Multi-Channel Vision Transformer for Epileptic Seizure Prediction

Transformers in EEG Analysis: A Review of Architectures and Applications in Motor Imagery, Seizure, and Emotion Classification

Transformers have rapidly influenced research across various domains. With their superior capability to encode long sequences, they have demonstrated exceptional performance, outperforming existing machine learning methods. There has been a rapid increase in the development of transformer-based models for EEG analysis. The high volumes of recently published papers highlight the need for further studies exploring transformer architectures, key components, and models employed particularly in EEG studies. This paper aims to explore four major transformer architectures: Time Series Transformer, Vision Transformer, Graph Attention Transformer, and hybrid models, along with their variants in recent EEG analysis. We categorize transformer-based EEG studies according to the most frequent applications in motor imagery classification, emotion recognition, and seizure detection. This paper also highlights the challenges of applying transformers to EEG datasets and reviews data augmentation and transfer learning as potential solutions explored in recent years. Finally, we provide a summarized comparison of the most recent reported results. We hope this paper serves as a roadmap for researchers interested in employing transformer architectures in EEG analysis.

CIT-EmotionNet: convolution interactive transformer network for EEG emotion recognition

Emotion recognition is a significant research problem in affective computing as it has a lot of potential areas of application. One of the approaches in emotion recognition uses electroencephalogram (EEG) signals to identify the emotion of a person. However, effectively using the global and local features of EEG signals to improve the performance of emotion recognition is still a challenge. In this study, we propose a novel Convolution Interactive Transformer Network for EEG Emotion Recognition, known as CIT-EmotionNet, which efficiently integrates the global and local features of EEG signals. We convert the raw EEG signals into spatial-spectral representations, which serve as the inputs into the model. The model integrates convolutional neural network (CNN) and Transformer within a single framework in a parallel manner. We propose a Convolution Interactive Transformer module, which facilitates the interaction and fusion of local and global features extracted by CNN and Transformer respectively, thereby improving the average accuracy of emotion recognition. The proposed CIT-EmotionNet outperforms state-of-the-art methods, achieving an average recognition accuracy of 98.57% and 92.09% on two publicly available datasets, SEED and SEED-IV, respectively.

An Efficient Epilepsy Prediction Model on European Dataset With Model Evaluation Considering Seizure Types

This paper develops a computationally efficient model for automatic patient-specific seizure prediction using a two-layer LSTM from multichannel intracranial electroencephalogram time-series data. We decrease the number of parameters by employing a smaller input size and fewer electrodes, thereby making the model a viable option for wearable and implantable devices. We test the proposed prediction model on 26 patients from the European iEEG dataset, which is the largest epileptic seizure dataset. We also apply an automatic preprocessing technique based on a common average reference to remove artifacts from this dataset. The simulation results show that the model with its simple structure in conjunction with the mean post-processing procedure performed the best, with an average AUC of 0.885. This study is the first that utilizes the European database for epilepsy prediction application and the first that analyzes the effect of the seizure type on the system performance and demonstrates that the seizure type has a considerable impact.

EEG-Based Seizure Prediction Using Hybrid DenseNet-ViT Network with Attention Fusion

Epilepsy seizure prediction is vital for enhancing the quality of life for individuals with epilepsy. In this study, we introduce a novel hybrid deep learning architecture, merging DenseNet and Vision Transformer (ViT) with an attention fusion layer for seizure prediction. DenseNet captures hierarchical features and ensures efficient parameter usage, while ViT offers self-attention mechanisms and global feature representation. The attention fusion layer effectively amalgamates features from both networks, guaranteeing the most relevant information is harnessed for seizure prediction. The raw EEG signals were preprocessed using the short-time Fourier transform (STFT) to implement time-frequency analysis and convert EEG signals into time-frequency matrices. Then, they were fed into the proposed hybrid DenseNet-ViT network model to achieve end-to-end seizure prediction. The CHB-MIT dataset, including data from 24 patients, was used for evaluation and the leave-one-out cross-validation method was utilized to evaluate the performance of the proposed model. Our results demonstrate superior performance in seizure prediction, exhibiting high accuracy and low redundancy, which suggests that combining DenseNet, ViT, and the attention mechanism can significantly enhance prediction capabilities and facilitate more precise therapeutic interventions.

