As an important part of the mass balance of the Ice Sheet,Supra-glacial Water not only reflects the diversity of polar environmental changes,but also plays an important role in the study of global climate and environm...As an important part of the mass balance of the Ice Sheet,Supra-glacial Water not only reflects the diversity of polar environmental changes,but also plays an important role in the study of global climate and environmental changes.In this paper,we chose northern Greenland as the research area,and constructed a Normalized Enhanced Water Index(NEWI)based on the high-precision WorldView-2 images of different phases during the ablation period in northern Greenland,followed by a statistical analysis on the spectral characteristics of the images were for the typical features in the study area.Then the fuzzy areas with similar gray values of thin sea ice and shallow ice water bodies were located,according to the distribution rules of ground objects and histogram graphic features of the images,so as to enhance the contrast of ground objects between the regions,and finally the extraction of the fine range of water bodies on the ice surface.Experimental results showed that the proposed index effectively highlighted the ice water with the water of the reflectivity difference,compared with the commonly used water index NDWI,etc.,especially in shallow water,which contributes to differentiation from other objects.The precision evaluation showed that the applied method of extraction has higher degree of refinement compared with other methods,by which the ice water can get complete ice water effectively.展开更多
Alzheimer’s Disease(AD)is a progressive neurodegenerative disorder that significantly affects cognitive function,making early and accurate diagnosis essential.Traditional Deep Learning(DL)-based approaches often stru...Alzheimer’s Disease(AD)is a progressive neurodegenerative disorder that significantly affects cognitive function,making early and accurate diagnosis essential.Traditional Deep Learning(DL)-based approaches often struggle with low-contrast MRI images,class imbalance,and suboptimal feature extraction.This paper develops a Hybrid DL system that unites MobileNetV2 with adaptive classification methods to boost Alzheimer’s diagnosis by processing MRI scans.Image enhancement is done using Contrast-Limited Adaptive Histogram Equalization(CLAHE)and Enhanced Super-Resolution Generative Adversarial Networks(ESRGAN).A classification robustness enhancement system integrates class weighting techniques and a Matthews Correlation Coefficient(MCC)-based evaluation method into the design.The trained and validated model gives a 98.88%accuracy rate and 0.9614 MCC score.We also performed a 10-fold cross-validation experiment with an average accuracy of 96.52%(±1.51),a loss of 0.1671,and an MCC score of 0.9429 across folds.The proposed framework outperforms the state-of-the-art models with a 98%weighted F1-score while decreasing misdiagnosis results for every AD stage.The model demonstrates apparent separation abilities between AD progression stages according to the results of the confusion matrix analysis.These results validate the effectiveness of hybrid DL models with adaptive preprocessing for early and reliable Alzheimer’s diagnosis,contributing to improved computer-aided diagnosis(CAD)systems in clinical practice.展开更多
As a form of discrete representation learning,Vector Quantized Variational Autoencoders(VQ-VAE)have increasingly been applied to generative and multimodal tasks due to their ease of embedding and representative capaci...As a form of discrete representation learning,Vector Quantized Variational Autoencoders(VQ-VAE)have increasingly been applied to generative and multimodal tasks due to their ease of embedding and representative capacity.However,existing VQ-VAEs often perform quantization in the spatial domain,ignoring global structural information and potentially suffering from codebook collapse and information coupling issues.This paper proposes a frequency quantized variational autoencoder(FQ-VAE)to address these issues.The proposed method transforms image features into linear combinations in the frequency domain using a 2D fast Fourier transform(2D-FFT)and performs adaptive quantization on these frequency components to preserve image’s global relationships.The codebook is dynamically optimized to avoid collapse and information coupling issue by considering the usage frequency and dependency of code vectors.Furthermore,we introduce a post-processing module based on graph convolutional networks to further improve reconstruction quality.Experimental results on four public datasets demonstrate that the proposed method outperforms state-of-the-art approaches in terms of Structural Similarity Index(SSIM),Learned Perceptual Image Patch Similarity(LPIPS),and Reconstruction Fréchet Inception Distance(rFID).In the experiments on the CIFAR-10 dataset,compared to the baselinemethod VQ-VAE,the proposedmethod improves the abovemetrics by 4.9%,36.4%,and 52.8%,respectively.展开更多
Land surface water mapping is one of the most important remote-sensing applications.However,water areas are spectrally similar and overlapped with shadow,making accurate water extraction from remote-sensing images sti...Land surface water mapping is one of the most important remote-sensing applications.However,water areas are spectrally similar and overlapped with shadow,making accurate water extraction from remote-sensing images still a challenging problem.This paper develops a novel water index named as NDWI-MSI,combining a new normalized difference water index(NDWI)and a recently developed morphological shadow index(MSI),to delineate water bodies from eight-band WorldView-2 imagery.The newly available bands(e.g.coastal,yellow,red-edge,and near-infrared 2)of WorldView-2 imagery provide more potential for constructing new NDWIs derived from various band combinations.Through our testing,a new NDWI is defined in this study.In addition,MSI,a recently developed automatic shadow extraction index from high-resolution imagery can be used to indicate shadow areas.The NDWI-MSI is created by combining NDWI and MSI,which is able to highlight water bodies and simultaneously suppress shadow areas.In experiments,it is shown that the new water index can achieve better performance than traditional NDWI,and even supervised classifiers,for example,maximum likelihood classifier,and support vector machine.展开更多
The detection of impervious surface (IS) in heterogeneous urban areas is one of the most challenging tasks in urban remote sensing. One of the limitations in IS detection at the parcel level is the lack of sufficient ...The detection of impervious surface (IS) in heterogeneous urban areas is one of the most challenging tasks in urban remote sensing. One of the limitations in IS detection at the parcel level is the lack of sufficient training data. In this study, a generic model of spatial distribution of roof materials is considered to overcome this limitation. A generic model that is based on spectral, spatial and textural information which is extracted from available training data is proposed. An object-based approach is used to extract the information inherent in the image. Furthermore, linear discriminant analysis is used for dimensionality reduction and to discriminate between different spatial, spectral and textural attributes. The generic model is composed of a discriminant function based on linear combinations of the predictor variables that provide the best discrimination among the groups. The discriminate analysis result shows that of the 54 attributes extracted from the WorldView-2 image, only 13 attributes related to spatial, spectral and textural information are useful for discriminating different roof materials. Finally, this model is applied to different WorldView-2 images from different areas and proves that this model has good potential to predict roof materials from the WorldView-2 images without using training data.展开更多
Background Integrating optical and LiDAR data is crucial for accurately predicting aboveground biomass(AGB)due to their complementarily essential characteristics.It can be anticipated that this integration approach ne...Background Integrating optical and LiDAR data is crucial for accurately predicting aboveground biomass(AGB)due to their complementarily essential characteristics.It can be anticipated that this integration approach needs to deal with an expanded set of variables and scale-related challenges.To achieve satisfactory accuracy in real-world applications,further exploration is needed to optimize AGB models by selecting appropriate scales and variables.Methods This study examined the impact of LiDAR point cloud-derived metrics on estimation accuracies at diferent scales,ranging from 2 to 16 m cell sizes.We integrated WorldView-2 imagery with LiDAR data to construct biomass models and developed a genetic algorithm-based wrapper for variable selection and parameter tuning in artifcial neural networks(GA-ANN wrapper).Results Our fndings indicated that the highest accuracies in estimating AGB were yielded by 4 m and 6 m cell sizes,followed by 8 m and 10 m,associated with the dimensions of vegetation canopies and sampling plots.Models integrating WorldView-2 and LiDAR data outperformed those using each data source individually,reducing RMSEr by 5.80%and 3.89%,respectively.Combining these data sources can capture the canopy spectral responses and vertical vegetation structure.The GA-ANN wrapper model decreased RMSEr by 1.69%over the ANN model and dwindled the number of variables from 38 to 9.The selected variables included vegetation density,height,species,and vegetation indices.Conclusions The appropriate cell size for AGB estimation should consider the sizes of vegetation canopies,tree densities,and sampling plots.The GA-ANN wrapper efectively reduced variables and achieved the highest accuracy.Additionally,canopy spectral and vertical structure information are vital for accurate AGB estimation.Our study ofered insights into optimizing mangrove AGB models by integrating optical and LiDAR data.The approach,data,model,and indices employed in this research can efectively predict AGB estimates of any other forest types or vegetation cover types in diferent climate regions.展开更多
目的探讨T_2 star mapping、T_1 images与3D DESS融合伪彩图在关节软骨损伤中的诊断价值。方法对26例关节软骨损伤患者行T_2 star mapping、T_1 images和3D DESS扫描,并将T_1 images、T_2 star mapping与3D DESS图像融合,评价患者股骨...目的探讨T_2 star mapping、T_1 images与3D DESS融合伪彩图在关节软骨损伤中的诊断价值。方法对26例关节软骨损伤患者行T_2 star mapping、T_1 images和3D DESS扫描,并将T_1 images、T_2 star mapping与3D DESS图像融合,评价患者股骨、胫骨、髌骨关节软骨损伤程度并与关节镜结果对比,计算融合伪彩图诊断软骨损伤的特异性、敏感性及与关节镜诊断结果一致性。结果 T_1 images-3D DESS融合伪彩图诊断关节软骨损伤的敏感度、特异度及Kappa值分别为92.8%、93.0%、0.769,T_2 star mapping-3D DESS融合伪彩图诊断关节软骨损伤的敏感度、特异度及Kappa值分别为91.4%、94.2%、0.787。结论 T_2 star mapping、T_1 images与3D DESS融合伪彩图在关节软骨早期损伤评价上优于关节镜。展开更多
新近,欧洲糖尿病预防指南与培训标准工作组(Development and Implementation of a European Guideline and Training Standards for Diabetes Prevention,IMAGE)颁布了2型糖尿病(T2DM)预防指南,其要点摘译如下:
Background:Anoplophora glabripennis(Motschulsky),commonly known as Asian longhorned beetle(ALB),is a wood-boring insect that can cause lethal infestation to multiple borer leaf trees.In Gansu Province,northwest China,...Background:Anoplophora glabripennis(Motschulsky),commonly known as Asian longhorned beetle(ALB),is a wood-boring insect that can cause lethal infestation to multiple borer leaf trees.In Gansu Province,northwest China,ALB has caused a large number of deaths of a local tree species Populus gansuensis.The damaged area belongs to Gobi desert where every single tree is artificially planted and is extremely difficult to cultivate.Therefore,the monitoring of the ALB infestation at the individual tree level in the landscape is necessary.Moreover,the determination of an abnormal phenotype that can be obtained directly from remote-sensing images to predict the damage degree can greatly reduce the cost of field investigation and management.Methods:Multispectral WorldView-2(WV-2)images and 5 tree physiological factors were collected as experimental materials.One-way ANOVA of the tree’s physiological factors helped in determining the phenotype to predict damage degrees.The original bands of WV-2 and derived vegetation indices were used as reference data to construct the dataset of a prediction model.Variance inflation factor and stepwise regression analyses were used to eliminate collinearity and redundancy.Finally,three machine learning algorithms,i.e.,Random Forest(RF),Support Vector Machine(SVM),Classification And Regression Tree(CART),were applied and compared to find the best classifier for predicting the damage stage of individual P.gansuensis.Results:The confusion matrix of RF achieved the highest overall classification accuracy(86.2%)and the highest Kappa index value(0.804),indicating the potential of using WV-2 imaging to accurately detect damage stages of individual trees.In addition,the canopy color was found to be positively correlated with P.gansuensis’damage stages.Conclusions:A novel method was developed by combining WV-2 and tree physiological index for semi-automatic classification of three damage stages of P.gansuensis infested with ALB.The canopy color was determined as an abnormal phenotype that could be directly assessed using remote-sensing images at the tree level to predict the damage degree.These tools are highly applicable for driving quick and effective measures to reduce damage to pure poplar forests in Gansu Province,China.展开更多
