Self-Supervised Distillation of Legacy Rule-Based Methods for Enhanced EEG-Based Decision-Making

TL;DR

This paper introduces SS2LD, a self-supervised framework that refines legacy HFO detectors in iEEG data to accurately identify pathological events, reducing reliance on manual labels and improving detection precision.

Contribution

The study presents a novel self-supervised learning approach that leverages legacy detectors and variational autoencoders to improve HFO detection without extensive labeled data.

Findings

SS2LD outperforms existing methods on multi-institutional datasets.

The framework effectively reduces false positives in HFO detection.

It demonstrates scalable and label-efficient detection of pathological HFOs.

Abstract

High-frequency oscillations (HFOs) in intracranial Electroencephalography (iEEG) are critical biomarkers for localizing the epileptogenic zone in epilepsy treatment. However, traditional rule-based detectors for HFOs suffer from unsatisfactory precision, producing false positives that require time-consuming manual review. Supervised machine learning approaches have been used to classify the detection results, yet they typically depend on labeled datasets, which are difficult to acquire due to the need for specialized expertise. Moreover, accurate labeling of HFOs is challenging due to low inter-rater reliability and inconsistent annotation practices across institutions. The lack of a clear consensus on what constitutes a pathological HFO further challenges supervised refinement approaches. To address this, we leverage the insight that legacy detectors reliably capture clinically relevant signals despite their relatively high false positive rates. We thus propose the Self-Supervised to Label Discovery (SS2LD) framework to refine the large set of candidate events generated by legacy detectors into a precise set of pathological HFOs. SS2LD employs a variational autoencoder (VAE) for morphological pre-training to learn meaningful latent representation of the detected events. These representations are clustered to derive weak supervision for pathological events. A classifier then uses this supervision to refine detection boundaries, trained on real and VAE-augmented data. Evaluated on large multi-institutional interictal iEEG datasets, SS2LD outperforms state-of-the-art methods. SS2LD offers a scalable, label-efficient, and clinically effective strategy to identify pathological HFOs using legacy detectors.