A microgravity environment has been shown to cause ocular damage and affect visual acuity,but the underlying mechanisms remain unclear.Therefore,we established an animal model of weightlessness via tail suspension to ...A microgravity environment has been shown to cause ocular damage and affect visual acuity,but the underlying mechanisms remain unclear.Therefore,we established an animal model of weightlessness via tail suspension to examine the pathological changes and molecular mechanisms of retinal damage under microgravity.After 4 weeks of tail suspension,there were no notable alterations in retinal function and morphology,while after 8 weeks of tail suspension,significant reductions in retinal function were observed,and the outer nuclear layer was thinner,with abundant apoptotic cells.To investigate the mechanism underlying the degenerative changes that occurred in the outer nuclear layer of the retina,proteomics was used to analyze differentially expressed proteins in rat retinas after 8 weeks of tail suspension.The results showed that the expression levels of fibroblast growth factor 2(also known as basic fibroblast growth factor)and glial fibrillary acidic protein,which are closely related to Müller cell activation,were significantly upregulated.In addition,Müller cell regeneration and Müller cell gliosis were observed after 4 and 8 weeks,respectively,of simulated weightlessness.These findings indicate that Müller cells play an important regulatory role in retinal outer nuclear layer degeneration during weightlessness.展开更多
The Internet of Vehicles (IoV) has become an important direction in the field of intelligent transportation, in which vehicle positioning is a crucial part. SLAM (Simultaneous Localization and Mapping) technology play...The Internet of Vehicles (IoV) has become an important direction in the field of intelligent transportation, in which vehicle positioning is a crucial part. SLAM (Simultaneous Localization and Mapping) technology plays a crucial role in vehicle localization and navigation. Traditional Simultaneous Localization and Mapping (SLAM) systems are designed for use in static environments, and they can result in poor performance in terms of accuracy and robustness when used in dynamic environments where objects are in constant movement. To address this issue, a new real-time visual SLAM system called MG-SLAM has been developed. Based on ORB-SLAM2, MG-SLAM incorporates a dynamic target detection process that enables the detection of both known and unknown moving objects. In this process, a separate semantic segmentation thread is required to segment dynamic target instances, and the Mask R-CNN algorithm is applied on the Graphics Processing Unit (GPU) to accelerate segmentation. To reduce computational cost, only key frames are segmented to identify known dynamic objects. Additionally, a multi-view geometry method is adopted to detect unknown moving objects. The results demonstrate that MG-SLAM achieves higher precision, with an improvement from 0.2730 m to 0.0135 m in precision. Moreover, the processing time required by MG-SLAM is significantly reduced compared to other dynamic scene SLAM algorithms, which illustrates its efficacy in locating objects in dynamic scenes.展开更多
Brain tumors present significant challenges in medical diagnosis and treatment,where early detection is crucial for reducing morbidity and mortality rates.This research introduces a novel deep learning model,the Progr...Brain tumors present significant challenges in medical diagnosis and treatment,where early detection is crucial for reducing morbidity and mortality rates.This research introduces a novel deep learning model,the Progressive Layered U-Net(PLU-Net),designed to improve brain tumor segmentation accuracy from Magnetic Resonance Imaging(MRI)scans.The PLU-Net extends the standard U-Net architecture by incorporating progressive layering,attention mechanisms,and multi-scale data augmentation.The progressive layering involves a cascaded structure that refines segmentation masks across multiple stages,allowing the model to capture features at different scales and resolutions.Attention gates within the convolutional layers selectively focus on relevant features while suppressing irrelevant ones,enhancing the model's ability to delineate tumor boundaries.Additionally,multi-scale data augmentation techniques increase the diversity of training data and boost the model's generalization capabilities.Evaluated on the BraTS 2021 dataset,the PLU-Net achieved state-of-the-art performance with a dice coefficient of 0.91,specificity of 0.92,sensitivity of 0.89,Hausdorff95 of 2.5,outperforming other modified U-Net architectures in segmentation accuracy.These results underscore the effectiveness of the PLU-Net in improving brain tumor segmentation from MRI scans,supporting clinicians in early diagnosis,treatment planning,and the development of new therapies.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
The Tan-Lu Fault Zone is a large NNE-trending fault zone that has a substantial effect on the development of eastern China and its earthquake disaster prevention efforts. Aiming at the azimuthally anisotropic structur...The Tan-Lu Fault Zone is a large NNE-trending fault zone that has a substantial effect on the development of eastern China and its earthquake disaster prevention efforts. Aiming at the azimuthally anisotropic structure in the upper crust and seismogenic tectonics in the Hefei segment of this fault, we collected phase velocity dispersion data of fundamental mode Rayleigh waves from ambient noise cross-correlation functions of ~400 temporal seismographs in an area of approximately 80 × 70 km along the fault zone. The period band of the dispersion data was ~0.5–10 s. We inverted for the upper crustal three-dimensional(3-D) shear velocity model with azimuthal anisotropy from the surface to 10 km depth by using a 3-D direct azimuthal anisotropy inversion method. The inversion result shows the spatial distribution characteristics of the tectonic units in the upper crust. Additionally, the deformation of the Tan-Lu Fault Zone