基于MobileNetV3Small-ECA的水稻病害轻量级识别研究

为实现水稻病害的轻量化识别与检测,使用ECA注意力机制改进MobileNetV3Small模型,并使用共享参数迁移学习对水稻病害进行智能化轻量级识别和检测。在PlantVillage数据集上进行预训练,将预训练得到的共享参数迁移到对水稻病害识别模型上微调优化。在开源水稻病害数据集上进行试验测试,试验结果表明,在非迁移学习下,识别准确率达到97.47%,在迁移学习下识别准确率达到99.92%,同时参数量减少26.69%。其次,通过Grad-CAM进行可视化,本文方法与其他注意力机制CBAM和SENET相比,ECA模块生成的结果与图像中病斑的位置和颜色更加一致,表明网络可以更好地聚焦水稻病害的特征,并且通过可视化和各水稻病害分析了误分类原因。本文方法实现了水稻病害识别模型的轻量化,使其能够在移动设备等资源受限的场景中部署,达到快速、高效、便携的目的。同时开发了基于Android的水稻病害识别系统,方便于在边缘端进行水稻病害识别分析。

Small nucleolar RNA and its potential role in the oncogenesis and development of colorectal cancer

Small nucleolar RNAs(snoRNAs)represent a class of non-coding RNAs that play pivotal roles in post-transcriptional RNA processing and modification,thereby contributing significantly to the maintenance of cellular functions related to protein synthesis.SnoRNAs have been discovered to possess the ability to influence cell fate and alter disease progression,holding immense potential in controlling human diseases.It is suggested that the dysregulation of snoRNAs in cancer exhibits differential expression across various cancer types,stages,metastasis,treatment response and/or prognosis in patients.On the other hand,colorectal cancer(CRC),a prevalent malignancy of the digestive system,is characterized by high incidence and mortality rates,ranking as the third most common cancer type.Recent research indicates that snoRNA dysregulation is associated with CRC,as snoRNA expression significantly differs between normal and cancerous conditions.Consequently,assessing snoRNA expression level and function holds promise for the prognosis and diagnosis of CRC.Nevertheless,current comprehension of the potential roles of snoRNAs in CRC remains limited.This review offers a comprehensive survey of the aberrant regulation of snoRNAs in CRC,providing valuable insights into the discovery of novel biomarkers,therapeutic targets,and potential tools for the diagnosis and treatment of CRC and furnishing critical cues for advancing research into CRC and the judicious selection of therapeutic targets.

Development of small molecule drugs targeting immune checkpoints

Immune checkpoint inhibitors(ICIs)are used to relieve and refuel anti-tumor immunity by blocking the interaction,transcription,and translation of co-inhibitory immune checkpoints or degrading co-inhibitory immune checkpoints.Thousands of small molecule drugs or biological materials,especially antibody-based ICIs,are actively being studied and antibodies are currently widely used.Limitations,such as anti-tumor efficacy,poor membrane permeability,and unneglected tolerance issues of antibody-based ICIs,remain evident but are thought to be overcome by small molecule drugs.Recent structural studies have broadened the scope of candidate immune checkpoint molecules,as well as innovative chemical inhibitors.By way of comparison,small molecule drug-based ICIs represent superior oral bioavailability and favorable pharmacokinetic features.Several ongoing clinical trials are exploring the synergetic effect of ICIs and other therapeutic strategies based on multiple ICI functions,including immune regulation,anti-angiogenesis,and cell cycle regulation.In this review we summarized the current progression of small molecule ICIs and the mechanism underlying immune checkpoint proteins,which will lay the foundation for further exploration.

Blood-brain barrier pathology in cerebral small vessel disease

Cerebral small vessel disease is a neurological disease that affects the brain microvasculature and which is commonly observed among the elderly.Although at first it was considered innocuous,small vessel disease is nowadays regarded as one of the major vascular causes of dementia.Radiological signs of small vessel disease include small subcortical infarcts,white matter magnetic resonance imaging hyperintensities,lacunes,enlarged perivascular spaces,cerebral microbleeds,and brain atrophy;however,great heterogeneity in clinical symptoms is observed in small vessel disease patients.The pathophysiology of these lesions has been linked to multiple processes,such as hypoperfusion,defective cerebrovascular reactivity,and blood-brain barrier dysfunction.Notably,studies on small vessel disease suggest that blood-brain barrier dysfunction is among the earliest mechanisms in small vessel disease and might contribute to the development of the hallmarks of small vessel disease.Therefore,the purpose of this review is to provide a new foundation in the study of small vessel disease pathology.First,we discuss the main structural domains and functions of the blood-brain barrier.Secondly,we review the most recent evidence on blood-brain barrier dysfunction linked to small vessel disease.Finally,we conclude with a discussion on future perspectives and propose potential treatment targets and interventions.

Cognitive impairment in cerebral small vessel disease induced by hypertension

Hypertension is a primary risk factor for the progression of cognitive impairment caused by cerebral small vessel disease,the most common cerebrovascular disease.Howeve r,the causal relationship between hypertension and cerebral small vessel disease remains unclear.Hypertension has substantial negative impacts on brain health and is recognized as a risk factor for cerebrovascular disease.Chronic hypertension and lifestyle factors are associated with risks for stro ke and dementia,and cerebral small vessel disease can cause dementia and stroke.Hypertension is the main driver of cerebral small vessel disease,which changes the structure and function of cerebral vessels via various mechanisms and leads to lacunar infarction,leukoaraiosis,white matter lesions,and intracerebral hemorrhage,ultimately res ulting in cognitive decline and demonstrating that the brain is the to rget organ of hypertension.This review updates our understanding of the pathogenesis of hypertensioninduced cerebral small vessel disease and the res ulting changes in brain structure and function and declines in cognitive ability.We also discuss drugs to treat cerebral small vessel disease and cognitive impairment.

Two-Layer Attention Feature Pyramid Network for Small Object Detection

Effective small object detection is crucial in various applications including urban intelligent transportation and pedestrian detection.However,small objects are difficult to detect accurately because they contain less information.Many current methods,particularly those based on Feature Pyramid Network(FPN),address this challenge by leveraging multi-scale feature fusion.However,existing FPN-based methods often suffer from inadequate feature fusion due to varying resolutions across different layers,leading to suboptimal small object detection.To address this problem,we propose the Two-layerAttention Feature Pyramid Network(TA-FPN),featuring two key modules:the Two-layer Attention Module(TAM)and the Small Object Detail Enhancement Module(SODEM).TAM uses the attention module to make the network more focused on the semantic information of the object and fuse it to the lower layer,so that each layer contains similar semantic information,to alleviate the problem of small object information being submerged due to semantic gaps between different layers.At the same time,SODEM is introduced to strengthen the local features of the object,suppress background noise,enhance the information details of the small object,and fuse the enhanced features to other feature layers to ensure that each layer is rich in small object information,to improve small object detection accuracy.Our extensive experiments on challenging datasets such as Microsoft Common Objects inContext(MSCOCO)and Pattern Analysis Statistical Modelling and Computational Learning,Visual Object Classes(PASCAL VOC)demonstrate the validity of the proposedmethod.Experimental results show a significant improvement in small object detection accuracy compared to state-of-theart detectors.

Contract Mechanism of Water Environment Regulation for Small and Medium Sized Enterprises Based on Optimal Control Theory

The small and scattered enterprise pattern in the county economy has formed numerous sporadic pollution sources, hindering the centralized treatment of the water environment, increasing the cost and difficulty of treatment. How enterprises can make reasonable decisions on their water environment behavior based on the external environment and their own factors is of great significance for scientifically and effectively designing water environment regulation mechanisms. Based on optimal control theory, this study investigates the design of contractual mechanisms for water environmental regulation for small and medium-sized enterprises. The enterprise is regarded as an independent economic entity that can adopt optimal control strategies to maximize its own interests. Based on the participation of multiple subjects including the government, enterprises, and the public, an optimal control strategy model for enterprises under contractual water environmental regulation is constructed using optimal control theory, and a method for calculating the amount of unit pollutant penalties is derived. The water pollutant treatment cost data of a paper company is selected to conduct empirical numerical analysis on the model. The results show that the increase in the probability of government regulation and public participation, as well as the decrease in local government protection for enterprises, can achieve the same regulatory effect while reducing the number of administrative penalties per unit. Finally, the implementation process of contractual water environmental regulation for small and medium-sized enterprises is designed.

