Cross-Modal Epileptic Signal Harmonization: Frequency Domain Mapping Quantization for Pre-training a Unified Neurophysiological Transformer

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Runkai, Yu, Hua, Gan, John Q., Wang, Haixian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915353218514944
author Zhang, Runkai
Yu, Hua
Gan, John Q.
Wang, Haixian
author_facet Zhang, Runkai
Yu, Hua
Gan, John Q.
Wang, Haixian
contents Scalp electroencephalography (EEG) and intracranial EEG (iEEG) are vital for epilepsy diagnosis and treatment. Their unified analysis offers the potential to harness the complementary strengths of each modality but is challenging due to variations in recording montages, amplitude and signal-to-noise ratio (SNR), and frequency components. To address the aforementioned challenges, this paper introduces EpiNT, a novel Transformer-based pre-trained model for unified EEG and iEEG analysis. EpiNT employs channel-independent modeling with masked autoencoders (MAE) and vector quantization (VQ), along with a frequency domain mapping quantizer to capture crucial frequency features. Pre-trained on over 2,700 hours of multi-modal clinical neurophysiological data from 1,199 patients, EpiNT outperformed both randomly initialized models and other pre-trained methods on six downstream classification tasks, demonstrating robust representation learning capabilities. This work presents a promising approach for unified epilepsy neurophysiology analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2506_17068
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cross-Modal Epileptic Signal Harmonization: Frequency Domain Mapping Quantization for Pre-training a Unified Neurophysiological Transformer
Zhang, Runkai
Yu, Hua
Gan, John Q.
Wang, Haixian
Neurons and Cognition
Emerging Technologies
Signal Processing
Scalp electroencephalography (EEG) and intracranial EEG (iEEG) are vital for epilepsy diagnosis and treatment. Their unified analysis offers the potential to harness the complementary strengths of each modality but is challenging due to variations in recording montages, amplitude and signal-to-noise ratio (SNR), and frequency components. To address the aforementioned challenges, this paper introduces EpiNT, a novel Transformer-based pre-trained model for unified EEG and iEEG analysis. EpiNT employs channel-independent modeling with masked autoencoders (MAE) and vector quantization (VQ), along with a frequency domain mapping quantizer to capture crucial frequency features. Pre-trained on over 2,700 hours of multi-modal clinical neurophysiological data from 1,199 patients, EpiNT outperformed both randomly initialized models and other pre-trained methods on six downstream classification tasks, demonstrating robust representation learning capabilities. This work presents a promising approach for unified epilepsy neurophysiology analysis.
title Cross-Modal Epileptic Signal Harmonization: Frequency Domain Mapping Quantization for Pre-training a Unified Neurophysiological Transformer
topic Neurons and Cognition
Emerging Technologies
Signal Processing
url https://arxiv.org/abs/2506.17068