RESUMEN
The development of automated grading equipment requires achieving high throughput and precise detection of disease spots on jujubes. However, the current algorithms are inadequate in accomplishing these objectives due to their high density, varying sizes and shapes, and limited location information regarding disease spots on jujubes. This paper proposes a method called JujubeSSD, to boost the precision of identifying disease spots in jujubes based on a single shot multi-box detector (SSD) network. In this study, a diverse dataset comprising disease spots of varied sizes and shapes, varying densities, and multiple location details on jujubes was created through artificial collection and data augmentation. The parameter information obtained from transfer learning into the backbone feature extraction network of the SSD model, which reduced the time of spot detection to 0.14 s. To enhance the learning of target detail features and improve the recognition of weak information, the traditional convolution layer was replaced with deformable convolutional networks (DCNs). Furthermore, to address the challenge of varying sizes and shapes of disease spot regions on jujubes, the path aggregation feature pyramid network (PAFPN) and balanced feature pyramid (BFP) were integrated into the SSD network. Experimental results demonstrate that the mean average precision at the IoU (intersection over union) threshold of 0.5 (mAP@0.5) of JujubeSSD reached 97.1%, representing an improvement of approximately 6.35% compared to the original algorithm. When compared to existing algorithms, such as YOLOv5 and Faster R-CNN, the improvements in mAP@0.5 were 16.84% and 8.61%, respectively. Therefore, the proposed method for detecting jujube disease spot achieves superior performance in jujube surface disease detection and meets the requirements for practical application in agricultural production.
Asunto(s)
Ziziphus , Agricultura , Algoritmos , Movimiento Celular , AprendizajeRESUMEN
OBJECTIVE: To study the effects of ulinastatin on coagulation in children who underwent open-heart surgery with cardiopulmonary bypass (CPB). METHODS: Fifty children who underwent open-heart surgery for ventricular septal defect were randomly divided into two groups: ulinastatin treatment and control. Before CPB, ulinastatin (1.0×10(4) U/kg) was added to CPB priming fluid only in the ulinastatin treatment group. Activated partial thromboplasin time (APTT), prothrombin time (PT), thrombin time (TT), fibrinogen and international normalized ratio (INR) were measured both before and at 1 hr, 6 hrs and 24 hrs after CPB. RESULTS: The PT in the ulinastatin group was more prolonged than in the control group at 1 hr after CPB (18.7 ± 0.7 s vs 15.5 ± 0.5 s) and 6 hrs after CPB (17.5 ± 0.6 s vs 15.0 ± 0.6 s). The APTT in the ulinatatin group was also significantly more prolonged than in the control group at 6 hrs after CPB (38.7 ± 3.1 s vs 35.3 ± 3.1 s) and 24 hrs after CPB (34.2 ± 3.0 s vs 31.1 ± 2.6 s). CONCLUSIONS: Ulinastatin may prolong PT and APTT after CPB, and thus affects coagulation in children.
Asunto(s)
Coagulación Sanguínea/efectos de los fármacos , Puente Cardiopulmonar , Glicoproteínas/farmacología , Inhibidores de Tripsina/farmacología , Procedimientos Quirúrgicos Cardíacos , Femenino , Humanos , Lactante , Masculino , Tiempo de Tromboplastina Parcial , Tiempo de ProtrombinaRESUMEN
OBJECTIVE: To present the clinical application of composite graft of acellular allo-dermis matrix (ADM) with thin auto-microskin on burn wound. METHODS: 8 inpatients with 18 full thickness skin burn wounds were transplanted with allo-ADM after eschar was excised, then the auto-microskin and allo-human skin were covered on the area of the matrix, the wound where no allo-ADM grafting were covered as control groups only with auto-microskin and allo-human skin. The area of donor to wound is 1:5 - 1:8. RESULTS: Survived rate of 18 pieces composite skin that allo-ADM with auto-microskin were grafted were 94%. After following up for 3 to 13 months, the skins of complex grifting had well elastic and smooth texture compared to auto-microskin grafted, they appeared less cicatrisation and ulceration. 3 months after operation, it was indicated by histological examination that tightknit the epithelial-dermal conjunction and epidermal papilla structure could be identified in the allo-ADM skin and there were orderly collagenous fibres, but scar skin structure was observed in that auto-microskin grifted area. CONCLUSION: The graft effectiveness of allo-ADM and auto-microskin was better than that of auto-microskin, and this method could be used on major deep burn wound healing.