and its conjugated fault systems could be inferred from the anisotropy model. In particular, the faults that have remained active from the early and middle Pleistocene control the anisotropic characteristics of the upper crustal structure in this area. The direction of fast axes near the fault zone area in the upper crust is consistent with the strike of the faults, whereas for the region far away from the fault zone, the direction of fast axes is consistent with the direction of the regional principal stress caused by plate movement. Combined with the azimuthal anisotropy models in the deep crust and uppermost mantle from the surface wave and Pn wave, the different anisotropic patterns caused by the Tan-Lu Fault Zone and its conjugated fault system nearby are shown in the upper and lower crust. Furthermore,by using the double-difference method, we relocated the Lujiang earthquake series, which contained 32 earthquakes with a depth shallower than 10 km. Both the Vs model and earthquake relocation results indicate that earthquakes mostly occurred in the vicinity of structural boundaries with fractured media, with high-level development of cracks and small-scale faults jammed between more rigid areas.展开更多
A segmented predictor-corrector method is proposed for hypersonic glide vehicles to address the issue of the slow computational speed of obtaining guidance commands using the traditional predictor-corrector guidance m...A segmented predictor-corrector method is proposed for hypersonic glide vehicles to address the issue of the slow computational speed of obtaining guidance commands using the traditional predictor-corrector guidance method.Firstly,an altitude-energy profile is designed,and the bank angle is derived analytically as the initial iteration value for the predictor-corrector method.The predictor-corrector guidance method has been improved by deriving an analytical form for predicting the range-to-go error,which greatly accelerates the iterative speed.Then,a segmented guidance algorithm is proposed.The above analytically predictor-corrector guidance method is adopted when the energy exceeds an energy threshold.When the energy is less than the threshold,the equidistant test method is used to calculate the bank angle command,which ensures guidance accuracy as well as computational efficiency.Additionally,an adaptive guidance cycle strategy is applied to reduce the computational time of the reentry guidance trajectory.Finally,the accuracy and robustness of the proposed method are verified through a series of simulations and Monte-Carlo experiments.Compared with the traditional integral method,the proposed method requires 75%less computation time on average and achieves a lower landing error.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
Retinal blood vessel segmentation is crucial for diagnosing ocular and cardiovascular diseases.Although the introduction of U-Net in 2015 by Olaf Ronneberger significantly advanced this field,yet issues like limited t...Retinal blood vessel segmentation is crucial for diagnosing ocular and cardiovascular diseases.Although the introduction of U-Net in 2015 by Olaf Ronneberger significantly advanced this field,yet issues like limited training data,imbalance data distribution,and inadequate feature extraction persist,hindering both the segmentation performance and optimal model generalization.Addressing these critical issues,the DEFFA-Unet is proposed featuring an additional encoder to process domain-invariant pre-processed inputs,thereby improving both richer feature encoding and enhanced model generalization.A feature filtering fusion module is developed to ensure the precise feature filtering and robust hybrid feature fusion.In response to the task-specific need for higher precision where false positives are very costly,traditional skip connections are replaced with the attention-guided feature reconstructing fusion module.Additionally,innovative data augmentation and balancing methods are proposed to counter data scarcity and distribution imbalance,further boosting the robustness and generalization of the model.With a comprehensive suite of evaluation metrics,extensive validations on four benchmark datasets(DRIVE,CHASEDB1,STARE,and HRF)and an SLO dataset(IOSTAR),demonstrate the proposed method’s superiority over both baseline and state-of-the-art models.Particularly the proposed method significantly outperforms the compared methods in cross-validation model generalization.展开更多
BACKGROUND The incidence of acute myocardial infarction(AMI)is rising,with cardiac rupture accounting for approximately 2%of deaths in patients with acute ST-segment elevation myocardial infarction(STEMI).Ventricular ...BACKGROUND The incidence of acute myocardial infarction(AMI)is rising,with cardiac rupture accounting for approximately 2%of deaths in patients with acute ST-segment elevation myocardial infarction(STEMI).Ventricular free wall rupture(FWR)occurs in approximately 2%of AMI patients and is notably rare in patients with non-STEMI.Types of cardiac rupture include left ventricular FWR,ventricular septal rupture,and papillary muscle rupture.The FWR usually leads to acute cardiac tamponade or electromechanical dissociation,where standard resuscitation efforts may not be effective.Ventricular septal rupture and papillary muscle rupture often result in refractory heart failure,with mortality rates over 50%,even with surgical or percutaneous repair options.CASE SUMMARY We present a rare case of an acute non-STEMI patient who suffered sudden FWR causing cardiac tamponade and loss of consciousness immediate before undergoing coronary angiography.Prompt resuscitation and emergency open-heart repair along with coronary artery bypass grafting resulted in successful patient recovery.CONCLUSION This case emphasizes the risks of AMI complications,shares a successful treatment scenario,and discusses measures to prevent such complications.展开更多
