Multi-Scale Mixed Attention Tea Shoot Instance Segmentation Model

Tea leaf picking is a crucial stage in tea production that directly influences the quality and value of the tea.Traditional tea-picking machines may compromise the quality of the tea leaves.High-quality teas are often handpicked and need more delicate operations in intelligent picking machines.Compared with traditional image processing techniques,deep learning models have stronger feature extraction capabilities,and better generalization and are more suitable for practical tea shoot harvesting.However,current research mostly focuses on shoot detection and cannot directly accomplish end-to-end shoot segmentation tasks.We propose a tea shoot instance segmentation model based on multi-scale mixed attention(Mask2FusionNet)using a dataset from the tea garden in Hangzhou.We further analyzed the characteristics of the tea shoot dataset,where the proportion of small to medium-sized targets is 89.9%.Our algorithm is compared with several mainstream object segmentation algorithms,and the results demonstrate that our model achieves an accuracy of 82%in recognizing the tea shoots,showing a better performance compared to other models.Through ablation experiments,we found that ResNet50,PointRend strategy,and the Feature Pyramid Network(FPN)architecture can improve performance by 1.6%,1.4%,and 2.4%,respectively.These experiments demonstrated that our proposed multi-scale and point selection strategy optimizes the feature extraction capability for overlapping small targets.The results indicate that the proposed Mask2FusionNet model can perform the shoot segmentation in unstructured environments,realizing the individual distinction of tea shoots,and complete extraction of the shoot edge contours with a segmentation accuracy of 82.0%.The research results can provide algorithmic support for the segmentation and intelligent harvesting of premium tea shoots at different scales.

维奈克拉联合去甲基化药物治疗急性髓系白血病的临床研究

目的:探讨维奈克拉联合去甲基化药物在不适合强化诱导化疗的初治急性髓系白血病(acute myeloid leukemia,AML)及复发难治性AML(relapsed/refractory AML,R/R AML)患者中的疗效、预后及安全性。方法:回顾性分析2020年7月至2022年10月于山东大学齐鲁医院收治的87例使用维奈克拉联合去甲基化药物治疗的AML患者,分为初治不适合强化化疗(unfit)组及复发难治组,收集患者临床资料,对两组患者的疗效、生存时间及不良反应进行分析。结果:在疗效评估中初治unfit组中位治疗疗程为3(1~14)个,1个疗程后完全缓解(complete response,CR)率为42.86%,CR/完全缓解伴血液学不完全恢复(CR with incomplete hematologic recovery,CRi)率为77.55%,总反应率(overall response rate,ORR)为83.67%,可检测残留病变(measurable residual disease,MRD)转阴率为34.69%;复发难治组中位治疗疗程为2(1~10)个疗程,1个疗程后CR率为23.68%,CR/CRi率为52.63%,ORR为60.53%,MRD转阴率为31.58%。基因型与疗效的相关分析显示复发难治组中异柠檬酸脱氢酶(isocitrate dehydrogenase,IDH)突变型CR/CRi率及MRD转阴率较IDH野生型更高。在生存分析中初治unfit组中位随访时间为14个月,中位生存时间未达到,1年累计生存率为64.6%;复发难治组中位随访时间为8个月,中位生存时间为9个月,1年累计生存率为46.7%。在安全性评估中血液系统不良反应发生率为100%;非血液系统不良反应发生率为97.7%,2.3%患者出现肿瘤溶解综合征(tumor lysis syndrome,TLS)。结论:维奈克拉联合去甲基化药物在初治unfit的AML及复发难治性AML患者中疗效肯定,几乎所有接受该方案治疗的患者均会出现不良反应,但大多数患者可耐受,治疗过程中需加强对TLS监测。

关于蔬果农药残留现象的实践调研

厦门大学化学化工学院“一点一滴”实践队结合所学专业知识,针对果蔬农药残留现象进行了实践调研。通过对不同背景市民进行的调查访问,了解到他们对农药残留的认识及日常采用的去除办法存在一定疑惑。在大量文献调研的基础上,总结目前农药残留的检测手段,从中筛选并优化适合本次实践活动的测定方法。对部分去除农药残留的方法进行实验检验,根据测定结果给出相应的建议。本次实践活动将所学专业知识运用于实际,培养和提高了学生的实践能力和综合素质。

Detection and Discrimination of Tea Plant Stresses Based on Hyperspectral Imaging Technique at a Canopy Level

Tea plant stresses threaten the quality of tea seriously.The technology corresponding to the fast detection and differentiation of stresses is of great significance for plant protection in tea plantation.In recent years,hyperspectral imaging technology has shown great potential in detecting and differentiating plant diseases,pests and some other stresses at the leaf level.However,the lack of studies at canopy level hampers the detection of tea plant stresses at a larger scale.In this study,based on the canopy-level hyperspectral imaging data,the methods for identifying and differentiating the three commonly occurred tea stresses(i.e.,the tea leafhopper,anthrax and sun burn)were studied.To account for the complexity of the canopy scenario,a stepwise detecting strategy was proposed that includes the process of background removal,identification of damaged areas and discrimination of stresses.Firstly,combining the successive projection algorithm(SPA)spectral analysis and K-means cluster analysis,the background and overexposed non-plant regions were removed from the image.Then,a rigorous sensitivity analysis and optimization were performed on various forms of spectral features,which yielded optimal features for detecting damaged areas(i.e.,YSV,Area,GI,CARI and NBNDVI)and optimal features for stresses discrimination(i.e.,MCARI,CI,LCI,RARS,TCI and VOG).Based on this information,the models for identifying damaged areas and those models for discriminating different stresses were established using K-nearest neighbor(KNN),Random Forest(RF)and Fisher discriminant analysis.The identification model achieved an accuracy over 95%,and the discrimination model achieved an accuracy over 93%for all stresses.The results suggested the feasibility of stress detection and differentiation using canopy-level hyperspectral imaging techniques,and indicated the potential for its extension over large areas.

RNA-seq analysis of Brachypodium distachyon responses to Barley stripe mosaic virus infection

Barley stripe mosaic virus(BSMV) is the type member of the genus Hordeivirus. Brachypodium distachyon line Bd3-1 shows resistance to the BSMV ND18 strain, but is susceptible to an ND18 double mutant(βNDTGB1R390K, T392K) in which lysine is substituted for an arginine at position 390 and for threonine at position 392 of the triple gene block 1(TGB1) protein. In order to understand differences in gene expression following infection with ND18 and double mutant ND18, Bd3-1 seedlings were subjected to RNA-seq analyses at 1, 6, and14 days post inoculation(dpi). The results revealed that basal immunity genes involved in cellulose synthesis and pathogenesis-related protein biosynthesis were enhanced in incompatible interactions between Bd3-1 and ND18. Most of the differentially expressed transcripts are related to trehalose biosynthesis, ethylene, jasmonic acid metabolism,protein phosphorylation, protein ubiquitination, transcriptional regulation, and transport process, as well as pathogenesis-related protein biosynthesis. In compatible interactions between Bd3-1 and ND18 mutant, Bd3-1 developed weak basal resistance responses to the virus. Many genes involved in cellulose biosynthesis, protein amino acid phosphorylation,protein biosynthesis, protein glycosylation, glycolysis and cellular macromolecular complex assembly that may be related to virus replication, assembly and movement were up-regulated. Some genes involved in oxidative stress responses were also up-regulated at14 dpi. BSMV ND18 mutant infection suppressed expression of genes functioning in regulation of transcription, protein kinase, cellular nitrogen compound biosynthetic process and photosynthesis. Differential expression patterns between compatible and incompatible interactions in Bd3-1 to the two BSMV strains provide important clues for understanding mechanism of resistance to BMSV in the model plant Brachypodium.

Boosting faradaic efficiency of CO_(2)electroreduction to CO for Fe-NC single-site catalysts by stabilizing Fe^(3+)sites via F-doping

The atomically dispersed Fe^(3+)sites of Fe-N-C single-site catalysts(SSCs)are demonstrated as the active sites for CO_(2)electroreduction(CO_(2)RR)to CO but suffer from the reduction to Fe^(2+)at~−0.5 V,accompanied by the drop of CO faradaic efficiency(FECO)and deterioration of partial current(JCO).Herein,we report the construction of F-doped Fe-N-C SSCs and the electron-withdrawing character of fluorine could stabilize Fe3+sites,which promotes the FECO from the volcano-like highest value(88.2%@−0.40 V)to the high plateau(>88.5%@−0.40-−0.60 V),with a much-increased JCO(from 3.24 to 11.23 mA·cm^(−2)).The enhancement is ascribed to the thermodynamically facilitated CO_(2)RR and suppressed competing hydrogen evolution reaction,as well as the kinetically increased electroactive surface area and improved charge transfer,due to the stabilized Fe^(3+)sites and enriched defects by fluorine doping.This finding provides an efficient strategy to enhance the CO_(2)RR performance of Fe-N-C SSCs by stabilizing Fe^(3+).

TiO_(2)@palygorskite composite for the efficient remediation of oil spills via a dispersion-photodegradation synergy

Removing spilled oil from the water surface is critically important given that oil spill accidents are a common occurrence.In this study,TiO_(2)@Palygorskite composite prepared by a simple coprecipitation method was used for oil spill remediation via a dispersion-photodegradation synergy.Diesel could be efficiently dispersed into small oil droplets by TiO_(2)@Palygorskite.These dispersed droplets had an average diameter of 20-30µm and exhibited good time stability.The tight adsorption of TiO_(2)@Palygorskite on the surface of the droplets was observed in fluorescence and SEM images.As a particulate dispersant,the direct contact of TiO_(2)@Palygorskite with oil pollutants effectively enhanced the photodegradation efficiency of TiO_(2)for oil.During the photodegradation process,·O_(2)^(−)and•OH were detected by ESR and radical trapping experiments.The photodegradation efficiency of diesel by TiO_(2)@Palygorskite was enhanced by about 5 times compared with pure TiO_(2)under simulated sunlight irradiation.The establishment of this new dispersion-photodegradation synergistic remediation system provides a new direction for the development of marine oil spill remediation.