Show simple item record

dc.contributor.author
Burrello, Alessio
dc.contributor.author
Schindler, Kaspar
dc.contributor.author
Benini, Luca
dc.contributor.author
Rahimi, Abbas
dc.date.accessioned
2020-02-12T09:38:27Z
dc.date.available
2019-06-27T01:03:23Z
dc.date.available
2019-06-27T11:48:28Z
dc.date.available
2019-09-03T13:32:03Z
dc.date.available
2020-02-12T09:38:27Z
dc.date.issued
2020-02
dc.identifier.issn
0018-9294
dc.identifier.issn
1558-2531
dc.identifier.other
10.1109/TBME.2019.2919137
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/350002
dc.identifier.doi
10.3929/ethz-b-000350002
dc.description.abstract
Objective: We develop a fast learning algorithm combining symbolic dynamics and brain-inspired hyperdimensional computing for both seizure onset detection and identification of ictogenic (seizure generating) brain regions from intracranial electroencephalography (iEEG). Methods: Our algorithm first transforms iEEG time series from each electrode into symbolic local binary pattern codes from which a holographic distributed representation of the brain state of interest is constructed across all the electrodes and over time in a hyperdimensional space. The representation is used to quickly learn from few seizures, detect their onset, and identify the spatial brain regions that generated them. Results: We assess our algorithm on our dataset that contains 99 short-time iEEG recordings from 16 drug-resistant epilepsy patients being implanted with 36 to 100 electrodes. For the majority of the patients (10 out of 16), our algorithm quickly learns from one or two seizures and perfectly (100%) generalizes on novel seizures using k-fold cross-validation. For the remaining six patients, the algorithm requires three to six seizures for learning. Our algorithm surpasses the state-of-the-art including deep learning algorithms by achieving higher specificity (94.84% vs. 94.77%) and macroaveraging accuracy (95.42% vs. 94.96%), and 74x lower memory footprint, but slightly higher average latency in detection (15.9 s vs. 14.7 s). Moreover, the algorithm can reliably identify (with a p-value < 0.01) the relevant electrodes covering an ictogenic brain region at two levels of granularity: cerebral hemispheres and lobes. Conclusion and significance: Our algorithm provides: (1) a unified method for both learning and classification tasks with end-to-end binary operations; (2) one-shot learning from seizure examples; (3) linear computational scalability for increasing number of electrodes; (4) generation of transparent codes that enables post-translational support for clinical decision making. Our source code and anonymized iEEG dataset are freely available at http://ieeg-swez.ethz.ch.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.rights.uri
http://rightsstatements.org/page/InC-NC/1.0/
dc.subject
Time series
en_US
dc.subject
Symbolic dynamics
en_US
dc.subject
Sizure detec
en_US
dc.title
Hyperdimensional Computing with Local Binary Patterns: One-shot Learning of Seizure Onset and Identification of Ictogenic Brain Regions using Short-time iEEG Recordings
en_US
dc.type
Journal Article
dc.rights.license
In Copyright - Non-Commercial Use Permitted
dc.date.published
2019-05-27
ethz.journal.title
IEEE Transactions on Biomedical Engineering
ethz.journal.volume
67
en_US
ethz.journal.issue
2
en_US
ethz.journal.abbreviated
IEEE trans. biomed. eng.
ethz.pages.start
601
en_US
ethz.pages.end
613
en_US
ethz.size
13 p. accepted version
en_US
ethz.version.deposit
acceptedVersion
en_US
ethz.grant
ETH Zurich Postdoctoral Fellowship Program II
en_US
ethz.grant
Computation-in-memory architecture based on resistive devices
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
New York, NY
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02636 - Institut für Integrierte Systeme / Integrated Systems Laboratory::03996 - Benini, Luca / Benini, Luca
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02636 - Institut für Integrierte Systeme / Integrated Systems Laboratory::03996 - Benini, Luca / Benini, Luca
en_US
ethz.tag
Seizure onset detection
en_US
ethz.tag
Ictogenic brain regions identification
en_US
ethz.tag
One-shot learning
en_US
ethz.tag
Hyperdimensional computing
en_US
ethz.tag
Intracranial electroencephalography (iEEG)
en_US
ethz.grant.agreementno
608881
ethz.grant.agreementno
780215
ethz.grant.fundername
EC
ethz.grant.fundername
EC
ethz.grant.funderDoi
10.13039/501100000780
ethz.grant.funderDoi
10.13039/501100000780
ethz.grant.program
FP7
ethz.grant.program
H2020
ethz.relation.isSupplementedBy
http://ieeg-swez.ethz.ch/
ethz.date.deposited
2019-06-27T01:03:30Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2020-02-12T09:38:44Z
ethz.rosetta.lastUpdated
2022-03-29T00:58:35Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&amp;rft_val_fmt=info:ofi/fmt:kev:mtx:journal&amp;rft.atitle=Hyperdimensional%20Computing%20with%20Local%20Binary%20Patterns:%20One-shot%20Learning%20of%20Seizure%20Onset%20and%20Identification%20of%20Ictogenic%20Brain%20Regions%2&amp;rft.jtitle=IEEE%20Transactions%20on%20Biomedical%20Engineering&amp;rft.date=2020-02&amp;rft.volume=67&amp;rft.issue=2&amp;rft.spage=601&amp;rft.epage=613&amp;rft.issn=0018-9294&amp;1558-2531&amp;rft.au=Burrello,%20Alessio&amp;Schindler,%20Kaspar&amp;Benini,%20Luca&amp;Rahimi,%20Abbas&amp;rft.genre=article&amp;rft_id=info:doi/10.1109/TBME.2019.2919137&amp;
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record