Dual-Cross Tri-Level Routing Transformer Based Metric Learning Network for Epileptic Seizure Prediction Using a Single-Channel iEEG

TY - JOUR

T1 - Dual-Cross Tri-Level Routing Transformer Based Metric Learning Network for Epileptic Seizure Prediction Using a Single-Channel iEEG

AU - Wang, Yifan

AU - Yan, Weidong

AU - Ma, Yulan

AU - Qiao, Liang

AU - Yu, Tao

AU - Liu, Jingyu

N1 - Publisher Copyright: © 2013 IEEE.

PY - 2026/4/1

Y1 - 2026/4/1

N2 - With the development of deep brain stimulation technique, single-channel intracranial electroencephalography (iEEG) based seizure prediction is a necessary and urgent needed tool for epilepsy closed-loop neuromodulation. However, previous prediction methods based on multi-channel scalp signals heavily relied on the spatial information, failing to fully exploit the interdependencies between temporal scales and spectral rhythms of single-channel iEEG. Additionally, current contrastive learning strategies can lead to model overfitting by excessively learning the feature distances in small samples, limiting the precision of seizure prediction. To tackle above issues, based on a single-channel iEEG, we propose a novel dual-cross tri-level routing transformer based metric learning network (DC-TRT-MLNet) for epileptic seizure prediction. First, a scale-rhythm dual-cross (DC) graph attention network is introduced to construct the dependent relationships across multi-scale temporal and multi-rhythm spectral features. Second, we design a tri-level routing transformer (TRT) network to comprehensively refine the most seizure-potential routing features while eliminating redundant information. Finally, a hard triplet optimization based metric learning (ML) strategy is developed to iteratively optimize the intra-class and inter-class distances of inter-ictal and pre-ictal routing features. Competitive experimental results on a private Xuanwu Single-Channel iEEG dataset validate the effectiveness of our proposed method, demonstrating the superior prediction performance of our DC-TRT-MLNet compared with the state-of-the-art methods. Our study may offer a new solution for intracranial single-channel seizure prediction.

AB - With the development of deep brain stimulation technique, single-channel intracranial electroencephalography (iEEG) based seizure prediction is a necessary and urgent needed tool for epilepsy closed-loop neuromodulation. However, previous prediction methods based on multi-channel scalp signals heavily relied on the spatial information, failing to fully exploit the interdependencies between temporal scales and spectral rhythms of single-channel iEEG. Additionally, current contrastive learning strategies can lead to model overfitting by excessively learning the feature distances in small samples, limiting the precision of seizure prediction. To tackle above issues, based on a single-channel iEEG, we propose a novel dual-cross tri-level routing transformer based metric learning network (DC-TRT-MLNet) for epileptic seizure prediction. First, a scale-rhythm dual-cross (DC) graph attention network is introduced to construct the dependent relationships across multi-scale temporal and multi-rhythm spectral features. Second, we design a tri-level routing transformer (TRT) network to comprehensively refine the most seizure-potential routing features while eliminating redundant information. Finally, a hard triplet optimization based metric learning (ML) strategy is developed to iteratively optimize the intra-class and inter-class distances of inter-ictal and pre-ictal routing features. Competitive experimental results on a private Xuanwu Single-Channel iEEG dataset validate the effectiveness of our proposed method, demonstrating the superior prediction performance of our DC-TRT-MLNet compared with the state-of-the-art methods. Our study may offer a new solution for intracranial single-channel seizure prediction.

KW - Seizure prediction

KW - dual-cross (DC) graph attention

KW - epilepsy

KW - iEEG

KW - metric learning (ML)

KW - routing transformer (TRT)

UR - https://www.scopus.com/pages/publications/105017183129

U2 - 10.1109/JBHI.2025.3613538

DO - 10.1109/JBHI.2025.3613538

M3 - Article

C2 - 40991605

AN - SCOPUS:105017183129

SN - 2168-2194

VL - 30

SP - 3461

EP - 3472

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

IS - 4

ER -