Hyperdimensional Computing With Local Binary Patterns: One-Shot Learning of Seizure Onset and Identification of Ictogenic Brain Regions Using Short-Time iEEG Recordings

• Published in: IEEE transactions on biomedical engineering Vol. 67; no. 2; pp. 601 - 613
• Main Authors: Burrello, Alessio, Schindler, Kaspar, Benini, Luca, Rahimi, Abbas
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.02.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Binary codes; Brain; Brain - physiopathology; Cerebral hemispheres; Computation; Computational neuroscience; Convulsions & seizures; Datasets; Decision making; Deep learning; Drug resistance; EEG; Electrocorticography - methods; Electrodes; Electroencephalography; Epilepsy; Feature extraction; Heuristic algorithms; Histograms; Humans; hyperdimensional computing; iEEG; Latency; Learning algorithms; local binary patterns; localization of seizure onset zone; Machine Learning; one-shot learning; Post-translation; Prototypes; Representations; seizure detection; Seizures; Seizures - diagnosis; Seizures - physiopathology; Signal Processing, Computer-Assisted; Source code; Surgery; symbolic dynamics
• ISSN: 0018-9294; 1558-2531; 1558-2531
• DOI: 10.1109/TBME.2019.2919137

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 36-100 electrodes. For the majority of the patients (ten 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% versus 94.77%) and macroaveraging accuracy (95.42% versus 94.96%), and 74 × lower memory footprint, but slightly higher average latency in detection (15.9 s versus 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; and 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://ieegswez.ethz.ch.