Emotion plays an important role in people's cognition and communication. By analyzing electroencephalogram (EEG) signals to identify internal emotions and feedback emotional information in an active or passive way, affective brain-computer interactions can effectively promote human-computer interaction. This paper focuses on emotion recognition using EEG. We systematically evaluate the performance of state-of-the-art feature extraction and classification methods with a public-available dataset for emotion analysis using physiological signals (DEAP). The common random split method will lead to high correlation between training and testing samples. Thus, we use block-wise K fold cross validation. Moreover, we compare the accuracy of emotion recognition with different time window length. The experimental results indicate that 4 s time window is appropriate for sampling. Filter-bank long short-term memory networks (FBLSTM) using differential entropy features as input was proposed. The average accuracy of low and high in valance dimension, arousal dimension and combination of the four in valance-arousal plane is 78.8%, 78.4% and 70.3%, respectively. These results demonstrate the advantage of our emotion recognition model over the current studies in terms of classification accuracy. Our model might provide a novel method for emotion recognition in affective brain-computer interactions.
ObjectiveTo investigate expression and clinical significance of long chain noncoding RNA POU6F2-AS2 in human gastric cancer tissues.MethodsSeventy-three pairs of human gastric cancer and matched paracancerous tissues from May 2017 to May 2018 in the Affiliated Hospital of North Sichuan Medical College were collected. The real-time fluorescence quantitative polymerase chain reaction was used to detect the expression level of POU6F2-AS2 in the gastric cancer tissue and its paracancerous tissue. The correlations between its expression level and clinicalpathologic features of patients were analyzed by the chi-square text. The relationship between the expression of POU6F2-AS2 and the overall survival rate of patient with gastric cancer was analyzed by the Kaplan Meier Plotter database data.ResultsThe relative expression of POU6F2-AS2 in the gastric cancer tissues was significantly higher than that in the corresponding adjacent tissues (P<0.050). The patients were divided into the high expression (43 cases) and low expression group (30 cases) according to the expression level of POU6F2-AS2 in the gastric cancer tissues and their corresponding adjacent tissues. The results of the relationship between the expression of POU6F2-AS2 and the clinicopathologic characteristics of patients with gastric cancer showed that the POU6F2-AS2 expression was significantly correlated with the depth of invasion (P=0.022) or the TNM stage (P=0.032). There were no significant differences in the gender, age, smoking history, drinking history, tumor diameter, degree of differentiation, lymph node metastasis, distant metastasis, vascular invasion, nerve invasion, liver metastasis, ascites, and fat nodule metastasis (P>0.050). The overall survival rate of high expression of POU6F2-AS2 in the patient with gastric cancer was significantly worse than that of the low expression of POU6F2-AS2 by the Kaplan Meier Plotter database.ConclusionsHigh expression of POU6F2-AS2 is related to depth of tumor invasion and TNM stage, which indicates that POU6F2-AS2 might play an important role in regulating occurrence and development of gastric cancer. It may be used as an important target for gene diagnosis and treatment of gastric cancer and as a biomarker for evaluating prognosis of patients with gastric cancer.
This study aims to compare the prostate cancer detection rate between magnetic resonance imaging (MRI)-transrectal ultrasound (TRUS) cognitive fusion targeted biopsy and systematic biopsy. A total of 614 patients who underwent transrectal prostate biopsy during 2016-2018 with multiparametric magnetic resonance imaging (mpMRI) were included. All patients with a PI-RADS V2 score ≥ 3 accepted both targeted biopsy and systematic biopsy, and those with a PI-RADS V2 score ≤ 2 only accepted systematic biopsy. Overall prostate cancer detection rate between the two biopsies was compared. MRI-TRUS cognitive fusion targeted biopsy identified 342 cases (75.7%) of prostate cancer while systematic biopsy identified 358 cases (79.2%). There was no significant difference in the detection rate between the two groups (χ2 = 1.621, P = 0.203). Targeted biopsy had significant fewer biopsy cores compared with systematic biopsy, reducing (9.3 ± 0.11) cores (P < 0.001) in average. Targeted biopsy had about 10.8% (P < 0.001) more tumor tissues in positive cores compared with systematic biopsy. The results show that both MRI-TRUS cognitive fusion targeted biopsy and systematic biopsy have good detection rate on prostate cancer. Cognitive targeted biopsy may reduce biopsy cores and provide more tumor tissues in positive cores.