A robust defect detection method for syringe scale without positive samples.

With the worldwide spread of the COVID-19 pandemic, the demand for medical syringes has increased dramatically. Scale defect, one of the most common defects on syringes, has become a major barrier to boosting syringe production. Existing methods for scale defect detection suffer from large volumes of data requirements and the inability to handle diverse and uncertain defects. In this paper, we propose a robust scale defects detection method with only negative samples and favorable detection performance to solve this problem. Different from conventional methods that work in a batch-mode defects detection manner, we propose to locate the defects on syringes with a two-stage framework, which consists of two components, that is, the scale extraction network and the scale defect discriminator. Concretely, the SeNet is first built to utilize the convolutional neural network to extract the main structure of the scale. After that, the scale defect discriminator is designed to detect and label the scale defects. To evaluate the performance of our method, we conduct experiments on one real-world syringe dataset. The competitive results, that is, 99.7% on F1, prove the effectiveness of our method.

Investigation on Risk Stratification and the Prognostic Value of hs-TnT Combined with MMP-2 in Patients with Acute Coronary Syndrome.

OBJECTIVE: The aim of this study was at investigating the risk stratification and prognostic value of hypersensitive troponin T (hs-TnT) combined with matrix metalloproteinase 2 (MMP-2) in patients with acute coronary syndrome (ACS). METHODS: 80 patients with coronary syndrome admitted to our hospital from January 2019 to January 2020 and 40 healthy people (control group) in the same period were selected. According to different types of diseases, the patients were divided into an acute group (n = 40) and stable group (n = 40). Besides, they all were monitored by the hs-TnT value, serum MMP-2, and coronary angiography at admission and the comparative analysis was carried out. The patients in both groups were followed up for 30 days, and the incidence of adverse cardiovascular events in the patients during this period was recorded. RESULTS: Compared with those in the control group, the MMP-2 and hs-TnT levels in the acute group and the stable group were significantly higher and the MMP-2 and hs-TnT levels in the acute group were significantly higher than those in the stable group, with statistically significant differences (P < 0.05). The 30-day follow-up results showed that the incidence of adverse cardiovascular events in the acute group was significantly higher than that in the stable group, with statistically significant differences (P < 0.05). The hs-TnT and MMP-2 levels in the acute myocardial infarction (AMI) group were significantly higher than those in the unstable angina pectoris (UAP) group, with statistically significant differences (P < 0.01). The hs-TnT and MMP-2 levels in the non-single-vessel group were significantly higher than those in the single-vessel group, with statistically significant differences (P < 0.01). CONCLUSION: The hs-TnT and MMP-2 high expression levels are closely associated with myocardial injury, and they can effectively predict the severity of patients' disease. In addition, the hs-TnT and MMP-2 elevated levels can be considered as an important index to judge the short-term treatment efficacy and the risk stratification of early ACS, playing an important role in clinical treatment and rehabilitation in the later stage.