Precise preoperative evaluation of drug-resistant epilepsy (DRE) requires accurate analysis of invasive stereoelectroencephalography (SEEG). With the tremendous breakthrough of Artificial intelligence (AI), previous studies can help clinical experts to identify pathological activities automatically. However, they still face limitations when applied in real-world clinical DRE scenarios, such as sample imbalance, cross-subject domain shift, and poor interpretability. Our objective is to propose a model that can address the above problems and realizes high-sensitivity SEEG pathological activity detection based on two real clinical datasets. Our proposed innovative and effective SEEG-Net introduces a multiscale convolutional neural network (MSCNN) to increase the receptive field of the model, and to learn SEEG multiple frequency domain features, local and global features. Moreover, we designed a novel focal domain generalization loss (FDG-loss) function to enhance the target sample weight and to learn domain consistency features. Furthermore, to enhance the interpretability and flexibility of SEEG-Net, we explain SEEG-Net from multiple perspectives, such as significantly different features, interpretable models, and model learning process interpretation by Grad-CAM++. The performance of our proposed method is verified on a public benchmark multicenter SEEG dataset and a private clinical SEEG dataset for a robust comparison. The experimental results demonstrate that the SEEG-Net model achieves the highest sensitivity and is state-of-the-art on cross-subject (for different patients) evaluation, and well deal with the known problems. Besides, we provide an SEEG processing and database construction flow, by maintaining consistency with the real-world clinical scenarios. According to the results, SEEG-Net is constructed to increase the sensitivity of SEEG pathological activity detection. Simultaneously, we settled certain problems about AI assistance in clinical DRE, built a bridge between AI algorithm application and clinical practice.

Surgical intervention or the control of drug-refractory epilepsy requires accurate analysis of invasive inspection intracranial EEG (iEEG) data. A multi-branch deep learning fusion model is proposed to identify epileptogenic signals from the epileptogenic area of the brain. The classical approach extracts multi-domain signal wave features to construct a time-series feature sequence and then abstracts it through the bi-directional long short-term memory attention machine (Bi-LSTM-AM) classifier. The deep learning approach uses raw time-series signals to build a one-dimensional convolutional neural network (1D-CNN) to achieve end-to-end deep feature extraction and signal detection. These two branches are integrated to obtain deep fusion features and results. Resampling is employed to split the imbalanced epileptogenic and non-epileptogenic samples into balanced subsets for clinical validation. The model is validated over two publicly available benchmark iEEG databases to verify its effectiveness on a private, large-scale, clinical stereo EEG database. The model achieves high sensitivity (97.78%), accuracy (97.60%), and specificity (97.42%) on the Bern–Barcelona database, surpassing the performance of existing state-of-the-art techniques. It is then demonstrated on a clinical dataset with an average intra-subject accuracy of 92.53% and cross-subject accuracy of 88.03%. The results suggest that the proposed method is a valuable and extremely robust approach to help researchers and clinicians develop an automated method to identify the source of iEEG signals.

Successful surgery on drug-resistant epilepsy patients (DRE) needs precise localization of the seizure onset zone (SOZ). Previous studies analyzing this issue still face limitations, such as inadequate analysis of features, low sensitivity and limited generality. Our study proposed an innovative and effective SOZ localization method based on multiple epileptogenic biomarkers (spike and HFOs), and analysis of single-contact (MEBM-SC) to address the above problems. We extracted contacts epileptic features from signal distributions and signal energy based on machine learning and end-to-end deep learning. Among them, a normalized pathological ripple rate was designed to reduce the disturbance of physiological ripple and enhance the performance of SOZ localization. Then, a feature selection algorithm based on Shapley value and hypothetical testing (ShapHT+) was used to limit interference from irrelevant features. Moreover, an attention mechanism and a focal loss algorithm were used on the classifier to learn significant features and overcome the unbalance of SOZ/nSOZ contacts. Finally, we provided an SOZ prediction and visualization on magnetic resonance imaging (MRI). Ten patients with DRE were selected to verify our method. The experiment performed cross-validation and revealed that MEBM-SC obtains higher sensitivity. Additionally, the spike has better sensitivity while HFOs have better specificity, and the combination of these biomarkers can achieve the best performance. The study confirmed that MEBM-SC can increase the sensitivity and accuracy of SOZ localization and help clinicians to perform a precise and reliable preoperative evaluation based on interictal SEEG.

