Construction of an epileptic seizure prediction model using a semi-supervised method of generative adversarial and long short term memory network combined with Stockwell transform / 南方医科大学学报

OBJECTIVE@#To propose a semi-supervised epileptic seizure prediction model (ST-WGAN-GP-Bi-LSTM) to enhance the prediction performance by improving time-frequency analysis of electroencephalogram (EEG) signals, enhancing the stability of the unsupervised feature learning model and improving the design of back-end classifier.@*METHODS@#Stockwell transform (ST) of the epileptic EEG signals was performed to locate the time-frequency information by adaptive adjustment of the resolution and retaining the absolute phase to obtain the time-frequency inputs. When there was no overlap between the generated data distribution and the real EEG data distribution, to avoid failure of feature learning due to a constant JS divergence, Wasserstein GAN was used as a feature learning model, and the cost function based on EM distance and gradient penalty strategy was adopted to constrain the unsupervised training process to allow the generation of a high-order feature extractor. A temporal prediction model was finally constructed based on a bi-directional long short term memory network (Bi-LSTM), and the classification performance was improved by obtaining the temporal correlation between high-order time-frequency features. The CHB-MIT scalp EEG dataset was used to validate the proposed patient-specific seizure prediction method.@*RESULTS@#The AUC, sensitivity, and specificity of the proposed method reached 90.40%, 83.62%, and 86.69%, respectively. Compared with the existing semi-supervised methods, the propose method improved the original performance by 17.77%, 15.41%, and 53.66%. The performance of this method was comparable to that of a supervised prediction model based on CNN.@*CONCLUSION@#The utilization of ST, WGAN-GP, and Bi-LSTM effectively improves the prediction performance of the semi-supervised deep learning model, which can be used for optimization of unsupervised feature extraction in epileptic seizure prediction.

Research on migraine time-series features classification based on small-sample functional magnetic resonance imaging data / 生物医学工程学杂志

The extraction of neuroimaging features of migraine patients and the design of identification models are of great significance for the auxiliary diagnosis of related diseases. Compared with the commonly used image features, this study directly uses time-series signals to characterize the functional state of the brain in migraine patients and healthy controls, which can effectively utilize the temporal information and reduce the computational effort of classification model training. Firstly, Group Independent Component Analysis and Dictionary Learning were used to segment different brain areas for small-sample groups and then the regional average time-series signals were extracted. Next, the extracted time series were divided equally into multiple subseries to expand the model input sample. Finally, the time series were modeled using a bi-directional long-short term memory network to learn the pre-and-post temporal information within each time series to characterize the periodic brain state changes to improve the diagnostic accuracy of migraine. The results showed that the classification accuracy of migraine patients and healthy controls was 96.94%, the area under the curve was 0.98, and the computation time was relatively shorter. The experiments indicate that the method in this paper has strong applicability, and the combination of time-series feature extraction and bi-directional long-short term memory network model can be better used for the classification and diagnosis of migraine. This work provides a new idea for the lightweight diagnostic model based on small-sample neuroimaging data, and contributes to the exploration of the neural discrimination mechanism of related diseases.

Automatic sleep staging model based on single channel electroencephalogram signal / 生物医学工程学杂志

Sleep staging is the basis for solving sleep problems. There's an upper limit for the classification accuracy of sleep staging models based on single-channel electroencephalogram (EEG) data and features. To address this problem, this paper proposed an automatic sleep staging model that mixes deep convolutional neural network (DCNN) and bi-directional long short-term memory network (BiLSTM). The model used DCNN to automatically learn the time-frequency domain features of EEG signals, and used BiLSTM to extract the temporal features between the data, fully exploiting the feature information contained in the data to improve the accuracy of automatic sleep staging. At the same time, noise reduction techniques and adaptive synthetic sampling were used to reduce the impact of signal noise and unbalanced data sets on model performance. In this paper, experiments were conducted using the Sleep-European Data Format Database Expanded and the Shanghai Mental Health Center Sleep Database, and achieved an overall accuracy rate of 86.9% and 88.9% respectively. When compared with the basic network model, all the experimental results outperformed the basic network, further demonstrating the validity of this paper's model, which can provide a reference for the construction of a home sleep monitoring system based on single-channel EEG signals.

Research on mild cognitive impairment diagnosis based on Bayesian optimized long-short-term neural network model / 生物医学工程学杂志

The recurrent neural network architecture improves the processing ability of time-series data. However, issues such as exploding gradients and poor feature extraction limit its application in the automatic diagnosis of mild cognitive impairment (MCI). This paper proposed a research approach for building an MCI diagnostic model using a Bayesian-optimized bidirectional long short-term memory network (BO-BiLSTM) to address this problem. The diagnostic model was based on a Bayesian algorithm and combined prior distribution and posterior probability results to optimize the BO-BiLSTM network hyperparameters. It also used multiple feature quantities that fully reflected the cognitive state of the MCI brain, such as power spectral density, fuzzy entropy, and multifractal spectrum, as the input of the diagnostic model to achieve automatic MCI diagnosis. The results showed that the feature-fused Bayesian-optimized BiLSTM network model achieved an MCI diagnostic accuracy of 98.64% and effectively completed the diagnostic assessment of MCI. In conclusion, based on this optimization, the long short-term neural network model has achieved automatic diagnostic assessment of MCI, providing a new diagnostic model for intelligent diagnosis of MCI.

