VISOR: VIsual Seizure Onset Detection PeRsonalized for Epilepsy Patients
VISOR: VIsual Seizure Onset Detection PeRsonalized for Epilepsy Patients
Dokument öffnen (1MB)Datum der Veröffentlichung
18.06.2025Verlag / herausgebende Einrichtung
Springer NatureVerlagsort
SingaporeMetadaten
Zur Langanzeige
Zitierbarer Link (Handle URI) 
https://hdl.handle.net/20.500.11811/14245
Inhalt
The onset detection of epileptic seizures from multivariate Electroencephalogram (EEG) data is a challenging task. The variation in seizure patterns across patients and epilepsy types makes it particularly difficult to create a generic solution. Existing approaches indicate low recall due to their inability to capture complex seizure onset patterns. In this paper, we propose VISOR – a novel approach to detect the onset of epileptic seizures based on novel patient profiles and visual, personalized feature representations. VISOR leverages a vision transformer model to learn the spatio-temporal relationships between features, capture individual seizure propagation patterns, and perform seizure onset detection in a heterogeneous multi-patient dataset. Evaluation on a real-world dataset demonstrates that VISOR outperforms state-of-the-art baselines by at least 5% points for seizure onset detection in terms of the F1 score and indicates higher effectiveness for more complex patterns of propagating seizures.
Klassifikation (DDC)
004 InformatikErschienen in
Advances in Knowledge Discovery and Data Mining : 29th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2025, Sydney, NSW, Australia, June 10–13, 2025, Proceedings, Part II, S. 482-494Erstpublikation
https://doi.org/10.1007/978-981-96-8173-0_38Kumar, Uttam; Yu, Ran; Wenzel, Michael; Demidova, Elena: Wu, Xintao; Spiliopoulou, Myra; Wang, Can; Kumar, Vipin; Cao, Longbing; Wu, Yanqiu; Yao, Yu; Wu, Zhangkai (Hrsg.): VISOR: VIsual Seizure Onset Detection PeRsonalized for Epilepsy Patients. Singapore: Springer Nature, 2025. In: Wu, Xintao; Spiliopoulou, Myra; Wang, Can; Kumar, Vipin; Cao, Longbing; Wu, Yanqiu; Yao, Yu; Wu, Zhangkai (Hrsg.): Advances in Knowledge Discovery and Data Mining : 29th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2025, Sydney, NSW, Australia, June 10–13, 2025, Proceedings, Part II. , . Singapore: Springer Nature, 2025. 482-494.
Online-Ausgabe in bonndoc: https://hdl.handle.net/20.500.11811/14245
Online-Ausgabe in bonndoc: https://hdl.handle.net/20.500.11811/14245
@proceedings{handle:20.500.11811/14245,
author = {{Uttam Kumar} and {Ran Yu} and {Michael Wenzel} and {Elena Demidova}},
editor = {{Xintao Wu} and {Myra Spiliopoulou} and {Can Wang} and {Vipin Kumar} and {Longbing Cao} and {Yanqiu Wu} and {Yu Yao} and {Zhangkai Wu}},
title = {VISOR: VIsual Seizure Onset Detection PeRsonalized for Epilepsy Patients},
publisher = {Springer Nature},
year = 2025,
month = jun,
booktitle = {Advances in Knowledge Discovery and Data Mining : 29th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2025, Sydney, NSW, Australia, June 10–13, 2025, Proceedings, Part II},
pages = 482--494,
note = {The onset detection of epileptic seizures from multivariate Electroencephalogram (EEG) data is a challenging task. The variation in seizure patterns across patients and epilepsy types makes it particularly difficult to create a generic solution. Existing approaches indicate low recall due to their inability to capture complex seizure onset patterns. In this paper, we propose VISOR – a novel approach to detect the onset of epileptic seizures based on novel patient profiles and visual, personalized feature representations. VISOR leverages a vision transformer model to learn the spatio-temporal relationships between features, capture individual seizure propagation patterns, and perform seizure onset detection in a heterogeneous multi-patient dataset. Evaluation on a real-world dataset demonstrates that VISOR outperforms state-of-the-art baselines by at least 5% points for seizure onset detection in terms of the F1 score and indicates higher effectiveness for more complex patterns of propagating seizures.},
url = {https://hdl.handle.net/20.500.11811/14245}
}
author = {{Uttam Kumar} and {Ran Yu} and {Michael Wenzel} and {Elena Demidova}},
editor = {{Xintao Wu} and {Myra Spiliopoulou} and {Can Wang} and {Vipin Kumar} and {Longbing Cao} and {Yanqiu Wu} and {Yu Yao} and {Zhangkai Wu}},
title = {VISOR: VIsual Seizure Onset Detection PeRsonalized for Epilepsy Patients},
publisher = {Springer Nature},
year = 2025,
month = jun,
booktitle = {Advances in Knowledge Discovery and Data Mining : 29th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2025, Sydney, NSW, Australia, June 10–13, 2025, Proceedings, Part II},
pages = 482--494,
note = {The onset detection of epileptic seizures from multivariate Electroencephalogram (EEG) data is a challenging task. The variation in seizure patterns across patients and epilepsy types makes it particularly difficult to create a generic solution. Existing approaches indicate low recall due to their inability to capture complex seizure onset patterns. In this paper, we propose VISOR – a novel approach to detect the onset of epileptic seizures based on novel patient profiles and visual, personalized feature representations. VISOR leverages a vision transformer model to learn the spatio-temporal relationships between features, capture individual seizure propagation patterns, and perform seizure onset detection in a heterogeneous multi-patient dataset. Evaluation on a real-world dataset demonstrates that VISOR outperforms state-of-the-art baselines by at least 5% points for seizure onset detection in terms of the F1 score and indicates higher effectiveness for more complex patterns of propagating seizures.},
url = {https://hdl.handle.net/20.500.11811/14245}
}
Die folgenden Nutzungsbestimmungen sind mit dieser Ressource verbunden:
