Search

Green plums have produced significant economic benefits because of their nutritional and medicinal value. However, green plums are affected by factors such as plant diseases and insect pests during their growth, picking, transportation, and storage, which seriously affect the quality of green plums and their products, reducing their economic and nutritional value. At present, in the detection of green plum defects, some researchers have applied deep learning to identify their surface defects. However, the recognition rate is not high, the types of defects identified are singular, and the classification of green plum defects is not detailed enough. In the actual production process, green plums often have more than one defect, and the existing detection methods ignore minor defects. Therefore, this study used the vision transformer network model to identify all defects on the surfaces of green plums. The dataset was classified into multiple defects based on the four types of defects in green plums (scars, flaws, rain spots, and rot) and one type of feature (stem). After the permutation and combination of these defects, a total of 18 categories were obtained after the screening, combined with the actual situation. Based on the VIT model, a fine-grained defect detection link was added to the network for the analysis layer of the major defect hazard level and the detection of secondary defects. The improved network model has an average recognition accuracy rate of 96.21% for multiple defect detection of green plums, which is better than that of the VGG16 network, the Desnet121 network, the Resnet18 network, and the WideResNet50 network. [ABSTRACT FROM AUTHOR]

Summary For autoimmune disease (AD) and autoinflammatory disease (AID)‐related haemophagocytic lymphohistiocytosis (HLH) (AD/AID‐HLH), there is still a lack of standardized treatment. Glucocorticoids (GCs) are the main treatment currently; however, 37.9% to 61% of patients fail to achieve effective control of HLH, making it urgent to find novel treatment strategies. We conducted a retrospective, single‐centre study examining ruxolitinib (RUX)‐based regimen in children with AD/AID‐HLH. Patients were first treated with RUX monotherapy, and additional treatments including methylprednisolone and etoposide were added sequentially when the disease could not be controlled. The study included 26 patients with a median follow‐up of 23.9 months, of whom 15 had prior treatments. The overall response rate at week 8 with the RUX‐based regimen was 96.2%, with 92.3% attaining complete response (CR) and 3.9% attaining partial response. The 2‐year overall survival rate was 96.2% (95% CI, 80.4% to 99.9%). During RUX monotherapy, 46.1% of patients achieved CR as the best response, with a median first response time to RUX of 2 days. Additionally, 53.8% of patients required additional GCs and 23.1% required etoposide chemotherapy. All observed adverse events were manageable and acceptable. Overall, our study supports the efficacy and safety of the RUX‐based regimen in children with AD/AID‐HLH. [ABSTRACT FROM AUTHOR]

Primary hemophagocytic lymphohistiocytosis (pHLH) is a rare immune disorder and hematopoietic stem cell transplan- tation (HSCT) is the only potentially curative treatment. Given the high pre-HSCT mortality of pHLH patients reported in the HLH-2004 study (17%), more regimens to effectively control the disease and form a bridge with HSCT are needed. We conducted a retrospective study of pHLH children treated by ruxolitinib (RUX)-based regimen. Generally, patients received RUX until HSCT or unacceptable toxic side-effect. Methylprednisolone and etoposide were added sequentially when the disease was suboptimally controlled. The primary end point was 1-year overall survival. Twenty-one pHLH patients (12 previously treated and 9 previously untreated) were included with a median follow-up of 1.4 years. At last follow-up, 17 (81.0%) patients were alive with a 1-year overall survival of 90.5% (95% confidence interval: 84.1-96.9). Within the first 8 weeks, all patients had an objective response, of which 19 (90.5%) achieved complete response (CR) and two (9.5%) achieved partial response (PR) as a best response. Seventeen (81.0%) patients received HSCT, of which 13 (76.5%) had CR, three (17.6%) had PR and one (5.9%) had disease reactivation at the time of HSCT. Fifteen (88.2) patients were alive post- HSCT. Notably, eight (38.1%) patients received zero doses of etoposide, suggesting the potential of RUX-based regimen to reduce chemotherapy intensity. Patients tolerated RUX-based regimen well and the most frequently observed adverse events were hematologic adverse events. Overall, RUX-based regimen was effective and safe and could be used as a bridge to HSCT for pHLH children.