Cabin cables,as critical components of an aircraft's electrical system,significantly impact the operational efficiency and safety of the aircraft.The existing cable segmentation methods in civil aviation cabins ar...Cabin cables,as critical components of an aircraft's electrical system,significantly impact the operational efficiency and safety of the aircraft.The existing cable segmentation methods in civil aviation cabins are limited,especially in automation,heavily dependent on large amounts of data and resources,lacking the flexibility to adapt to different scenarios.To address these challenges,this paper introduces a novel image segmentation model,CableSAM,specifically designed for automated segmentation of cabin cables.CableSAM improves segmentation efficiency and accuracy using knowledge distillation and employs a context ensemble strategy.It accurately segments cables in various scenarios with minimal input prompts.Comparative experiments on three cable datasets demonstrate that CableSAM surpasses other advanced cable segmentation methods in performance.展开更多
In recent years,video coding has been widely applied in the field of video image processing to remove redundant information and improve data transmission efficiency.However,during the video coding process,irrelevant o...In recent years,video coding has been widely applied in the field of video image processing to remove redundant information and improve data transmission efficiency.However,during the video coding process,irrelevant objects such as background elements are often encoded due to environmental disturbances,resulting in the wastage of computational resources.Existing research on video coding efficiency optimization primarily focuses on optimizing encoding units during intra-frame or inter frame prediction after the generation of coding units,neglecting the optimization of video images before coding unit generation.To address this challenge,This work proposes an image semantic segmentation compression algorithm based on macroblock encoding,called image semantic segmentation compression algorithm based on macroblock encoding(ISSC-ME),which consists of three modules.(1)The semantic label generation module generates interesting object labels using a grid-based approach to reduce redundant coding of consecutive frames.(2)The image segmentation network module generates a semantic segmentation image using U-Net.(3)The macroblock coding module,is a block segmentation-based video encoding and decoding algorithm used to compress images and improve video transmission efficiency.Experimental results show that the proposed image semantic segmentation optimization algorithm can reduce the computational costs,and improve the overall accuracy by 1.00%and the mean intersection over union(IoU)by 1.20%.In addition,the proposed compression algorithm utilizes macroblock fusion,resulting in the image compression rate achieving 80.64%.It has been proven that the proposed algorithm greatly reduces data storage and transmission,and enables fast image compression processing at the millisecond level.展开更多
Medical image segmentation has become a cornerstone for many healthcare applications,allowing for the automated extraction of critical information from images such as Computed Tomography(CT)scans,Magnetic Resonance Im...Medical image segmentation has become a cornerstone for many healthcare applications,allowing for the automated extraction of critical information from images such as Computed Tomography(CT)scans,Magnetic Resonance Imaging(MRIs),and X-rays.The introduction of U-Net in 2015 has significantly advanced segmentation capabilities,especially for small datasets commonly found in medical imaging.Since then,various modifications to the original U-Net architecture have been proposed to enhance segmentation accuracy and tackle challenges like class imbalance,data scarcity,and multi-modal image processing.This paper provides a detailed review and comparison of several U-Net-based architectures,focusing on their effectiveness in medical image segmentation tasks.We evaluate performance metrics such as Dice Similarity Coefficient(DSC)and Intersection over Union(IoU)across different U-Net variants including HmsU-Net,CrossU-Net,mResU-Net,and others.Our results indicate that architectural enhancements such as transformers,attention mechanisms,and residual connections improve segmentation performance across diverse medical imaging applications,including tumor detection,organ segmentation,and lesion identification.The study also identifies current challenges in the field,including data variability,limited dataset sizes,and issues with class imbalance.Based on these findings,the paper suggests potential future directions for improving the robustness and clinical applicability of U-Net-based models in medical image segmentation.展开更多
Data augmentation plays an important role in training deep neural model by expanding the size and diversity of the dataset.Initially,data augmentation mainly involved some simple transformations of images.Later,in ord...Data augmentation plays an important role in training deep neural model by expanding the size and diversity of the dataset.Initially,data augmentation mainly involved some simple transformations of images.Later,in order to increase the diversity and complexity of data,more advanced methods appeared and evolved to sophisticated generative models.However,these methods required a mass of computation of training or searching.In this paper,a novel training-free method that utilises the Pre-Trained Segment Anything Model(SAM)model as a data augmentation tool(PTSAM-DA)is proposed to generate the augmented annotations for images.Without the need for training,it obtains prompt boxes from the original annotations and then feeds the boxes to the pre-trained SAM to generate diverse and improved annotations.In this way,annotations are augmented more ingenious than simple manipulations without incurring huge computation for training a data augmentation model.Multiple comparative experiments on three datasets are conducted,including an in-house dataset,ADE20K and COCO2017.On this in-house dataset,namely Agricultural Plot Segmentation Dataset,maximum improvements of 3.77%and 8.92%are gained in two mainstream metrics,mIoU and mAcc,respectively.Consequently,large vision models like SAM are proven to be promising not only in image segmentation but also in data augmentation.展开更多
