In the context of rural revitalization and the development of smart agriculture, image classification technology based on deep learning has emerged as a crucial tool for digital monitoring and intelligent prevention a...In the context of rural revitalization and the development of smart agriculture, image classification technology based on deep learning has emerged as a crucial tool for digital monitoring and intelligent prevention and control of agricultural diseases. This paper provides a systematic review of the evolutionary development of algorithms within this field. Addressing challenges such as domain drift and limited global awareness in classical convolutional neural networks (CNNs) applied to complex agricultural environments, the paper focuses on the latest advancements in vision transformers (ViT) and their hybrid architectures to enhance cross-domain robustness and fine-grained recognition capabilities. In response to the challenges posed by scarce long-tail data and limited edge computing power in real-world scenarios, the paper explores solutions related to few-shot learning and ultra-lightweight network deployment. Finally, a forward-looking analysis is presented on the application paradigms of multimodal feature fusion, vision-based large models, and explainable artificial intelligence (AI) within smart plant protection. This analysis aims to offer theoretical insights for the development of efficient and transparent intelligent diagnostic systems for agricultural diseases, thereby supporting the advancement of digital agriculture and the construction of a robust agricultural nation.展开更多
Imaging observations of solar X-ray bursts can reveal details of the energy release process and particle acceleration in flares.Most hard X-ray imagers make use of the modulation-based Fourier transform imaging method...Imaging observations of solar X-ray bursts can reveal details of the energy release process and particle acceleration in flares.Most hard X-ray imagers make use of the modulation-based Fourier transform imaging method,an indirect imaging technique that requires algorithms to reconstruct and optimize images.During the last decade,a variety of algorithms have been developed and improved.However,it is difficult to quantitatively evaluate the image quality of different solutions without a true,reference image of observation.How to choose the values of imaging parameters for these algorithms to get the best performance is also an open question.In this study,we present a detailed test of the characteristics of these algorithms,imaging dynamic range and a crucial parameter for the CLEAN method,clean beam width factor(CBWF).We first used SDO/AIA EUV images to compute DEM maps and calculate thermal X-ray maps.Then these realistic sources and several types of simulated sources are used as the ground truth in the imaging simulations for both RHESSI and ASO-S/HXI.The different solutions are evaluated quantitatively by a number of means.The overall results suggest that EM,PIXON,and CLEAN are exceptional methods for sidelobe elimination,producing images with clear source details.Although MEM_GE,MEM_NJIT,VIS_WV and VIS_CS possess fast imaging processes and generate good images,they too possess associated imperfections unique to each method.The two forward fit algorithms,VF and FF,perform differently,and VF appears to be more robust and useful.We also demonstrated the imaging capability of HXI and available HXI algorithms.Furthermore,the effect of CBWF on image quality was investigated,and the optimal settings for both RHESSI and HXI were proposed.展开更多
Multispectral imaging,which simultaneously captures the spatial and spectral information of a scene,is widely used across diverse fields,including remote sensing,biomedical imaging,and agricultural monitoring.We intro...Multispectral imaging,which simultaneously captures the spatial and spectral information of a scene,is widely used across diverse fields,including remote sensing,biomedical imaging,and agricultural monitoring.We introduce a snapshot multispectral imaging approach employing a standard monochrome image sensor with no additional spectral filters or customized components.Our system leverages the inherent chromatic aberration of wavelength-dependent defocusing as a natural source of physical encoding of multispectral information;this encoded image information is rapidly decoded via a deep learning-based multispectral Fourier imager network(mFIN).We experimentally tested our method with six illumination bands and demonstrated an overall accuracy of 98.25%for predicting the illumination channels at the input and achieved a robust multispectral image reconstruction on various test objects.This deep learning-powered framework achieves high-quality multispectral image reconstruction using snapshot image acquisition with a monochrome image sensor and could be useful for applications in biomedicine,industrial quality control,and agriculture,among others.展开更多
Crop leaf area index(LAI)and biomass are two major biophysical parameters to measure crop growth and health condition.Measuring LAI and biomass in field experiments is a destructive method.Therefore,we focused on the ...Crop leaf area index(LAI)and biomass are two major biophysical parameters to measure crop growth and health condition.Measuring LAI and biomass in field experiments is a destructive method.Therefore,we focused on the application of unmanned aerial vehicles(UAVs)in agriculture,which is a cost and labor-efficientmethod.Hence,UAV-captured multispectral images were applied to monitor crop growth,identify plant bio-physical conditions,and so on.In this study,we monitored soybean crops using UAV and field experiments.This experiment was conducted at theMAFES(Mississippi Agricultural and Forestry Experiment Station)Pontotoc Ridge-Flatwoods Branch Experiment Station.It followed a randomized block design with five cover crops:Cereal Rye,Vetch,Wheat,MC:mixed Mustard and Cereal Rye,and native vegetation.Planting was made in the fall,and three fertilizer treatments were applied:Synthetic Fertilizer,Poultry Litter,and none,applied before planting the soybean,in a full factorial combination.We monitored soybean reproductive phases at R3(initial pod development),R5(initial seed development),R6(full seed development),and R7(initial maturity)and used UAV multispectral remote sensing for soybean LAI and biomass estimations.The major goal of this study was to assess LAI and biomass estimations from UAV multispectral images in the reproductive stages when the development of leaves and biomass was stabilized.Wemade about fourteen vegetation indices(VIs)fromUAVmultispectral images at these stages to estimate LAI and biomass.Wemodeled LAI and biomass based on these remotely sensed VIs and ground-truth measurements usingmachine learning methods,including linear regression,Random Forest(RF),and support vector regression(SVR).Thereafter,the models were applied to estimate LAI and biomass.According to the model results,LAI was better estimated at the R6 stage and biomass at the R3 stage.Compared to the other models,the RF models showed better estimation,i.e.,an R^(2) of about 0.58–0.68 with an RMSE(rootmean square error)of 0.52–0.60(m^(2)/m^(2))for the LAI and about 0.44–0.64 for R^(2) and 21–26(g dry weight/5 plants)for RMSE of biomass estimation.We performed a leave-one-out cross-validation.Based on cross-validatedmodels with field experiments,we also found that the R6 stage was the best for estimating LAI,and the R3 stage for estimating crop biomass.The cross-validated RF model showed the estimation ability with an R^(2) about 0.25–0.44 and RMSE of 0.65–0.85(m^(2)/m^(2))for LAI estimation;and R^(2) about 0.1–0.31 and an RMSE of about 28–35(g dry weight/5 plants)for crop biomass estimation.This result will be helpful to promote the use of non-destructive remote sensing methods to determine the crop LAI and biomass status,which may bring more efficient crop production and management.展开更多
