Recently, deep neural networks (DNNs) have been widely used in the field of electrocardiogram (ECG) signal classification, but the previous models have limited ability to extract features from raw ECG data. In this paper, a deep residual network model based on pyramidal convolutional layers (PC-DRN) was proposed to implement ECG signal classification. The pyramidal convolutional (PC) layer could simultaneously extract multi-scale features from the original ECG data. And then, a deep residual network was designed to train the classification model for arrhythmia detection. The public dataset provided by the physionet computing in cardiology challenge 2017(CinC2017) was used to validate the classification experiment of 4 types of ECG data. In this paper, the harmonic mean of classification accuracy and recall was selected as the evaluation indexes. The experimental results showed that the average sequence level ( ) of PC-DRN was improved from 0.857 to 0.920, and the average set level ( ) was improved from 0.876 to 0.925. Therefore, the PC-DRN model proposed in this paper provided a promising way for the feature extraction and classification of ECG signals, and provided an effective tool for arrhythmia classification.
Arrhythmias, Cardiac ; Disease Progression ; Electrocardiography ; Humans ; Neural Networks, Computer

T cells and T cell receptors (TCRs) play pivotal roles in adaptive immune responses against tumors. The development of next-generation sequencing technologies has enabled the analysis of the TCRβ repertoire usage. Given the scarce investigations on the TCR repertoire in lung cancer tissues, in this study, we analyzed TCRβ repertoires in lung cancer tissues and the matched distant non-tumor lung tissues (normal lung tissues) from 15 lung cancer patients. Based on our results, the general distribution of T cell clones was similar between cancer tissues and normal lung tissues; however, the proportion of highly expanded clones was significantly higher in normal lung tissues than in cancer tissues (0.021% ± 0.002% vs. 0.016% ± 0.001%, P = 0.0054, Wilcoxon signed rank test). In addition, a significantly higher TCR diversity was observed in cancer tissues than in normal lung tissues (431.37 ± 305.96 vs. 166.20 ± 101.58, P = 0.0075, Mann-Whitney U test). Moreover, younger patients had a significantly higher TCR diversity than older patients (640.7 ± 295.3 vs. 291.8 ± 233.6, P = 0.036, Mann-Whitney U test), and the higher TCR diversity in tumors was significantly associated with worse cancer outcomes. Thus, we provided a comprehensive comparison of the TCR repertoires between cancer tissues and matched normal lung tissues and demonstrated the presence of distinct T cell immune microenvironments in lung cancer patients.