Deep learning-based automatic inpainting for material microscopic images.

The microscopic image is important data for recording the microstructure information of materials. Researchers usually use image-processing algorithms to extract material features from that and then characterise the material microstructure. However, the microscopic images obtained by a microscope often have random damaged regions, which will cause the loss of information and thus inevitably influence the accuracy of microstructural characterisation, even lead to a wrong result. To handle this problem, we provide a deep learning-based fully automatic method for detecting and inpainting damaged regions in material microscopic images, which can automatically inpaint damaged regions with different positions and shapes, as well as we also use a data augmentation method to improve the performance of inpainting model. We evaluate our method on Al-La alloy microscopic images, which indicates that our method can achieve promising performance on inpainted and material microstructure characterisation results compared to other image inpainting software for both accuracy and time consumption. LAY DESCRIPTION: A basic goal of materials data analysis is to extract useful information from materials datasets that can in turn be used to establish connections along the composition-processing-structure-properties chain. The microscopic images obtained by a microscope is the key carrier of material microstructural information. Researchers usually use image analysis algorithms to extract regions of interest or useful features from microscopic images, aiming to analyse material microstructure, organ tissues or device quality etc. Therefore, the integrity and clarity of the microscopic image are the most important attributes for image feature extraction. Scientists and engineers have been trying to develop various technologies to obtain perfect microscopic images. However, in practice, some extrinsic defects are often introduced during the preparation and/or shooting processes, and the elimination of these defects often requires mass efforts and cost, or even is impossible at present. Take the microstructure image of metallic material for example, samples prepared to microstructure characterisation often need to go through several steps such as cutting, grinding with sandpaper, polishing, etching, and cleaning. During the grinding and polishing process, defects such as scratches could be introduced. During the etching and cleaning process, some defects such as rust caused by substandard etching, stains etc. may arise and be persisted. These defects can be treated as damaged regions with nonfixed positions, different sizes, and random shapes, resulting in the loss of information, which seriously affects subsequent visual observation and microstructural feature extraction. To handle this problem, we provide a deep learning-based fully automatic method for detecting and inpainting damaged regions in material microscopic images, which can automatically inpaint damaged regions with different positions and shapes, as well as we also use a data augmentation method to improve the performance of inpainting model. We evaluate our method on Al-La alloy microscopic images, which indicates that our method can achieve promising performance on inpainted and material microstructure characterisation results compared to other image inpainting software for both accuracy and time consumption.

Study on Connective Tissue Growth Factor Expressed in Patients with ST-Segment Elevation Myocardial Infarction.

BACKGROUND: This study measured the change in connective tissue growth factor levels after the onset of unstable angina and ST-segment elevation myocardial infarction, and studied its correlation with peak creatine kinase-MB (CK-MB) enzyme. It also discussed the significance of myocardial fibrosis after myocardial infarction. To detect the serum levels of connective tissue growth factor in patients with ST-segment elevation myocardial infarction and its relationship with the maximum level of CK-MB. METHODS: We selected 50 patients with ST-segment elevation myocardial infarction and 50 patients with unstable angina. Connective tissue growth factor levels were examined 24 h, 2 d, 7 d, and 14 d after the onset of ST-segment elevation myocardial infarction, and within 24 h for unstable angina, using enzyme-linked immunosorbent assay (ELISA). The maximum level of CK-MB was detected by immunosuppression. RESULTS: The serum level of connective tissue growth factor in the unstable angina patients was 10.34 ± 2.00 ng/mL, and the levels in the ST-segment elevation myocardial infarction patients were 16.76 ± 3.17 ng/mL at 24 h, 29.87 ± 4.90 ng/mL at 2 d, 45.02 ± 8.35 ng/mL at 7 d, and 31.61 ± 4.40 ng/mL at 14 d. Compared with the unstable angina patients, the connective tissue growth factor levels in the ST-segment elevation myocardial infarction patients were significantly higher since day 1 (p < 0.01). The maximum level of CK-MB was correlated with connective tissue growth factor levels at 7 d (r = 0.859, p = 0.000). CONCLUSIONS: Connective tissue growth factor was significantly expressed in the ST-segment elevation myocardial infarction patients, indicating that it might play an important role in myocardial fibrosis.

Predictive value of neutrophil to lymphocyte ratio in patients with acute ST segment elevation myocardial infarction after percutaneous coronary intervention: a meta-analysis.

