One-shot Learning for iEEG Seizure Detection Using End-to-end Binary Operations: Local Binary Patterns with Hyperdimensional Computing

TL;DR

This paper introduces a novel end-to-end binary algorithm combining local binary patterns and hyperdimensional computing for efficient, few-shot seizure detection from iEEG data, outperforming existing methods.

Contribution

The paper presents a new binarized learning algorithm that enables rapid seizure detection with minimal training data using local binary patterns and hyperdimensional computing.

Findings

Achieves perfect generalization for most patients with one or two seizures.

Requires only three to six seizures for some patients to learn effectively.

Outperforms state-of-the-art methods in sensitivity, specificity, and memory efficiency.

Abstract

This paper presents an efficient binarized algorithm for both learning and classification of human epileptic seizures from intracranial electroencephalography (iEEG). The algorithm combines local binary patterns with brain-inspired hyperdimensional computing to enable end-to-end learning and inference with binary operations. The algorithm first transforms iEEG time series from each electrode into local binary pattern codes. Then atomic high-dimensional binary vectors are used to construct composite representations of seizures across all electrodes. For the majority of our patients (10 out of 16), the algorithm quickly learns from one or two seizures (i.e., one-/few-shot learning) and perfectly generalizes on 27 further seizures. For other patients, the algorithm requires three to six seizures for learning. Overall, our algorithm surpasses the state-of-the-art methods for detecting 65 novel seizures with higher specificity and sensitivity, and lower memory footprint.