Automatic diagnosis of epileptic seizures using entropy-based features and multimodel deep learning approaches

Epilepsy is one of the most common brain diseases, characterised by repeated seizures that occur on a regular basis. During a seizure, a patient's muscles flex uncontrollably, causing a loss of mobility and balance, which can be harmful or even fatal. Developing an automatic approach for warning patients of oncoming seizures necessitates substantial research. Analyzing the electroencephalogram (EEG) output from the human brain's scalp region can help predict seizures. EEG data were analyzed to extract time domain features such as Hurst exponent (Hur), Tsallis entropy (TsEn), enhanced permutation entropy (impe), and amplitude-aware permutation entropy (AAPE). In order to automatically diagnose epileptic seizure in children from normal children, this study conducted two sessions. In the first session, the extracted features from the EEG dataset were classified using three machine learning (ML)-based models, including support vector machine (SVM), K nearest neighbor (KNN), or decision tree (DT), and in the second session, the dataset was classified using three deep learning (DL)-based recurrent neural network (RNN) classifiers in The EEG dataset was obtained from the Neurology Clinic of the Ibn Rushd Training Hospital. In this regard, extensive explanations and research from the time domain and entropy characteristics demonstrate that employing GRU, LSTM, and BiLSTM RNN deep learning classifiers on the All-time-entropy fusion feature improves the final classification results.

BISeizuRe: BERT-Inspired Seizure Data Representation to Improve Epilepsy Monitoring

This study presents a novel approach for EEG-based seizure detection leveraging a BERT-based model. The model, BENDR, undergoes a two-phase training process. Initially, it is pre-trained on the extensive Temple University Hospital EEG Corpus (TUEG), a 1.5 TB dataset comprising over 10,000 subjects, to extract common EEG data patterns. Subsequently, the model is fine-tuned on the CHB-MIT Scalp EEG Database, consisting of 664 EEG recordings from 24 pediatric patients, of which 198 contain seizure events. Key contributions include optimizing fine-tuning on the CHB-MIT dataset, where the impact of model architecture, pre-processing, and post-processing techniques are thoroughly examined to enhance sensitivity and reduce false positives per hour (FP/h). We also explored custom training strategies to ascertain the most effective setup. The model undergoes a novel second pre-training phase before subject-specific fine-tuning, enhancing its generalization capabilities. The optimized model demonstrates substantial performance enhancements, achieving as low as 0.23 FP/h, 2.5× lower than the baseline model, with a lower but still acceptable sensitivity rate, showcasing the effectiveness of applying a BERT-based approach on EEG-based seizure detection.Clinical relevance- The model enhances clinical seizure detection, offering personalized treatments and better generalization to new patients, akin to successes with transformer-based models, thus significantly improving patient safety and care.

Utilizing portable electroencephalography to screen for pathology of Alzheimer's disease: a methodological advancement in diagnosis of neurodegenerative diseases

Background

The current biomarker-supported diagnosis of Alzheimer's disease (AD) is hindered by invasiveness and cost issues. This study aimed to address these challenges by utilizing portable electroencephalography (EEG). We propose a novel, non-invasive, and cost-effective method for identifying AD, using a sample of patients with biomarker-verified AD, to facilitate early and accessible disease screening.

Methods

This study included 35 patients with biomarker-verified AD, confirmed via cerebrospinal fluid sampling, and 35 age- and sex-balanced healthy volunteers (HVs). All participants underwent portable EEG recordings, focusing on 2-minute resting-state EEG epochs with closed eyes state. EEG recordings were transformed into scalogram images, which were analyzed using "vision Transformer(ViT)," a cutting-edge deep learning model, to differentiate patients from HVs.

Results

The application of ViT to the scalogram images derived from portable EEG data demonstrated a significant capability to distinguish between patients with biomarker-verified AD and HVs. The method achieved an accuracy of 73%, with an area under the receiver operating characteristic curve of 0.80, indicating robust performance in identifying AD pathology using neurophysiological measures.

Conclusions

Our findings highlight the potential of portable EEG combined with advanced deep learning techniques as a transformative tool for screening of biomarker-verified AD. This study not only contributes to the neurophysiological understanding of AD but also opens new avenues for the development of accessible and non-invasive diagnostic methods. The proposed approach paves the way for future clinical applications, offering a promising solution to the limitations of advanced diagnostic practices for dementia.

Seizure prediction based on improved vision transformer model for EEG channel optimization

Epileptic seizures are unpredictable events caused by abnormal discharges of a patient's brain cells. Extensive research has been conducted to develop seizure prediction algorithms based on long-term continuous electroencephalogram (EEG) signals. This paper describes a patient-specific seizure prediction method that can serve as a basis for the design of lightweight, wearable and effective seizure-prediction devices. We aim to achieve two objectives using this method. The first aim is to extract robust feature representations from multichannel EEG signals, and the second aim is to reduce the number of channels used for prediction by selecting an optimal set of channels from multichannel EEG signals while ensuring good prediction performance. We design a seizure-prediction algorithm based on a vision transformer (ViT) model. The algorithm selects channels that play a key role in seizure prediction from 22 channels of EEG signals. First, we perform a time-frequency analysis of processed time-series signals to obtain EEG spectrograms. We then segment the spectrograms of multiple channels into many non-overlapping patches of the same size, which are input into the channel selection layer of the proposed model, named Sel-JPM-ViT, enabling it to select channels. Application of the Sel-JPM-ViT model to the Boston Children's Hospital-Massachusetts Institute of Technology scalp EEG dataset yields results using only three to six channels of EEG signals that are slightly better that the results obtained using 22 channels of EEG signals. Overall, the Sel-JPM-ViT model exhibits an average classification accuracy of 93.65%, an average sensitivity of 94.70% and an average specificity of 92.78%.

