Deep generative networks for algorithm development in implantable neural technology
Electrical stimulation of deep brain structures is an established therapy for drug-resistant focal epilepsy. The emerging implantable neural sensing and stimulating (INSS) technology enables simultaneous delivery of chronic deep brain stimulation (DBS) and recording of electrical brain activity from...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers
2022
|
| _version_ | 1797109637428805632 |
|---|---|
| author | Mivalt, F Sladky, V Balzekas, I Pridalova, T Miller, KJ Van Gompel, J Denison, T Brinkmann, BH Kremen, V Worrell, GA |
| author_facet | Mivalt, F Sladky, V Balzekas, I Pridalova, T Miller, KJ Van Gompel, J Denison, T Brinkmann, BH Kremen, V Worrell, GA |
| author_sort | Mivalt, F |
| collection | OXFORD |
| description | Electrical stimulation of deep brain structures is an established therapy for drug-resistant focal epilepsy. The emerging implantable neural sensing and stimulating (INSS) technology enables simultaneous delivery of chronic deep brain stimulation (DBS) and recording of electrical brain activity from deep brain structures while patients live in their home environment. Long-term intracranial electroencephalography (iEEG) iEEG signals recorded by INSS devices represent an opportunity to investigate brain neurophysiology and how DBS affects neural circuits. However, novel algorithms and data processing pipelines need to be developed to facilitate research of these long-term iEEG signals. Early-stage analytical infrastructure development for INSS applications can be limited by lacking iEEG data that might not always be available. Here, we investigate the feasibility of utilizing the Deep Generative Adversarial Network (DCGAN) for synthetic iEEG data generation. We trained DCGAN using 3-second iEEG segments and validated synthetic iEEG usability by training a classification model, using synthetic iEEG only and providing a good classification performance on unseen real iEEG with an F1 score 0.849. Subsequently, we demonstrated the feasibility of utilizing the synthetic iEEG in the INSS application development by training a deep learning network for DBS artifact removal using synthetic data only and demonstrated the performance on real iEEG signals. The presented strategy of on-demand generating synthetic iEEG will benefit early-stage algorithm development for INSS applications. |
| first_indexed | 2024-03-07T07:44:19Z |
| format | Conference item |
| id | oxford-uuid:af3357d6-92f9-45fc-a21a-04f06bbe7362 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T07:44:19Z |
| publishDate | 2022 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | oxford-uuid:af3357d6-92f9-45fc-a21a-04f06bbe73622023-05-23T06:19:37ZDeep generative networks for algorithm development in implantable neural technologyConference itemhttp://purl.org/coar/resource_type/c_5794uuid:af3357d6-92f9-45fc-a21a-04f06bbe7362EnglishSymplectic ElementsInstitute of Electrical and Electronics Engineers2022Mivalt, FSladky, VBalzekas, IPridalova, TMiller, KJVan Gompel, JDenison, TBrinkmann, BHKremen, VWorrell, GAElectrical stimulation of deep brain structures is an established therapy for drug-resistant focal epilepsy. The emerging implantable neural sensing and stimulating (INSS) technology enables simultaneous delivery of chronic deep brain stimulation (DBS) and recording of electrical brain activity from deep brain structures while patients live in their home environment. Long-term intracranial electroencephalography (iEEG) iEEG signals recorded by INSS devices represent an opportunity to investigate brain neurophysiology and how DBS affects neural circuits. However, novel algorithms and data processing pipelines need to be developed to facilitate research of these long-term iEEG signals. Early-stage analytical infrastructure development for INSS applications can be limited by lacking iEEG data that might not always be available. Here, we investigate the feasibility of utilizing the Deep Generative Adversarial Network (DCGAN) for synthetic iEEG data generation. We trained DCGAN using 3-second iEEG segments and validated synthetic iEEG usability by training a classification model, using synthetic iEEG only and providing a good classification performance on unseen real iEEG with an F1 score 0.849. Subsequently, we demonstrated the feasibility of utilizing the synthetic iEEG in the INSS application development by training a deep learning network for DBS artifact removal using synthetic data only and demonstrated the performance on real iEEG signals. The presented strategy of on-demand generating synthetic iEEG will benefit early-stage algorithm development for INSS applications. |
| spellingShingle | Mivalt, F Sladky, V Balzekas, I Pridalova, T Miller, KJ Van Gompel, J Denison, T Brinkmann, BH Kremen, V Worrell, GA Deep generative networks for algorithm development in implantable neural technology |
| title | Deep generative networks for algorithm development in implantable neural technology |
| title_full | Deep generative networks for algorithm development in implantable neural technology |
| title_fullStr | Deep generative networks for algorithm development in implantable neural technology |
| title_full_unstemmed | Deep generative networks for algorithm development in implantable neural technology |
| title_short | Deep generative networks for algorithm development in implantable neural technology |
| title_sort | deep generative networks for algorithm development in implantable neural technology |
| work_keys_str_mv | AT mivaltf deepgenerativenetworksforalgorithmdevelopmentinimplantableneuraltechnology AT sladkyv deepgenerativenetworksforalgorithmdevelopmentinimplantableneuraltechnology AT balzekasi deepgenerativenetworksforalgorithmdevelopmentinimplantableneuraltechnology AT pridalovat deepgenerativenetworksforalgorithmdevelopmentinimplantableneuraltechnology AT millerkj deepgenerativenetworksforalgorithmdevelopmentinimplantableneuraltechnology AT vangompelj deepgenerativenetworksforalgorithmdevelopmentinimplantableneuraltechnology AT denisont deepgenerativenetworksforalgorithmdevelopmentinimplantableneuraltechnology AT brinkmannbh deepgenerativenetworksforalgorithmdevelopmentinimplantableneuraltechnology AT kremenv deepgenerativenetworksforalgorithmdevelopmentinimplantableneuraltechnology AT worrellga deepgenerativenetworksforalgorithmdevelopmentinimplantableneuraltechnology |