Improved attention-based PCNN with GhostNet for epilepsy seizure detection using EEG and fMRI modalities: extractive pattern and histogram feature set

TL;DR

This paper introduces a new method for detecting epileptic seizures using EEG and fMRI data with improved accuracy and reliability.

Contribution

A novel hybrid attention-based PCNN-GhostNet framework for multimodal seizure detection with enhanced interpretability and performance.

Findings

The HPG-ESD framework achieved 94.1% accuracy in detecting epileptic seizures.

The method outperformed conventional unimodal and state-of-the-art approaches.

Multimodal learning with attention mechanisms improves spatial-temporal modeling and generalization.

Abstract

Detecting epileptic seizures remains a major challenge in clinical neurology due to the complex, heterogeneous, and non-stationary characteristics of electroencephalogram (EEG) signals. Although recent machine learning (ML) and deep learning (DL) approaches have improved detection performance, most methods still struggle with limited interpretability, inadequate spatial–temporal modeling, and suboptimal generalization. To address these limitations, this study proposes an enhanced hybrid parallel convolutional-GhostNet framework (HPG-ESD) for robust seizure detection using multimodal EEG and functional Magnetic Resonance Imaging (fMRI) data.

The experimental data consist of pediatric scalp EEG recordings from 24 subjects in the CHB-MIT dataset (22-channel 10–20 system, 256 Hz sampling, continuous multi-hour recordings) and resting-state 3T fMRI scans from 52 participants in the UNAM TLE dataset (26 epilepsy patients and 26 healthy controls). EEG data underwent Gauss-based median filtering, while fMRI images were denoised using an adaptive weight-based Wiener filter. Spatial, temporal, and spectral EEG features were extracted alongside an enhanced common spatial pattern (E-CSP) representation, whereas fMRI features were obtained using deep 3D CNN embeddings combined with a smoothened pyramid histogram of oriented gradients (S-PHOG) descriptor. These multimodal features were fused within a soft voting hybrid parallel convolutional–GhostNet (S-HPCGN) model, integrating an improved attention based parallel convolutional network (IAPCNet) and GhostNet to capture complementary spatial–temporal patterns.

The proposed HPG-ESD framework achieved an accuracy of 0.941, precision of 0.939, and sensitivity of 0.944, outperforming conventional unimodal and state-of-the-art methods.

These results demonstrate the potential of multi-modal learning and lightweight attention-enhanced architectures for reliable and clinically relevant seizure detection.

Figures