H-and J-aggregation of conjugated small molecules in organic solar cells

As H-and J-aggregation receive more and more attention in the research of organic solar cells(OSCs),especially in small molecular systems,deep understanding of aggregation behavior is needed to guide the design of conjugated small molecular structure and the fabrication process of OSC device.For this end,this review is written.Here,the review firstly introduced the basic information about H-and J-aggregation of conjugated small molecules in OSCs.Then,the characteristics of H-and J-aggregation and the methods to identify them were summarized.Next,it reviewed the research progress of H-and J-aggregation of conjugated small molecules in OSCs,including the factors influencing H-and J-aggregation in thin film and the effects of H-and J-aggregation on OPV performance.

Stage Ⅳ non-small cell lung cancer with multiple metastases to the small intestine leading to intussusception: A case report

BACKGROUND Gastrointestinal tract metastasis from lung cancer is rare and compared to small cell lung cancer(SCLC),non-SCLC(NSCLC)is even less likely to metastasize in this manner.Additionally,small intestinal tumors can also present with diverse complications,some of which require urgent intervention.CASE SUMMARY In this report,we detail a unique case of stage IV lung cancer,where the presence of small intestine tumors led to intussusception.Subsequent to a small intestine resection,pathology confirmed that all three tumors within the small intestine were metastases from adenocarcinoma of the lung.The postoperative follow-up period extended beyond 14 mo.CONCLUSION In patients with stage IV NSCLC,local tumor control can be achieved with various treatments.However,if small intestinal metastasis occurs,surgical intervention remains necessary,as it may improve survival.

Socio-environmental factors associated with small mammal assemblage and Leptospira prevalence in Suburban Areas of Terengganu,Malaysia

Objective:To examine the socio-environmental factors associated with the assemblage of small mammals and the prevalence of Leptospira pathogen in poor suburban communities of Terengganu,Malaysia.Methods:We trapped small mammals from 119 trapping points scattered around three suburban communities of Terengganu using sausage-baited live traps.On the average,we set up five traps for three nights at each sampling point during the trapping period.Kidneys of captured animals were harvested and processed for Leptospira investigation.Additionally,environmental survey was conducted at each trapping point to obtain information about possible variables supporting small mammal assemblage.We used a generalized linear model to evaluate the effect of different socio-environmental variables on small mammals’assemblage.Results:A total of 89 small mammals,specifically,Rattus norvegicus(n=39),Rattus rattus(n=27),Rattus exulans(n=10),Suncus murinus(n=11),and Tupaia glis(n=2)were captured from 1385 trap nights.Fourteen individuals(15.7%)of the captured animals tested positive for Leptospira bacteria using PCR detection.Results of our generalized linear model showed only residences bordering vacant lots as the variable positively associated with small mammal occurrence in the three study sites.Conclusions:Small mammal community,especially the often neglected species,could harbour and potentially contribute towards pathogenic Leptospira maintenance in the study sites.To adequately control small mammals’population and subsequent human zoonoses transmission,it is critical to advocate and promote appropriate infrastructure and suburban services,together with good hygiene practices that can reduce the animals’access to food and harborage.

Enhancing Dense Small Object Detection in UAV Images Based on Hybrid Transformer

Transformer-based models have facilitated significant advances in object detection.However,their extensive computational consumption and suboptimal detection of dense small objects curtail their applicability in unmanned aerial vehicle(UAV)imagery.Addressing these limitations,we propose a hybrid transformer-based detector,H-DETR,and enhance it for dense small objects,leading to an accurate and efficient model.Firstly,we introduce a hybrid transformer encoder,which integrates a convolutional neural network-based cross-scale fusion module with the original encoder to handle multi-scale feature sequences more efficiently.Furthermore,we propose two novel strategies to enhance detection performance without incurring additional inference computation.Query filter is designed to cope with the dense clustering inherent in drone-captured images by counteracting similar queries with a training-aware non-maximum suppression.Adversarial denoising learning is a novel enhancement method inspired by adversarial learning,which improves the detection of numerous small targets by counteracting the effects of artificial spatial and semantic noise.Extensive experiments on the VisDrone and UAVDT datasets substantiate the effectiveness of our approach,achieving a significant improvement in accuracy with a reduction in computational complexity.Our method achieves 31.9%and 21.1%AP on the VisDrone and UAVDT datasets,respectively,and has a faster inference speed,making it a competitive model in UAV image object detection.

THE EXISTENCE OF PSEUDOHARMONIC MAPS FOR SMALL HORIZONTAL ENERGY

In this paper,we consider pseudoharmonic heat flow with small initial horizontal energy and give the existence of pseudoharmonic maps from closed pseudo-Hermitian manifolds into closed Riemannian manifolds.

Ten-year observation of corneal densitometry and associated factors following small incision lenticule extraction

●AIM:To investigate the long-term changes of corneal densitometry(CD)and its contributing elements after small incision lenticule extraction(SMILE).●METHODS:Totally 31 eyes of 31 patients with mean spherical equivalent of-6.46±1.50 D and mean age 28.23±7.38y were enrolled.Full-scale examinations were conducted on all patients preoperatively and during followup.Visual acuity,manifest refraction,axial length,corneal thickness,corneal higher-order aberrations,and CD were evaluated.●RESULTS:All surgeries were completed successfully without complications or adverse events.Ten-year safety index was 1.17±0.20 and efficacy 1.04±0.28.CD value of 0–6 mm zones in central layer was statistically significantly lower 10y postoperatively,compared with preoperative values(0–2 mmΔ=-1.62,2–6 mmΔ=-1.24,P<0.01).There were no correlations between CD values and factors evaluated.●CONCLUSION:SMILE is a safe and efficient procedure for myopia on a long-term basis.CD values get lower 10y postoperatively,whose mechanism is to be further discussed.

Artificial intelligence in detection of small bowel lesions and their bleeding risk:A new step forward

The present letter to the editor is related to the study with the title“Automatic detection of small bowel(SB)lesions with different bleeding risk based on deep learning models”.Capsule endoscopy(CE)is the main tool to assess SB diseases but it is a time-consuming procedure with a significant error rate.The development of artificial intelligence(AI)in CE could simplify physicians’tasks.The novel deep learning model by Zhang et al seems to be able to identify various SB lesions and their bleeding risk,and it could pave the way to next perspective studies to better enhance the diagnostic support of AI in the detection of different types of SB lesions in clinical practice.

Clinicopathological analysis of small intestinal metastasis from extra-abdominal/extra-pelvic malignancy

BACKGROUND The metastatic tumors in the small intestine secondary to extra-abdominal/extrapelvic malignancy are extremely rare.However,the small intestine metastases are extremely prone to misdiagnosis and missed diagnosis due to the lack of specific clinical manifestations and examination methods,thus delaying its treatment.Therefore,in order to improve clinical diagnosis and treatment capabilities,it is necessary to summarize its clinical pathological characteristics and prognosis.AIM To summarize the clinicopathological characteristics of patients with small intestinal metastases from extra-abdominal/extra-pelvic malignancy,and to improve the clinical capability of diagnosis and treatment for rare metastatic tumors in the small intestine.METHODS The clinical data of patients with small intestinal metastases from extra-abdominal/extra-pelvic malignancy were retrieved and summarized,who admitted to and treated in the Air Force Medical Center,Chinese People’s Liberation Army.Then descriptive statistics were performed on the general conditions,primary tumors,secondary tumors in the small intestine,diagnosis and treatment processes,and prognosis.RESULTS Totally 11 patients(9 males and 2 females)were enrolled in this study,including 8 cases(72.3%)of primary lung cancer,1 case(9.1%)of malignant lymphoma of the thyroid,1 case(9.1%)of cutaneous malignant melanoma,and 1 case(9.1%)of testicular cancer.The median age at the diagnosis of primary tumors was 57.9 years old,the median age at the diagnosis of metastatic tumors in the small intestine was 58.81 years old,and the average duration from initial diagnosis of primary tumors to definite diagnosis of small intestinal metastases was 9 months(0-36 months).Moreover,small intestinal metastases was identified at the diagnosis of primary tumors in 4 cases.The small intestinal metastases were distributed in the jejunum and ileum,with such clinical manifestations as hematochezia(5,45.4%)and abdominal pain,vomiting and other obstruction(4,36.4%).In addition,2 patients had no obvious symptoms at the diagnosis of small intestinal metastases,and 5 patients underwent radical resection of small intestinal malignancies and recovered well after surgery.A total of 3 patients did not receive subsequent treatment due to advanced conditions.CONCLUSION Small intestinal metastases of extra-abdominal/extra-pelvic malignancy is rare with high malignancy and great difficulty in diagnosis and treatment.Clinically,patients with extra-abdominal/extra-pelvic malignancy should be alert to the occurrence of this disease,and their prognosis may be improved through active surgery combined with standard targeted therapy.

