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

2025-07-19

AI Summary

To address the clinical challenges of high false-positive rates in high-frequency oscillation (HFO) detection from intracranial electroencephalography (iEEG) and the scarcity and unreliability of pathological annotations, this paper proposes SS2LD—a self-supervised distillation framework. SS2LD innovatively leverages the high-recall outputs of conventional rule-based detectors as weak supervision signals. It employs a variational autoencoder (VAE) to learn morphological representations of HFOs and integrates clustering to uncover implicit pathological patterns, enabling unsupervised refinement of pathological HFOs. Subsequently, a classifier is jointly trained on both real and VAE-augmented data to optimize decision boundaries. Evaluated on a multicenter resting-state iEEG dataset, SS2LD significantly reduces false positives and improves accuracy in identifying pathological HFOs, while demonstrating strong clinical applicability and cross-institutional generalizability.

Technology Category

• Machine Learning: Unsupervised & Self-Supervised Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Improving precision of rule-based HFO detectors in EEG
• Reducing reliance on labeled datasets for HFO classification
• Addressing inconsistent HFO annotations across institutions

Innovation

• Self-supervised framework refines legacy detector outputs
• Variational autoencoder learns latent event representations
• Clustering provides weak supervision for pathological events