Localising the Seizure Onset Zone from Single-Pulse Electrical Stimulation Responses with a CNN Transformer

Jamie Norris, Aswin Chari, Dorien van Blooijs, Gerald K. Cooray, Karl Friston, Martin M Tisdall, Richard E Rosch
Proceedings of the 9th Machine Learning for Healthcare Conference, PMLR 252, 2024.

Abstract

Epilepsy is one of the most common neurological disorders, often requiring surgical intervention when medication fails to control seizures. For effective surgical outcomes, precise localisation of the epileptogenic focus - often approximated through the Seizure Onset Zone (SOZ) - is critical yet remains a challenge. Active probing through electrical stimulation is already standard clinical practice for identifying epileptogenic areas. Our study advances the application of deep learning for SOZ localisation using Single-Pulse Electrical Stimulation (SPES) responses, with two key contributions. Firstly, we implement an existing deep learning model to compare two SPES analysis paradigms: divergent and convergent. These paradigms evaluate outward and inward effective connections, respectively. We assess the generalisability of these models to unseen patients and electrode placements using held-out test sets. Our findings reveal a notable improvement in moving from a divergent (AUROC: 0.574) to a convergent approach (AUROC: 0.666), marking the first application of the latter in this context. Secondly, we demonstrate the efficacy of CNN Transformers with cross-channel attention in handling heterogeneous electrode placements, increasing the AUROC to 0.730. These findings represent a significant step in modelling patient-specific intracranial EEG electrode placements in SPES. Future work will explore integrating these models into clinical decision-making processes to bridge the gap between deep learning research and practical healthcare applications.

Cite this Paper

BibTeX
@InProceedings{pmlr-v252-norris24a, title = {Localising the Seizure Onset Zone from Single-Pulse Electrical Stimulation Responses with a {CNN} Transformer}, author = {Norris, Jamie and Chari, Aswin and van Blooijs, Dorien and Cooray, Gerald K. and Friston, Karl and Tisdall, Martin M and Rosch, Richard E}, booktitle = {Proceedings of the 9th Machine Learning for Healthcare Conference}, year = {2024}, editor = {Deshpande, Kaivalya and Fiterau, Madalina and Joshi, Shalmali and Lipton, Zachary and Ranganath, Rajesh and Urteaga, Iñigo}, volume = {252}, series = {Proceedings of Machine Learning Research}, month = {16--17 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v252/main/assets/norris24a/norris24a.pdf}, url = {https://proceedings.mlr.press/v252/norris24a.html}, abstract = {Epilepsy is one of the most common neurological disorders, often requiring surgical intervention when medication fails to control seizures. For effective surgical outcomes, precise localisation of the epileptogenic focus - often approximated through the Seizure Onset Zone (SOZ) - is critical yet remains a challenge. Active probing through electrical stimulation is already standard clinical practice for identifying epileptogenic areas. Our study advances the application of deep learning for SOZ localisation using Single-Pulse Electrical Stimulation (SPES) responses, with two key contributions. Firstly, we implement an existing deep learning model to compare two SPES analysis paradigms: divergent and convergent. These paradigms evaluate outward and inward effective connections, respectively. We assess the generalisability of these models to unseen patients and electrode placements using held-out test sets. Our findings reveal a notable improvement in moving from a divergent (AUROC: 0.574) to a convergent approach (AUROC: 0.666), marking the first application of the latter in this context. Secondly, we demonstrate the efficacy of CNN Transformers with cross-channel attention in handling heterogeneous electrode placements, increasing the AUROC to 0.730. These findings represent a significant step in modelling patient-specific intracranial EEG electrode placements in SPES. Future work will explore integrating these models into clinical decision-making processes to bridge the gap between deep learning research and practical healthcare applications.} }
Endnote
%0 Conference Paper %T Localising the Seizure Onset Zone from Single-Pulse Electrical Stimulation Responses with a CNN Transformer %A Jamie Norris %A Aswin Chari %A Dorien van Blooijs %A Gerald K. Cooray %A Karl Friston %A Martin M Tisdall %A Richard E Rosch %B Proceedings of the 9th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2024 %E Kaivalya Deshpande %E Madalina Fiterau %E Shalmali Joshi %E Zachary Lipton %E Rajesh Ranganath %E Iñigo Urteaga %F pmlr-v252-norris24a %I PMLR %U https://proceedings.mlr.press/v252/norris24a.html %V 252 %X Epilepsy is one of the most common neurological disorders, often requiring surgical intervention when medication fails to control seizures. For effective surgical outcomes, precise localisation of the epileptogenic focus - often approximated through the Seizure Onset Zone (SOZ) - is critical yet remains a challenge. Active probing through electrical stimulation is already standard clinical practice for identifying epileptogenic areas. Our study advances the application of deep learning for SOZ localisation using Single-Pulse Electrical Stimulation (SPES) responses, with two key contributions. Firstly, we implement an existing deep learning model to compare two SPES analysis paradigms: divergent and convergent. These paradigms evaluate outward and inward effective connections, respectively. We assess the generalisability of these models to unseen patients and electrode placements using held-out test sets. Our findings reveal a notable improvement in moving from a divergent (AUROC: 0.574) to a convergent approach (AUROC: 0.666), marking the first application of the latter in this context. Secondly, we demonstrate the efficacy of CNN Transformers with cross-channel attention in handling heterogeneous electrode placements, increasing the AUROC to 0.730. These findings represent a significant step in modelling patient-specific intracranial EEG electrode placements in SPES. Future work will explore integrating these models into clinical decision-making processes to bridge the gap between deep learning research and practical healthcare applications.
APA
Norris, J., Chari, A., van Blooijs, D., Cooray, G.K., Friston, K., Tisdall, M.M. & Rosch, R.E.. (2024). Localising the Seizure Onset Zone from Single-Pulse Electrical Stimulation Responses with a CNN Transformer. Proceedings of the 9th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 252 Available from https://proceedings.mlr.press/v252/norris24a.html.

Related Material