MSC-YOLO:Improved YOLOv7 Based on Multi-Scale Spatial Context for Small Object Detection in UAV-View

Accurately identifying small objects in high-resolution aerial images presents a complex and crucial task in thefield of small object detection on unmanned aerial vehicles(UAVs).This task is challenging due to variations inUAV flight altitude,differences in object scales,as well as factors like flight speed and motion blur.To enhancethe detection efficacy of small targets in drone aerial imagery,we propose an enhanced You Only Look Onceversion 7(YOLOv7)algorithm based on multi-scale spatial context.We build the MSC-YOLO model,whichincorporates an additional prediction head,denoted as P2,to improve adaptability for small objects.We replaceconventional downsampling with a Spatial-to-Depth Convolutional Combination(CSPDC)module to mitigatethe loss of intricate feature details related to small objects.Furthermore,we propose a Spatial Context Pyramidwith Multi-Scale Attention(SCPMA)module,which captures spatial and channel-dependent features of smalltargets acrossmultiple scales.This module enhances the perception of spatial contextual features and the utilizationof multiscale feature information.On the Visdrone2023 and UAVDT datasets,MSC-YOLO achieves remarkableresults,outperforming the baseline method YOLOv7 by 3.0%in terms ofmean average precision(mAP).The MSCYOLOalgorithm proposed in this paper has demonstrated satisfactory performance in detecting small targets inUAV aerial photography,providing strong support for practical applications.

A Real-Time Small Target Vehicle Detection Algorithm with an Improved YOLOv5m Network Model

To address the challenges of high complexity,poor real-time performance,and low detection rates for small target vehicles in existing vehicle object detection algorithms,this paper proposes a real-time lightweight architecture based on You Only Look Once(YOLO)v5m.Firstly,a lightweight upsampling operator called Content-Aware Reassembly of Features(CARAFE)is introduced in the feature fusion layer of the network to maximize the extraction of deep-level features for small target vehicles,reducing the missed detection rate and false detection rate.Secondly,a new prediction layer for tiny targets is added,and the feature fusion network is redesigned to enhance the detection capability for small targets.Finally,this paper applies L1 regularization to train the improved network,followed by pruning and fine-tuning operations to remove redundant channels,reducing computational and parameter complexity and enhancing the detection efficiency of the network.Training is conducted on the VisDrone2019-DET dataset.The experimental results show that the proposed algorithmreduces parameters and computation by 63.8% and 65.8%,respectively.The average detection accuracy improves by 5.15%,and the detection speed reaches 47 images per second,satisfying real-time requirements.Compared with existing approaches,including YOLOv5m and classical vehicle detection algorithms,our method achieves higher accuracy and faster speed for real-time detection of small target vehicles in edge computing.

Responses of Nutrients to the Precipitation Variation and Land Use in Subtropical Monsoonal Small Mountainous Rivers:A Case Study of Baixi Watershed

Small mountainous rivers are characterized by large instantaneous fluxes and susceptible to extreme weather events,which can rapidly transport materials into the sea and have a significant impact on the ecological environment of estuaries and bays.In order to investigate the seasonal characteristics of nutrients in small mountainous rivers in the subtropical monsoon region and the output pattern to the sea during heavy precipitation,surveys on the mountainous rivers were carried out in Baixi watershed in August 2020(wet season),March 2021(dry season)and June 2021(Meiyu period).The results showed that the dissolved inorganic nitrogen(DIN)of the rivers has an average concentration of 752μg L^(−1)in the wet season and 1472μg L^(−1)in the dry season.The concentrations of dissolved inorganic phosphorus(DIP)in wet season and dry season were 63μg L^(−1)and 51μg L^(−1),respectively.Influenced by the changes of land use in sub-watersheds,DIN concentrations in the mainstream increased from 701μg L^(−1)in the upper reaches to 1284μg L^(−1)in the middle reaches.Two rainstorms during the Meiyu period in the watershed caused the pulse runoff in the river.The maximum daily runoff reached 70 times that before rains.The maximum daily fluxes of DIN and DIP were 109 and 247 times that before rains,respectively.In view that the watershed experienced several rainstorms in the wet season,the river,with pulse runoff,carries a large amount of nutrients into the sea in a short time,which will have a significant impact on the environment of Sanmen bay and its adjacent sea.

A Simple and Effective Surface Defect Detection Method of Power Line Insulators for Difficult Small Objects

Insulator defect detection plays a vital role in maintaining the secure operation of power systems.To address the issues of the difficulty of detecting small objects and missing objects due to the small scale,variable scale,and fuzzy edge morphology of insulator defects,we construct an insulator dataset with 1600 samples containing flashovers and breakages.Then a simple and effective surface defect detection method of power line insulators for difficult small objects is proposed.Firstly,a high-resolution featuremap is introduced and a small object prediction layer is added so that the model can detect tiny objects.Secondly,a simplified adaptive spatial feature fusion(SASFF)module is introduced to perform cross-scale spatial fusion to improve adaptability to variable multi-scale features.Finally,we propose an enhanced deformable attention mechanism(EDAM)module.By integrating a gating activation function,the model is further inspired to learn a small number of critical sampling points near reference points.And the module can improve the perception of object morphology.The experimental results indicate that concerning the dataset of flashover and breakage defects,this method improves the performance of YOLOv5,YOLOv7,and YOLOv8.In practical application,it can simply and effectively improve the precision of power line insulator defect detection and reduce missing detection for difficult small objects.

CAW-YOLO:Cross-Layer Fusion and Weighted Receptive Field-Based YOLO for Small Object Detection in Remote Sensing

In recent years,there has been extensive research on object detection methods applied to optical remote sensing images utilizing convolutional neural networks.Despite these efforts,the detection of small objects in remote sensing remains a formidable challenge.The deep network structure will bring about the loss of object features,resulting in the loss of object features and the near elimination of some subtle features associated with small objects in deep layers.Additionally,the features of small objects are susceptible to interference from background features contained within the image,leading to a decline in detection accuracy.Moreover,the sensitivity of small objects to the bounding box perturbation further increases the detection difficulty.In this paper,we introduce a novel approach,Cross-Layer Fusion and Weighted Receptive Field-based YOLO(CAW-YOLO),specifically designed for small object detection in remote sensing.To address feature loss in deep layers,we have devised a cross-layer attention fusion module.Background noise is effectively filtered through the incorporation of Bi-Level Routing Attention(BRA).To enhance the model’s capacity to perceive multi-scale objects,particularly small-scale objects,we introduce a weightedmulti-receptive field atrous spatial pyramid poolingmodule.Furthermore,wemitigate the sensitivity arising from bounding box perturbation by incorporating the joint Normalized Wasserstein Distance(NWD)and Efficient Intersection over Union(EIoU)losses.The efficacy of the proposedmodel in detecting small objects in remote sensing has been validated through experiments conducted on three publicly available datasets.The experimental results unequivocally demonstrate the model’s pronounced advantages in small object detection for remote sensing,surpassing the performance of current mainstream models.