BACKGROUND: The neutrophil to lymphocyte ratio (NLR) is an indicator of systemic inflammation and a prognostic marker in patients with acute coronary syndrome (ACS). This study aims to investigate the value of NLR to predict the in-hospital and long-term prognosis in patients with ST segment elevation myocardial infarction (STEMI) after percutaneous coronary intervention (PCI) by meta-analysis. METHOD: The studies related to the prognosis of NLR and STEMI patients published in the Pubmed, Embase, and Ovid databases before June 2017 were retrieved. The relevant data were extracted. Review Manager Version 5.3 was used for meta-analysis. RESULTS: A total of 14 studies of 10,245 patients with STEMI after PCI were included. A significant difference was observed for mortality (P < 0.001; relative risk (RR) 3.32; 95% confidence interval (CI) 2.45-4.49), hospital cardiac mortality(P < 0.001; RR 3.22; 95% CI 2.25-4.60), all mortality (P < 0.001; RR 3.23; 95% CI 2.28-4.57), major adverse cardiovascular events (MACE) (P < 0.001; RR 2.00; 95% CI 1.62-2.46), in-stent thrombosis (P < 0.001; RR 2.72 95% CI 1.66-4.44), nonfatal myocardial infarction(MI) (P < 0.001; RR 1.93; 95%CI 1.43-2.61), angina (P = 0.007; RR 1.67; 95%CI 1.15-2.41), advanced heart failure (AHF) (P < 0.001; RR 1.81; 95% CI 1.48-2.21), arrhythmia (P = 0.002; RR 1.38; 95% CI 1.13-1.69), no reflow (P < 0.001; RR 2.28; 95% CI 1.46-3.57), long-term all mortality (P < 0.001; RR 3.82; 95% CI 2.94-4.96), cardiac mortality (P = 0.004; RR 3.02; 95% CI 1.41-6.45), MACE (P < 0.001; RR 2.49; 95% CI 1.47-4.23), and nonfatal MI (P = 0.46; RR 1.32; 95% CI 0.63-2.75). CONCLUSIONS: Meta-analysis shows that NLR is a predictor of hospitalization and long-term prognosis in patients with STEMI after PCI, but requires further confirmation by large randomized clinical trials.

Identifying Vulnerable Atherosclerotic Plaque in Rabbits Using DMSA-USPIO Enhanced Magnetic Resonance Imaging to Investigate the Effect of Atorvastatin.

BACKGROUND: Rupture of an atherosclerotic plaque is the primary cause of acute cardiovascular and cerebrovascular syndromes. Early and non-invasive detection of vulnerable atherosclerotic plaques (VP) would be significant in preventing some aspects of these syndromes. As a new contrast agent, dimercaptosuccinic acid (DMSA) modified ultra-small super paramagnetic iron oxide (USPIO) was synthesized and used to identify VP and rupture plaque by magnetic resonance imaging (MRI). METHODS: Atherosclerosis was induced in male New Zealand White rabbits by feeding a high cholesterol diet (n = 30). Group A with atherosclerosis plaque (n = 10) were controls. VP was established in groups B (n = 10) and C (n = 10) using balloon-induced endothelial injury of the abdominal aorta. Adenovirus-carrying p53 genes were injected into the aortic segments rich in plaques after 8 weeks. Group C was treated with atorvastatin for 8 weeks. Sixteen weeks later, all rabbits underwent pharmacological triggering, and imaging were taken daily for 5 d after DMSA-USPIO infusion. At the first day and before being killed, serum MMP-9, sCD40L, and other lipid indicators were measured. RESULTS: DMSA-USPIO particles accumulated in VP and rupture plaques. Rupture plaques appeared as areas of hyper-intensity on DMSA-USPIO enhanced MRI, especially T2*-weighted sequences, with a signal strength peaking at 96 h. The group given atorvastatin showed few DMSA-USPIO particles and had lower levels of serum indicators. MMP-9 and sCD40L levels in group B were significantly higher than in the other 2 groups (P <0.05). CONCLUSION: After successfully establishing a VP model in rabbits, DMSA-USPIO was used to enhance MRI for clear identification of plaque inflammation and rupture. Rupture plaques were detectable in this way probably due to an activating inflammatory process. Atorvastatin reduced the inflammatory response and stabilizing VP possibly by decreasing MMP-9 and sCD40L levels.

Detection of Vulnerable Atherosclerotic Plaques in Experimental Atherosclerosis with the USPIO-Enhanced MRI.

This study's goal was to assess the diagnostic value of the USPIO-(ultra-small superparamagnetic iron oxide) enhanced magnetic resonance imaging (MRI) in detection of vulnerable atherosclerotic plaques in abdominal aorta in experimental atherosclerosis. Thirty New Zealand rabbits were randomly divided into two groups, Group A and Group B. Each group comprised 15 animals which were fed with high cholesterol diet for 8 weeks and then subjected to balloon-induced endothelial injury of the abdominal aorta. After another 8 weeks, animals in Group B received adenovirus carrying p53 gene that was injected through a catheter into the aortic segments rich in plaques. Two weeks later, all rabbits were challenged with the injection of Chinese Russell's viper venom and histamine. Pre-contrast images and USPIO-enhanced MRI images were obtained after pharmacological triggering with injection of USPIO for 5 days. Blood specimens were taken for biochemical and serological tests at 0 and 18 weeks. Abdominal aorta was histologically studied. The levels of serum ICAM-1 and VCAM-1 were quantified by ELISA. Vulnerable plaques appeared as a local hypo-intense signal on the USPIO-enhanced MRI, especially on T2*-weighted sequences. The signal strength of plaques reached the peak at 96 h. Lipid levels were significantly (p < 0.05) higher in both Group A and B compared with the levels before the high cholesterol diet. The ICAM-1 and VCAM-1 levels were significantly (p < 0.05) higher in Group B compared with Group A. The USPIO-enhanced MRI efficiently identifies vulnerable plaques due to accumulation of USPIO within macrophages in abdominal aorta plaques.