Electrocardiogram signal classification algorithm of nested long short-term memory network based on focal loss function / 生物医学工程学杂志

Electrocardiogram (ECG) can visually reflect the physiological electrical activity of human heart, which is important in the field of arrhythmia detection and classification. To address the negative effect of label imbalance in ECG data on arrhythmia classification, this paper proposes a nested long short-term memory network (NLSTM) model for unbalanced ECG signal classification. The NLSTM is built to learn and memorize the temporal characteristics in complex signals, and the focal loss function is used to reduce the weights of easily identifiable samples. Then the residual attention mechanism is used to modify the assigned weights according to the importance of sample characteristic to solve the sample imbalance problem. Then the synthetic minority over-sampling technique is used to perform a simple manual oversampling process on the Massachusetts institute of technology and Beth Israel hospital arrhythmia (MIT-BIH-AR) database to further increase the classification accuracy of the model. Finally, the MIT-BIH arrhythmia database is applied to experimentally verify the above algorithms. The experimental results show that the proposed method can effectively solve the issues of imbalanced samples and unremarkable features in ECG signals, and the overall accuracy of the model reaches 98.34%. It also significantly improves the recognition and classification of minority samples and has provided a new feasible method for ECG-assisted diagnosis, which has practical application significance.

Intelligent fault diagnosis of medical equipment based on long short term memory network / 生物医学工程学杂志

In order to solve the current problems in medical equipment maintenance, this study proposed an intelligent fault diagnosis method for medical equipment based on long short term memory network(LSTM). Firstly, in the case of no circuit drawings and unknown circuit board signal direction, the symptom phenomenon and port electrical signal of 7 different fault categories were collected, and the feature coding, normalization, fusion and screening were preprocessed. Then, the intelligent fault diagnosis model was built based on LSTM, and the fused and screened multi-modal features were used to carry out the fault diagnosis classification and identification experiment. The results were compared with those using port electrical signal, symptom phenomenon and the fusion of the two types. In addition, the fault diagnosis algorithm was compared with BP neural network (BPNN), recurrent neural network (RNN) and convolution neural network (CNN). The results show that based on the fused and screened multi-modal features, the average classification accuracy of LSTM algorithm model reaches 0.970 9, which is higher than that of using port electrical signal alone, symptom phenomenon alone or the fusion of the two types. It also has higher accuracy than BPNN, RNN and CNN, which provides a relatively feasible new idea for intelligent fault diagnosis of similar equipment.

A fetal electrocardiogram signal extraction method based on long short term memory network optimized by genetic algorithm / 生物医学工程学杂志

Fetal electrocardiogram signal extraction is of great significance for perinatal fetal monitoring. In order to improve the prediction accuracy of fetal electrocardiogram signal, this paper proposes a fetal electrocardiogram signal extraction method (GA-LSTM) based on genetic algorithm (GA) optimization with long and short term memory (LSTM) network. Firstly, according to the characteristics of the mixed electrocardiogram signal of the maternal abdominal wall, the global search ability of the GA is used to optimize the number of hidden layer neurons, learning rate and training times of the LSTM network, and the optimal combination of parameters is calculated to make the network topology and the mother body match the characteristics of the mixed signals of the abdominal wall. Then, the LSTM network model is constructed using the optimal network parameters obtained by the GA, and the nonlinear transformation of the maternal chest electrocardiogram signals to the abdominal wall is estimated by the GA-LSTM network. Finally, using the non-linear transformation obtained from the maternal chest electrocardiogram signal and the GA-LSTM network model, the maternal electrocardiogram signal contained in the abdominal wall signal is estimated, and the estimated maternal electrocardiogram signal is subtracted from the mixed abdominal wall signal to obtain a pure fetal electrocardiogram signal. This article uses clinical electrocardiogram signals from two databases for experimental analysis. The final results show that compared with the traditional normalized minimum mean square error (NLMS), genetic algorithm-support vector machine method (GA-SVM) and LSTM network methods, the method proposed in this paper can extract a clearer fetal electrocardiogram signal, and its accuracy, sensitivity, accuracy and overall probability have been better improved. Therefore, the method could extract relatively pure fetal electrocardiogram signals, which has certain application value for perinatal fetal health monitoring.

A heart sound classification method based on joint decision of extreme gradient boosting and deep neural network / 生物医学工程学杂志

Heart sound is one of the common medical signals for diagnosing cardiovascular diseases. This paper studies the binary classification between normal or abnormal heart sounds, and proposes a heart sound classification algorithm based on the joint decision of extreme gradient boosting (XGBoost) and deep neural network, achieving a further improvement in feature extraction and model accuracy. First, the preprocessed heart sound recordings are segmented into four status, and five categories of features are extracted from the signals based on segmentation. The first four categories of features are sieved through recursive feature elimination, which is used as the input of the XGBoost classifier. The last category is the Mel-frequency cepstral coefficient (MFCC), which is used as the input of long short-term memory network (LSTM). Considering the imbalance of the data set, these two classifiers are both improved with weights. Finally, the heterogeneous integrated decision method is adopted to obtain the prediction. The algorithm was applied to the open heart sound database of the PhysioNet Computing in Cardiology(CINC) Challenge in 2016 on the PhysioNet website, to test the sensitivity, specificity, modified accuracy and F score. The results were 93%, 89.4%, 91.2% and 91.3% respectively. Compared with the results of machine learning, convolutional neural networks (CNN) and other methods used by other researchers, the accuracy and sensibility have been obviously improved, which proves that the method in this paper could effectively improve the accuracy of heart sound signal classification, and has great potential in the clinical auxiliary diagnosis application of some cardiovascular diseases.