Automatic Detection of High-Frequency Oscillations Based on an End-to-End Bi-Branch Neural Network and Clinical Cross-Validation

Abstract

Accurate identification of high-frequency oscillation (HFO) is an important prerequisite for precise localization of epileptic foci and good prognosis of drug-refractory epilepsy. Exploring a high-performance automatic detection method for HFOs can effectively help clinicians reduce the error rate and reduce manpower. Due to the limited analysis perspective and simple model design, it is difficult to meet the requirements of clinical application by the existing methods. Therefore, an end-to-end bi-branch fusion model is proposed to automatically detect HFOs. With the filtered band-pass signal (signal branch) and time-frequency image (TFpic branch) as the input of the model, two backbone networks for deep feature extraction are established, respectively. Specifically, a hybrid model based on ResNet1d and long short-term memory (LSTM) is designed for signal branch, which can focus on both the features in time and space dimension, while a ResNet2d with a Convolutional Block Attention Module (CBAM) is constructed for TFpic branch, by which more attention is paid to useful information of TF images. Then the outputs of two branches are fused to realize end-to-end automatic identification of HFOs. Our method is verified on 5 patients with intractable epilepsy. In intravalidation, the proposed method obtained high sensitivity of 94.62%, specificity of 92.7%, and F1-score of 93.33%, and in cross-validation, our method achieved high sensitivity of 92.00%, specificity of 88.26%, and F1-score of 89.11% on average. The results show that the proposed method outperforms the existing detection paradigms of either single signal or single time-frequency diagram strategy. In addition, the average kappa coefficient of visual analysis and automatic detection results is 0.795. The method shows strong generalization ability and high degree of consistency with the gold standard meanwhile. Therefore, it has great potential to be a clinical assistant tool.

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

“…The biomarkers deep learning detector, contacts feature selector and classifier may perform differently with different parameter values. For the parameters of multiple epileptogenic biomarkers detectors, the optimal values have been presented in the previous studies [ 24 , 25 , 26 , 27 ], respectively. All the settings for the contacts feature selector and deep learning classifier are shown in Table 4 .…”

“…Among these, for spikes detection, we demonstrated that deep learning can detect subtle changes in SEEG [ 24 ], and a more adaptive and highly interpretable SEEG-Net was then designed [ 25 ]. In addition, we have detected HFOs accurately from the filtered band-pass part and time-frequency image part, showing strong generalization ability and consistency with the gold standard [ 26 , 27 ]. Furthermore, for other important biomarkers, Akter et al [ 22 ] detected the epileptic focus from interictal EEG using the information-theoretic features extracted from the high-frequency sub-bands.…”

Computerized application for epilepsy in China: Does the era of artificial intelligence comes?

“…40 Simultaneously, Liu's group was also devoted to automated HFOs detection by using an end-to-end bi-branch neural network, and it showed great potential to automatically detect HFOs with a high sensitivity of 94.62%. 41 With these published researches, it can be concluded that advances have been substantively achieved in China for computer-aided automated detection of HFOs with both high sensitivity and good precision, and these methods greatly contribute to the clinical utility of HFOs in presurgical evaluation, especially in localizing EZ.…”

“…And we tended to improve this in 2021, by using a MATLAB‐based unsupervised automatic HFO detection method, we achieved a precision of 91.27% along with a 96.23% sensitivity in detecting previously labeled HFOs, and it seemed that the performance of this algorithm was superior to other available single feature‐based detection methods in sensitivity 40 . Simultaneously, Liu's group was also devoted to automated HFOs detection by using an end‐to‐end bi‐branch neural network, and it showed great potential to automatically detect HFOs with a high sensitivity of 94.62% 41 . With these published researches, it can be concluded that advances have been substantively achieved in China for computer‐aided automated detection of HFOs with both high sensitivity and good precision, and these methods greatly contribute to the clinical utility of HFOs in presurgical evaluation, especially in localizing EZ.…”

CNO-LSTM: A Chaotic Neural Oscillatory Long Short-Term Memory Model for Text Classification

“…Lee-Oscillator is applied as a neural structure network substitution especially for memory association and recalling long-term memory within a short time in highfrequency oscillation. [38]…”