This paper presents CW-HRNet,a high-resolution,lightweight crack segmentation network designed to address challenges in complex scenes with slender,deformable,and blurred crack structures.The model incorporates two ke...This paper presents CW-HRNet,a high-resolution,lightweight crack segmentation network designed to address challenges in complex scenes with slender,deformable,and blurred crack structures.The model incorporates two key modules:Constrained Deformable Convolution(CDC),which stabilizes geometric alignment by applying a tanh limiter and learnable scaling factor to the predicted offsets,and the Wavelet Frequency Enhancement Module(WFEM),which decomposes features using Haar wavelets to preserve low-frequency structures while enhancing high-frequency boundaries and textures.Evaluations on the CrackSeg9k benchmark demonstrate CW-HRNet’s superior performance,achieving 82.39%mIoU with only 7.49M parameters and 10.34 GFLOPs,outperforming HrSegNet-B48 by 1.83% in segmentation accuracy with minimal complexity overhead.The model also shows strong cross-dataset generalization,achieving 60.01%mIoU and 66.22%F1 on Asphalt3k without fine-tuning.These results highlight CW-HRNet’s favorable accuracyefficiency trade-off for real-world crack segmentation tasks.展开更多
Ownership is an increasingly important conflict in outer space at this moment in time.Despite the principle in the Outer Space Treaty(1967),that emphasizes the importance of all states'free access to outer space b...Ownership is an increasingly important conflict in outer space at this moment in time.Despite the principle in the Outer Space Treaty(1967),that emphasizes the importance of all states'free access to outer space based on equality for exploration and use.Moreover,outer space including the Moon and other celestial bodies is not subject to national appropriation by claim of sovereignty,by means of use or occupation,or by any other means.However,outer space activity is not free from sovereignty and jurisdiction after all.Anyway,the legal situation relating to space resource exploitation and utilization activities under the adoption of United Nations is a challenge.Some scholars implied that the Outer Space Treaty(1967)clearly prohibits appropriation of whole celestial bodies but is far less clear concerning the rights of over-extracted resources.Nevertheless,the Moon Agreement(1979)promotes the idea of property ownership of over-extracted resources.It permits states to collect and remove samples of lunar minerals and other substances for further interest in scientific investigation.The application of the Moon Agreement(1979)is not only to the Moon itself but to other celestial bodies,thus potentially covering the planets and asteroids where the mining potential is considered to be limitless.Under this circumstance,numerous countries,such as the United States,Luxembourg,The United Arab Emirates,and Japan have enacted legal regimes that glorify the rights of their entities in mineral resources in outer space.However,these regimes could be disputed under the international legal framework if countries have merely interpreted and applied their rights and obligations on a national level as they understand them.Therefore,this paper purports to clarify the ownership rights in outer space and analyze the purpose of the legal situation relating to space resource exploitation and utilization activities under the adoption of the United States,Luxembourg,The United Arab Emirates,and Japan.展开更多
The segmentation of retinal vessels and coronary angiographs is essential for diagnosing conditions such as glaucoma,diabetes,hypertension,and coronary artery disease.However,retinal vessels and coronary angiographs a...The segmentation of retinal vessels and coronary angiographs is essential for diagnosing conditions such as glaucoma,diabetes,hypertension,and coronary artery disease.However,retinal vessels and coronary angiographs are characterized by low contrast and complex structures,posing challenges for vessel segmentation.Moreover,CNN-based approaches are limited in capturing long-range pixel relationships due to their focus on local feature extraction,while ViT-based approaches struggle to capture fine local details,impacting tasks like vessel segmentation that require precise boundary detection.To address these issues,in this paper,we propose a Global–Local Hybrid Modulation Network(GLHM-Net),a dual-encoder architecture that combines the strengths of CNNs and ViTs for vessel segmentation.First,the Hybrid Non-Local Transformer Block(HNLTB)is proposed to efficiently consolidate long-range spatial dependencies into a compact feature representation,providing a global perspective while significantly reducing computational overhead.Second,the Collaborative Attention Fusion Block(CAFB)is proposed to more effectively integrate local and global vessel features at the same hierarchical level during the encoding phase.Finally,the proposed Feature Cross-Modulation Block(FCMB)better complements the local and global features in the decoding stage,effectively enhancing feature learning and minimizing information loss.The experiments conducted on the DRIVE,CHASEDB1,DCA1,and XCAD datasets,achieving AUC values of 0.9811,0.9864,0.9915,and 0.9919,F1 scores of 0.8288,0.8202,0.8040,and 0.8150,and IOU values of 0.7076,0.6952,0.6723,and 0.6878,respectively,demonstrate the strong performance of our proposed network for vessel segmentation.展开更多
The key to the success of few-shot semantic segmentation(FSS)depends on the efficient use of limited annotated support set to accurately segment novel classes in the query set.Due to the few samples in the support set...The key to the success of few-shot semantic segmentation(FSS)depends on the efficient use of limited annotated support set to accurately segment novel classes in the query set.Due to the few samples in the support set,FSS faces challenges such as intra-class differences,background(BG)mismatches between query and support sets,and ambiguous segmentation between the foreground(FG)and BG in the query set.To address these issues,The paper propose a multi-module network called CAMSNet,which includes four modules:the General Information Module(GIM),the Class Activation Map Aggregation(CAMA)module,the Self-Cross Attention(SCA)Block,and the Feature Fusion Module(FFM).In CAMSNet,The GIM employs an improved triplet loss,which concatenates word embedding vectors and support prototypes as anchors,and uses local support features of FG and BG as positive and negative samples to help solve the problem of intra-class differences.Then for the first time,the Class Activation Map(CAM)from the Weakly Supervised Semantic Segmentation(WSSS)is applied to FSS within the CAMA module.This method replaces the traditional use of cosine similarity to locate query information.Subsequently,the SCA Block processes the support and query features aggregated by the CAMA module,significantly enhancing the understanding of input information,leading to more accurate predictions and effectively addressing BG mismatch and ambiguous FG-BG segmentation.Finally,The FFM combines general class information with the enhanced query information to achieve accurate segmentation of the query image.Extensive Experiments on PASCAL and COCO demonstrate that-5i-20ithe CAMSNet yields superior performance and set a state-of-the-art.展开更多
Neuronal soma segmentation plays a crucial role in neuroscience applications.However,the fine structure,such as boundaries,small-volume neuronal somata and fibers,are commonly present in cell images,which pose a chall...Neuronal soma segmentation plays a crucial role in neuroscience applications.However,the fine structure,such as boundaries,small-volume neuronal somata and fibers,are commonly present in cell images,which pose a challenge for accurate segmentation.In this paper,we propose a 3D semantic segmentation network for neuronal soma segmentation to address this issue.Using an encoding-decoding structure,we introduce a Multi-Scale feature extraction and Adaptive Weighting fusion module(MSAW)after each encoding block.The MSAW module can not only emphasize the fine structures via an upsampling strategy,but also provide pixel-wise weights to measure the importance of the multi-scale features.Additionally,a dynamic convolution instead of normal convolution is employed to better adapt the network to input data with different distributions.The proposed MSAW-based semantic segmentation network(MSAW-Net)was evaluated on three neuronal soma images from mouse brain and one neuronal soma image from macaque brain,demonstrating the efficiency of the proposed method.It achieved an F1 score of 91.8%on Fezf2-2A-CreER dataset,97.1%on LSL-H2B-GFP dataset,82.8%on Thy1-EGFP-Mline dataset,and 86.9%on macaque dataset,achieving improvements over the 3D U-Net model by 3.1%,3.3%,3.9%,and 2.3%,respectively.展开更多
The use of AI technologies in remote sensing(RS)tasks has been the focus of many individuals in both the professional and academic domains.Having more accessible interfaces and tools that allow people of little or no ...The use of AI technologies in remote sensing(RS)tasks has been the focus of many individuals in both the professional and academic domains.Having more accessible interfaces and tools that allow people of little or no experience to intuitively interact with RS data of multiple formats is a potential provided by this integration.However,the use of AI and AI agents to help automate RS-related tasks is still in its infancy stage,with some frameworks and interfaces built on top of well-known vision language models(VLM)such as GPT-4,segment anything model(SAM),and grounding DINO.These tools do promise and draw guidelines on the potentials and limitations of existing solutions concerning the use of said models.In this work,the state of the art AI foundation models(FM)are reviewed and used in a multi-modal manner to ingest RS imagery input and perform zero-shot object detection using natural language.The natural language input is then used to define the classes or labels the model should look for,then,both inputs are fed to the pipeline.The pipeline presented in this work makes up for the shortcomings of the general knowledge FMs by stacking pre-processing and post-processing applications on top of the FMs;these applications include tiling to produce uniform patches of the original image for faster detection,outlier rejection of redundant bounding boxes using statistical and machine learning methods.The pipeline was tested with UAV,aerial and satellite images taken over multiple areas.The accuracy for the semantic segmentation showed improvement from the original 64%to approximately 80%-99%by utilizing the pipeline and techniques proposed in this work.GitHub Repository:MohanadDiab/LangRS.展开更多
The complexity of the seismicity pattern for the subduction zone along the oceanic plate triggered the outer rise events and revealed cyclic tectonic deformation conditions along the plate subduction zones.The outer r...The complexity of the seismicity pattern for the subduction zone along the oceanic plate triggered the outer rise events and revealed cyclic tectonic deformation conditions along the plate subduction zones.The outer rise earthquakes have been observed along the Sunda arc,following the estimated rupture area of the 2005 M_(W)8.6 Nias earthquakes.Here,we used kinematic waveform inversion(KIWI)to obtain the source parameters of the 14 May 2021 M_(W)6.6 event off the west coast of northern Sumatra and to define the fault plane that triggered this outer rise event.The KIWI algorithm allows two types of seismic source to be configured:the moment tensor model to describe the type of shear with six moment tensor components and the Eikonal model for the rupture of pure double-couple sources.This method was chosen for its flexibility to be applied for different sources of seismicity and also for the automated full-moment tensor solution with real-time monitoring.We used full waveform traces from 8 broadband seismic stations within 1000 km epicentral distances sourced from the Incorporated Research Institutions for Seismology(IRIS-IDA)and Geofon GFZ seismic record databases.The initial origin time and hypocenter values are obtained from the IRIS-IDA.The synthetic seismograms used in the inversion process are based on the existing regional green function database model and were accessed from the KIWI Tools Green's Function Database.The obtained scalar seismic moment value is 1.18×10^(19)N·m,equivalent to a moment magnitude M_(W)6.6.The source parameters are 140°,44°,and−99°for the strike,dip,and rake values at a centroid depth of 10.2 km,indicating that this event is a normal fault earthquake that occurred in the outer rise area.The outer rise events with normal faults typically occur at the shallow part of the plate,with nodal-plane dips predominantly in the range of 30°-60°on the weak oceanic lithosphere due to hydrothermal alteration.The stress regime around the plate subduction zone varies both temporally and spatially due to the cyclic influences of megathrust earthquakes.Tensional outer rise earthquakes tend to occur after the megathrust events.The relative timing of these events is not known due to the viscous relaxation of the down going slab and poroelastic response in the trench slope region.The occurrence of the 14 May 2021 earthquake shows the seismicity in the outer rise region in the strongly coupled Sunda arc subduction zone due to elastic bending stress within the duration of the seismic cycle.展开更多
基金supported by the Army Laboratory Animal Foundation of China,No.SYDW[2020]22(to TC)the Shaanxi Provincial Key R&D Plan General Project of China,No.2022SF-236(to YM)the National Natural Science Foundation of China,No.82202070(to TC)。
文摘A microgravity environment has been shown to cause ocular damage and affect visual acuity,but the underlying mechanisms remain unclear.Therefore,we established an animal model of weightlessness via tail suspension to examine the pathological changes and molecular mechanisms of retinal damage under microgravity.After 4 weeks of tail suspension,there were no notable alterations in retinal function and morphology,while after 8 weeks of tail suspension,significant reductions in retinal function were observed,and the outer nuclear layer was thinner,with abundant apoptotic cells.To investigate the mechanism underlying the degenerative changes that occurred in the outer nuclear layer of the retina,proteomics was used to analyze differentially expressed proteins in rat retinas after 8 weeks of tail suspension.The results showed that the expression levels of fibroblast growth factor 2(also known as basic fibroblast growth factor)and glial fibrillary acidic protein,which are closely related to Müller cell activation,were significantly upregulated.In addition,Müller cell regeneration and Müller cell gliosis were observed after 4 and 8 weeks,respectively,of simulated weightlessness.These findings indicate that Müller cells play an important regulatory role in retinal outer nuclear layer degeneration during weightlessness.
基金funded by the Natural Science Foundation of the Jiangsu Higher Education Institutions of China(grant number 22KJD440001)Changzhou Science&Technology Program(grant number CJ20220232).
文摘The Internet of Vehicles (IoV) has become an important direction in the field of intelligent transportation, in which vehicle positioning is a crucial part. SLAM (Simultaneous Localization and Mapping) technology plays a crucial role in vehicle localization and navigation. Traditional Simultaneous Localization and Mapping (SLAM) systems are designed for use in static environments, and they can result in poor performance in terms of accuracy and robustness when used in dynamic environments where objects are in constant movement. To address this issue, a new real-time visual SLAM system called MG-SLAM has been developed. Based on ORB-SLAM2, MG-SLAM incorporates a dynamic target detection process that enables the detection of both known and unknown moving objects. In this process, a separate semantic segmentation thread is required to segment dynamic target instances, and the Mask R-CNN algorithm is applied on the Graphics Processing Unit (GPU) to accelerate segmentation. To reduce computational cost, only key frames are segmented to identify known dynamic objects. Additionally, a multi-view geometry method is adopted to detect unknown moving objects. The results demonstrate that MG-SLAM achieves higher precision, with an improvement from 0.2730 m to 0.0135 m in precision. Moreover, the processing time required by MG-SLAM is significantly reduced compared to other dynamic scene SLAM algorithms, which illustrates its efficacy in locating objects in dynamic scenes.
文摘Brain tumors present significant challenges in medical diagnosis and treatment,where early detection is crucial for reducing morbidity and mortality rates.This research introduces a novel deep learning model,the Progressive Layered U-Net(PLU-Net),designed to improve brain tumor segmentation accuracy from Magnetic Resonance Imaging(MRI)scans.The PLU-Net extends the standard U-Net architecture by incorporating progressive layering,attention mechanisms,and multi-scale data augmentation.The progressive layering involves a cascaded structure that refines segmentation masks across multiple stages,allowing the model to capture features at different scales and resolutions.Attention gates within the convolutional layers selectively focus on relevant features while suppressing irrelevant ones,enhancing the model's ability to delineate tumor boundaries.Additionally,multi-scale data augmentation techniques increase the diversity of training data and boost the model's generalization capabilities.Evaluated on the BraTS 2021 dataset,the PLU-Net achieved state-of-the-art performance with a dice coefficient of 0.91,specificity of 0.92,sensitivity of 0.89,Hausdorff95 of 2.5,outperforming other modified U-Net architectures in segmentation accuracy.These results underscore the effectiveness of the PLU-Net in improving brain tumor segmentation from MRI scans,supporting clinicians in early diagnosis,treatment planning,and the development of new therapies.
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financially supported by the National Key Research and Development Program of China (2022YFC3005600)the Foundation of the Anhui Educational Commission (2023AH051198)+1 种基金the National Natural Science Foundation of China (42125401 and 42104063)the Joint Open Fund of Mengcheng National Geophysical Observatory (MENGO-202201)。
文摘The Tan-Lu Fault Zone is a large NNE-trending fault zone that has a substantial effect on the development of eastern China and its earthquake disaster prevention efforts. Aiming at the azimuthally anisotropic structure in the upper crust and seismogenic tectonics in the Hefei segment of this fault, we collected phase velocity dispersion data of fundamental mode Rayleigh waves from ambient noise cross-correlation functions of ~400 temporal seismographs in an area of approximately 80 × 70 km along the fault zone. The period band of the dispersion data was ~0.5–10 s. We inverted for the upper crustal three-dimensional(3-D) shear velocity model with azimuthal anisotropy from the surface to 10 km depth by using a 3-D direct azimuthal anisotropy inversion method. The inversion result shows the spatial distribution characteristics of the tectonic units in the upper crust. Additionally, the deformation of the Tan-Lu Fault Zone and its conjugated fault systems could be inferred from the anisotropy model. In particular, the faults that have remained active from the early and middle Pleistocene control the anisotropic characteristics of the upper crustal structure in this area. The direction of fast axes near the fault zone area in the upper crust is consistent with the strike of the faults, whereas for the region far away from the fault zone, the direction of fast axes is consistent with the direction of the regional principal stress caused by plate movement. Combined with the azimuthal anisotropy models in the deep crust and uppermost mantle from the surface wave and Pn wave, the different anisotropic patterns caused by the Tan-Lu Fault Zone and its conjugated fault system nearby are shown in the upper and lower crust. Furthermore,by using the double-difference method, we relocated the Lujiang earthquake series, which contained 32 earthquakes with a depth shallower than 10 km. Both the Vs model and earthquake relocation results indicate that earthquakes mostly occurred in the vicinity of structural boundaries with fractured media, with high-level development of cracks and small-scale faults jammed between more rigid areas.
基金National Natural Science Foundation of China(Nos.61773387 and 62022061).
文摘A segmented predictor-corrector method is proposed for hypersonic glide vehicles to address the issue of the slow computational speed of obtaining guidance commands using the traditional predictor-corrector guidance method.Firstly,an altitude-energy profile is designed,and the bank angle is derived analytically as the initial iteration value for the predictor-corrector method.The predictor-corrector guidance method has been improved by deriving an analytical form for predicting the range-to-go error,which greatly accelerates the iterative speed.Then,a segmented guidance algorithm is proposed.The above analytically predictor-corrector guidance method is adopted when the energy exceeds an energy threshold.When the energy is less than the threshold,the equidistant test method is used to calculate the bank angle command,which ensures guidance accuracy as well as computational efficiency.Additionally,an adaptive guidance cycle strategy is applied to reduce the computational time of the reentry guidance trajectory.Finally,the accuracy and robustness of the proposed method are verified through a series of simulations and Monte-Carlo experiments.Compared with the traditional integral method,the proposed method requires 75%less computation time on average and achieves a lower landing error.
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.
文摘Retinal blood vessel segmentation is crucial for diagnosing ocular and cardiovascular diseases.Although the introduction of U-Net in 2015 by Olaf Ronneberger significantly advanced this field,yet issues like limited training data,imbalance data distribution,and inadequate feature extraction persist,hindering both the segmentation performance and optimal model generalization.Addressing these critical issues,the DEFFA-Unet is proposed featuring an additional encoder to process domain-invariant pre-processed inputs,thereby improving both richer feature encoding and enhanced model generalization.A feature filtering fusion module is developed to ensure the precise feature filtering and robust hybrid feature fusion.In response to the task-specific need for higher precision where false positives are very costly,traditional skip connections are replaced with the attention-guided feature reconstructing fusion module.Additionally,innovative data augmentation and balancing methods are proposed to counter data scarcity and distribution imbalance,further boosting the robustness and generalization of the model.With a comprehensive suite of evaluation metrics,extensive validations on four benchmark datasets(DRIVE,CHASEDB1,STARE,and HRF)and an SLO dataset(IOSTAR),demonstrate the proposed method’s superiority over both baseline and state-of-the-art models.Particularly the proposed method significantly outperforms the compared methods in cross-validation model generalization.
文摘BACKGROUND The incidence of acute myocardial infarction(AMI)is rising,with cardiac rupture accounting for approximately 2%of deaths in patients with acute ST-segment elevation myocardial infarction(STEMI).Ventricular free wall rupture(FWR)occurs in approximately 2%of AMI patients and is notably rare in patients with non-STEMI.Types of cardiac rupture include left ventricular FWR,ventricular septal rupture,and papillary muscle rupture.The FWR usually leads to acute cardiac tamponade or electromechanical dissociation,where standard resuscitation efforts may not be effective.Ventricular septal rupture and papillary muscle rupture often result in refractory heart failure,with mortality rates over 50%,even with surgical or percutaneous repair options.CASE SUMMARY We present a rare case of an acute non-STEMI patient who suffered sudden FWR causing cardiac tamponade and loss of consciousness immediate before undergoing coronary angiography.Prompt resuscitation and emergency open-heart repair along with coronary artery bypass grafting resulted in successful patient recovery.CONCLUSION This case emphasizes the risks of AMI complications,shares a successful treatment scenario,and discusses measures to prevent such complications.