In the methods of image thresholding segmentation, such methods based on two-dimensional （2D） histogram and optimal objective functions are important. However, when they are used for infrared image segmentation, the...In the methods of image thresholding segmentation, such methods based on two-dimensional （2D） histogram and optimal objective functions are important. However, when they are used for infrared image segmentation, they are weak in suppressing background noises and worse in segmenting targets with non-uniform gray level. The concept of 2D histogram shape modification is proposed, which is realized by target information prior restraint after enhancing target information using plateau histogram equalization. The formula of 2D minimum Renyi entropy is deduced for image segmentation, then the shape-modified 2D histogram is combined wfth four optimal objective functions （i.e., maximum between-class variance, maximum entropy, maximum correlation and minimum Renyi entropy） respectively for the appli- cation of infrared image segmentation. Simultaneously, F-measure is introduced to evaluate the segmentation effects objectively. The experimental results show that F-measure is an effective evaluation index for image segmentation since its value is fully consistent with the subjective evaluation, and after 2D histogram shape modification, the methods of optimal objective functions can overcome their original forms＇ deficiency and their segmentation effects are more or less improvements, where the best one is the maximum entropy method based on 2D histogram shape modification.展开更多
A novel image fusion network framework with an autonomous encoder and decoder is suggested to increase thevisual impression of fused images by improving the quality of infrared and visible light picture fusion. The ne...A novel image fusion network framework with an autonomous encoder and decoder is suggested to increase thevisual impression of fused images by improving the quality of infrared and visible light picture fusion. The networkcomprises an encoder module, fusion layer, decoder module, and edge improvementmodule. The encoder moduleutilizes an enhanced Inception module for shallow feature extraction, then combines Res2Net and Transformerto achieve deep-level co-extraction of local and global features from the original picture. An edge enhancementmodule (EEM) is created to extract significant edge features. A modal maximum difference fusion strategy isintroduced to enhance the adaptive representation of information in various regions of the source image, therebyenhancing the contrast of the fused image. The encoder and the EEM module extract features, which are thencombined in the fusion layer to create a fused picture using the decoder. Three datasets were chosen to test thealgorithmproposed in this paper. The results of the experiments demonstrate that the network effectively preservesbackground and detail information in both infrared and visible images, yielding superior outcomes in subjectiveand objective evaluations.展开更多
In order to improve the work efficiency of non-destructive testing(NDT)and the reliability of NDT results,an automatic method to detect defects in the ultrasonic image was researched.According to the characterization ...In order to improve the work efficiency of non-destructive testing(NDT)and the reliability of NDT results,an automatic method to detect defects in the ultrasonic image was researched.According to the characterization of ultrasonic D-scan image,clutter wave suppression and de-noising were presented firstly.Then,the image is processed by binaryzation using KSW 2 D entropy based on image segmentation method.The results showed that,the global threshold based segmentation method was somewhat ineffective for D-scan image because of under-segmentation.Especially,when the image is big in size,small targets which are composed by a small amount of pixels are often undetected.Whereas,local threshold based image segmentation method is effective in recognizing small defects because it takes local image character into account.展开更多
The lunar map is a product of primary scientific objectives of lunar exploration. Aiming at the characteristics of the Chang＇E-2 CCD data, an automatic stitching method used for 2C level CCD data from Chang＇E-2 luna...The lunar map is a product of primary scientific objectives of lunar exploration. Aiming at the characteristics of the Chang＇E-2 CCD data, an automatic stitching method used for 2C level CCD data from Chang＇E-2 lunar mission is proposed. Combining with the image registration technique and the characteristics of Chang＇E CCD images, the fast method proposed not only can overcome the contradiction of the high spatial resolution of the CCD images and the low positioning accuracy of the location coordinates, but also can speed up the processing and minimize the utilization of human resources to produce lunar mosaic map. Meanwhile, a new lunar map from 70oN to 70oS with spatial resolution of less than 10 m has been completed by the proposed method. Its average relative location accuracy of the adjacent orbits CCD image data is less than 3 pixels.展开更多
A new image thresholding method is introduced, which is based on 2-D histgram and minimizing the measures of fuzziness of an input image. A new definition of fuzzy membership function is proposed, it denotes the chara...A new image thresholding method is introduced, which is based on 2-D histgram and minimizing the measures of fuzziness of an input image. A new definition of fuzzy membership function is proposed, it denotes the characteristic relationship between the gray level of each pixel and the average value of its neighborhood. When the threshold is not located at the obvious and deep valley of the histgram, genetic algorithm is devoted to the problem of selecting the appropriate threshold value. The experimental results indicate that the proposed method has good performance.展开更多