A ResNet-LSTM hybrid model for predicting epileptic seizures using a pretrained model with supervised contrastive learning

In this paper, we propose a method for predicting epileptic seizures using a pre-trained model utilizing supervised contrastive learning and a hybrid model combining residual networks (ResNet) and long short-term memory (LSTM). The proposed training approach encompasses three key phases: pre-processing, pre-training as a pretext task, and training as a downstream task. In the pre-processing phase, the data is transformed into a spectrogram image using short time Fourier transform (STFT), which extracts both time and frequency information. This step compensates for the inherent complexity and irregularity of electroencephalography (EEG) data, which often hampers effective data analysis. During the pre-training phase, augmented data is generated from the original dataset using techniques such as band-stop filtering and temporal cutout. Subsequently, a ResNet model is pre-trained alongside a supervised contrastive loss model, learning the representation of the spectrogram image. In the training phase, a hybrid model is constructed by combining ResNet, initialized with weight values from the pre-trained model, and LSTM. This hybrid model extracts image features and time information to enhance prediction accuracy. The proposed method's effectiveness is validated using datasets from CHB-MIT and Seoul National University Hospital (SNUH). The method's generalization ability is confirmed through Leave-one-out cross-validation. From the experimental results measuring accuracy, sensitivity, and false positive rate (FPR), CHB-MIT was 91.90%, 89.64%, 0.058 and SNUH was 83.37%, 79.89%, and 0.131. The experimental results demonstrate that the proposed method outperforms the conventional methods.

DeepSOZ: A Robust Deep Model for Joint Temporal and Spatial Seizure Onset Localization from Multichannel EEG Data

We propose a robust deep learning framework to simultaneously detect and localize seizure activity from multichannel scalp EEG. Our model, called DeepSOZ, consists of a transformer encoder to generate global and channel-wise encodings. The global branch is combined with an LSTM for temporal seizure detection. In parallel, we employ attention-weighted multi-instance pooling of channel-wise encodings to predict the seizure onset zone. DeepSOZ is trained in a supervised fashion and generates high-resolution predictions on the order of each second (temporal) and EEG channel (spatial). We validate DeepSOZ via bootstrapped nested cross-validation on a large dataset of 120 patients curated from the Temple University Hospital corpus. As compared to baseline approaches, DeepSOZ provides robust overall performance in our multi-task learning setup. We also evaluate the intra-seizure and intra-patient consistency of DeepSOZ as a first step to establishing its trustworthiness for integration into the clinical workflow for epilepsy.

Efficient graph convolutional networks for seizure prediction using scalp EEG

Epilepsy is a chronic brain disease that causes persistent and severe damage to the physical and mental health of patients. Daily effective prediction of epileptic seizures is crucial for epilepsy patients especially those with refractory epilepsy. At present, a large number of deep learning algorithms such as Convolutional Neural Networks and Recurrent Neural Networks have been used to predict epileptic seizures and have obtained better performance than traditional machine learning methods. However, these methods usually transform the Electroencephalogram (EEG) signal into a Euclidean grid structure. The conversion suffers from loss of adjacent spatial information, which results in deep learning models requiring more storage and computational consumption in the process of information fusion after information extraction. This study proposes a general Graph Convolutional Networks (GCN) model architecture for predicting seizures to solve the problem of oversized seizure prediction models based on exploring the graph structure of EEG signals. As a graph classification task, the network architecture includes graph convolution layers that extract node features with one-hop neighbors, pooling layers that summarize abstract node features; and fully connected layers that implement classification, resulting in superior prediction performance and smaller network size. The experiment shows that the model has an average sensitivity of 96.51%, an average AUC of 0.92, and a model size of 15.5 k on 18 patients in the CHB-MIT scalp EEG dataset. Compared with traditional deep learning methods, which require a large number of parameters and computational effort and are demanding in terms of storage space and energy consumption, this method is more suitable for implementation on compact, low-power wearable devices as a standard process for building a generic low-consumption graph network model on similar biomedical signals. Furthermore, the edge features of graphs can be used to make a preliminary determination of locations and types of discharge, making it more clinically interpretable.