Computer-Aided Intracranial EEG Signal Identification Method Based on a Multi-Branch Deep Learning Fusion Model and Clinical Validation

Advanced framework for epilepsy detection through image-based EEG signal analysis

Background

Recurrent and unpredictable seizures characterize epilepsy, a neurological disorder affecting millions worldwide. Epilepsy diagnosis is crucial for timely treatment and better outcomes. Electroencephalography (EEG) time-series data analysis is essential for epilepsy diagnosis and surveillance. Complex signal processing methods used in traditional EEG analysis are computationally demanding and difficult to generalize across patients. Researchers are using machine learning to improve epilepsy detection, particularly visual feature extraction from EEG time-series data.

Objective

This study examines the application of a Gramian Angular Summation Field (GASF) approach for the analysis of EEG signals. Additionally, it explores the utilization of image features, specifically the Scale-Invariant Feature Transform (SIFT) and Oriented FAST and Rotated BRIEF (ORB) techniques, for the purpose of epilepsy detection in EEG data.

Methods

The proposed methodology encompasses the transformation of EEG signals into images based on GASF, followed by the extraction of features utilizing SIFT and ORB techniques, and ultimately, the selection of relevant features. A state-of-the-art machine learning classifier is employed to classify GASF images into two categories: normal EEG patterns and focal EEG patterns. Bern-Barcelona EEG recordings were used to test the proposed method.

Results

This method classifies EEG signals with 96% accuracy using SIFT features and 94% using ORB features. The Random Forest (RF) classifier surpasses state-of-the-art approaches in precision, recall, F1-score, specificity, and Area Under Curve (AUC). The Receiver Operating Characteristic (ROC) curve shows that Random Forest outperforms Support Vector Machine (SVM) and k-Nearest Neighbors (k-NN) classifiers.

Significance

The suggested method has many advantages over time-series EEG data analysis and machine learning classifiers used in epilepsy detection studies. A novel image-based preprocessing pipeline using GASF for robust image synthesis and SIFT and ORB for feature extraction is presented here. The study found that the suggested method can accurately discriminate between normal and focal EEG signals, improving patient outcomes through early and accurate epilepsy diagnosis.

Information Entropy Measures for Evaluation of Reliability of Deep Neural Network Results

Deep neural networks (DNN) try to analyze given data, to come up with decisions regarding the inputs. The decision-making process of the DNN model is not entirely transparent. The confidence of the model predictions on new data fed into the network can vary. We address the question of certainty of decision making and adequacy of information capturing by DNN models during this process of decision-making. We introduce a measure called certainty index, which is based on the outputs in the most penultimate layer of DNN. In this approach, we employed iEEG (intracranial electroencephalogram) data to train and test DNN. When arriving at model predictions, the contribution of the entire information content of the input may be important. We explored the relationship between the certainty of DNN predictions and information content of the signal by estimating the sample entropy and using a heatmap of the signal. While it can be assumed that the entire sample must be utilized for arriving at the most appropriate decisions, an evaluation of DNNs from this standpoint has not been reported. We demonstrate that the robustness of the relationship between certainty index with the sample entropy, demonstrated through sample entropy-heatmap correlation, is higher than that with the original signal, indicating that the DNN focuses on information rich regions of the signal to arrive at decisions. Therefore, it can be concluded that the certainty of a decision is related to the DNN's ability to capture the information in the original signal. Our results indicate that, within its limitations, the certainty index can be used as useful tool in estimating the confidence of predictions. The certainty index appears to be related to how effectively DNN heatmaps captured the information content in the signal.

Automatic Localization of Seizure Onset Zone Based on Multi-Epileptogenic Biomarkers Analysis of Single-Contact from Interictal SEEG

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.

SEEG-Net: An explainable and deep learning-based cross-subject pathological activity detection method for drug-resistant epilepsy

OBJECTIVE

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.

METHODS

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++.

RESULTS

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.

SIGNIFICANCE

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.

Stereo-Encephalographic Presurgical Evaluation of Temporal Lobe Epilepsy: An Evolving Science

Drug-resistant epilepsy is present in nearly 30% of patients. Resection of the epileptogenic zone has been found to be the most effective in achieving seizure freedom. The study of temporal lobe epilepsy for surgical treatment is extensive and complex. It involves a multidisciplinary team in decision-making with initial non-invasive studies (Phase I), providing 70% of the required information to elaborate a hypothesis and treatment plans. Select cases present more complexity involving bilateral clinical or electrographic manifestations, have contradicting information, or may involve deeper structures as a part of the epileptogenic zone. These cases are discussed by a multidisciplinary team of experts with a hypothesis for invasive methods of study. Subdural electrodes were once the mainstay of invasive presurgical evaluation and in later years most Comprehensive Epilepsy Centers have shifted to intracranial recordings. The intracranial recording follows original concepts since its development by Bancaud and Talairach, but great advances have been made in the field. Stereo-electroencephalography is a growing field of study, treatment, and establishment of seizure pattern complexities. In this comprehensive review, we explore the indications, usefulness, discoveries in interictal and ictal findings, pitfalls, and advances in the science of presurgical stereo-encephalography for temporal lobe epilepsy.

Prediction of seizure recurrence using electroencephalogram analysis with multiscale deep neural networks before withdrawal of antiepileptic drugs

BACKGROUND

The decision to continue or discontinue antiepileptic drug (AED) treatment in patients who are seizure free for a prolonged time is critical. Studies have used certain risk factors or electroencephalogram (EEG) findings to predict seizure recurrence after the withdrawal of AEDs. However, applicable biomarkers to guide the withdrawal of AEDs are lacking.

METHODS

In this study, we used EEG analysis based on multiscale deep neural networks (MSDNN) to establish a method for predicting seizure recurrence after the withdrawal of AEDs. A total of 60 patients with epilepsy were divided into two groups (30 in the recurrence group and 30 in the non-recurrence group). All patients were seizure free for at least 2 years. Before AED withdrawal, an EEG was performed for each patient, which showed no epileptiform discharges. These EEG recordings were classified using MSDNN.

RESULTS

We found that the performance indices of classification between recurrence and non-recurrence groups had a mean sensitivity, mean specificity, mean accuracy, and mean area under the receiver operating characteristic curve of 74.23%, 75.83%, 74.66%, and 82.66%, respectively.

CONCLUSION

Our proposed method is a promising tool to help physicians to predict seizure recurrence after AED withdrawal among seizure-free patients.