In recent years,Pix2Pix,a model within the domain of GANs,has found widespread application in the field of image-to-image translation.However,traditional Pix2Pix models suffer from significant drawbacks in image gener...In recent years,Pix2Pix,a model within the domain of GANs,has found widespread application in the field of image-to-image translation.However,traditional Pix2Pix models suffer from significant drawbacks in image generation,such as the loss of important information features during the encoding and decoding processes,as well as a lack of constraints during the training process.To address these issues and improve the quality of Pix2Pixgenerated images,this paper introduces two key enhancements.Firstly,to reduce information loss during encoding and decoding,we utilize the U-Net++network as the generator for the Pix2Pix model,incorporating denser skip-connection to minimize information loss.Secondly,to enhance constraints during image generation,we introduce a specialized discriminator designed to distinguish differential images,further enhancing the quality of the generated images.We conducted experiments on the facades dataset and the sketch portrait dataset from the Chinese University of Hong Kong to validate our proposed model.The experimental results demonstrate that our improved Pix2Pix model significantly enhances image quality and outperforms other models in the selected metrics.Notably,the Pix2Pix model incorporating the differential image discriminator exhibits the most substantial improvements across all metrics.An analysis of the experimental results reveals that the use of the U-Net++generator effectively reduces information feature loss,while the Pix2Pix model incorporating the differential image discriminator enhances the supervision of the generator during training.Both of these enhancements collectively improve the quality of Pix2Pix-generated images.展开更多
The generation method of the key stream and the structure of the algorithm determine the security of the cryptosystem.The classical chaotic map has simple dynamic behavior and few control parameters,so it is not suita...The generation method of the key stream and the structure of the algorithm determine the security of the cryptosystem.The classical chaotic map has simple dynamic behavior and few control parameters,so it is not suitable for modern cryptography.In this paper,we design a new 2D hyperchaotic system called 2D simple structure and complex dynamic behavior map(2D-SSCDB).The 2D-SSCDB has a simple structure but has complex dynamic behavior.The Lyapunov exponent verifies that the 2D-SSCDB has hyperchaotic behavior,and the parameter space in the hyperchaotic state is extensive and continuous.Trajectory analysis and some randomness tests verify that the 2D-SSCDB can generate random sequences with good performance.Next,to verify the excellent performance of the 2D-SSCDB,we use the 2D-SSCDB to generate a keystream for color image encryption.In the encryption algorithm,the encryption algorithm scrambles and diffuses simultaneously,increasing the cryptographic system’s security.The horizontal correlation,vertical correlation,and diagonal correlation of ciphertext are−0.0004,−0.0004 and 0.0007,respectively.The average information entropy of the ciphertext is 7.9993.In addition,the designed encryption algorithm reduces the correlation between the three channels of the color image.Security analysis shows that the color image encryption algorithm designed using 2DSSCDB has good security,can resist standard attack methods,and has high efficiency.展开更多
Objective To qualitatively assess the diagnostic performance of dynamic contrast enhancement(DCE),diffusionweighted imaging(DWI),and T2-weighted imaging(T2WI),alone or in combination,in the evaluation of breast cancer...Objective To qualitatively assess the diagnostic performance of dynamic contrast enhancement(DCE),diffusionweighted imaging(DWI),and T2-weighted imaging(T2WI),alone or in combination,in the evaluation of breast cancer.Methods We retrospectively reviewed the records of 394 consecutive patients with pathologically confirmed breast lesions who had undergone 3-T magnetic resonance imaging(MRI).The morphological characteristics of breast lesions were evaluated using DCE,DWI,and T2WI based on BI-RADS lexicon descriptors by trained radiologists.Patients were categorized into mass and non-mass groups based on MRI characteristics of the lesions,and the differences between benign and malignant lesions in each group were compared.Clinical prediction models for breast cancer diagnosis were constructed using logistic regression analysis.Diagnostic efficacies were compared using the area under the receiver operating characteristic curve(AUC)and DeLong test.Results For mass-like lesions,all the morphological parameters significantly differentiated benign and malignant lesions on consensus DCE,DWI,and T2WI(P<0.05).The combined method(DCE+DWI+T2WI)had a higher AUC(0.865)than any of the individual modality(DCE:0.786;DWI:0.793;T2WI:0.809)(P<0.05).For non-mass-like lesions,DWI signal intensity was a significant predictor of malignancy(P=0.036),but the model using DWI alone had a low AUC(0.669).Conclusion Morphological assessment using the combination of DCE,DWI,and T2WI provides better diagnostic value in differentiating benign and malignant breast mass-like lesions than assessment with only one of the modalities.展开更多
Assimilating Sentinel-2 images with the CERES-Wheat model can improve the precision of winter wheat yield estimates at a regional scale. To verify this method, we applied the ensemble Kalman filter(EnKF) to assimilate...Assimilating Sentinel-2 images with the CERES-Wheat model can improve the precision of winter wheat yield estimates at a regional scale. To verify this method, we applied the ensemble Kalman filter(EnKF) to assimilate the leaf area index(LAI) derived from Sentinel-2 data and simulated by the CERES-Wheat model. From this, we obtained the assimilated daily LAI during the growth stage of winter wheat across three counties located in the southeast of the Loess Plateau in China: Xiangfen, Xinjiang, and Wenxi. We assigned LAI weights at different growth stages by comparing the improved analytic hierarchy method, the entropy method, and the normalized combination weighting method, and constructed a yield estimation model with the measurements to accurately estimate the yield of winter wheat. We found that the changes of assimilated LAI during the growth stage of winter wheat strongly agreed with the simulated LAI. With the correction of the derived LAI from the Sentinel-2 images, the LAI from the green-up stage to the heading–filling stage was enhanced, while the LAI decrease from the milking stage was slowed down, which was more in line with the actual changes of LAI for winter wheat. We also compared the simulated and derived LAI and found the assimilated LAI had reduced the root mean square error(RMSE) by 0.43 and 0.29 m^(2) m^(–2), respectively, based on the measured LAI. The assimilation improved the estimation accuracy of the LAI time series. The highest determination coefficient(R2) was 0.8627 and the lowest RMSE was 472.92 kg ha^(–1) in the regression of the yields estimated by the normalized weighted assimilated LAI method and measurements. The relative error of the estimated yield of winter wheat in the study counties was less than 1%, suggesting that Sentinel-2 data with high spatial-temporal resolution can be assimilated with the CERES-Wheat model to obtain more accurate regional yield estimates.展开更多