Kinship verification is a key biometric recognition task that determines biological relationships based on physical features.Traditional methods predominantly use facial recognition,leveraging established techniques a...Kinship verification is a key biometric recognition task that determines biological relationships based on physical features.Traditional methods predominantly use facial recognition,leveraging established techniques and extensive datasets.However,recent research has highlighted ear recognition as a promising alternative,offering advantages in robustness against variations in facial expressions,aging,and occlusions.Despite its potential,a significant challenge in ear-based kinship verification is the lack of large-scale datasets necessary for training deep learning models effectively.To address this challenge,we introduce the EarKinshipVN dataset,a novel and extensive collection of ear images designed specifically for kinship verification.This dataset consists of 4876 high-resolution color images from 157 multiracial families across different regions,forming 73,220 kinship pairs.EarKinshipVN,a diverse and large-scale dataset,advances kinship verification research using ear features.Furthermore,we propose the Mixer Attention Inception(MAI)model,an improved architecture that enhances feature extraction and classification accuracy.The MAI model fuses Inceptionv4 and MLP Mixer,integrating four attention mechanisms to enhance spatial and channel-wise feature representation.Experimental results demonstrate that MAI significantly outperforms traditional backbone architectures.It achieves an accuracy of 98.71%,surpassing Vision Transformer models while reducing computational complexity by up to 95%in parameter usage.These findings suggest that ear-based kinship verification,combined with an optimized deep learning model and a comprehensive dataset,holds significant promise for biometric applications.展开更多
The development of modern high-altitude wide-swath imaging systems has brought about adaptive quantization bit-depths(10 ~ 16 bits) and large-scale datasets with a single frame approaching I0 GB,posing two major techn...The development of modern high-altitude wide-swath imaging systems has brought about adaptive quantization bit-depths(10 ~ 16 bits) and large-scale datasets with a single frame approaching I0 GB,posing two major technical challenges for thin-cloud removal in large-format aerial images.Firstly,it is difficult to construct a unified model across different bit-depths,resulting in poor model reusability and the need for high retraining costs in new domains.Secondly,traditional neural networks have to segment images into sub-blocks for processing and then splice them,which is prone to generating chromatic artifacts.To address these issues,we propose the Seamless Cloud Elimination Network(SCENet),whose core innovations are as follows:I achieving bit-depth unification through 8-bit standardization of paired images to support unified model training;2 adopting an adaptive transfer learning architecture that freezes encoder weights and fine-tunes decoders to realize efficient domain adaptation and rapid cloud removal;3 innovating a white-balance-aware cross-patch network architecture,which avoids chromatic artifacts during reconstruction while learning cloud features.Experiments show that this method performs excellently on real datasets,and SCENet achieves the highest Peak Signal-to-Noise Ratio(PSNR) compared with eight existing state-of-the-art methods.展开更多
Accurate segmentation of camouflage objects in aerial imagery is vital for improving the efficiency of UAV-based reconnaissance and rescue missions.However,camouflage object segmentation is increasingly challenging du...Accurate segmentation of camouflage objects in aerial imagery is vital for improving the efficiency of UAV-based reconnaissance and rescue missions.However,camouflage object segmentation is increasingly challenging due to advances in both camouflage materials and biological mimicry.Although multispectral-RGB based technology shows promise,conventional dual-aperture multispectral-RGB imaging systems are constrained by imprecise and time-consuming registration and fusion across different modalities,limiting their performance.Here,we propose the Reconstructed Multispectral-RGB Fusion Network(RMRF-Net),which reconstructs RGB images into multispectral ones,enabling efficient multimodal segmentation using only an RGB camera.Specifically,RMRF-Net employs a divergentsimilarity feature correction strategy to minimize reconstruction errors and includes an efficient boundary-aware decoder to enhance object contours.Notably,we establish the first real-world aerial multispectral-RGB semantic segmentation of camouflage objects dataset,including 11 object categories.Experimental results demonstrate that RMRF-Net outperforms existing methods,achieving 17.38 FPS on the NVIDIA Jetson AGX Orin,with only a 0.96%drop in mIoU compared to the RTX 3090,showing its practical applicability in multimodal remote sensing.展开更多
Organoids possess immense potential for unraveling the intricate functions of human tissues and facilitating preclinical disease treatment.Their applications span from high-throughput drug screening to the modeling of...Organoids possess immense potential for unraveling the intricate functions of human tissues and facilitating preclinical disease treatment.Their applications span from high-throughput drug screening to the modeling of complex diseases,with some even achieving clinical translation.Changes in the overall size,shape,boundary,and other morphological features of organoids provide a noninvasive method for assessing organoid drug sensitivity.However,the precise segmentation of organoids in bright-field microscopy images is made difficult by the complexity of the organoid morphology and interference,including overlapping organoids,bubbles,dust particles,and cell fragments.This paper introduces the precision organoid segmentation technique(POST),which is a deep-learning algorithm for segmenting challenging organoids under simple bright-field imaging conditions.Unlike existing methods,POST accurately segments each organoid and eliminates various artifacts encountered during organoid culturing and imaging.Furthermore,it is sensitive to and aligns with measurements of organoid activity in drug sensitivity experiments.POST is expected to be a valuable tool for drug screening using organoids owing to its capability of automatically and rapidly eliminating interfering substances and thereby streamlining the organoid analysis and drug screening process.展开更多
