Measurement of vegetation coverage on a small scale is the foundation for the monitoring of changes in vegetation coverage and of the inversion model of monitoring vegetation coverage on a large scale by remote sensin...Measurement of vegetation coverage on a small scale is the foundation for the monitoring of changes in vegetation coverage and of the inversion model of monitoring vegetation coverage on a large scale by remote sensing. Using the object-oriented analytical software, Definiens Professional 5, a new method for calculating vegetation coverage based on high-resolution images （aerial photographs or near-surface photography） is proposed. Our research supplies references to remote sensing measurements of vegetation coverage on a small scale and accurate fundamental data for the inversion model of vegetation coverage on a large and intermediate scale to improve the accuracy of remote sensing monitoring of changes in vegetation coverage.展开更多
Nowadays, remote sensing imagery, especially with its high spatialresolution, has become an indispensable tool to provide timely up-gradation of urban land use andland cover information, which is a prerequisite for pr...Nowadays, remote sensing imagery, especially with its high spatialresolution, has become an indispensable tool to provide timely up-gradation of urban land use andland cover information, which is a prerequisite for proper urban planning and management. Thepossible method described in the present paper to obtain urban land use types is based on theprinciple that land use can be derived from the land cover existing in a neighborhood. Here, movingwindow is used to represent the spatial pattern of land cover within a neighborhood and seven windowsizes (61mx61m, 68mx68m, 75mx75m, 87mx87m, 99mx99m, 110mx110m and 121mxl21m) are applied todetermining the most proper window size. Then, the unsupervised method of ISODATA is employed toclassify the layered land cover density maps obtained by the moving window. The results of accuracyevaluation show that the window size of 99mx99m is proper to infer urban land use categories and theproposed method has produced a land use map with a total accuracy of 85%.展开更多
Ephemeral gullies,which are widely developed worldwide and threaten farmlands,have aroused a growing concern.Identifying and mapping gullies are generally considered prerequisites of gully erosion assessment.However,e...Ephemeral gullies,which are widely developed worldwide and threaten farmlands,have aroused a growing concern.Identifying and mapping gullies are generally considered prerequisites of gully erosion assessment.However,ephemeral gully mapping remains a challenge.In this study,we proposed a flow-directional detection for identifying ephemeral gullies from high-resolution images and digital elevation models(DEMs).Ephemeral gullies exhibit clear linear features in high-resolution images.An edge detection operator was initially used to identify linear features from high-resolution images.Then,according to gully erosion mechanism,the flow-directional detection was designed.Edge images obtained from edge detection and flow directions obtained from DEMs were used to implement the flow-directional detection that detects ephemeral gullies along the flow direction.Results from ten study areas in the Loess Plateau of China showed that ranges of precision,recall,and Fmeasure are 6 o.66%-90.47%,65.74%-94.98%,and63.10%-91.93%,respectively.The proposed method is flexible and can be used with various images and DEMs.However,analysis of the effect of DEM resolution and accuracy showed that DEM resolution only demonstrates a minor effect on the detection results.Conversely,DEM accuracy influences the detection result and is more important than the DEM resolution.The worse the vertical accuracy of DEM,the lower the performance of the flow-directional detection will be.This work is beneficial to research related to monitoring gully erosion and assessing soil loss.展开更多
On the basis of a thorough understanding of the physical characteristics of remote sensing image, this paper employs the theories of wavelet transform and signal sampling to develop a new image fusion algorithm. The a...On the basis of a thorough understanding of the physical characteristics of remote sensing image, this paper employs the theories of wavelet transform and signal sampling to develop a new image fusion algorithm. The algorithm has been successfully applied to the image fusion of SPOT PAN and TM of Guangdong province, China. The experimental results show that a perfect image fusion can be built up by using the image analytical solution and re-construction in the image frequency domain based on the physical characteristics of the image formation. The method has demonstrated that the results of the image fusion do not change spectral characteristics of the original image.展开更多
A large number of debris flow disasters(called Seismic debris flows) would occur after an earthquake, which can cause a great amount of damage. UAV low-altitude remote sensing technology has become a means of quickly ...A large number of debris flow disasters(called Seismic debris flows) would occur after an earthquake, which can cause a great amount of damage. UAV low-altitude remote sensing technology has become a means of quickly obtaining disaster information as it has the advantage of convenience and timeliness, but the spectral information of the image is so scarce, making it difficult to accurately detect the information of earthquake debris flow disasters. Based on the above problems, a seismic debris flow detection method based on transfer learning(TL) mechanism is proposed. On the basis of the constructed seismic debris flow disaster database, the features acquired from the training of the convolutional neural network(CNN) are transferred to the disaster information detection of the seismic debris flow. The automatic detection of earthquake debris flow disaster information is then completed, and the results of object-oriented seismic debris flow disaster information detection are compared and analyzed with the detection results supported by transfer learning.展开更多
BACKGROUND Fistula-in-ano is an abnormal tunnel formation linking the anal canal with the perineum and perianal skin.Multiple imagining methods are available to evaluate it,among which magnetic resonance imaging(MRI)i...BACKGROUND Fistula-in-ano is an abnormal tunnel formation linking the anal canal with the perineum and perianal skin.Multiple imagining methods are available to evaluate it,among which magnetic resonance imaging(MRI)is the most advanced nonin-vasive preoperative method.However,it is limited in its visualization function.AIM To investigate the use of intraluminal MRI for perianal fistulas via a novel direct MRI fistulography method.METHODS We mixed 3%hydrogen peroxide(HP)with gadolinium for HPMRI fistulogra-phy,retrospectively analyzing 60 cases of complex/recurrent fistula-in-ano using physical examination,trans-perineal ultrasonography(TPUS),low-spatial-reso-lution MRI,and high-resolution direct HPMRI fistulography.We assessed detec-tion rates of fistula tracks,internal openings,their relationship with anal sphinc-ters,and perianal abscesses using statistical analyses,including interobserver agreement(Kappa statistic),and compared results with intraoperative findings.RESULTS Surgical confirmation in 60 cases showed that high-resolution direct HPMRI fis-tulography provided superior detection rates for internal openings(153)and fistula tracks(162)compared to physical exams,TPUS,and low-spatial-resolution MRI(Z>5.7,P<0.05).The effectiveness of physical examination and TPUS was also inferior to that of our method for detecting perianal abscesses(54)(Z=6.773,3.694,P<0.05),whereas that of low-spatial-resolution MRI was not significantly different(Z=1.851,P=0.06).High-resolution direct HPMRI fistulography also achieved the highest interobserver agreement(Kappa:0.89,0.85,and 0.80),while low-spatial-resolution MRI showed moderate agreement(Kappa:0.78,0.74,and 0.69).TPUS and physical examination had lower agreement(Kappa range:0.33-0.63).CONCLUSION High-resolution direct HPMRI fistulography enhances the visualization of recurrent and complex fistula-in-ano,including branched fistulas,allowing for precise planning and improved surgical outcomes.展开更多