The dynamic propagation of epileptic discharges complicates Drug-Resistant Epilepsy (DRE) seizure detection using traditional machine learning methods and Stereotactic Electroencephalography (SEEG). Several challenges remain unresolved in prior studies: (1) incomprehensive representations of epileptic brain network features; (2) lacking of flexible and dynamic mechanisms to learn brain network evolving features; and (3) the absence of model mechanisms interpretation corresponds with seizure mechanisms. In response, we propose a novel multi-band dynamic graph attention network, DynSeizureGAT, to detect and analyze DRE seizures with precision and interpretability. Specifically, a seizure network sequence is first constructed by integrating a multi-band directed transfer function matrix and enhanced epileptic index node features. Second, a dynamic graph attention module is integrated to dynamically weigh the contribution of various spatial scales. Third, spatial-spectral-temporal attention mechanisms enhance the model's capacity to better characterize and interpret the ictal and interictal states. Extensive experiments are conducted on the large-scale public clinical SEEG dataset (OpenNeuro). The proposed model demonstrates high seizure detection performance, achieving an average of 94.6% accuracy, 93.4% sensitivity, and 96.4% specificity. In addition, the importance of frequency bands and dynamic abnormal connectivity patterns is successfully quantified and visualized, which contributes most to the explainability. Experimental results indicate that DynSeizureGAT demonstrates strong dynamic propagation feature learning capability, corresponding with seizure propagation mechanisms, and is promising to assist DRE epileptogenic zone localization.

High frequency oscillations (HFOs) in intracranial electroencephalography (iEEG) recordings are considered as promising clinical biomarker of epileptogenic regions of the brain. Previous automatic detection methods for HFOs require plenty of labeled training samples to build effective computational models, while expert labeling of HFOs is an expensive, subjective, time-consuming, and laborious task. Therefore, to relieve the problem of the severe lacking of HFOs labels and reduce labeling costs, we propose a label generation method for HFOs called Consistency Residual Memory (CRM). Firstly, to focus on temporal and spatial features, we design a network architecture composed of a Recurrent Neural Network (RNN) and a Convolutional Neural Network (CNN). Secondly, to take full advantage of a large amount of unlabeled data, we explore a semi-supervised algorithm consisting of supervised and unsupervised components. The supervised component minimizes the cross-entropy of the input and output labels based on labeled training samples. Meanwhile, the unsupervised component maximizes the consistency of the output, based on the original input and the disturbed input, utilizing the entire training set (labeled and unlabeled). We validated the high accuracy and sensitivity of CRM method on a large-scale public benchmark dataset of HFOs and a private clinical dataset. Our method achieves state-of-the-art performance, with high accuracy (91.83%) and sensitivity (96.19%) on the public datasets, and achieves an accuracy (87.83%) and sensitivity (91.10%) on the private clinical datasets. It is demonstrated that CRM method can be applied in clinical applications, which relieves the difficulty of the clinician in the signal labeling and visual analysis of HFOs.

Epilepsy is a common neurological disorder caused by the abnormal discharge of brain neurons. The automatic detection of epileptic signals (ES) is of great significance for the clinical diagnosis of epilepsy. However, there are still problems such as imperfect feature extraction, ignoring channel correlation, and unbalanced data distribution. Therefore, in this paper, we propose an ES detection method based on adaptive feature fusion (AFF) of brain network features (BNF) and single-channel features (SCF). First, two types of features, BNF and SCF, are extracted. The in-degree of each channel calculated from brain functional connectivity based on Pearson correlation is used as BNF. A multi-temporal resolution convolutional neural network (MTRCNN) extracts low-frequency and high-frequency features from single-channel stereo electroencephalography (SEEG) data as SCF. In the feature extraction process, cross-norm and self-norm (CNSN) reduce individual differences. Second, AFF automatically adjusts the fused features, aiming to combine BNF with SCF more effectively. Finally, the weighted loss function considers both the proportion and discriminability of positive and negative samples to reduce imbalanced data distribution. In this paper, we investigated interictal SEEG data from 7 patients with refractory focal hippocampal sclerosing epilepsy and performed cross-patient cross-validation. The results show that our method outperforms the state-of-the-art in all 5 metrics. Our ES automatic detection method provides an objective reference for epilepsy diagnosis, thereby reducing the workload of neurologists.