基金supported by the 2020 Key project of Science and Technology for Economy(Grant No. SQ2020YFF0426316)。
文摘As an important part of the mass balance of the Ice Sheet,Supra-glacial Water not only reflects the diversity of polar environmental changes,but also plays an important role in the study of global climate and environmental changes.In this paper,we chose northern Greenland as the research area,and constructed a Normalized Enhanced Water Index(NEWI)based on the high-precision WorldView-2 images of different phases during the ablation period in northern Greenland,followed by a statistical analysis on the spectral characteristics of the images were for the typical features in the study area.Then the fuzzy areas with similar gray values of thin sea ice and shallow ice water bodies were located,according to the distribution rules of ground objects and histogram graphic features of the images,so as to enhance the contrast of ground objects between the regions,and finally the extraction of the fine range of water bodies on the ice surface.Experimental results showed that the proposed index effectively highlighted the ice water with the water of the reflectivity difference,compared with the commonly used water index NDWI,etc.,especially in shallow water,which contributes to differentiation from other objects.The precision evaluation showed that the applied method of extraction has higher degree of refinement compared with other methods,by which the ice water can get complete ice water effectively.
基金funded by the Deanship of Graduate Studies and Scientific Research at Jouf University under grant No.(DGSSR-2025-02-01295).
文摘Alzheimer’s Disease(AD)is a progressive neurodegenerative disorder that significantly affects cognitive function,making early and accurate diagnosis essential.Traditional Deep Learning(DL)-based approaches often struggle with low-contrast MRI images,class imbalance,and suboptimal feature extraction.This paper develops a Hybrid DL system that unites MobileNetV2 with adaptive classification methods to boost Alzheimer’s diagnosis by processing MRI scans.Image enhancement is done using Contrast-Limited Adaptive Histogram Equalization(CLAHE)and Enhanced Super-Resolution Generative Adversarial Networks(ESRGAN).A classification robustness enhancement system integrates class weighting techniques and a Matthews Correlation Coefficient(MCC)-based evaluation method into the design.The trained and validated model gives a 98.88%accuracy rate and 0.9614 MCC score.We also performed a 10-fold cross-validation experiment with an average accuracy of 96.52%(±1.51),a loss of 0.1671,and an MCC score of 0.9429 across folds.The proposed framework outperforms the state-of-the-art models with a 98%weighted F1-score while decreasing misdiagnosis results for every AD stage.The model demonstrates apparent separation abilities between AD progression stages according to the results of the confusion matrix analysis.These results validate the effectiveness of hybrid DL models with adaptive preprocessing for early and reliable Alzheimer’s diagnosis,contributing to improved computer-aided diagnosis(CAD)systems in clinical practice.
基金supported by the Interdisciplinary project of Dalian University DLUXK-2023-ZD-001.
文摘As a form of discrete representation learning,Vector Quantized Variational Autoencoders(VQ-VAE)have increasingly been applied to generative and multimodal tasks due to their ease of embedding and representative capacity.However,existing VQ-VAEs often perform quantization in the spatial domain,ignoring global structural information and potentially suffering from codebook collapse and information coupling issues.This paper proposes a frequency quantized variational autoencoder(FQ-VAE)to address these issues.The proposed method transforms image features into linear combinations in the frequency domain using a 2D fast Fourier transform(2D-FFT)and performs adaptive quantization on these frequency components to preserve image’s global relationships.The codebook is dynamically optimized to avoid collapse and information coupling issue by considering the usage frequency and dependency of code vectors.Furthermore,we introduce a post-processing module based on graph convolutional networks to further improve reconstruction quality.Experimental results on four public datasets demonstrate that the proposed method outperforms state-of-the-art approaches in terms of Structural Similarity Index(SSIM),Learned Perceptual Image Patch Similarity(LPIPS),and Reconstruction Fréchet Inception Distance(rFID).In the experiments on the CIFAR-10 dataset,compared to the baselinemethod VQ-VAE,the proposedmethod improves the abovemetrics by 4.9%,36.4%,and 52.8%,respectively.
文摘Land surface water mapping is one of the most important remote-sensing applications.However,water areas are spectrally similar and overlapped with shadow,making accurate water extraction from remote-sensing images still a challenging problem.This paper develops a novel water index named as NDWI-MSI,combining a new normalized difference water index(NDWI)and a recently developed morphological shadow index(MSI),to delineate water bodies from eight-band WorldView-2 imagery.The newly available bands(e.g.coastal,yellow,red-edge,and near-infrared 2)of WorldView-2 imagery provide more potential for constructing new NDWIs derived from various band combinations.Through our testing,a new NDWI is defined in this study.In addition,MSI,a recently developed automatic shadow extraction index from high-resolution imagery can be used to indicate shadow areas.The NDWI-MSI is created by combining NDWI and MSI,which is able to highlight water bodies and simultaneously suppress shadow areas.In experiments,it is shown that the new water index can achieve better performance than traditional NDWI,and even supervised classifiers,for example,maximum likelihood classifier,and support vector machine.
