Seizure-NGCLNet: Representation Learning of SEEG Spatial Pathological Patterns for Epileptic Seizure Detection via Node-Graph Dual Contrastive Learning

TL;DR

Seizure-NGCLNet is a novel contrastive learning framework that leverages spatial connectivity patterns in SEEG data to improve detection of drug-resistant epilepsy seizures with high accuracy and interpretability.

Contribution

The paper introduces a dual contrastive learning approach with adaptive graph augmentation to effectively learn spatial pathological patterns in SEEG data for seizure detection.

Findings

Achieves 95.93% accuracy in seizure detection

Effectively separates ictal and interictal states in embeddings

Enhances seizure onset zone localization

Abstract

Complex spatial connectivity patterns, such as interictal suppression and ictal propagation, complicate accurate drug-resistant epilepsy (DRE) seizure detection using stereotactic electroencephalography (SEEG) and traditional machine learning methods. Two critical challenges remain:(1)a low signal-to-noise ratio in functional connectivity estimates, making it difficult to learn seizure-related interactions; and (2)expert labels for spatial pathological connectivity patterns are difficult to obtain, meanwhile lacking the patterns' representation to improve seizure detection. To address these issues, we propose a novel node-graph dual contrastive learning framework, Seizure-NGCLNet, to learn SEEG interictal suppression and ictal propagation patterns for detecting DRE seizures with high precision. First, an adaptive graph augmentation strategy guided by centrality metrics is developed to generate seizure-related brain networks. Second, a dual-contrastive learning approach is integrated, combining global graph-level contrast with local node-graph contrast, to encode both spatial structural and semantic epileptogenic features. Third, the pretrained embeddings are fine-tuned via a top-k localized graph attention network to perform the final classification. Extensive experiments on a large-scale public SEEG dataset from 33 DRE patients demonstrate that Seizure-NGCLNet achieves state-of-the-art performance, with an average accuracy of 95.93%, sensitivity of 96.25%, and specificity of 94.12%. Visualizations confirm that the learned embeddings clearly separate ictal from interictal states, reflecting suppression and propagation patterns that correspond to the clinical mechanisms. These results highlight Seizure-NGCLNet's ability to learn interpretable spatial pathological patterns, enhancing both seizure detection and seizure onset zone localization.