Search

The effective classification of multi-task motor imagery electroencephalogram (EEG) is helpful to achieve accurate multi-dimensional human-computer interaction, and the high frequency domain specificity between subjects can improve the classification accuracy and robustness. Therefore, this paper proposed a multi-task EEG signal classification method based on adaptive time-frequency common spatial pattern (CSP) combined with convolutional neural network (CNN). The characteristics of subjects' personalized rhythm were extracted by adaptive spectrum awareness, and the spatial characteristics were calculated by using the one-versus-rest CSP, and then the composite time-domain characteristics were characterized to construct the spatial-temporal frequency multi-level fusion features. Finally, the CNN was used to perform high-precision and high-robust four-task classification. The algorithm in this paper was verified by the self-test dataset containing 10 subjects (33 ± 3 years old, inexperienced) and the dataset of the 4th 2018 Brain-Computer Interface Competition (BCI competition Ⅳ-2a). The average accuracy of the proposed algorithm for the four-task classification reached 93.96% and 84.04%, respectively. Compared with other advanced algorithms, the average classification accuracy of the proposed algorithm was significantly improved, and the accuracy range error between subjects was significantly reduced in the public dataset. The results show that the proposed algorithm has good performance in multi-task classification, and can effectively improve the classification accuracy and robustness.多任务运动想象脑电信号有效分类有助于实现精准的多维人机交互，充分利用受试者的高度频域特异性可提升分类准确率和鲁棒性。为此，本文提出基于自适应时频共空间模式结合卷积神经网络的多任务脑电信号分类方法。通过自适应频谱感知提取受试者个性化节律特性，再采用一对多共空间模式计算空域特性，进而表征复合时域特性构建时空频多层次融合特征，最后利用卷积神经网络进行高精度高鲁棒性四分类。本文采用包含10位受试者［（33 ± 3）岁］实测数据的自测数据集以及第四届2018脑机接口竞赛数据集2a（BCI competition Ⅳ-2a）对本文算法进行验证，所提算法四分类平均准确率分别达到了93.96%和84.04%，且在公开数据集中本文算法相较于其它先进算法平均分类准确率明显提高，受试者间准确率范围误差则大幅降低。结果表明，本文所提算法在多任务分类中表现出良好性能，能有效提高分类精度和鲁棒性。.

Aiming at the limitations of clinical diagnosis of Parkinson's disease (PD) with rapid eye movement sleep behavior disorder (RBD), in order to improve the accuracy of diagnosis, an intelligent-aided diagnosis method based on few-channel electroencephalogram (EEG) and time-frequency deep network is proposed for PD with RBD. Firstly, in order to improve the speed of the operation and robustness of the algorithm, the 6-channel scalp EEG of each subject were segmented with the same time-window. Secondly, the model of time-frequency deep network was constructed and trained with time-window EEG data to obtain the segmentation-based classification result. Finally, the output of time-frequency deep network was postprocessed to obtain the subject-based diagnosis result. Polysomnography (PSG) of 60 patients, including 30 idiopathic PD and 30 PD with RBD, were collected by Nanjing Brain Hospital Affiliated to Nanjing Medical University and the doctor's detection results of PSG were taken as the gold standard in our study. The accuracy of the segmentation-based classification was 0.902 4 in the validation set. The accuracy of the subject-based classification was 0.933 3 in the test set. Compared with the RBD screening questionnaire (RBDSQ), the novel approach has clinical application value.针对临床帕金森病（PD）伴快速眼动睡眠行为障碍（RBD）诊断方法的局限性，为了提高诊断准确率，提出基于少导联脑电和时频深度网络的智能辅助诊断方法。首先，为提高运算速度及算法鲁棒性，对各被试者的6导联头皮脑电数据进行等长的时间窗提取；然后，基于时间窗脑电数据构建时频深度网络，并得到基于时间窗的分类结果；最后，对各被试者所有时间窗脑电数据的分类结果进行综合决策，实现基于被试者的PD伴RBD辅助诊断。本文以南京医科大学附属脑科医院采集的PD伴和不伴RBD患者的多导睡眠图（PSG）为研究对象，两类数据各30例，以医生诊断结果作为金标准进行算法性能验证。本文方法基于时间窗的分类准确率为0.902 4，基于被试者的分类准确率为0.933 3，比RBD临床筛查问卷效果更好

Alteration of DNA methylation is an important event in pathogenesis and progression of hepatocellular carcinoma (HCC). DNA methyltransferase (DNMT) 1, the foremost contributor in DNA methylation machinery, was revealed elevated in HCC and significantly correlates with poor prognosis. However, the transcriptional regulation of DNMT1 in HCC remains unknown.Real-time PCR and immunohistochemistry were performed to detect DNMT1 and zinc finger transcription factor 191 (ZNF191) expressions in HCCs. Transcription activity of DNMT1promoter was analyzed with Luciferase reporter activity assay. The binding capacity of ZNF191 protein to DNMT1 promoter was examined with chromatin immunoprecipitation-qPCR (ChIP-qPCR) and electrophoretic mobility shift assay (EMSA). DNA methylation level of hepatoma cells was detected with Methylation array.ZNF191 can regulate DNMT1 mRNA and protein expression positively, and increase the transcription activity of the DNMT1 promoter. ChIP-qPCR and EMSA revealed that ZNF191 protein directly binds to the DNMT1 promoter at nt-240 AT(TCAT)ZNF191 is a novel transcription regulator for DNMT1, and the pro-proliferation effect of ZNF191/DNMT1/p-AKT axis in hepatoma cells implies that ZNF191 status in HCCs may affect the therapeutic effect of DNMTs inhibitors and PI3K inhibitors for precise treatment of the disease.

Numerous studies have focused on the treatment of melanoma, but the current therapies for melanoma have limited therapeutic effects. To find a more effective therapy for melanoma, we combined artificially designed CpG ODN (cytosine-phosphate-guanine oligodeoxynucleotides) and siRNAs (small-interfering ribonucleic acids) targeting PD-1 (programmed cell death protein 1), which were delivered by attenuated Salmonella to treat melanoma in mice, and explored the underlying antitumor mechanisms. We found that mice receiving the combination therapy had the smallest tumor size and the longest survival time. The possible mechanisms underlying this phenomenon include pathways mediated by cyclin D1, p-STAT3 (phosphorylated signal transducers and activators of transcription protein 3), MMP2 (matrix metallopeptidase 2) and cleaved caspase 3, since after treatment, the expression of cyclin D1, p-STAT3, and MMP2 decreased but that of cleaved caspase 3 increased; additional mechanisms include increases in the recruitment of immune cells to tumor sites and in the number of immune cells in mouse spleens and the upregulation of TNF-α (tumor necrosis factor) and IL-6 (interleukin 6). We demonstrated that the combination therapy composed of CpG ODN and PD-1-siRNA delivered by attenuated Salmonella exhibited a strong ability to inhibit melanoma and improve the antitumor immune responses of tumor-bearing mice.