Cloud detection from satellite and drone imagery is crucial for applications such as weather forecasting and environmentalmonitoring.Addressing the limitations of conventional convolutional neural networks,we propose ...Cloud detection from satellite and drone imagery is crucial for applications such as weather forecasting and environmentalmonitoring.Addressing the limitations of conventional convolutional neural networks,we propose an innovative transformer-based method.This method leverages transformers,which are adept at processing data sequences,to enhance cloud detection accuracy.Additionally,we introduce a Cyclic Refinement Architecture that improves the resolution and quality of feature extraction,thereby aiding in the retention of critical details often lost during cloud detection.Our extensive experimental validation shows that our approach significantly outperforms established models,excelling in high-resolution feature extraction and precise cloud segmentation.By integrating Positional Visual Transformers(PVT)with this architecture,our method advances high-resolution feature delineation and segmentation accuracy.Ultimately,our research offers a novel perspective for surmounting traditional challenges in cloud detection and contributes to the advancement of precise and dependable image analysis across various domains.展开更多
Significant advancements have been achieved in road surface extraction based on high-resolution remote sensingimage processing. Most current methods rely on fully supervised learning, which necessitates enormous human...Significant advancements have been achieved in road surface extraction based on high-resolution remote sensingimage processing. Most current methods rely on fully supervised learning, which necessitates enormous humaneffort to label the image. Within this field, other research endeavors utilize weakly supervised methods. Theseapproaches aim to reduce the expenses associated with annotation by leveraging sparsely annotated data, such asscribbles. This paper presents a novel technique called a weakly supervised network using scribble-supervised andedge-mask (WSSE-net). This network is a three-branch network architecture, whereby each branch is equippedwith a distinct decoder module dedicated to road extraction tasks. One of the branches is dedicated to generatingedge masks using edge detection algorithms and optimizing road edge details. The other two branches supervise themodel’s training by employing scribble labels and spreading scribble information throughout the image. To addressthe historical flaw that created pseudo-labels that are not updated with network training, we use mixup to blendprediction results dynamically and continually update new pseudo-labels to steer network training. Our solutiondemonstrates efficient operation by simultaneously considering both edge-mask aid and dynamic pseudo-labelsupport. The studies are conducted on three separate road datasets, which consist primarily of high-resolutionremote-sensing satellite photos and drone images. The experimental findings suggest that our methodologyperforms better than advanced scribble-supervised approaches and specific traditional fully supervised methods.展开更多
Current data-driven deep learning(DL)methods typically reconstruct subsurface velocity models directly from pre-stack seismic records.However,these purely data-driven methods are often less robust and produce results ...Current data-driven deep learning(DL)methods typically reconstruct subsurface velocity models directly from pre-stack seismic records.However,these purely data-driven methods are often less robust and produce results that are less physically interpretative.Here,the authors propose a new method that uses migration images as input,combined with convolutional neural networks to construct high-resolution velocity models.Compared to directly using pre-stack seismic records as input,the nonlinearity between migration images and velocity models is significantly reduced.Additionally,the advantage of using migration images lies in its ability to more comprehensively capture the reflective properties of the subsurface medium,including amplitude and phase information,thereby to provide richer physical information in guiding the reconstruction of the velocity model.This approach not only improves the accuracy and resolution of the reconstructed velocity models,but also enhances the physical interpretability and robustness.Numerical experiments on synthetic data show that the proposed method has superior reconstruction performance and strong generalization capability when dealing with complex geological structures,and shows great potential in providing efficient solutions for the task of reconstructing high-wavenumber components.展开更多
The commercial high-resolution imaging satellite with 1 m spatial resolution IKONOS is an important data source of information for urban planning and geographical information system (GIS) applications. In this paper, ...The commercial high-resolution imaging satellite with 1 m spatial resolution IKONOS is an important data source of information for urban planning and geographical information system (GIS) applications. In this paper, a morphological method is proposed. The proposed method combines the automatic thresholding and morphological operation techniques to extract the road centerline of the urban environment. This method intends to solve urban road centerline problems, vehicle, vegetation, building etc. Based on this morphological method, an object extractor is designed to extract road networks from highly remote sensing images. Some filters are applied in this experiment such as line reconstruction and region filling techniques to connect the disconnected road segments and remove the small redundant. Finally, the thinning algorithm is used to extract the road centerline. Experiments have been conducted on a high-resolution IKONOS and QuickBird images showing the efficiency of the proposed method.展开更多
Machine learning(ML)is increasingly applied for medical image processing with appropriate learning paradigms.These applications include analyzing images of various organs,such as the brain,lung,eye,etc.,to identify sp...Machine learning(ML)is increasingly applied for medical image processing with appropriate learning paradigms.These applications include analyzing images of various organs,such as the brain,lung,eye,etc.,to identify specific flaws/diseases for diagnosis.The primary concern of ML applications is the precise selection of flexible image features for pattern detection and region classification.Most of the extracted image features are irrelevant and lead to an increase in computation time.Therefore,this article uses an analytical learning paradigm to design a Congruent Feature Selection Method to select the most relevant image features.This process trains the learning paradigm using similarity and correlation-based features over different textural intensities and pixel distributions.The similarity between the pixels over the various distribution patterns with high indexes is recommended for disease diagnosis.Later,the correlation based on intensity and distribution is analyzed to improve the feature selection congruency.Therefore,the more congruent pixels are sorted in the descending order of the selection,which identifies better regions than the distribution.Now,the learning paradigm is trained using intensity and region-based similarity to maximize the chances of selection.Therefore,the probability of feature selection,regardless of the textures and medical image patterns,is improved.This process enhances the performance of ML applications for different medical image processing.The proposed method improves the accuracy,precision,and training rate by 13.19%,10.69%,and 11.06%,respectively,compared to other models for the selected dataset.The mean error and selection time is also reduced by 12.56%and 13.56%,respectively,compared to the same models and dataset.展开更多