文摘The detection of impervious surface (IS) in heterogeneous urban areas is one of the most challenging tasks in urban remote sensing. One of the limitations in IS detection at the parcel level is the lack of sufficient training data. In this study, a generic model of spatial distribution of roof materials is considered to overcome this limitation. A generic model that is based on spectral, spatial and textural information which is extracted from available training data is proposed. An object-based approach is used to extract the information inherent in the image. Furthermore, linear discriminant analysis is used for dimensionality reduction and to discriminate between different spatial, spectral and textural attributes. The generic model is composed of a discriminant function based on linear combinations of the predictor variables that provide the best discrimination among the groups. The discriminate analysis result shows that of the 54 attributes extracted from the WorldView-2 image, only 13 attributes related to spatial, spectral and textural information are useful for discriminating different roof materials. Finally, this model is applied to different WorldView-2 images from different areas and proves that this model has good potential to predict roof materials from the WorldView-2 images without using training data.
基金supported by the National Natural Science Foundation of China(Grant Nos.42001358 and 42201353)the Guangdong Basic and Applied Basic Research Foundation(Grant Nos.2021A1515011462 and 2021A1515110157)+1 种基金the Guangzhou Science,Technology and Innovation Commission(Grant No.201804020016)Forestry Science and Technology Innovation Project of Guangdong Province(Grant No.2023KJCX008).
文摘Background Integrating optical and LiDAR data is crucial for accurately predicting aboveground biomass(AGB)due to their complementarily essential characteristics.It can be anticipated that this integration approach needs to deal with an expanded set of variables and scale-related challenges.To achieve satisfactory accuracy in real-world applications,further exploration is needed to optimize AGB models by selecting appropriate scales and variables.Methods This study examined the impact of LiDAR point cloud-derived metrics on estimation accuracies at diferent scales,ranging from 2 to 16 m cell sizes.We integrated WorldView-2 imagery with LiDAR data to construct biomass models and developed a genetic algorithm-based wrapper for variable selection and parameter tuning in artifcial neural networks(GA-ANN wrapper).Results Our fndings indicated that the highest accuracies in estimating AGB were yielded by 4 m and 6 m cell sizes,followed by 8 m and 10 m,associated with the dimensions of vegetation canopies and sampling plots.Models integrating WorldView-2 and LiDAR data outperformed those using each data source individually,reducing RMSEr by 5.80%and 3.89%,respectively.Combining these data sources can capture the canopy spectral responses and vertical vegetation structure.The GA-ANN wrapper model decreased RMSEr by 1.69%over the ANN model and dwindled the number of variables from 38 to 9.The selected variables included vegetation density,height,species,and vegetation indices.Conclusions The appropriate cell size for AGB estimation should consider the sizes of vegetation canopies,tree densities,and sampling plots.The GA-ANN wrapper efectively reduced variables and achieved the highest accuracy.Additionally,canopy spectral and vertical structure information are vital for accurate AGB estimation.Our study ofered insights into optimizing mangrove AGB models by integrating optical and LiDAR data.The approach,data,model,and indices employed in this research can efectively predict AGB estimates of any other forest types or vegetation cover types in diferent climate regions.
文摘目的探讨T_2 star mapping、T_1 images与3D DESS融合伪彩图在关节软骨损伤中的诊断价值。方法对26例关节软骨损伤患者行T_2 star mapping、T_1 images和3D DESS扫描,并将T_1 images、T_2 star mapping与3D DESS图像融合,评价患者股骨、胫骨、髌骨关节软骨损伤程度并与关节镜结果对比,计算融合伪彩图诊断软骨损伤的特异性、敏感性及与关节镜诊断结果一致性。结果 T_1 images-3D DESS融合伪彩图诊断关节软骨损伤的敏感度、特异度及Kappa值分别为92.8%、93.0%、0.769,T_2 star mapping-3D DESS融合伪彩图诊断关节软骨损伤的敏感度、特异度及Kappa值分别为91.4%、94.2%、0.787。结论 T_2 star mapping、T_1 images与3D DESS融合伪彩图在关节软骨早期损伤评价上优于关节镜。
文摘新近,欧洲糖尿病预防指南与培训标准工作组(Development and Implementation of a European Guideline and Training Standards for Diabetes Prevention,IMAGE)颁布了2型糖尿病(T2DM)预防指南,其要点摘译如下:
基金supported by National Key Research&Development Program of China“Research on key technologies for prevention and control of major disasters in plantation”(Grant No.2018YFD0600200)Beijing’s Science and Technology Planning Project“Key technologies for prevention and control of major pests in Beijing ecological public welfare forests”(Grant Nos.Z191100008519004 and Z201100008020001).
文摘Background:Anoplophora glabripennis(Motschulsky),commonly known as Asian longhorned beetle(ALB),is a wood-boring insect that can cause lethal infestation to multiple borer leaf trees.In Gansu Province,northwest China,ALB has caused a large number of deaths of a local tree species Populus gansuensis.The damaged area belongs to Gobi desert where every single tree is artificially planted and is extremely difficult to cultivate.Therefore,the monitoring of the ALB infestation at the individual tree level in the landscape is necessary.Moreover,the determination of an abnormal phenotype that can be obtained directly from remote-sensing images to predict the damage degree can greatly reduce the cost of field investigation and management.Methods:Multispectral WorldView-2(WV-2)images and 5 tree physiological factors were collected as experimental materials.One-way ANOVA of the tree’s physiological factors helped in determining the phenotype to predict damage degrees.The original bands of WV-2 and derived vegetation indices were used as reference data to construct the dataset of a prediction model.Variance inflation factor and stepwise regression analyses were used to eliminate collinearity and redundancy.Finally,three machine learning algorithms,i.e.,Random Forest(RF),Support Vector Machine(SVM),Classification And Regression Tree(CART),were applied and compared to find the best classifier for predicting the damage stage of individual P.gansuensis.Results:The confusion matrix of RF achieved the highest overall classification accuracy(86.2%)and the highest Kappa index value(0.804),indicating the potential of using WV-2 imaging to accurately detect damage stages of individual trees.In addition,the canopy color was found to be positively correlated with P.gansuensis’damage stages.Conclusions:A novel method was developed by combining WV-2 and tree physiological index for semi-automatic classification of three damage stages of P.gansuensis infested with ALB.The canopy color was determined as an abnormal phenotype that could be directly assessed using remote-sensing images at the tree level to predict the damage degree.These tools are highly applicable for driving quick and effective measures to reduce damage to pure poplar forests in Gansu Province,China.
