3155364532 cites W3121468319 @default.
• W3155364532 cites W3123796542 @default.
• W3155364532 cites W3126216973 @default.
• W3155364532 cites W3126317075 @default.
• W3155364532 hasPublicationYear "2021" @default.
• W3155364532 type Work @default.
• W3155364532 sameAs 3155364532 @default.
• W3155364532 citedByCount "0" @default.
• W3155364532 crossrefType "posted-content" @default.
• W3155364532 hasAuthorship W3155364532A5004336107 @default.
• W3155364532 hasAuthorship W3155364532A5004965117 @default.
• W3155364532 hasAuthorship W3155364532A5016622484 @default.
• W3155364532 hasAuthorship W3155364532A5020160974 @default.
• W3155364532 hasAuthorship W3155364532A5023339664 @default.
• W3155364532 hasAuthorship W3155364532A5049093095 @default.
• W3155364532 hasAuthorship W3155364532A5061240205 @default.
• W3155364532 hasAuthorship W3155364532A5077447259 @default.
• W3155364532 hasConcept C119857082 @default.
• W3155364532 hasConcept C132525143 @default.
• W3155364532 hasConcept C153083717 @default.
• W3155364532 hasConcept C153180895 @default.
• W3155364532 hasConcept C154945302 @default.
• W3155364532 hasConcept C15744967 @default.
• W3155364532 hasConcept C169760540 @default.
• W3155364532 hasConcept C2778186239 @default.
• W3155364532 hasConcept C2779334592 @default.
• W3155364532 hasConcept C2781067378 @default.
• W3155364532 hasConcept C41008148 @default.
• W3155364532 hasConcept C522805319 @default.

• next