Large language models(LLMs),such as ChatGPT developed by OpenAI,represent a significant advancement in artificial intelligence(AI),designed to understand,generate,and interpret human language by analyzing extensive te...Large language models(LLMs),such as ChatGPT developed by OpenAI,represent a significant advancement in artificial intelligence(AI),designed to understand,generate,and interpret human language by analyzing extensive text data.Their potential integration into clinical settings offers a promising avenue that could transform clinical diagnosis and decision-making processes in the future(Thirunavukarasu et al.,2023).This article aims to provide an in-depth analysis of LLMs’current and potential impact on clinical practices.Their ability to generate differential diagnosis lists underscores their potential as invaluable tools in medical practice and education(Hirosawa et al.,2023;Koga et al.,2023).展开更多
Existing semi-supervisedmedical image segmentation algorithms use copy-paste data augmentation to correct the labeled-unlabeled data distribution mismatch.However,current copy-paste methods have three limitations:(1)t...Existing semi-supervisedmedical image segmentation algorithms use copy-paste data augmentation to correct the labeled-unlabeled data distribution mismatch.However,current copy-paste methods have three limitations:(1)training the model solely with copy-paste mixed pictures from labeled and unlabeled input loses a lot of labeled information;(2)low-quality pseudo-labels can cause confirmation bias in pseudo-supervised learning on unlabeled data;(3)the segmentation performance in low-contrast and local regions is less than optimal.We design a Stochastic Augmentation-Based Dual-Teaching Auxiliary Training Strategy(SADT),which enhances feature diversity and learns high-quality features to overcome these problems.To be more precise,SADT trains the Student Network by using pseudo-label-based training from Teacher Network 1 and supervised learning with labeled data,which prevents the loss of rare labeled data.We introduce a bi-directional copy-pastemask with progressive high-entropy filtering to reduce data distribution disparities and mitigate confirmation bias in pseudo-supervision.For the mixed images,Deep-Shallow Spatial Contrastive Learning(DSSCL)is proposed in the feature spaces of Teacher Network 2 and the Student Network to improve the segmentation capabilities in low-contrast and local areas.In this procedure,the features retrieved by the Student Network are subjected to a random feature perturbation technique.On two openly available datasets,extensive trials show that our proposed SADT performs much better than the state-ofthe-art semi-supervised medical segmentation techniques.Using only 10%of the labeled data for training,SADT was able to acquire a Dice score of 90.10%on the ACDC(Automatic Cardiac Diagnosis Challenge)dataset.展开更多
BACKGROUND Intracranial atherosclerosis,a leading cause of stroke,involves arterial plaque formation.This study explores the link between plaque remodelling patterns and diabetes using high-resolution vessel wall imag...BACKGROUND Intracranial atherosclerosis,a leading cause of stroke,involves arterial plaque formation.This study explores the link between plaque remodelling patterns and diabetes using high-resolution vessel wall imaging(HR-VWI).AIM To investigate the factors of intracranial atherosclerotic remodelling patterns and the relationship between intracranial atherosclerotic remodelling and diabetes mellitus using HR-VWI.METHODS Ninety-four patients diagnosed with middle cerebral artery or basilar artery INTRODUCTION Intracranial atherosclerotic disease is one of the main causes of ischaemic stroke in the world,accounting for approx-imately 10%of transient ischaemic attacks and 30%-50%of ischaemic strokes[1].It is the most common factor among Asian people[2].The adaptive changes in the structure and function of blood vessels that can adapt to changes in the internal and external environment are called vascular remodelling,which is a common and important pathological mechanism in atherosclerotic diseases,and the remodelling mode of atherosclerotic plaques is closely related to the occurrence of stroke.Positive remodelling(PR)is an outwards compensatory remodelling where the arterial wall grows outwards in an attempt to maintain a constant lumen diameter.For a long time,it was believed that the degree of stenosis can accurately reflect the risk of ischaemic stroke[3-5].Previous studies have revealed that lesions without significant luminal stenosis can also lead to acute events[6,7],as summarized in a recent meta-analysis study in which approximately 50%of acute/subacute ischaemic events were due to this type of lesion[6].Research[8,9]has pointed out that the PR of plaques is more dangerous and more likely to cause acute ischaemic stroke.Previous studies[10-13]have found that there are specific vascular remodelling phenomena in the coronary and carotid arteries of diabetic patients.However,due to the deep location and small lumen of intracranial arteries and limitations of imaging techniques,the relationship between intracranial arterial remodelling and diabetes is still unclear.In recent years,with the development of magnetic resonance technology and the emergence of high-resolution(HR)vascular wall imaging,a clear and multidimensional display of the intracranial vascular wall has been achieved.Therefore,in this study,HR wall imaging(HR-VWI)was used to display the remodelling characteristics of bilateral middle cerebral arteries and basilar arteries and to explore the factors of intracranial vascular remodelling and its relationship with diabetes.展开更多
BACKGROUND Vertebral artery dissection(VAD)is a rare but life-threatening condition characterized by tearing of the intimal layer of the vertebral artery,leading to stenosis,occlusion or rupture.The clinical presentat...BACKGROUND Vertebral artery dissection(VAD)is a rare but life-threatening condition characterized by tearing of the intimal layer of the vertebral artery,leading to stenosis,occlusion or rupture.The clinical presentation of VAD can be heterogeneous,with common symptoms including headache,dizziness and balance problems.Timely diagnosis and treatment are crucial for favorable outcomes;however,VAD is often missed due to its variable clinical presentation and lack of robust diagnostic guidelines.High-resolution magnetic resonance imaging(HRMRI)has emerged as a reliable diagnostic tool for VAD,providing detailed visualization of vessel wall abnormalities.CASE SUMMARY A young male patient presented with an acute onset of severe headache,vomiting,and seizures,followed by altered consciousness.Imaging studies revealed bilateral VAD,basilar artery thrombosis,multiple brainstem and cerebellar infarcts,and subarachnoid hemorrhage.Digital subtraction angiography(DSA)revealed vertebral artery stenosis but failed to detect the dissection,potentially because intramural thrombosis obscured the VAD.In contrast,HRMRI confirmed the diagnosis by revealing specific signs of dissection.The patient was managed conservatively with antiplatelet therapy and other supportive measures,such as blood pressure control and pain management.After 5 mo of rehabilitation,the patient showed significant improvement in swallowing and limb strength.CONCLUSION HR-MRI can provide precise evidence for the identification of VAD.展开更多
In recent years,with the development of synthetic aperture radar(SAR)technology and the widespread application of deep learning,lightweight detection of SAR images has emerged as a research direction.The ultimate goal...In recent years,with the development of synthetic aperture radar(SAR)technology and the widespread application of deep learning,lightweight detection of SAR images has emerged as a research direction.The ultimate goal is to reduce computational and storage requirements while ensuring detection accuracy and reliability,making it an ideal choice for achieving rapid response and efficient processing.In this regard,a lightweight SAR ship target detection algorithm based on YOLOv8 was proposed in this study.Firstly,the C2f-Sc module was designed by fusing the C2f in the backbone network with the ScConv to reduce spatial redundancy and channel redundancy between features in convolutional neural networks.At the same time,the Ghost module was introduced into the neck network to effectively reduce model parameters and computational complexity.A relatively lightweight EMA attention mechanism was added to the neck network to promote the effective fusion of features at different levels.Experimental results showed that the Parameters and GFLOPs of the improved model are reduced by 8.5%and 7.0%when mAP@0.5 and mAP@0.5:0.95 are increased by 0.7%and 1.8%,respectively.It makes the model lightweight and improves the detection accuracy,which has certain application value.展开更多
Significant advancements have been achieved in the field of Single Image Super-Resolution(SISR)through the utilization of Convolutional Neural Networks(CNNs)to attain state-of-the-art performance.Recent efforts have e...Significant advancements have been achieved in the field of Single Image Super-Resolution(SISR)through the utilization of Convolutional Neural Networks(CNNs)to attain state-of-the-art performance.Recent efforts have explored the incorporation of Transformers to augment network performance in SISR.However,the high computational cost of Transformers makes them less suitable for deployment on lightweight devices.Moreover,the majority of enhancements for CNNs rely predominantly on small spatial convolutions,thereby neglecting the potential advantages of large kernel convolution.In this paper,the authors propose a Multi-Perception Large Kernel convNet(MPLKN)which delves into the exploration of large kernel convolution.Specifically,the authors have architected a Multi-Perception Large Kernel(MPLK)module aimed at extracting multi-scale features and employ a stepwise feature fusion strategy to seamlessly integrate these features.In addition,to enhance the network's capacity for nonlinear spatial information processing,the authors have designed a Spatial-Channel Gated Feed-forward Network(SCGFN)that is capable of adapting to feature interactions across both spatial and channel dimensions.Experimental results demonstrate that MPLKN outperforms other lightweight image super-resolution models while maintaining a minimal number of parameters and FLOPs.展开更多
Lower back pain is one of the most common medical problems in the world and it is experienced by a huge percentage of people everywhere.Due to its ability to produce a detailed view of the soft tissues,including the s...Lower back pain is one of the most common medical problems in the world and it is experienced by a huge percentage of people everywhere.Due to its ability to produce a detailed view of the soft tissues,including the spinal cord,nerves,intervertebral discs,and vertebrae,Magnetic Resonance Imaging is thought to be the most effective method for imaging the spine.The semantic segmentation of vertebrae plays a major role in the diagnostic process of lumbar diseases.It is difficult to semantically partition the vertebrae in Magnetic Resonance Images from the surrounding variety of tissues,including muscles,ligaments,and intervertebral discs.U-Net is a powerful deep-learning architecture to handle the challenges of medical image analysis tasks and achieves high segmentation accuracy.This work proposes a modified U-Net architecture namely MU-Net,consisting of the Meijering convolutional layer that incorporates the Meijering filter to perform the semantic segmentation of lumbar vertebrae L1 to L5 and sacral vertebra S1.Pseudo-colour mask images were generated and used as ground truth for training the model.The work has been carried out on 1312 images expanded from T1-weighted mid-sagittal MRI images of 515 patients in the Lumbar Spine MRI Dataset publicly available from Mendeley Data.The proposed MU-Net model for the semantic segmentation of the lumbar vertebrae gives better performance with 98.79%of pixel accuracy(PA),98.66%of dice similarity coefficient(DSC),97.36%of Jaccard coefficient,and 92.55%mean Intersection over Union(mean IoU)metrics using the mentioned dataset.展开更多
Brain tumor segmentation is critical in clinical diagnosis and treatment planning.Existing methods for brain tumor segmentation with missing modalities often struggle when dealing with multiple missing modalities,a co...Brain tumor segmentation is critical in clinical diagnosis and treatment planning.Existing methods for brain tumor segmentation with missing modalities often struggle when dealing with multiple missing modalities,a common scenario in real-world clinical settings.These methods primarily focus on handling a single missing modality at a time,making them insufficiently robust for the additional complexity encountered with incomplete data containing various missing modality combinations.Additionally,most existing methods rely on single models,which may limit their performance and increase the risk of overfitting the training data.This work proposes a novel method called the ensemble adversarial co-training neural network(EACNet)for accurate brain tumor segmentation from multi-modal magnetic resonance imaging(MRI)scans with multiple missing modalities.The proposed method consists of three key modules:the ensemble of pre-trained models,which captures diverse feature representations from the MRI data by employing an ensemble of pre-trained models;adversarial learning,which leverages a competitive training approach involving two models;a generator model,which creates realistic missing data,while sub-networks acting as discriminators learn to distinguish real data from the generated“fake”data.Co-training framework utilizes the information extracted by the multimodal path(trained on complete scans)to guide the learning process in the path handling missing modalities.The model potentially compensates for missing information through co-training interactions by exploiting the relationships between available modalities and the tumor segmentation task.EACNet was evaluated on the BraTS2018 and BraTS2020 challenge datasets and achieved state-of-the-art and competitive performance respectively.Notably,the segmentation results for the whole tumor(WT)dice similarity coefficient(DSC)reached 89.27%,surpassing the performance of existing methods.The analysis suggests that the ensemble approach offers potential benefits,and the adversarial co-training contributes to the increased robustness and accuracy of EACNet for brain tumor segmentation of MRI scans with missing modalities.The experimental results show that EACNet has promising results for the task of brain tumor segmentation of MRI scans with missing modalities and is a better candidate for real-world clinical applications.展开更多
基金funded by the National Natural Science Foundation of China(Grant No.40571029).
文摘Measurement of vegetation coverage on a small scale is the foundation for the monitoring of changes in vegetation coverage and of the inversion model of monitoring vegetation coverage on a large scale by remote sensing. Using the object-oriented analytical software, Definiens Professional 5, a new method for calculating vegetation coverage based on high-resolution images （aerial photographs or near-surface photography） is proposed. Our research supplies references to remote sensing measurements of vegetation coverage on a small scale and accurate fundamental data for the inversion model of vegetation coverage on a large and intermediate scale to improve the accuracy of remote sensing monitoring of changes in vegetation coverage.
基金Under the auspices of Jiangsu Provincial Natural ScienceFoundation(No .BK2002420 )
文摘Nowadays, remote sensing imagery, especially with its high spatialresolution, has become an indispensable tool to provide timely up-gradation of urban land use andland cover information, which is a prerequisite for proper urban planning and management. Thepossible method described in the present paper to obtain urban land use types is based on theprinciple that land use can be derived from the land cover existing in a neighborhood. Here, movingwindow is used to represent the spatial pattern of land cover within a neighborhood and seven windowsizes (61mx61m, 68mx68m, 75mx75m, 87mx87m, 99mx99m, 110mx110m and 121mxl21m) are applied todetermining the most proper window size. Then, the unsupervised method of ISODATA is employed toclassify the layered land cover density maps obtained by the moving window. The results of accuracyevaluation show that the window size of 99mx99m is proper to infer urban land use categories and theproposed method has produced a land use map with a total accuracy of 85%.
基金funded by the National Natural Science Foundation of China (Grant No. 41930102, 41971333, 41771415, and 41701449)the Priority Academic Program Development of Jiangsu Higher Education Institutions (Grant No. 164320H116)the Open Fund of Key Laboratory for Synergistic Prevention of Water and Soil Environmental Pollution (Grant No. KLSPWSEPA04)。
文摘Ephemeral gullies,which are widely developed worldwide and threaten farmlands,have aroused a growing concern.Identifying and mapping gullies are generally considered prerequisites of gully erosion assessment.However,ephemeral gully mapping remains a challenge.In this study,we proposed a flow-directional detection for identifying ephemeral gullies from high-resolution images and digital elevation models(DEMs).Ephemeral gullies exhibit clear linear features in high-resolution images.An edge detection operator was initially used to identify linear features from high-resolution images.Then,according to gully erosion mechanism,the flow-directional detection was designed.Edge images obtained from edge detection and flow directions obtained from DEMs were used to implement the flow-directional detection that detects ephemeral gullies along the flow direction.Results from ten study areas in the Loess Plateau of China showed that ranges of precision,recall,and Fmeasure are 6 o.66%-90.47%,65.74%-94.98%,and63.10%-91.93%,respectively.The proposed method is flexible and can be used with various images and DEMs.However,analysis of the effect of DEM resolution and accuracy showed that DEM resolution only demonstrates a minor effect on the detection results.Conversely,DEM accuracy influences the detection result and is more important than the DEM resolution.The worse the vertical accuracy of DEM,the lower the performance of the flow-directional detection will be.This work is beneficial to research related to monitoring gully erosion and assessing soil loss.
基金ProjectsupportedbytheNationalNaturalScienceFoundationofChina (No .40 0 2 30 0 4 ) .
文摘On the basis of a thorough understanding of the physical characteristics of remote sensing image, this paper employs the theories of wavelet transform and signal sampling to develop a new image fusion algorithm. The algorithm has been successfully applied to the image fusion of SPOT PAN and TM of Guangdong province, China. The experimental results show that a perfect image fusion can be built up by using the image analytical solution and re-construction in the image frequency domain based on the physical characteristics of the image formation. The method has demonstrated that the results of the image fusion do not change spectral characteristics of the original image.
基金supported by the National Natural Science Foundation of China(41701499)the Sichuan Science and Technology Program(2018GZ0265)the Geomatics Technology and Application Key Laboratory of Qinghai Province(QHDX-2018-07)
文摘A large number of debris flow disasters(called Seismic debris flows) would occur after an earthquake, which can cause a great amount of damage. UAV low-altitude remote sensing technology has become a means of quickly obtaining disaster information as it has the advantage of convenience and timeliness, but the spectral information of the image is so scarce, making it difficult to accurately detect the information of earthquake debris flow disasters. Based on the above problems, a seismic debris flow detection method based on transfer learning(TL) mechanism is proposed. On the basis of the constructed seismic debris flow disaster database, the features acquired from the training of the convolutional neural network(CNN) are transferred to the disaster information detection of the seismic debris flow. The automatic detection of earthquake debris flow disaster information is then completed, and the results of object-oriented seismic debris flow disaster information detection are compared and analyzed with the detection results supported by transfer learning.
基金Supported by Bozhou Key Research and Development Project,No.bzzc2020031.
文摘BACKGROUND Fistula-in-ano is an abnormal tunnel formation linking the anal canal with the perineum and perianal skin.Multiple imagining methods are available to evaluate it,among which magnetic resonance imaging(MRI)is the most advanced nonin-vasive preoperative method.However,it is limited in its visualization function.AIM To investigate the use of intraluminal MRI for perianal fistulas via a novel direct MRI fistulography method.METHODS We mixed 3%hydrogen peroxide(HP)with gadolinium for HPMRI fistulogra-phy,retrospectively analyzing 60 cases of complex/recurrent fistula-in-ano using physical examination,trans-perineal ultrasonography(TPUS),low-spatial-reso-lution MRI,and high-resolution direct HPMRI fistulography.We assessed detec-tion rates of fistula tracks,internal openings,their relationship with anal sphinc-ters,and perianal abscesses using statistical analyses,including interobserver agreement(Kappa statistic),and compared results with intraoperative findings.RESULTS Surgical confirmation in 60 cases showed that high-resolution direct HPMRI fis-tulography provided superior detection rates for internal openings(153)and fistula tracks(162)compared to physical exams,TPUS,and low-spatial-resolution MRI(Z>5.7,P<0.05).The effectiveness of physical examination and TPUS was also inferior to that of our method for detecting perianal abscesses(54)(Z=6.773,3.694,P<0.05),whereas that of low-spatial-resolution MRI was not significantly different(Z=1.851,P=0.06).High-resolution direct HPMRI fistulography also achieved the highest interobserver agreement(Kappa:0.89,0.85,and 0.80),while low-spatial-resolution MRI showed moderate agreement(Kappa:0.78,0.74,and 0.69).TPUS and physical examination had lower agreement(Kappa range:0.33-0.63).CONCLUSION High-resolution direct HPMRI fistulography enhances the visualization of recurrent and complex fistula-in-ano,including branched fistulas,allowing for precise planning and improved surgical outcomes.
基金funded by the Chongqing Normal University Startup Foundation for PhD(22XLB021)supported by the Open Research Project of the State Key Laboratory of Industrial Control Technology,Zhejiang University,China(No.ICT2023B40).
文摘Cloud detection from satellite and drone imagery is crucial for applications such as weather forecasting and environmentalmonitoring.Addressing the limitations of conventional convolutional neural networks,we propose an innovative transformer-based method.This method leverages transformers,which are adept at processing data sequences,to enhance cloud detection accuracy.Additionally,we introduce a Cyclic Refinement Architecture that improves the resolution and quality of feature extraction,thereby aiding in the retention of critical details often lost during cloud detection.Our extensive experimental validation shows that our approach significantly outperforms established models,excelling in high-resolution feature extraction and precise cloud segmentation.By integrating Positional Visual Transformers(PVT)with this architecture,our method advances high-resolution feature delineation and segmentation accuracy.Ultimately,our research offers a novel perspective for surmounting traditional challenges in cloud detection and contributes to the advancement of precise and dependable image analysis across various domains.
基金the National Natural Science Foundation of China(42001408,61806097).
文摘Significant advancements have been achieved in road surface extraction based on high-resolution remote sensingimage processing. Most current methods rely on fully supervised learning, which necessitates enormous humaneffort to label the image. Within this field, other research endeavors utilize weakly supervised methods. Theseapproaches aim to reduce the expenses associated with annotation by leveraging sparsely annotated data, such asscribbles. This paper presents a novel technique called a weakly supervised network using scribble-supervised andedge-mask (WSSE-net). This network is a three-branch network architecture, whereby each branch is equippedwith a distinct decoder module dedicated to road extraction tasks. One of the branches is dedicated to generatingedge masks using edge detection algorithms and optimizing road edge details. The other two branches supervise themodel’s training by employing scribble labels and spreading scribble information throughout the image. To addressthe historical flaw that created pseudo-labels that are not updated with network training, we use mixup to blendprediction results dynamically and continually update new pseudo-labels to steer network training. Our solutiondemonstrates efficient operation by simultaneously considering both edge-mask aid and dynamic pseudo-labelsupport. The studies are conducted on three separate road datasets, which consist primarily of high-resolutionremote-sensing satellite photos and drone images. The experimental findings suggest that our methodologyperforms better than advanced scribble-supervised approaches and specific traditional fully supervised methods.
文摘Current data-driven deep learning(DL)methods typically reconstruct subsurface velocity models directly from pre-stack seismic records.However,these purely data-driven methods are often less robust and produce results that are less physically interpretative.Here,the authors propose a new method that uses migration images as input,combined with convolutional neural networks to construct high-resolution velocity models.Compared to directly using pre-stack seismic records as input,the nonlinearity between migration images and velocity models is significantly reduced.Additionally,the advantage of using migration images lies in its ability to more comprehensively capture the reflective properties of the subsurface medium,including amplitude and phase information,thereby to provide richer physical information in guiding the reconstruction of the velocity model.This approach not only improves the accuracy and resolution of the reconstructed velocity models,but also enhances the physical interpretability and robustness.Numerical experiments on synthetic data show that the proposed method has superior reconstruction performance and strong generalization capability when dealing with complex geological structures,and shows great potential in providing efficient solutions for the task of reconstructing high-wavenumber components.
文摘The commercial high-resolution imaging satellite with 1 m spatial resolution IKONOS is an important data source of information for urban planning and geographical information system (GIS) applications. In this paper, a morphological method is proposed. The proposed method combines the automatic thresholding and morphological operation techniques to extract the road centerline of the urban environment. This method intends to solve urban road centerline problems, vehicle, vegetation, building etc. Based on this morphological method, an object extractor is designed to extract road networks from highly remote sensing images. Some filters are applied in this experiment such as line reconstruction and region filling techniques to connect the disconnected road segments and remove the small redundant. Finally, the thinning algorithm is used to extract the road centerline. Experiments have been conducted on a high-resolution IKONOS and QuickBird images showing the efficiency of the proposed method.
基金the Deanship of Scientifc Research at King Khalid University for funding this work through large group Research Project under grant number RGP2/421/45supported via funding from Prince Sattam bin Abdulaziz University project number(PSAU/2024/R/1446)+1 种基金supported by theResearchers Supporting Project Number(UM-DSR-IG-2023-07)Almaarefa University,Riyadh,Saudi Arabia.supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(No.2021R1F1A1055408).
文摘Machine learning(ML)is increasingly applied for medical image processing with appropriate learning paradigms.These applications include analyzing images of various organs,such as the brain,lung,eye,etc.,to identify specific flaws/diseases for diagnosis.The primary concern of ML applications is the precise selection of flexible image features for pattern detection and region classification.Most of the extracted image features are irrelevant and lead to an increase in computation time.Therefore,this article uses an analytical learning paradigm to design a Congruent Feature Selection Method to select the most relevant image features.This process trains the learning paradigm using similarity and correlation-based features over different textural intensities and pixel distributions.The similarity between the pixels over the various distribution patterns with high indexes is recommended for disease diagnosis.Later,the correlation based on intensity and distribution is analyzed to improve the feature selection congruency.Therefore,the more congruent pixels are sorted in the descending order of the selection,which identifies better regions than the distribution.Now,the learning paradigm is trained using intensity and region-based similarity to maximize the chances of selection.Therefore,the probability of feature selection,regardless of the textures and medical image patterns,is improved.This process enhances the performance of ML applications for different medical image processing.The proposed method improves the accuracy,precision,and training rate by 13.19%,10.69%,and 11.06%,respectively,compared to other models for the selected dataset.The mean error and selection time is also reduced by 12.56%and 13.56%,respectively,compared to the same models and dataset.
文摘Large language models(LLMs),such as ChatGPT developed by OpenAI,represent a significant advancement in artificial intelligence(AI),designed to understand,generate,and interpret human language by analyzing extensive text data.Their potential integration into clinical settings offers a promising avenue that could transform clinical diagnosis and decision-making processes in the future(Thirunavukarasu et al.,2023).This article aims to provide an in-depth analysis of LLMs’current and potential impact on clinical practices.Their ability to generate differential diagnosis lists underscores their potential as invaluable tools in medical practice and education(Hirosawa et al.,2023;Koga et al.,2023).
基金supported by the Natural Science Foundation of China(No.41804112,author:Chengyun Song).
文摘Existing semi-supervisedmedical image segmentation algorithms use copy-paste data augmentation to correct the labeled-unlabeled data distribution mismatch.However,current copy-paste methods have three limitations:(1)training the model solely with copy-paste mixed pictures from labeled and unlabeled input loses a lot of labeled information;(2)low-quality pseudo-labels can cause confirmation bias in pseudo-supervised learning on unlabeled data;(3)the segmentation performance in low-contrast and local regions is less than optimal.We design a Stochastic Augmentation-Based Dual-Teaching Auxiliary Training Strategy(SADT),which enhances feature diversity and learns high-quality features to overcome these problems.To be more precise,SADT trains the Student Network by using pseudo-label-based training from Teacher Network 1 and supervised learning with labeled data,which prevents the loss of rare labeled data.We introduce a bi-directional copy-pastemask with progressive high-entropy filtering to reduce data distribution disparities and mitigate confirmation bias in pseudo-supervision.For the mixed images,Deep-Shallow Spatial Contrastive Learning(DSSCL)is proposed in the feature spaces of Teacher Network 2 and the Student Network to improve the segmentation capabilities in low-contrast and local areas.In this procedure,the features retrieved by the Student Network are subjected to a random feature perturbation technique.On two openly available datasets,extensive trials show that our proposed SADT performs much better than the state-ofthe-art semi-supervised medical segmentation techniques.Using only 10%of the labeled data for training,SADT was able to acquire a Dice score of 90.10%on the ACDC(Automatic Cardiac Diagnosis Challenge)dataset.
基金Supported by National Natural Science Foundation of China,No.82071871Guangdong Basic and Applied Basic Research Foundation,No.2021A1515220131+1 种基金Guangdong Medical Science and Technology Research Fund Project,No.2022111520491834Clinical Research Project of Shenzhen Second People's Hospital,No.20223357022。
文摘BACKGROUND Intracranial atherosclerosis,a leading cause of stroke,involves arterial plaque formation.This study explores the link between plaque remodelling patterns and diabetes using high-resolution vessel wall imaging(HR-VWI).AIM To investigate the factors of intracranial atherosclerotic remodelling patterns and the relationship between intracranial atherosclerotic remodelling and diabetes mellitus using HR-VWI.METHODS Ninety-four patients diagnosed with middle cerebral artery or basilar artery INTRODUCTION Intracranial atherosclerotic disease is one of the main causes of ischaemic stroke in the world,accounting for approx-imately 10%of transient ischaemic attacks and 30%-50%of ischaemic strokes[1].It is the most common factor among Asian people[2].The adaptive changes in the structure and function of blood vessels that can adapt to changes in the internal and external environment are called vascular remodelling,which is a common and important pathological mechanism in atherosclerotic diseases,and the remodelling mode of atherosclerotic plaques is closely related to the occurrence of stroke.Positive remodelling(PR)is an outwards compensatory remodelling where the arterial wall grows outwards in an attempt to maintain a constant lumen diameter.For a long time,it was believed that the degree of stenosis can accurately reflect the risk of ischaemic stroke[3-5].Previous studies have revealed that lesions without significant luminal stenosis can also lead to acute events[6,7],as summarized in a recent meta-analysis study in which approximately 50%of acute/subacute ischaemic events were due to this type of lesion[6].Research[8,9]has pointed out that the PR of plaques is more dangerous and more likely to cause acute ischaemic stroke.Previous studies[10-13]have found that there are specific vascular remodelling phenomena in the coronary and carotid arteries of diabetic patients.However,due to the deep location and small lumen of intracranial arteries and limitations of imaging techniques,the relationship between intracranial arterial remodelling and diabetes is still unclear.In recent years,with the development of magnetic resonance technology and the emergence of high-resolution(HR)vascular wall imaging,a clear and multidimensional display of the intracranial vascular wall has been achieved.Therefore,in this study,HR wall imaging(HR-VWI)was used to display the remodelling characteristics of bilateral middle cerebral arteries and basilar arteries and to explore the factors of intracranial vascular remodelling and its relationship with diabetes.
基金Supported by The Clinical Innovation Guidance Program of Hunan Provincial Science and Technology Department,China,No.2021SK51714The Hunan Nature Science Foundation,China,No.2023JJ30531.
文摘BACKGROUND Vertebral artery dissection(VAD)is a rare but life-threatening condition characterized by tearing of the intimal layer of the vertebral artery,leading to stenosis,occlusion or rupture.The clinical presentation of VAD can be heterogeneous,with common symptoms including headache,dizziness and balance problems.Timely diagnosis and treatment are crucial for favorable outcomes;however,VAD is often missed due to its variable clinical presentation and lack of robust diagnostic guidelines.High-resolution magnetic resonance imaging(HRMRI)has emerged as a reliable diagnostic tool for VAD,providing detailed visualization of vessel wall abnormalities.CASE SUMMARY A young male patient presented with an acute onset of severe headache,vomiting,and seizures,followed by altered consciousness.Imaging studies revealed bilateral VAD,basilar artery thrombosis,multiple brainstem and cerebellar infarcts,and subarachnoid hemorrhage.Digital subtraction angiography(DSA)revealed vertebral artery stenosis but failed to detect the dissection,potentially because intramural thrombosis obscured the VAD.In contrast,HRMRI confirmed the diagnosis by revealing specific signs of dissection.The patient was managed conservatively with antiplatelet therapy and other supportive measures,such as blood pressure control and pain management.After 5 mo of rehabilitation,the patient showed significant improvement in swallowing and limb strength.CONCLUSION HR-MRI can provide precise evidence for the identification of VAD.