基金supported by the China Postdoctoral Science Foundation(20100471451)the Science and Technology Foundation of State Key Laboratory of Underwater Measurement&Control Technology(9140C2603051003)
文摘In the methods of image thresholding segmentation, such methods based on two-dimensional （2D） histogram and optimal objective functions are important. However, when they are used for infrared image segmentation, they are weak in suppressing background noises and worse in segmenting targets with non-uniform gray level. The concept of 2D histogram shape modification is proposed, which is realized by target information prior restraint after enhancing target information using plateau histogram equalization. The formula of 2D minimum Renyi entropy is deduced for image segmentation, then the shape-modified 2D histogram is combined wfth four optimal objective functions （i.e., maximum between-class variance, maximum entropy, maximum correlation and minimum Renyi entropy） respectively for the appli- cation of infrared image segmentation. Simultaneously, F-measure is introduced to evaluate the segmentation effects objectively. The experimental results show that F-measure is an effective evaluation index for image segmentation since its value is fully consistent with the subjective evaluation, and after 2D histogram shape modification, the methods of optimal objective functions can overcome their original forms＇ deficiency and their segmentation effects are more or less improvements, where the best one is the maximum entropy method based on 2D histogram shape modification.
文摘A novel image fusion network framework with an autonomous encoder and decoder is suggested to increase thevisual impression of fused images by improving the quality of infrared and visible light picture fusion. The networkcomprises an encoder module, fusion layer, decoder module, and edge improvementmodule. The encoder moduleutilizes an enhanced Inception module for shallow feature extraction, then combines Res2Net and Transformerto achieve deep-level co-extraction of local and global features from the original picture. An edge enhancementmodule (EEM) is created to extract significant edge features. A modal maximum difference fusion strategy isintroduced to enhance the adaptive representation of information in various regions of the source image, therebyenhancing the contrast of the fused image. The encoder and the EEM module extract features, which are thencombined in the fusion layer to create a fused picture using the decoder. Three datasets were chosen to test thealgorithmproposed in this paper. The results of the experiments demonstrate that the network effectively preservesbackground and detail information in both infrared and visible images, yielding superior outcomes in subjectiveand objective evaluations.
基金supported by the National Nature Science Foundation of China(51375002,51005056)。
文摘In order to improve the work efficiency of non-destructive testing(NDT)and the reliability of NDT results,an automatic method to detect defects in the ultrasonic image was researched.According to the characterization of ultrasonic D-scan image,clutter wave suppression and de-noising were presented firstly.Then,the image is processed by binaryzation using KSW 2 D entropy based on image segmentation method.The results showed that,the global threshold based segmentation method was somewhat ineffective for D-scan image because of under-segmentation.Especially,when the image is big in size,small targets which are composed by a small amount of pixels are often undetected.Whereas,local threshold based image segmentation method is effective in recognizing small defects because it takes local image character into account.
基金supported in part by the Science and Technology Development Fund of Macao,China (Nos.048/2016/A2,110/2014/A3,091/2013/A3,084/2012/A3,and 048/2012/A2)the National Natural Science Foundation of China (Nos.61170320 and 61272364)the Open Project Program of the State Key Lab of CAD & CG of Zhejiang University (No.A1513)
文摘The lunar map is a product of primary scientific objectives of lunar exploration. Aiming at the characteristics of the Chang＇E-2 CCD data, an automatic stitching method used for 2C level CCD data from Chang＇E-2 lunar mission is proposed. Combining with the image registration technique and the characteristics of Chang＇E CCD images, the fast method proposed not only can overcome the contradiction of the high spatial resolution of the CCD images and the low positioning accuracy of the location coordinates, but also can speed up the processing and minimize the utilization of human resources to produce lunar mosaic map. Meanwhile, a new lunar map from 70oN to 70oS with spatial resolution of less than 10 m has been completed by the proposed method. Its average relative location accuracy of the adjacent orbits CCD image data is less than 3 pixels.
基金This project was supported by Science and Technology Research Emphasis Fund of Ministry of Education(204010) .
文摘A new image thresholding method is introduced, which is based on 2-D histgram and minimizing the measures of fuzziness of an input image. A new definition of fuzzy membership function is proposed, it denotes the characteristic relationship between the gray level of each pixel and the average value of its neighborhood. When the threshold is not located at the obvious and deep valley of the histgram, genetic algorithm is devoted to the problem of selecting the appropriate threshold value. The experimental results indicate that the proposed method has good performance.
基金supported in part by the Xinjiang Natural Science Foundation of China(2021D01C078).
