A medical device detection method based on improved YOLOv5s was proposed to solve the problem of medical device stacking and further improve the detection accuracy of medical devices.The proposed method uses C2f module to optimize YOLOv5s network for improving the detection accuracy,introduces squeeze-and-excitation network into the feature fusion network for improving the model's attention to effective information,and constructs α-DIOU by introducing Alpha intersection union ratio(α-IOU)on the basis of the distance-intersection over union(DIOU)loss function,which makes the bounding box regression more accurate and enables the accurate detection of medical devices in the image.Experimental results show that the improved model has precision,recall rate and mean average precision of 81.8%,93.7%and 91.5%,respectively,for medical device detection on the validation set,which are 3.2%,3.4%and 4.6%higher than YOLOv5s model.The proposed method is simple and effective,and is expected to provide new ideas for the detection methods of medical devices.

A medical device detection method based on improved YOLOv5s was proposed to solve the problem of medical device stacking and further improve the detection accuracy of medical devices.The proposed method uses C2f module to optimize YOLOv5s network for improving the detection accuracy,introduces squeeze-and-excitation network into the feature fusion network for improving the model's attention to effective information,and constructs α-DIOU by introducing Alpha intersection union ratio(α-IOU)on the basis of the distance-intersection over union(DIOU)loss function,which makes the bounding box regression more accurate and enables the accurate detection of medical devices in the image.Experimental results show that the improved model has precision,recall rate and mean average precision of 81.8%,93.7%and 91.5%,respectively,for medical device detection on the validation set,which are 3.2%,3.4%and 4.6%higher than YOLOv5s model.The proposed method is simple and effective,and is expected to provide new ideas for the detection methods of medical devices.

With the constant development of the drug screening technology, new screening methods and techniques have came to the fore, driving drug screening to grow rapidly and efficiently with a high throughput. Characterized by micro-scale analysis, high throughput, inheritability and good biocompatibility, the micro-fluidic analytical technology provides a new method and technical platform for screening active ingredients from natural products. This essay introduces multiple methods used for screening active ingredients from natural products and focuses on the micro-fluidic chip screening technology combined with cell culture and its characteristics, the composition of the platform of the micro-fluidic chip screening technology and its application in screening active ingredients from natural products.
Animals ; Biological Products ; chemistry ; Drug Evaluation, Preclinical ; methods ; Humans ; Microfluidic Analytical Techniques ; methods

Objective To study the optimization of extraction technology for total flavonoid-aglycone from Scutellaria baicalensis after enzymatic hydrolysis. Methods With three factors of alcohol concentration, dosage and speed of percolation as the indexes, orthogonal experiment was performed. Concentrations of Baicalein, Wogonin and oroxylin-A were analyzed by HPLC. Results The optimal extraction technology is A2B3C2: extracting the medical material by 10 times(V) 95 % alcohol, the speed being 6 mL/kg per min. Conclusion Under optimal extraction technology, extraction rate of total flavonoid-aglycone is very considerable and the concentration is high to 60 % .