Objective To compare the impact of different reconstruction algorithms on the image quality of 60 kVp head and neck CT angiography(CTA)using subjective and objective metrics,with a focus on vessel edge sharpness.Metho...Objective To compare the impact of different reconstruction algorithms on the image quality of 60 kVp head and neck CT angiography(CTA)using subjective and objective metrics,with a focus on vessel edge sharpness.Methods This prospective study enrolled 45 patients who underwent ultra-low-voltage(60 kVp)head and neck CTA.Image datasets were reconstructed with filtered back-projection(FBP),ClearView(CV)and ClearInfinity(CI)algorithms at low(30%),medium(50%),and high(70%)strengths.Image quality was assessed subjectively and objectively via the Kruskal‒Wallis test for multiple comparisons.Objective parameters,including edge rise slope(ERS)and edge rise distance(ERD),were analyzed via the Friedman test of multiple comparisons statistics.Results Subjective assessments favored the CI50 reconstruction algorithm,demonstrating superior or satisfactory results compared to the other algorithms,with significantly better vessel delineation,edge definition and diagnostic confidence(all P<0.05).Objective analysis revealed that the CV50 and CV70 algorithms significantly reduced ERS and/or elevated ERD(both P<0.05).However,the CI50 algorithm maintained comparable vessel edge sharpness(P>0.05)across all evaluated head and neck vascular segments when compared with the FBP algorithm.Conclusions The CI50 reconstruction algorithm optimizes image quality in 60 kVp head and neck CTA.It provides vessel edge sharpness comparable to FBP while offering superior vessel delineation,edge definition,and diagnostic confidence compared to FBP and CV algorithm.These findings suggest that CI50 has the potential to improve diagnostic accuracy in low-dose vascular imaging.展开更多
In recent years,the rapid advancement of artificial intelligence(AI)technology has enabled AI-assisted negative screening to significantly enhance physicians'efficiency through image feature analysis and multimoda...In recent years,the rapid advancement of artificial intelligence(AI)technology has enabled AI-assisted negative screening to significantly enhance physicians'efficiency through image feature analysis and multimodal data modeling,allowing them to focus more on diagnosing positive cases.Meanwhile,multispectral imaging(MSI)integrates spectral and spatial resolution to capture subtle tissue features invisible to the human eye,providing high-resolution data support for pathological analysis.Combining AI technology with MSI and employing quantitative methods to analyze multiband biomarkers(such as absorbance differences in keratin pearls)can effectively improve diagnostic specificity and reduce subjective errors in manual slide interpretation.To address the challenge of identifying negative tissue sections,we developed a discrimination algorithm powered by MSI.We demonstrated its efficacy using cutaneous squamous cell carcinoma(cSCC)as a representative case study.The algorithm achieved 100%accuracy in excluding negative cases and effectively mitigated the false-positive problem caused by cSCC heterogeneity.We constructed a multispectral image(MSI)dataset acquired at 520 nm,600 nm,and 630 nm wavelengths.Subsequently,we employed an optimized MobileViT model for tissue classification and performed comparative analyses against other models.The experimental results showed that our optimized MobileViT model achieved superior performance in identifying negative tissue sections,with a perfect accuracy rate of 100%.Thus,our results confirm the feasibility of integrating MSI with AI to exclude negative cases with perfect accuracy,offering a novel solution to alleviate the workload of pathologists.展开更多
Scientific and precise evaluations of the megafaunal and landform characteristics of seamounts are important guides for their protection and study.A series of manned and unmanned submersibles have provided invaluable ...Scientific and precise evaluations of the megafaunal and landform characteristics of seamounts are important guides for their protection and study.A series of manned and unmanned submersibles have provided invaluable observational imaging data for the ecological study of seamounts.However,traditional methods of artificial observation of seamount imaging data cannot accurately and efficiently determine the characteristics of megafauna and landforms.This research harnesses data-driven technology to systematically investigate the distributional traits and morphological features of megafaunal organisms,as well as the topographical characteristics,in the Caiwei Guyot region of the western Pacific’s Magellan Seamounts.To construct the landform and megafauna dataset of the Caiwei Guyot region,we used a data preprocessing technology based on image enhancement to provide high-quality imaging data for data-driven technologies.A megafaunal identification and counting algorithm based on YOLOv5(You Only Look Once Version 5)was developed to efficiently assess the abundance,variety,and dominant species of megafauna.Simultaneously,a landform three-dimensional(3D)reconstruction algorithm based on PatchmatchNet was developed to reconstruct the 3D form of the terrain accurately.This study pioneers the application of data-driven technology to deep-sea imaging within the Caiwei Guyot region,offering an innovative approach to accurately and efficiently characterize the region’s unique megafauna and landforms.展开更多
To enable proper diagnosis of a patient,medical images must demonstrate no presence of noise and artifacts.The major hurdle lies in acquiring these images in such a manner that extraneous variables,causing distortions...To enable proper diagnosis of a patient,medical images must demonstrate no presence of noise and artifacts.The major hurdle lies in acquiring these images in such a manner that extraneous variables,causing distortions in the form of noise and artifacts,are kept to a bare minimum.The unexpected change realized during the acquisition process specifically attacks the integrity of the image’s quality,while indirectly attacking the effectiveness of the diagnostic process.It is thus crucial that this is attended to with maximum efficiency at the level of pertinent expertise.The solution to these challenges presents a complex dilemma at the acquisition stage,where image processing techniques must be adopted.The necessity of this mandatory image pre-processing step underpins the implementation of traditional state-of-the-art methods to create functional and robust denoising or recovery devices.This article hereby provides an extensive systematic review of the above techniques,with the purpose of presenting a systematic evaluation of their effect on medical images under three different distributions of noise,i.e.,Gaussian,Poisson,and Rician.A thorough analysis of these methods is conducted using eight evaluation parameters to highlight the unique features of each method.The covered denoising methods are essential in actual clinical scenarios where the preservation of anatomical details is crucial for accurate and safe diagnosis,such as tumor detection in MRI and vascular imaging in CT.展开更多
Given the importance of sentiment analysis in diverse environments,various methods are used for image sentiment analysis,including contextual sentiment analysis that utilizes character and scene relationships.However,...Given the importance of sentiment analysis in diverse environments,various methods are used for image sentiment analysis,including contextual sentiment analysis that utilizes character and scene relationships.However,most existing works employ character faces in conjunction with context,yet lack the capacity to analyze the emotions of characters in unconstrained environments,such as when their faces are obscured or blurred.Accordingly,this article presents the Adaptive Multi-Channel Sentiment Analysis Network(AMSA),a contextual image sentiment analysis framework,which consists of three channels:body,face,and context.AMSA employs Multi-task Cascaded Convolutional Networks(MTCNN)to detect faces within body frames;if detected,facial features are extracted and fused with body and context information for emotion recognition.If not,the model leverages body and context features alone.Meanwhile,to address class imbalance in the EMOTIC dataset,Focal Loss is introduced to improve classification performance,especially for minority emotion categories.Experimental results have shown that certain sentiment categories with lower representation in the dataset demonstrate leading classification accuracy,the AMSA yields a 2.53%increase compared with state-of-the-art methods.展开更多
