Automatic sleep staging of single-channel EEG based on domain adversarial neural networks and domain self-attention.

The diagnosis and management of sleep problems depend heavily on sleep staging. For autonomous sleep staging, many data-driven deep learning models have been presented by trying to construct a large-labeled auxiliary sleep dataset and test it by electroencephalograms on different subjects. These approaches suffer a significant setback cause it assumes the training and test data come from the same or similar distribution. However, this is almost impossible in scenario cross-dataset due to inherent domain shift between domains. Unsupervised domain adaption was recently created to address the domain shift issue. However, only a few customized UDA solutions for sleep staging due to two limitations in previous UDA methods. First, the domain classifier does not consider boundaries between classes. Second, they depend on a shared model to align the domain that could miss the information of domains when extracting features. Given those restrictions, we present a novel UDA approach that combines category decision boundaries and domain discriminator to align the distributions of source and target domains. Also, to keep the domain-specific features, we create an unshared attention method. In addition, we investigated effective data augmentation in cross-dataset sleep scenarios. The experimental results on three datasets validate the efficacy of our approach and show that the proposed method is superior to state-of-the-art UDA methods on accuracy and MF1-Score.

Automatic Sleep Staging Algorithm Based on Time Attention Mechanism.

The most important part of sleep quality assessment is the automatic classification of sleep stages. Sleep staging is helpful in the diagnosis of sleep-related diseases. This study proposes an automatic sleep staging algorithm based on the time attention mechanism. Time-frequency and non-linear features are extracted from the physiological signals of six channels and then normalized. The time attention mechanism combined with the two-way bi-directional gated recurrent unit (GRU) was used to reduce computing resources and time costs, and the conditional random field (CRF) was used to obtain information between tags. After five-fold cross-validation on the Sleep-EDF dataset, the values of accuracy, WF1, and Kappa were 0.9218, 0.9177, and 0.8751, respectively. After five-fold cross-validation on the our own dataset, the values of accuracy, WF1, and Kappa were 0.9006, 0.8991, and 0.8664, respectively, which is better than the result of the latest algorithm. In the study of sleep staging, the recognition rate of the N1 stage was low, and the imbalance has always been a problem. Therefore, this study introduces a type of balancing strategy. By adopting the proposed strategy, SEN-N1 and ACC of 0.7 and 0.86, respectively, can be achieved. The experimental results show that compared to the latest method, the proposed model can achieve significantly better performance and significantly improve the recognition rate of the N1 period. The performance comparison of different channels shows that even when the EEG channel was not used, considerable accuracy can be obtained.

[Feasibility and outcome of rotational atherectomy for treating resistant chronic total occlusions].

OBJECTIVE: To assess the application of rotational atherectomy to improving the success rate and outcome of percutaneous recanalization of resistant chronic total occlusion (CTO), i.e. the guidewire could cross the lesion but it is impossible to advance any device over the wire through the occluded segment. METHODS: From August 2008 to December 2012, 26 consecutive patients with 27 resistant CTO lesions were additionally treated by high-speed rotational atherectomy (rotational atherectomy group). The control group included 751 non-resistant CTO lesions. Drug-eluting stents were implanted in two groups after the balloon catheter crossed the CTO lesions. The successful rate of rotational atherectomy and in hospital major adverse cardiovascular events (including cardiac death, interventional treatment related myocardial infarction and target vessel revascularization) were observed. RESULTS: The rate of heavily calcified coronary lesions was significantly higher in rotational atherectomy group than in the control group[63.0% (17/27) vs. 21.2% (159/751), P < 0.05] according to pre-procedural coronary angiography. Rotational atherectomy was successful in 25 out of 27 resistant CTO lesions (92.6 %). The rate of cardiac death [0 vs. 0.5% (4/751), P > 0.05], interventional treatment related myocardial infarction [38.5% (10/26) vs. 22.2% (167/751), P > 0.05] and target vessel revascularization [0 vs. 1.2% (9/751), P > 0.05] were similar between the rotational atherectomy group and the control group. CONCLUSION: Rotational atherectomy is a safe and helpful technique to overcome the inability of balloon catheter to cross a resistant CTO.