文摘In recent years,Pix2Pix,a model within the domain of GANs,has found widespread application in the field of image-to-image translation.However,traditional Pix2Pix models suffer from significant drawbacks in image generation,such as the loss of important information features during the encoding and decoding processes,as well as a lack of constraints during the training process.To address these issues and improve the quality of Pix2Pixgenerated images,this paper introduces two key enhancements.Firstly,to reduce information loss during encoding and decoding,we utilize the U-Net++network as the generator for the Pix2Pix model,incorporating denser skip-connection to minimize information loss.Secondly,to enhance constraints during image generation,we introduce a specialized discriminator designed to distinguish differential images,further enhancing the quality of the generated images.We conducted experiments on the facades dataset and the sketch portrait dataset from the Chinese University of Hong Kong to validate our proposed model.The experimental results demonstrate that our improved Pix2Pix model significantly enhances image quality and outperforms other models in the selected metrics.Notably,the Pix2Pix model incorporating the differential image discriminator exhibits the most substantial improvements across all metrics.An analysis of the experimental results reveals that the use of the U-Net++generator effectively reduces information feature loss,while the Pix2Pix model incorporating the differential image discriminator enhances the supervision of the generator during training.Both of these enhancements collectively improve the quality of Pix2Pix-generated images.
基金Funds for New Generation Information Technology of the Industry-University-Research Innovation Foundation of China University(No.2020ITA03022).
文摘The generation method of the key stream and the structure of the algorithm determine the security of the cryptosystem.The classical chaotic map has simple dynamic behavior and few control parameters,so it is not suitable for modern cryptography.In this paper,we design a new 2D hyperchaotic system called 2D simple structure and complex dynamic behavior map(2D-SSCDB).The 2D-SSCDB has a simple structure but has complex dynamic behavior.The Lyapunov exponent verifies that the 2D-SSCDB has hyperchaotic behavior,and the parameter space in the hyperchaotic state is extensive and continuous.Trajectory analysis and some randomness tests verify that the 2D-SSCDB can generate random sequences with good performance.Next,to verify the excellent performance of the 2D-SSCDB,we use the 2D-SSCDB to generate a keystream for color image encryption.In the encryption algorithm,the encryption algorithm scrambles and diffuses simultaneously,increasing the cryptographic system’s security.The horizontal correlation,vertical correlation,and diagonal correlation of ciphertext are−0.0004,−0.0004 and 0.0007,respectively.The average information entropy of the ciphertext is 7.9993.In addition,the designed encryption algorithm reduces the correlation between the three channels of the color image.Security analysis shows that the color image encryption algorithm designed using 2DSSCDB has good security,can resist standard attack methods,and has high efficiency.
文摘Objective To qualitatively assess the diagnostic performance of dynamic contrast enhancement(DCE),diffusionweighted imaging(DWI),and T2-weighted imaging(T2WI),alone or in combination,in the evaluation of breast cancer.Methods We retrospectively reviewed the records of 394 consecutive patients with pathologically confirmed breast lesions who had undergone 3-T magnetic resonance imaging(MRI).The morphological characteristics of breast lesions were evaluated using DCE,DWI,and T2WI based on BI-RADS lexicon descriptors by trained radiologists.Patients were categorized into mass and non-mass groups based on MRI characteristics of the lesions,and the differences between benign and malignant lesions in each group were compared.Clinical prediction models for breast cancer diagnosis were constructed using logistic regression analysis.Diagnostic efficacies were compared using the area under the receiver operating characteristic curve(AUC)and DeLong test.Results For mass-like lesions,all the morphological parameters significantly differentiated benign and malignant lesions on consensus DCE,DWI,and T2WI(P<0.05).The combined method(DCE+DWI+T2WI)had a higher AUC(0.865)than any of the individual modality(DCE:0.786;DWI:0.793;T2WI:0.809)(P<0.05).For non-mass-like lesions,DWI signal intensity was a significant predictor of malignancy(P=0.036),but the model using DWI alone had a low AUC(0.669).Conclusion Morphological assessment using the combination of DCE,DWI,and T2WI provides better diagnostic value in differentiating benign and malignant breast mass-like lesions than assessment with only one of the modalities.
基金supported by the National Key Research and Development Program of China (2018YFD020040103)the National Key Research and Development Program of Shanxi Province, China (201803D221005-2)。
文摘Assimilating Sentinel-2 images with the CERES-Wheat model can improve the precision of winter wheat yield estimates at a regional scale. To verify this method, we applied the ensemble Kalman filter(EnKF) to assimilate the leaf area index(LAI) derived from Sentinel-2 data and simulated by the CERES-Wheat model. From this, we obtained the assimilated daily LAI during the growth stage of winter wheat across three counties located in the southeast of the Loess Plateau in China: Xiangfen, Xinjiang, and Wenxi. We assigned LAI weights at different growth stages by comparing the improved analytic hierarchy method, the entropy method, and the normalized combination weighting method, and constructed a yield estimation model with the measurements to accurately estimate the yield of winter wheat. We found that the changes of assimilated LAI during the growth stage of winter wheat strongly agreed with the simulated LAI. With the correction of the derived LAI from the Sentinel-2 images, the LAI from the green-up stage to the heading–filling stage was enhanced, while the LAI decrease from the milking stage was slowed down, which was more in line with the actual changes of LAI for winter wheat. We also compared the simulated and derived LAI and found the assimilated LAI had reduced the root mean square error(RMSE) by 0.43 and 0.29 m^(2) m^(–2), respectively, based on the measured LAI. The assimilation improved the estimation accuracy of the LAI time series. The highest determination coefficient(R2) was 0.8627 and the lowest RMSE was 472.92 kg ha^(–1) in the regression of the yields estimated by the normalized weighted assimilated LAI method and measurements. The relative error of the estimated yield of winter wheat in the study counties was less than 1%, suggesting that Sentinel-2 data with high spatial-temporal resolution can be assimilated with the CERES-Wheat model to obtain more accurate regional yield estimates.