Objective:In the Radiology Department of Mzuzu Central Hospital(MCH),daily training for radiographers now includes content on Computed Tomography(CT)image quality control and equipment maintenance to ensure the normal...Objective:In the Radiology Department of Mzuzu Central Hospital(MCH),daily training for radiographers now includes content on Computed Tomography(CT)image quality control and equipment maintenance to ensure the normal,continuous,and stable operation of the 16-slice spiral CT scanner.Methods:Through comprehensive analysis of relevant equipment,we have identified key parameters that significantly impact CT image quality.Innovative optimization strategies and solutions targeting these parameters have been developed and integrated into daily training programs.Furthermore,starting from an examination of prevalent failure modes observed in CT equipment,we delve into essential maintenance and preservation techniques that CT technologists must master to ensure optimal system performance.Results:(1)Crucial factors affecting CT image quality include artifacts,noise,partial volume effects,and surrounding gap phenomena,alongside spatial and density resolutions,CT dose,reconstruction algorithms,and human factors during the scanning process.In the daily training for radiographers,emphasis is placed on strictly implementing image quality control measures at every stage of the CT scanning process and skillfully applying advanced scanning and image processing techniques.By doing so,we can provide clinicians with accurate and reliable imaging references for diagnosis and treatment.(2)Strategies for CT equipment maintenance:①Environmental inspection of the CT room to ensure cleanliness and hygiene.②Rational and accurate operation,including calibration software proficiency.③Regular maintenance and servicing for minimizing machine downtime.④Maintenance of the CT X-ray tube.CT technicians can become proficient in equipment maintenance and upkeep techniques through training,which can significantly extend the service life of CT systems and reduce the occurrence of malfunctions.Conclusion:Through the regular implementation of rigorous CT image quality control training for radiology technicians,coupled with diligent and proactive CT equipment maintenance,we have observed profound and beneficial impacts on improving image quality.The accuracy and fidelity of radiological data ultimately leads to more accurate diagnoses and effective treatments.展开更多
Zhuge Liang was an eminent and universally known historical figure whose name is familiar to almost every household.He possessed exceptional talents in many areas and made significant contributions,particularly in pol...Zhuge Liang was an eminent and universally known historical figure whose name is familiar to almost every household.He possessed exceptional talents in many areas and made significant contributions,particularly in politics,military affairs,and diplomacy.In historical records,Zhuge Liang was regarded as a statesman skilled in military administration rather than unconventional stratagems,and more proficient in civil governance than in battlefield command-an internal affairs expert described as“strong in pacifying the state and managing the army,but less given to extraordinary schemes,and better at governing the people than leading troops”.Among the general public,however,his image transformed into an almost deified and omniscient figure,one who could“make impeccable plans and even summon the wind and rain”.This contrast reflects the significant evolution of Zhuge Liang’s image.This dissertation focuses on the image of Zhuge Liang as portrayed in Ming Dynasty Three Kingdoms operas,analyzes the reasons for the transformation of his image,and attempts to offer modest supplementary insights based on previous research.展开更多
Objective:This study aims to develop a deep multiscale image learning system(DMILS)to differentiate malignant from benign thyroid follicular neoplasms on multiscale whole-slide images(WSIs)of intraoperative frozen pat...Objective:This study aims to develop a deep multiscale image learning system(DMILS)to differentiate malignant from benign thyroid follicular neoplasms on multiscale whole-slide images(WSIs)of intraoperative frozen pathological images.Methods:A total of 1,213 patients were divided into training and validation sets,an internal test set,a pooled external test set,and a pooled prospective test set at three centers.DMILS was constructed using a deep learningbased weakly supervised method based on multiscale WSIs at 10×,20×,and 40×magnifications.The performance of the DMILS was compared with that of a single magnification and validated in two pathologist-unidentified subsets.Results:The DMILS yielded good performance,with areas under the receiver operating characteristic curves(AUCs)of 0.848,0.857,0.810,and 0.787 in the training and validation sets,internal test set,pooled external test set,and pooled prospective test set,respectively.The AUC of the DMILS was higher than that of a single magnification,with 0.788 of 10×,0.824 of 20×,and 0.775 of 40×in the internal test set.Moreover,DMILS yielded satisfactory performance on the two pathologist-unidentified subsets.Furthermore,the most indicative region predicted by DMILS is the follicular epithelium.Conclusions:DMILS has good performance in differentiating thyroid follicular neoplasms on multiscale WSIs of intraoperative frozen pathological images.展开更多
Although Transformer-based image restoration methods have demonstrated impressive performance,existing Transformers still insufficiently exploit multiscale information.Previous non-Transformer-based studies have shown...Although Transformer-based image restoration methods have demonstrated impressive performance,existing Transformers still insufficiently exploit multiscale information.Previous non-Transformer-based studies have shown that incorporating multiscale features is crucial for improving restoration results.In this paper,we propose a multiscale Transformer(MST)that captures cross-scale attention among tokens,thereby effectively leveraging the multiscale patch recurrence prior of natural images.Furthermore,we introduce a channel-gate feed-forward network(CGFN)to enhance inter-channel information aggregation and reduce channel redundancy.To simultaneously utilise global,local and multiscale features,we design a multitype feature integration block(MFIB).Extensive experiments on both image super-resolution and HEVC compressed video artefact reduction demonstrate that the proposed MST achieves state-of-the-art performance.Ablation studies further verify the effectiveness of each proposed module.展开更多
基金Supported by School-level Project of Shaoyang Industry Polytechnic College(SKY24A06)Science and Technology Plan(Special Fund Subsidy)of Shaoyang City(2024PT4070)General Research Project of Hunan Provincial Department of Education in 2025(25C1457).
