DCU-Net: a dual-channel U-shaped network for image splicing forgery detection.

The detection and location of image splicing forgery are a challenging task in the field of image forensics. It is to study whether an image contains a suspicious tampered area pasted from another image. In this paper, we propose a new image tamper location method based on dual-channel U-Net, that is, DCU-Net. The detection framework based on DCU-Net is mainly divided into three parts: encoder, feature fusion, and decoder. Firstly, high-pass filters are used to extract the residual of the tampered image and generate the residual image, which contains the edge information of the tampered area. Secondly, a dual-channel encoding network model is constructed. The input of the model is the original tampered image and the tampered residual image. Then, the deep features extracted from the dual-channel encoding network are fused for the first time, and then the tampered features with different granularity are extracted by dilation convolution, and then, the secondary fusion is carried out. Finally, the fused feature map is input into the decoder, and the predicted image is decoded layer by layer. The experimental results on Casia2.0 and Columbia datasets show that DCU-Net performs better than the latest algorithm and can accurately locate tampered areas. In addition, the attack experiments show that DCU-Net model has good robustness and can resist noise and JPEG recompression attacks.

Impact of Left Atrial Sphericity Index on the Outcome of Catheter Ablation for Atrial Fibrillation.

Left atrial sphericity index (LASI) is one significant geometric remodeling parameter to evaluate the prognosis of atrial fibrillation (AF). We aimed to determine whether transthoracic echocardiography (TTE)-derived LASI may help predict the outcomes following AF radiofrequency catheter ablation (RFCA). This prospective study enrolled 190 consecutive AF patients who underwent TTE 24 h before RFCA. LASI was calculated as the ratio of left atrial maximum volume to spherical volume. After 1-year follow-up, 56 patients (29.5%) relapsed. Multivariate Cox regression showed that LASI (hazard ratio = 1.48, 95% Cl 1.15-1.92, P = 0.003) was an independent predictor of AF recurrence. Stratifying patients into four subgroups with different LAVI showed that high LASI value indicated a high risk of recurrence, especially in patients with mildly and moderately enlarged atria (the recurrence rate was 0% vs. 26.3%, P = 0.049; 9.5% vs. 40.9%, P = 0.018, respectively). In conclusion, TTE-derived LASI may be useful to predict AF recurrence after RFCA.

Circulating long noncoding RNA, GAS5, as a novel biomarker for patients with atrial fibrillation.

BACKGROUND: Circulating long noncoding RNA (lncRNA) plays a vital role in clinical disease diagnosis and prognosis. Here, we evaluate the role of a lncRNA, named growth arrest specific 5 (GAS5), in atrial fibrillation (AF). METHODS: Expression of GAS5 was measured by qRT-PCR. Diagnostic and prognostic values of GAS5 were assessed by the receiver operating characteristics curve (ROC), Kaplan-Meier (KM) and Cox regression analyses. RESULTS: A total of 173 participants were enrolled in this study. Circulating GAS5 expression was significantly down-regulated in AF patients. This change occurred prior to enlargement of the left atrial volume and was strongly associated with AF progression, which demonstrates the potential use of GAS5 as an early biomarker. The area under the ROC curve (AUC) was 0.858 (95% CI 0.789-0.926, P < .001). Seventy of the 85 AF patients received radiofrequency catheter ablation (RFCA), and 22 (31.4%) had relapsed by the 1-year follow-up. The KM analysis (log-rank test, P = .031) and multivariable Cox analysis (HR = 0.127, 95% CI 0.026-0.616; P = .01) revealed that GAS5 has a role in predicting recurrence after RFCA. CONCLUSION: Circulating lncRNA GAS5 is a potential biomarker for AF diagnosis and prognosis. Down-regulation of GAS5 occurs prior to left atrial enlargement and can be used for the prognosis of AF progression and recurrence.

Meta-analysis of the association of the CYP2J2 G-50T polymorphism with coronary artery disease.

The association of the CYP2J2 G-50T polymorphism with coronary artery disease has been explored, but the results remain controversial. Thus, a meta-analysis was conducted to provide a comprehensive estimate of this association. We selected ten articles encompassing 12 independent case-control studies with 7063 cases and 10,453 controls for this meta-analysis. Overall, we found significant associations between the CYP2J2 G-50T polymorphism and coronary artery disease risk in three genetic models (allele model: odds ratio (OR) = 1.19, 95% confidence interval (CI) = 1.05-1.34; homozygote model: OR = 2.25, 95% CI = 1.27-4.01; recessive model: OR = 2.17, 95% CI = 1.22-3.86). In these three genetic models, a significant association was observed in Caucasians but not in Asians when the data were stratified by ethnicity. However, no significant associations were found between the CYP2J2 polymorphism G-50T and coronary artery disease risk in heterozygote model and dominant model. In conclusion, our meta-analysis suggested that the CYP2J2 G-50T polymorphism was associated with coronary artery disease risk in the allele, homozygote and recessive models in Caucasians.