Strip steel surface defect detection based on lightweight YOLOv5.

Deep learning-based methods for detecting surface defects on strip steel have advanced detection capabilities, but there are still problems of target loss, false alarms, large computation, and imbalance between detection accuracy and detection speed. In order to achieve a good balance between detection accuracy and speed, a lightweight YOLOv5 strip steel surface defect detection algorithm based on YOLOv5s is proposed. Firstly, we introduce the efficient lightweight convolutional layer called GSConv. The Slim Neck, designed based on GSConv, replaces the original algorithm's neck, reducing the number of network parameters and improving detection speed. Secondly, we incorporate SimAM, a non-parametric attention mechanism, into the improved neck to enhance detection accuracy. Finally, we utilize the SIoU function as the regression prediction loss instead of the original CIoU to address the issue of slow convergence and improve efficiency. According to experimental findings, the YOLOv5-GSS algorithm outperforms the YOLOv5 method by 2.9% on the NEU-DET dataset and achieves an average accuracy (mAP) of 83.8% with a detection speed (FPS) of 100 Hz, which is 3.8 Hz quicker than the YOLOv5 algorithm. The proposed model outperforms existing approaches and is more useful, demonstrating the efficacy of the optimization strategy.

Off-label indications of aspirin in gynaecology and obstetrics outpatients at two Chinese tertiary care hospitals: a retrospective cross-sectional study.

OBJECTIVE: To investigate the prevalence of off-label aspirin indications and the level of scientific support for off-label indications of aspirin in gynaecology and obstetrics outpatients. DESIGN: A retrospective cross-sectional study. SETTING: Two tertiary hospitals (a general hospital and a women and children's specialised hospital) in Xiamen, a city located on the southeastern coast of China. PARTICIPANTS: A total of 4257 prescriptions were included for 2091 female patients aged >18 who visited the gynaecology and obstetrics outpatient clinics and received aspirin treatment. OUTCOME MEASURES: The primary measure of this study was the proportion of off-label indications and of off-label indications supported by strong scientific evidence. Evidence from clinical guidelines and Micromedex is shown using descriptive statements. On-label indications of drugs in the same class as aspirin were also referred to for off-label aspirin use without strong evidence support. RESULTS: All indications of aspirin on outpatient prescriptions were determined as off-label use in this study. The most frequent off-label indication was recurrent miscarriage (2244 prescriptions, 52.71%). Totally, 30.94% of the prescriptions were supported by strong evidence for indications, including recurrent miscarriage with antiphospholipid syndrome and prophylaxis for pre-eclampsia. No drugs in the same class as aspirin had on-label indications for off-label aspirin use without strong evidence support. CONCLUSIONS: This study demonstrated that all indications of aspirin used in gynaecology and obstetrics outpatients at the two tertiary hospitals were off-label and not always supported by strong evidence, implicating that physicians should be cautious when issuing off-label prescriptions. More original clinical research on off-label aspirin use is needed to provide reference for routine clinical practice.

Human ß-defensin-2 suppresses key features of asthma in murine models of allergic airways disease.

BACKGROUND: Asthma is an airway inflammatory disease and a major health problem worldwide. Anti-inflammatory steroids and bronchodilators are the gold-standard therapy for asthma. However, they do not prevent the development of the disease, and critically, a subset of asthmatics are resistant to steroid therapy. OBJECTIVE: To elucidate the therapeutic potential of human ß-defensins (hBD), such as hBD2 mild to moderate and severe asthma. METHODS: We investigated the role of hBD2 in a steroid-sensitive, house dust mite-induced allergic airways disease (AAD) model and a steroid-insensitive model combining ovalbumin-induced AAD with C muridarum (Cmu) respiratory infection. RESULTS: In both models, we demonstrated that therapeutic intranasal application of hBD2 significantly reduced the influx of inflammatory cells into the bronchoalveolar lavage fluid. Furthermore, key type 2 asthma-related cytokines IL-9 and IL-13, as well as additional immunomodulating cytokines, were significantly decreased after administration of hBD2 in the steroid-sensitive model. The suppression of inflammation was associated with improvements in airway physiology and treatment also suppressed airway hyper-responsiveness (AHR) in terms of airway resistance and compliance to methacholine challenge. CONCLUSIONS AND CLINICAL RELEVANCE: These data indicate that hBD2 reduces the hallmark features and has potential as a new therapeutic agent in allergic and especially steroid-resistant asthma.

Emerging therapeutic targets and preclinical models for severe asthma.

INTRODUCTION: Asthma is a heterogeneous disease with complex multifactorial causes. It is possible to subclassify asthma into different phenotypes that have distinct immunological features. Eosinophilic asthma is a well-known phenotype of severe asthma; however, a large body of clinical and experimental evidence strongly associates persistent airway inflammation, including the accumulation of neutrophils in the bronchial mucosa, and resistance to corticosteroid therapy and non-Type-2 immune responses with severe asthma. Importantly, mainstay therapies are often ineffective in severe asthma and effective alternatives are urgently needed. AREAS COVERED: Here, we discussed recently developed mouse models of severe asthma that recapitulates key features of the disease in humans. We also provide findings from clinically relevant experimental models that have identified potential therapeutic targets for severe asthma. The most relevant publications on the topic of interest were selected from PubMed. EXPERT COMMENTARY: Increasing the understanding of disease-causing mechanisms in severe asthma may lead to the identification of novel therapeutic targets and the development of more effective therapies. Intense research interest into investigating the pathophysiological mechanisms of severe asthma has driven the development and interrogation of a myriad of mouse models that aim to replicate hallmark features of severe asthma in humans.