An Ensemble Learning Model for Detecting Soybean Seedling Emergence in UAV Imagery.

Efficient detection and evaluation of soybean seedling emergence is an important measure for making field management decisions. However, there are many indicators related to emergence, and using multiple models to detect them separately makes data processing too slow to aid timely field management. In this study, we aimed to integrate several deep learning and image processing methods to build a model to evaluate multiple soybean seedling emergence information. An unmanned aerial vehicle (UAV) was used to acquire soybean seedling RGB images at emergence (VE), cotyledon (VC), and first node (V1) stages. The number of soybean seedlings that emerged was obtained by the seedling emergence detection module, and image datasets were constructed using the seedling automatic cutting module. The improved AlexNet was used as the backbone network of the growth stage discrimination module. The above modules were combined to calculate the emergence proportion in each stage and determine soybean seedlings emergence uniformity. The results show that the seedling emergence detection module was able to identify the number of soybean seedlings with an average accuracy of 99.92%, a R2 of 0.9784, a RMSE of 6.07, and a MAE of 5.60. The improved AlexNet was more lightweight, training time was reduced, the average accuracy was 99.07%, and the average loss was 0.0355. The model was validated in the field, and the error between predicted and real emergence proportions was up to 0.0775 and down to 0.0060. It provides an effective ensemble learning model for the detection and evaluation of soybean seedling emergence, which can provide a theoretical basis for making decisions on soybean field management and precision operations and has the potential to evaluate other crops emergence information.

Circular RNA circMMP1 Contributes to the Progression of Glioma Through Regulating TGIF2 Expression by Sponging miR-195-5p.

Glioma is characterized by high morbidity and mortality worldwide. Circular RNA (circRNA) matrix metallopeptidase 1 (circMMP1, hsa_circ_0024108) was reported to be increased in glioma. This study is designed to explore the role and mechanism of circMMP1 in glioma progression. CircMMP1, linear MMP1, microRNA-195-5p (miR-195-5p), and transforming growth factor-beta-induced 2 (TGIF2) level were detected by real-time quantitative polymerase chain reaction (RT-qPCR). The protein levels of TGIF2, Beclin1, and p62 were examined by Western blot assay. Colony number, migration, invasion, and apoptosis were detected by Colony formation, transwell, and flow cytometry assays, severally. The binding relationship between miR-195-5p and circMMP1 or TGIF2 was predicted by starbase or Targetscan and then verified by a dual-luciferase reporter and RNA Immunoprecipitation (RIP) assays. The biological role of circMMP1 on glioma cell growth was examined by the xenograft tumor model in vivo. CircMMP1 and TGIF2 expression were upregulated, and miR-195-5p expression was downregulated in glioma tissues and cells. And the knockdown of circMMP1 could block colony formation, migration, and invasion and expedite apoptosis and autophagy in glioma cells. The mechanical analysis discovered that circMMP1 acted as a sponge of miR-195-5p to regulate TGIF2 expression. CircMMP1 knockdown suppressed cell growth of glioma in vivo. CircMMP1 boosted glioma progression partly by targeting the miR-195-5p/TGIF2 axis, suggesting a promising circRNA-targeted therapy for glioma treatment.

Determinants of quality of life in people with epilepsy and their gender differences.

Improving the patient's quality of life (QOL) is the most important goal of epilepsy management. We performed this study to determine the factors associated with QOL in people with epilepsy and to assess whether there are gender differences in these determinants. Patients were interviewed using the Quality of Life in Epilepsy Inventory-31(QOLIE-31), the Adverse Event Profile (AEP), the Self-Rating Anxiety Scale (SAS), and the Hamilton Depression Rating Scale (HAMD). Two hundred forty-seven patients (152 men, 95 women) were included in the analysis. Among all patients, regressive analyses showed that AEP score was the strongest predictor of the QOLIE-31 overall score, accounting for 10.4% of the variance. The next strongest predictors were the number of currently used antiepileptic drugs (AEDs) (3.6%), the HAMD score (2.5%), and the SAS score (1.2%). Importantly, there were gender differences in these predictors of QOL. The strongest predictors of the QOLIE-31 overall score in women were the AEP score and the number of AEDs. In contrast, the strongest predictors in men were the SAS score, the AEP score and the frequency of seizures. These results indicate that perceived adverse effects of treatments and number of AEDs exerted greater effects on QOL in women, whereas anxiety and seizure-related variables had a stronger impact on QOL among men. Accordingly, it may be necessary to individualize interventions to improve the QOL of people with epilepsy.

[Factors associated with quality of life in epileptics and the variations between men and women, younger and older people].

OBJECTIVE: To determine factors associated with quality of life (QOL) in epileptics and the variations between men and women, younger and older people. METHODS: A total of 204 patients (160 younger, 49 older; 125 men, 79 women) were interviewed by the quality of life in epilepsy-31 (QOLIE-31), side effect profile (SEP), self-rating anxiety scale (SAS) and Hamilton depression scale (HAMD). Medical and socio-demographic data were acquired from patient records. Multivariate linear regressive analyses were used to determine the set of best predictors of composite QOLIE-31 score. RESULTS: No statistical difference was revealed in QOLIE-31 overall score either between younger and older patients or between men and women. Among all patients, regressive analyses revealed that SEP (beta = - 0.395, P = 0.000) and SAS (beta = -0.152, P = 0.016) were two strong predictors of QOLIE-31 overall score. Grouped by gender, among men, epilepsy duration (beta = -0.165, P = 0.028) and seizure frequency (beta = -0.284, P = 0.001) respectively associated with QOLIE-31 overall score and "social function" score while the number of AEDs (antiepileptic drugs) substantially correlated with QOLIE-31 overall score among women (beta= -0.238, P = 0.006). Grouped by ages, seizure frequency (beta = -0.284, P = 0.000) and education level (beta = 0.203, P = 0.005) predicted QOLIE-31 "social function" score only among younger patients; among older patients, a significant association were found between the number of AEDs and QOLIE-31 overall score (beta = - 0.363, P = 0.004). CONCLUSION: Side effects of AEDs and number of AEDs exert greater effect on QOL in women and older patients. And such seizure-related variables as epileptic duration and seizure frequency influence QOL only among men and younger patients.