文摘In recent years,with the development of synthetic aperture radar(SAR)technology and the widespread application of deep learning,lightweight detection of SAR images has emerged as a research direction.The ultimate goal is to reduce computational and storage requirements while ensuring detection accuracy and reliability,making it an ideal choice for achieving rapid response and efficient processing.In this regard,a lightweight SAR ship target detection algorithm based on YOLOv8 was proposed in this study.Firstly,the C2f-Sc module was designed by fusing the C2f in the backbone network with the ScConv to reduce spatial redundancy and channel redundancy between features in convolutional neural networks.At the same time,the Ghost module was introduced into the neck network to effectively reduce model parameters and computational complexity.A relatively lightweight EMA attention mechanism was added to the neck network to promote the effective fusion of features at different levels.Experimental results showed that the Parameters and GFLOPs of the improved model are reduced by 8.5%and 7.0%when mAP@0.5 and mAP@0.5:0.95 are increased by 0.7%and 1.8%,respectively.It makes the model lightweight and improves the detection accuracy,which has certain application value.
文摘Significant advancements have been achieved in the field of Single Image Super-Resolution(SISR)through the utilization of Convolutional Neural Networks(CNNs)to attain state-of-the-art performance.Recent efforts have explored the incorporation of Transformers to augment network performance in SISR.However,the high computational cost of Transformers makes them less suitable for deployment on lightweight devices.Moreover,the majority of enhancements for CNNs rely predominantly on small spatial convolutions,thereby neglecting the potential advantages of large kernel convolution.In this paper,the authors propose a Multi-Perception Large Kernel convNet(MPLKN)which delves into the exploration of large kernel convolution.Specifically,the authors have architected a Multi-Perception Large Kernel(MPLK)module aimed at extracting multi-scale features and employ a stepwise feature fusion strategy to seamlessly integrate these features.In addition,to enhance the network's capacity for nonlinear spatial information processing,the authors have designed a Spatial-Channel Gated Feed-forward Network(SCGFN)that is capable of adapting to feature interactions across both spatial and channel dimensions.Experimental results demonstrate that MPLKN outperforms other lightweight image super-resolution models while maintaining a minimal number of parameters and FLOPs.
文摘Lower back pain is one of the most common medical problems in the world and it is experienced by a huge percentage of people everywhere.Due to its ability to produce a detailed view of the soft tissues,including the spinal cord,nerves,intervertebral discs,and vertebrae,Magnetic Resonance Imaging is thought to be the most effective method for imaging the spine.The semantic segmentation of vertebrae plays a major role in the diagnostic process of lumbar diseases.It is difficult to semantically partition the vertebrae in Magnetic Resonance Images from the surrounding variety of tissues,including muscles,ligaments,and intervertebral discs.U-Net is a powerful deep-learning architecture to handle the challenges of medical image analysis tasks and achieves high segmentation accuracy.This work proposes a modified U-Net architecture namely MU-Net,consisting of the Meijering convolutional layer that incorporates the Meijering filter to perform the semantic segmentation of lumbar vertebrae L1 to L5 and sacral vertebra S1.Pseudo-colour mask images were generated and used as ground truth for training the model.The work has been carried out on 1312 images expanded from T1-weighted mid-sagittal MRI images of 515 patients in the Lumbar Spine MRI Dataset publicly available from Mendeley Data.The proposed MU-Net model for the semantic segmentation of the lumbar vertebrae gives better performance with 98.79%of pixel accuracy(PA),98.66%of dice similarity coefficient(DSC),97.36%of Jaccard coefficient,and 92.55%mean Intersection over Union(mean IoU)metrics using the mentioned dataset.
基金supported by Gansu Natural Science Foundation Programme(No.24JRRA231)National Natural Science Foundation of China(No.62061023)Gansu Provincial Education,Science and Technology Innovation and Industry(No.2021CYZC-04)。
文摘Brain tumor segmentation is critical in clinical diagnosis and treatment planning.Existing methods for brain tumor segmentation with missing modalities often struggle when dealing with multiple missing modalities,a common scenario in real-world clinical settings.These methods primarily focus on handling a single missing modality at a time,making them insufficiently robust for the additional complexity encountered with incomplete data containing various missing modality combinations.Additionally,most existing methods rely on single models,which may limit their performance and increase the risk of overfitting the training data.This work proposes a novel method called the ensemble adversarial co-training neural network(EACNet)for accurate brain tumor segmentation from multi-modal magnetic resonance imaging(MRI)scans with multiple missing modalities.The proposed method consists of three key modules:the ensemble of pre-trained models,which captures diverse feature representations from the MRI data by employing an ensemble of pre-trained models;adversarial learning,which leverages a competitive training approach involving two models;a generator model,which creates realistic missing data,while sub-networks acting as discriminators learn to distinguish real data from the generated“fake”data.Co-training framework utilizes the information extracted by the multimodal path(trained on complete scans)to guide the learning process in the path handling missing modalities.The model potentially compensates for missing information through co-training interactions by exploiting the relationships between available modalities and the tumor segmentation task.EACNet was evaluated on the BraTS2018 and BraTS2020 challenge datasets and achieved state-of-the-art and competitive performance respectively.Notably,the segmentation results for the whole tumor(WT)dice similarity coefficient(DSC)reached 89.27%,surpassing the performance of existing methods.The analysis suggests that the ensemble approach offers potential benefits,and the adversarial co-training contributes to the increased robustness and accuracy of EACNet for brain tumor segmentation of MRI scans with missing modalities.The experimental results show that EACNet has promising results for the task of brain tumor segmentation of MRI scans with missing modalities and is a better candidate for real-world clinical applications.