文摘In the context of rural revitalization and the development of smart agriculture, image classification technology based on deep learning has emerged as a crucial tool for digital monitoring and intelligent prevention and control of agricultural diseases. This paper provides a systematic review of the evolutionary development of algorithms within this field. Addressing challenges such as domain drift and limited global awareness in classical convolutional neural networks (CNNs) applied to complex agricultural environments, the paper focuses on the latest advancements in vision transformers (ViT) and their hybrid architectures to enhance cross-domain robustness and fine-grained recognition capabilities. In response to the challenges posed by scarce long-tail data and limited edge computing power in real-world scenarios, the paper explores solutions related to few-shot learning and ultra-lightweight network deployment. Finally, a forward-looking analysis is presented on the application paradigms of multimodal feature fusion, vision-based large models, and explainable artificial intelligence (AI) within smart plant protection. This analysis aims to offer theoretical insights for the development of efficient and transparent intelligent diagnostic systems for agricultural diseases, thereby supporting the advancement of digital agriculture and the construction of a robust agricultural nation.
基金supported by the National Key R&D Program of China 2022YFF0503002the National Natural Science Foundation of China(NSFC,Grant Nos.12333010 and 12233012)+2 种基金the Strategic Priority Research Program of the Chinese Academy of Sciences(grant No.XDB0560000)supported by the Prominent Postdoctoral Project of Jiangsu Province(2023ZB304)supported by the Strategic Priority Research Program on Space Science,the Chinese Academy of Sciences,grant No.XDA15320000.
文摘Imaging observations of solar X-ray bursts can reveal details of the energy release process and particle acceleration in flares.Most hard X-ray imagers make use of the modulation-based Fourier transform imaging method,an indirect imaging technique that requires algorithms to reconstruct and optimize images.During the last decade,a variety of algorithms have been developed and improved.However,it is difficult to quantitatively evaluate the image quality of different solutions without a true,reference image of observation.How to choose the values of imaging parameters for these algorithms to get the best performance is also an open question.In this study,we present a detailed test of the characteristics of these algorithms,imaging dynamic range and a crucial parameter for the CLEAN method,clean beam width factor(CBWF).We first used SDO/AIA EUV images to compute DEM maps and calculate thermal X-ray maps.Then these realistic sources and several types of simulated sources are used as the ground truth in the imaging simulations for both RHESSI and ASO-S/HXI.The different solutions are evaluated quantitatively by a number of means.The overall results suggest that EM,PIXON,and CLEAN are exceptional methods for sidelobe elimination,producing images with clear source details.Although MEM_GE,MEM_NJIT,VIS_WV and VIS_CS possess fast imaging processes and generate good images,they too possess associated imperfections unique to each method.The two forward fit algorithms,VF and FF,perform differently,and VF appears to be more robust and useful.We also demonstrated the imaging capability of HXI and available HXI algorithms.Furthermore,the effect of CBWF on image quality was investigated,and the optimal settings for both RHESSI and HXI were proposed.
文摘Multispectral imaging,which simultaneously captures the spatial and spectral information of a scene,is widely used across diverse fields,including remote sensing,biomedical imaging,and agricultural monitoring.We introduce a snapshot multispectral imaging approach employing a standard monochrome image sensor with no additional spectral filters or customized components.Our system leverages the inherent chromatic aberration of wavelength-dependent defocusing as a natural source of physical encoding of multispectral information;this encoded image information is rapidly decoded via a deep learning-based multispectral Fourier imager network(mFIN).We experimentally tested our method with six illumination bands and demonstrated an overall accuracy of 98.25%for predicting the illumination channels at the input and achieved a robust multispectral image reconstruction on various test objects.This deep learning-powered framework achieves high-quality multispectral image reconstruction using snapshot image acquisition with a monochrome image sensor and could be useful for applications in biomedicine,industrial quality control,and agriculture,among others.
基金This research was supported in part by a postdoctoral research fellow appointment to the Agricultural Research Service(ARS)Research Participation Program administered by the Oak Ridge Institute for Science and Education(ORISE)through an interagency agreement between the U.S.Department of Energy(DOE)and the U.S.Department of Agriculture(USDA).
文摘Crop leaf area index(LAI)and biomass are two major biophysical parameters to measure crop growth and health condition.Measuring LAI and biomass in field experiments is a destructive method.Therefore,we focused on the application of unmanned aerial vehicles(UAVs)in agriculture,which is a cost and labor-efficientmethod.Hence,UAV-captured multispectral images were applied to monitor crop growth,identify plant bio-physical conditions,and so on.In this study,we monitored soybean crops using UAV and field experiments.This experiment was conducted at theMAFES(Mississippi Agricultural and Forestry Experiment Station)Pontotoc Ridge-Flatwoods Branch Experiment Station.It followed a randomized block design with five cover crops:Cereal Rye,Vetch,Wheat,MC:mixed Mustard and Cereal Rye,and native vegetation.Planting was made in the fall,and three fertilizer treatments were applied:Synthetic Fertilizer,Poultry Litter,and none,applied before planting the soybean,in a full factorial combination.We monitored soybean reproductive phases at R3(initial pod development),R5(initial seed development),R6(full seed development),and R7(initial maturity)and used UAV multispectral remote sensing for soybean LAI and biomass estimations.The major goal of this study was to assess LAI and biomass estimations from UAV multispectral images in the reproductive stages when the development of leaves and biomass was stabilized.Wemade about fourteen vegetation indices(VIs)fromUAVmultispectral images at these stages to estimate LAI and biomass.Wemodeled LAI and biomass based on these remotely sensed VIs and ground-truth measurements usingmachine learning methods,including linear regression,Random Forest(RF),and support vector regression(SVR).Thereafter,the models were applied to estimate LAI and biomass.According to the model results,LAI was better estimated at the R6 stage and biomass at the R3 stage.Compared to the other models,the RF models showed better estimation,i.e.,an R^(2) of about 0.58–0.68 with an RMSE(rootmean square error)of 0.52–0.60(m^(2)/m^(2))for the LAI and about 0.44–0.64 for R^(2) and 21–26(g dry weight/5 plants)for RMSE of biomass estimation.We performed a leave-one-out cross-validation.Based on cross-validatedmodels with field experiments,we also found that the R6 stage was the best for estimating LAI,and the R3 stage for estimating crop biomass.The cross-validated RF model showed the estimation ability with an R^(2) about 0.25–0.44 and RMSE of 0.65–0.85(m^(2)/m^(2))for LAI estimation;and R^(2) about 0.1–0.31 and an RMSE of about 28–35(g dry weight/5 plants)for crop biomass estimation.This result will be helpful to promote the use of non-destructive remote sensing methods to determine the crop LAI and biomass status,which may bring more efficient crop production and management.
文摘Kinship verification is a key biometric recognition task that determines biological relationships based on physical features.Traditional methods predominantly use facial recognition,leveraging established techniques and extensive datasets.However,recent research has highlighted ear recognition as a promising alternative,offering advantages in robustness against variations in facial expressions,aging,and occlusions.Despite its potential,a significant challenge in ear-based kinship verification is the lack of large-scale datasets necessary for training deep learning models effectively.To address this challenge,we introduce the EarKinshipVN dataset,a novel and extensive collection of ear images designed specifically for kinship verification.This dataset consists of 4876 high-resolution color images from 157 multiracial families across different regions,forming 73,220 kinship pairs.EarKinshipVN,a diverse and large-scale dataset,advances kinship verification research using ear features.Furthermore,we propose the Mixer Attention Inception(MAI)model,an improved architecture that enhances feature extraction and classification accuracy.The MAI model fuses Inceptionv4 and MLP Mixer,integrating four attention mechanisms to enhance spatial and channel-wise feature representation.Experimental results demonstrate that MAI significantly outperforms traditional backbone architectures.It achieves an accuracy of 98.71%,surpassing Vision Transformer models while reducing computational complexity by up to 95%in parameter usage.These findings suggest that ear-based kinship verification,combined with an optimized deep learning model and a comprehensive dataset,holds significant promise for biometric applications.
文摘The development of modern high-altitude wide-swath imaging systems has brought about adaptive quantization bit-depths(10 ~ 16 bits) and large-scale datasets with a single frame approaching I0 GB,posing two major technical challenges for thin-cloud removal in large-format aerial images.Firstly,it is difficult to construct a unified model across different bit-depths,resulting in poor model reusability and the need for high retraining costs in new domains.Secondly,traditional neural networks have to segment images into sub-blocks for processing and then splice them,which is prone to generating chromatic artifacts.To address these issues,we propose the Seamless Cloud Elimination Network(SCENet),whose core innovations are as follows:I achieving bit-depth unification through 8-bit standardization of paired images to support unified model training;2 adopting an adaptive transfer learning architecture that freezes encoder weights and fine-tunes decoders to realize efficient domain adaptation and rapid cloud removal;3 innovating a white-balance-aware cross-patch network architecture,which avoids chromatic artifacts during reconstruction while learning cloud features.Experiments show that this method performs excellently on real datasets,and SCENet achieves the highest Peak Signal-to-Noise Ratio(PSNR) compared with eight existing state-of-the-art methods.
基金National Natural Science Foundation of China(Grant Nos.62005049 and 62072110)Natural Science Foundation of Fujian Province(Grant No.2020J01451).
文摘Accurate segmentation of camouflage objects in aerial imagery is vital for improving the efficiency of UAV-based reconnaissance and rescue missions.However,camouflage object segmentation is increasingly challenging due to advances in both camouflage materials and biological mimicry.Although multispectral-RGB based technology shows promise,conventional dual-aperture multispectral-RGB imaging systems are constrained by imprecise and time-consuming registration and fusion across different modalities,limiting their performance.Here,we propose the Reconstructed Multispectral-RGB Fusion Network(RMRF-Net),which reconstructs RGB images into multispectral ones,enabling efficient multimodal segmentation using only an RGB camera.Specifically,RMRF-Net employs a divergentsimilarity feature correction strategy to minimize reconstruction errors and includes an efficient boundary-aware decoder to enhance object contours.Notably,we establish the first real-world aerial multispectral-RGB semantic segmentation of camouflage objects dataset,including 11 object categories.Experimental results demonstrate that RMRF-Net outperforms existing methods,achieving 17.38 FPS on the NVIDIA Jetson AGX Orin,with only a 0.96%drop in mIoU compared to the RTX 3090,showing its practical applicability in multimodal remote sensing.
基金supported by the National Key R&D Program of China(No.2022YFC2504403)the National Natural Science Foundation of China(No.62172202)+1 种基金the Experiment Project of China Manned Space Program(No.HYZHXM01019)the Fundamental Research Funds for the Central Universities from Southeast University(No.3207032101C3)。
文摘Organoids possess immense potential for unraveling the intricate functions of human tissues and facilitating preclinical disease treatment.Their applications span from high-throughput drug screening to the modeling of complex diseases,with some even achieving clinical translation.Changes in the overall size,shape,boundary,and other morphological features of organoids provide a noninvasive method for assessing organoid drug sensitivity.However,the precise segmentation of organoids in bright-field microscopy images is made difficult by the complexity of the organoid morphology and interference,including overlapping organoids,bubbles,dust particles,and cell fragments.This paper introduces the precision organoid segmentation technique(POST),which is a deep-learning algorithm for segmenting challenging organoids under simple bright-field imaging conditions.Unlike existing methods,POST accurately segments each organoid and eliminates various artifacts encountered during organoid culturing and imaging.Furthermore,it is sensitive to and aligns with measurements of organoid activity in drug sensitivity experiments.POST is expected to be a valuable tool for drug screening using organoids owing to its capability of automatically and rapidly eliminating interfering substances and thereby streamlining the organoid analysis and drug screening process.
基金the Grant from the National Key Research and Development Program of China(No.2024YFC2419300)the National Natural Science Foundation of China(No.82471967)+1 种基金the Hubei Provincial Key Research and Development Program(No.2024BCB008)the Hubei Provincial Natural Science Foundation of China(No.2025AFB733).
文摘Objective To compare the impact of different reconstruction algorithms on the image quality of 60 kVp head and neck CT angiography(CTA)using subjective and objective metrics,with a focus on vessel edge sharpness.Methods This prospective study enrolled 45 patients who underwent ultra-low-voltage(60 kVp)head and neck CTA.Image datasets were reconstructed with filtered back-projection(FBP),ClearView(CV)and ClearInfinity(CI)algorithms at low(30%),medium(50%),and high(70%)strengths.Image quality was assessed subjectively and objectively via the Kruskal‒Wallis test for multiple comparisons.Objective parameters,including edge rise slope(ERS)and edge rise distance(ERD),were analyzed via the Friedman test of multiple comparisons statistics.Results Subjective assessments favored the CI50 reconstruction algorithm,demonstrating superior or satisfactory results compared to the other algorithms,with significantly better vessel delineation,edge definition and diagnostic confidence(all P<0.05).Objective analysis revealed that the CV50 and CV70 algorithms significantly reduced ERS and/or elevated ERD(both P<0.05).However,the CI50 algorithm maintained comparable vessel edge sharpness(P>0.05)across all evaluated head and neck vascular segments when compared with the FBP algorithm.Conclusions The CI50 reconstruction algorithm optimizes image quality in 60 kVp head and neck CTA.It provides vessel edge sharpness comparable to FBP while offering superior vessel delineation,edge definition,and diagnostic confidence compared to FBP and CV algorithm.These findings suggest that CI50 has the potential to improve diagnostic accuracy in low-dose vascular imaging.
基金funded by the Natural Science Foundation of Shanghai Municipality(No.21ZR1440500)the Shanghai Science and Technology Commission(Grant No.21S31902700).
文摘In recent years,the rapid advancement of artificial intelligence(AI)technology has enabled AI-assisted negative screening to significantly enhance physicians'efficiency through image feature analysis and multimodal data modeling,allowing them to focus more on diagnosing positive cases.Meanwhile,multispectral imaging(MSI)integrates spectral and spatial resolution to capture subtle tissue features invisible to the human eye,providing high-resolution data support for pathological analysis.Combining AI technology with MSI and employing quantitative methods to analyze multiband biomarkers(such as absorbance differences in keratin pearls)can effectively improve diagnostic specificity and reduce subjective errors in manual slide interpretation.To address the challenge of identifying negative tissue sections,we developed a discrimination algorithm powered by MSI.We demonstrated its efficacy using cutaneous squamous cell carcinoma(cSCC)as a representative case study.The algorithm achieved 100%accuracy in excluding negative cases and effectively mitigated the false-positive problem caused by cSCC heterogeneity.We constructed a multispectral image(MSI)dataset acquired at 520 nm,600 nm,and 630 nm wavelengths.Subsequently,we employed an optimized MobileViT model for tissue classification and performed comparative analyses against other models.The experimental results showed that our optimized MobileViT model achieved superior performance in identifying negative tissue sections,with a perfect accuracy rate of 100%.Thus,our results confirm the feasibility of integrating MSI with AI to exclude negative cases with perfect accuracy,offering a novel solution to alleviate the workload of pathologists.
基金The Key Research and Development Program of Shandong Province of China under contract No.2020JMRH0101the National Key Research and Development Project of China under contract No.2021YFC2802100the Qingdao Natural Science Foundation under contract No.24-4-4-zrij-127-jch.
文摘Scientific and precise evaluations of the megafaunal and landform characteristics of seamounts are important guides for their protection and study.A series of manned and unmanned submersibles have provided invaluable observational imaging data for the ecological study of seamounts.However,traditional methods of artificial observation of seamount imaging data cannot accurately and efficiently determine the characteristics of megafauna and landforms.This research harnesses data-driven technology to systematically investigate the distributional traits and morphological features of megafaunal organisms,as well as the topographical characteristics,in the Caiwei Guyot region of the western Pacific’s Magellan Seamounts.To construct the landform and megafauna dataset of the Caiwei Guyot region,we used a data preprocessing technology based on image enhancement to provide high-quality imaging data for data-driven technologies.A megafaunal identification and counting algorithm based on YOLOv5(You Only Look Once Version 5)was developed to efficiently assess the abundance,variety,and dominant species of megafauna.Simultaneously,a landform three-dimensional(3D)reconstruction algorithm based on PatchmatchNet was developed to reconstruct the 3D form of the terrain accurately.This study pioneers the application of data-driven technology to deep-sea imaging within the Caiwei Guyot region,offering an innovative approach to accurately and efficiently characterize the region’s unique megafauna and landforms.
文摘To enable proper diagnosis of a patient,medical images must demonstrate no presence of noise and artifacts.The major hurdle lies in acquiring these images in such a manner that extraneous variables,causing distortions in the form of noise and artifacts,are kept to a bare minimum.The unexpected change realized during the acquisition process specifically attacks the integrity of the image’s quality,while indirectly attacking the effectiveness of the diagnostic process.It is thus crucial that this is attended to with maximum efficiency at the level of pertinent expertise.The solution to these challenges presents a complex dilemma at the acquisition stage,where image processing techniques must be adopted.The necessity of this mandatory image pre-processing step underpins the implementation of traditional state-of-the-art methods to create functional and robust denoising or recovery devices.This article hereby provides an extensive systematic review of the above techniques,with the purpose of presenting a systematic evaluation of their effect on medical images under three different distributions of noise,i.e.,Gaussian,Poisson,and Rician.A thorough analysis of these methods is conducted using eight evaluation parameters to highlight the unique features of each method.The covered denoising methods are essential in actual clinical scenarios where the preservation of anatomical details is crucial for accurate and safe diagnosis,such as tumor detection in MRI and vascular imaging in CT.
