Objective To explore the correlations between image quality of prospective and retrospective electrocardiogram(ECG)-gated CT coronary angiogram and radiation dose in patients with different heart rates.Methods A total of 135 patients undergoing 256-slice spiral CT coronary angiography were enrolled in the study.Among them,66 cases received prospective ECG-gated scanning(prospective ECG-gated group)and further divided into two subgroups with heart rate≤80 beats/min(prospective ECG-gated+low heart rate subgroup,n=39)and>80 beats/min(prospective ECG-gated+high heart rate subgroup,n=27).The other 69 cases underwent retrospective ECG-gated scanning(retrospective ECG-gated group),including 45 cases with heart rate≤80 beats/min(retrospective ECG-gated+low heart rate subgroup)and 24 with heart rate>80 beats/min(retrospective ECG-gated+high heart rate subgroup).The baseline data,image quality[mean CT value,image noise,signal-to-noise ratio(SNR),subjective image quality score]and radiation dos[CT volume dose index(CTDIvol),dose length product(DLP),effective dose(ED)]were compared among 4 subgroups.The correlations of image quality with heart rate and radiation dose in prospective and retrospective ECG-gated groups were analyzed.Results The heart rates in prospective and retrospective ECG-gated+low heart rate subgroups were lower than those in prospective and retrospective ECG-gated+high heart rate subgroups(P<0.05).When comparing the mean CT value,image noise,SNR and subjective image quality score among 4 subgroups,no statistically significant differences were observed(P>0.05).The CTDIvol,DLP and ED in prospective ECG-gated+low heart rate subgroup were significantly lower than those in the other 3 subgroups(P<0.05),and the indicators in prospective ECG-gated+high heart rate subgroup were lower than those in retrospective ECG-gated group(including low and high heart rate subgroups)(P<0.05).Pearson correlation coefficient analysis revealed that the mean CT value,image noise,SNR,subjective image quality score had no significant correlation with heart rate,CTDIvol,DLP and ED in prospective and retrospective ECG-gated groups(P>0.05).Conclusion The subjective and objective image quality of 256-slice spiral CT coronary angiography is not correlated with radiation dose.Prospective ECG-gated scanning can reduce the radiation dose and ensure the image quality as compared with retrospective ECG-gated scanning.This holds true for eligible patients with high heart rate,and the former can effectively reduce radiation exposure.Therefore,prospective ECG-gated scanning is worthy to be promoted in clinic.

Sleep stage classification is a necessary fundamental method for the diagnosis of sleep diseases, which has attracted extensive attention in recent years. Traditional methods for sleep stage classification, such as manual marking methods and machine learning algorithms, have the limitations of low efficiency and defective generalization. Recently, deep neural networks have shown improved results by the capability of learning complex pattern in the sleep data. However, these models ignore the intra-temporal sequential information and the correlation among all channels in each segment of the sleep data. To solve these problems, a hybrid attention temporal sequential network model is proposed in this paper, choosing recurrent neural network to replace traditional convolutional neural network, and extracting temporal features of polysomnography from the perspective of time. Furthermore, intra-temporal attention mechanism and channel attention mechanism are adopted to achieve the fusion of the intra-temporal representation and the fusion of channel-correlated representation. And then, based on recurrent neural network and inter-temporal attention mechanism, this model further realized the fusion of inter-temporal contextual representation. Finally, the end-to-end automatic sleep stage classification is accomplished according to the above hybrid representation. This paper evaluates the proposed model based on two public benchmark sleep datasets downloaded from open-source website, which include a number of polysomnography. Experimental results show that the proposed model could achieve better performance compared with ten state-of-the-art baselines. The overall accuracy of sleep stage classification could reach 0.801, 0.801 and 0.717, respectively. Meanwhile, the macro average F1-scores of the proposed model could reach 0.752, 0.728 and 0.700. All experimental results could demonstrate the effectiveness of the proposed model.
Electroencephalography ; Neural Networks, Computer ; Polysomnography ; Sleep ; Sleep Stages