Search

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.

Objective By summarizing the clinical characteristics and follow-up outcomes of 5 patients with immune checkpoint inhibitor induced diabetes mellitus (ICI-DM) and reviewing the relevant literatures, the article aims at providing reference to clinicians in the diagnosis and treatment of the ICI-DM. Methods Clinical data of 5 patients with ICI-DM who were admitted to Peking Union Medical College Hospital from December 2018 to February 2023 and did retrospectively analyzed. Results Five patients with a mean age of (65±7)years received treatment by the programmed cell death 1 (PD-1) or its ligand inhibitor (PD-L1). The median time from the first immunotherapy to the discovery of elevated plasma glucose was 100 (43, 210)days, and the median cycle of immunotherapy was 7 (2.5, 10.5). The onset of the illness of all the 5 patients started with diabetic ketosis or ketoacidosis. At the onset, urine ketone bodies were positive, random plasma glucose was (36.36±15.89)mmol/L, glycosylated hemoglobin A1c (HbA1c)was (8.6%±0.66%), arterial blood pH was (7.28±0.16), and the median fasting C-peptide level was 0.09 (0.05, 0.32)μg/L. Five patients had an onset plasma glucose level of grade 3 or 4.Then, ICI treatment was discontinued in all patients and insulin therapy started. The daily dosage of insulin was (56±20)IU, supplemented with hypoglycemic drugs. After treatment, urine ketone body turned negative, pH value increased to normal range, and random plasma glucose decreased significantly (the median difference of random blood glucose before and after treatment was 21.30 mmol/L, P=0.043) showing that the treatment was effective. During the follow-up, all patients continued to use insulin. The PD-1 or PD-L1 inhibitors were restarted after hyperglycemia remission. The tumor condition was under control. Conclusions ICI-DM mainly occurs in patients who receive treatment with PD-1 or PD-L1 inhibitors usually with acute hyperglycemia whose laboratory tests indicate insulin secretion defects. Some patients had positive islet cell antibodies, glutamic acid decarboxylase antibodies and autoantibodies.Patients with positive autoantibodies needed early diagnosis and continuous insulin treatment. ICI treatment can be restarted after endocrinologists brought the blood glucose under control.

The development of computer maintenance has now become the focus of attention in the education sector, standing in the overall situation of economic, social and educational development, to comprehensively improve the level of computer maintenance education, and teaching quality has become an important measure to meet the new round of technological revolution and industrial change. The traditional teaching model has not been able to adapt to the industry and enterprise demand for job competence, with the development of VR technology computer maintenance training platform. This study uses the NTM-VR model as the theoretical basis and incorporates the data of traditional practical training platform and VR practical training platform into the model for analysis and calculation. The calculation results show that the acceptance of the VR practical training platform by college students is quite high at 67.4%, much higher than 32.6% of the traditional platform. And under the uniform learning intensity, the learning outcome based on the VR computer maintenance practical training platform is 76%, much higher than that based on the traditional computer maintenance practical training platform of 24%.