文摘Given the importance of sentiment analysis in diverse environments,various methods are used for image sentiment analysis,including contextual sentiment analysis that utilizes character and scene relationships.However,most existing works employ character faces in conjunction with context,yet lack the capacity to analyze the emotions of characters in unconstrained environments,such as when their faces are obscured or blurred.Accordingly,this article presents the Adaptive Multi-Channel Sentiment Analysis Network(AMSA),a contextual image sentiment analysis framework,which consists of three channels:body,face,and context.AMSA employs Multi-task Cascaded Convolutional Networks(MTCNN)to detect faces within body frames;if detected,facial features are extracted and fused with body and context information for emotion recognition.If not,the model leverages body and context features alone.Meanwhile,to address class imbalance in the EMOTIC dataset,Focal Loss is introduced to improve classification performance,especially for minority emotion categories.Experimental results have shown that certain sentiment categories with lower representation in the dataset demonstrate leading classification accuracy,the AMSA yields a 2.53%increase compared with state-of-the-art methods.
基金supported by the First Affiliated Hospital of Xi’an Jiaotong University Teaching Reform Project(Grant No.JG2023-0206 and JG2022-0324).
文摘Objective:In the Radiology Department of Mzuzu Central Hospital(MCH),daily training for radiographers now includes content on Computed Tomography(CT)image quality control and equipment maintenance to ensure the normal,continuous,and stable operation of the 16-slice spiral CT scanner.Methods:Through comprehensive analysis of relevant equipment,we have identified key parameters that significantly impact CT image quality.Innovative optimization strategies and solutions targeting these parameters have been developed and integrated into daily training programs.Furthermore,starting from an examination of prevalent failure modes observed in CT equipment,we delve into essential maintenance and preservation techniques that CT technologists must master to ensure optimal system performance.Results:(1)Crucial factors affecting CT image quality include artifacts,noise,partial volume effects,and surrounding gap phenomena,alongside spatial and density resolutions,CT dose,reconstruction algorithms,and human factors during the scanning process.In the daily training for radiographers,emphasis is placed on strictly implementing image quality control measures at every stage of the CT scanning process and skillfully applying advanced scanning and image processing techniques.By doing so,we can provide clinicians with accurate and reliable imaging references for diagnosis and treatment.(2)Strategies for CT equipment maintenance:①Environmental inspection of the CT room to ensure cleanliness and hygiene.②Rational and accurate operation,including calibration software proficiency.③Regular maintenance and servicing for minimizing machine downtime.④Maintenance of the CT X-ray tube.CT technicians can become proficient in equipment maintenance and upkeep techniques through training,which can significantly extend the service life of CT systems and reduce the occurrence of malfunctions.Conclusion:Through the regular implementation of rigorous CT image quality control training for radiology technicians,coupled with diligent and proactive CT equipment maintenance,we have observed profound and beneficial impacts on improving image quality.The accuracy and fidelity of radiological data ultimately leads to more accurate diagnoses and effective treatments.
文摘Zhuge Liang was an eminent and universally known historical figure whose name is familiar to almost every household.He possessed exceptional talents in many areas and made significant contributions,particularly in politics,military affairs,and diplomacy.In historical records,Zhuge Liang was regarded as a statesman skilled in military administration rather than unconventional stratagems,and more proficient in civil governance than in battlefield command-an internal affairs expert described as“strong in pacifying the state and managing the army,but less given to extraordinary schemes,and better at governing the people than leading troops”.Among the general public,however,his image transformed into an almost deified and omniscient figure,one who could“make impeccable plans and even summon the wind and rain”.This contrast reflects the significant evolution of Zhuge Liang’s image.This dissertation focuses on the image of Zhuge Liang as portrayed in Ming Dynasty Three Kingdoms operas,analyzes the reasons for the transformation of his image,and attempts to offer modest supplementary insights based on previous research.
基金supported by the Taishan Scholar Project(No.ts20190991,tsqn202211378)the Key R&D Project of Shandong Province(No.2022CXPT023)the General Program of National Natural Science Foundation of China(No.82371933)。
文摘Objective:This study aims to develop a deep multiscale image learning system(DMILS)to differentiate malignant from benign thyroid follicular neoplasms on multiscale whole-slide images(WSIs)of intraoperative frozen pathological images.Methods:A total of 1,213 patients were divided into training and validation sets,an internal test set,a pooled external test set,and a pooled prospective test set at three centers.DMILS was constructed using a deep learningbased weakly supervised method based on multiscale WSIs at 10×,20×,and 40×magnifications.The performance of the DMILS was compared with that of a single magnification and validated in two pathologist-unidentified subsets.Results:The DMILS yielded good performance,with areas under the receiver operating characteristic curves(AUCs)of 0.848,0.857,0.810,and 0.787 in the training and validation sets,internal test set,pooled external test set,and pooled prospective test set,respectively.The AUC of the DMILS was higher than that of a single magnification,with 0.788 of 10×,0.824 of 20×,and 0.775 of 40×in the internal test set.Moreover,DMILS yielded satisfactory performance on the two pathologist-unidentified subsets.Furthermore,the most indicative region predicted by DMILS is the follicular epithelium.Conclusions:DMILS has good performance in differentiating thyroid follicular neoplasms on multiscale WSIs of intraoperative frozen pathological images.
基金supported in part by the National Natural Science Foundation of China under Grants 62101346 and 62301330the Guangdong Basic and Applied Basic Research Foundation under Grants 2021A1515011702 and 2022A1515110101+1 种基金the Shenzhen Science and Technology Programme under Grants JCYJ20240813141358076 and 20231121103807001the Guangdong Provincial Key Laboratory under Grant 2023B1212060076.
文摘Although Transformer-based image restoration methods have demonstrated impressive performance,existing Transformers still insufficiently exploit multiscale information.Previous non-Transformer-based studies have shown that incorporating multiscale features is crucial for improving restoration results.In this paper,we propose a multiscale Transformer(MST)that captures cross-scale attention among tokens,thereby effectively leveraging the multiscale patch recurrence prior of natural images.Furthermore,we introduce a channel-gate feed-forward network(CGFN)to enhance inter-channel information aggregation and reduce channel redundancy.To simultaneously utilise global,local and multiscale features,we design a multitype feature integration block(MFIB).Extensive experiments on both image super-resolution and HEVC compressed video artefact reduction demonstrate that the proposed MST achieves state-of-the-art performance.Ablation studies further verify the effectiveness of each proposed module.