基金supported by the Innovation Foundation of National Commercial Aircraft Manufacturing Engineering Technology Research Center(No.COMAC-SFGS-2022-1877)in part by the National Natural Science Foundation of China(No.92048301)。
文摘Cabin cables,as critical components of an aircraft's electrical system,significantly impact the operational efficiency and safety of the aircraft.The existing cable segmentation methods in civil aviation cabins are limited,especially in automation,heavily dependent on large amounts of data and resources,lacking the flexibility to adapt to different scenarios.To address these challenges,this paper introduces a novel image segmentation model,CableSAM,specifically designed for automated segmentation of cabin cables.CableSAM improves segmentation efficiency and accuracy using knowledge distillation and employs a context ensemble strategy.It accurately segments cables in various scenarios with minimal input prompts.Comparative experiments on three cable datasets demonstrate that CableSAM surpasses other advanced cable segmentation methods in performance.
文摘In recent years,video coding has been widely applied in the field of video image processing to remove redundant information and improve data transmission efficiency.However,during the video coding process,irrelevant objects such as background elements are often encoded due to environmental disturbances,resulting in the wastage of computational resources.Existing research on video coding efficiency optimization primarily focuses on optimizing encoding units during intra-frame or inter frame prediction after the generation of coding units,neglecting the optimization of video images before coding unit generation.To address this challenge,This work proposes an image semantic segmentation compression algorithm based on macroblock encoding,called image semantic segmentation compression algorithm based on macroblock encoding(ISSC-ME),which consists of three modules.(1)The semantic label generation module generates interesting object labels using a grid-based approach to reduce redundant coding of consecutive frames.(2)The image segmentation network module generates a semantic segmentation image using U-Net.(3)The macroblock coding module,is a block segmentation-based video encoding and decoding algorithm used to compress images and improve video transmission efficiency.Experimental results show that the proposed image semantic segmentation optimization algorithm can reduce the computational costs,and improve the overall accuracy by 1.00%and the mean intersection over union(IoU)by 1.20%.In addition,the proposed compression algorithm utilizes macroblock fusion,resulting in the image compression rate achieving 80.64%.It has been proven that the proposed algorithm greatly reduces data storage and transmission,and enables fast image compression processing at the millisecond level.
文摘Medical image segmentation has become a cornerstone for many healthcare applications,allowing for the automated extraction of critical information from images such as Computed Tomography(CT)scans,Magnetic Resonance Imaging(MRIs),and X-rays.The introduction of U-Net in 2015 has significantly advanced segmentation capabilities,especially for small datasets commonly found in medical imaging.Since then,various modifications to the original U-Net architecture have been proposed to enhance segmentation accuracy and tackle challenges like class imbalance,data scarcity,and multi-modal image processing.This paper provides a detailed review and comparison of several U-Net-based architectures,focusing on their effectiveness in medical image segmentation tasks.We evaluate performance metrics such as Dice Similarity Coefficient(DSC)and Intersection over Union(IoU)across different U-Net variants including HmsU-Net,CrossU-Net,mResU-Net,and others.Our results indicate that architectural enhancements such as transformers,attention mechanisms,and residual connections improve segmentation performance across diverse medical imaging applications,including tumor detection,organ segmentation,and lesion identification.The study also identifies current challenges in the field,including data variability,limited dataset sizes,and issues with class imbalance.Based on these findings,the paper suggests potential future directions for improving the robustness and clinical applicability of U-Net-based models in medical image segmentation.
基金Natural Science Foundation of Zhejiang Province,Grant/Award Number:LY23F020025Science and Technology Commissioner Program of Huzhou,Grant/Award Number:2023GZ42Sichuan Provincial Science and Technology Support Program,Grant/Award Numbers:2023ZHCG0005,2023ZHCG0008。
文摘Data augmentation plays an important role in training deep neural model by expanding the size and diversity of the dataset.Initially,data augmentation mainly involved some simple transformations of images.Later,in order to increase the diversity and complexity of data,more advanced methods appeared and evolved to sophisticated generative models.However,these methods required a mass of computation of training or searching.In this paper,a novel training-free method that utilises the Pre-Trained Segment Anything Model(SAM)model as a data augmentation tool(PTSAM-DA)is proposed to generate the augmented annotations for images.Without the need for training,it obtains prompt boxes from the original annotations and then feeds the boxes to the pre-trained SAM to generate diverse and improved annotations.In this way,annotations are augmented more ingenious than simple manipulations without incurring huge computation for training a data augmentation model.Multiple comparative experiments on three datasets are conducted,including an in-house dataset,ADE20K and COCO2017.On this in-house dataset,namely Agricultural Plot Segmentation Dataset,maximum improvements of 3.77%and 8.92%are gained in two mainstream metrics,mIoU and mAcc,respectively.Consequently,large vision models like SAM are proven to be promising not only in image segmentation but also in data augmentation.
文摘This paper presents CW-HRNet,a high-resolution,lightweight crack segmentation network designed to address challenges in complex scenes with slender,deformable,and blurred crack structures.The model incorporates two key modules:Constrained Deformable Convolution(CDC),which stabilizes geometric alignment by applying a tanh limiter and learnable scaling factor to the predicted offsets,and the Wavelet Frequency Enhancement Module(WFEM),which decomposes features using Haar wavelets to preserve low-frequency structures while enhancing high-frequency boundaries and textures.Evaluations on the CrackSeg9k benchmark demonstrate CW-HRNet’s superior performance,achieving 82.39%mIoU with only 7.49M parameters and 10.34 GFLOPs,outperforming HrSegNet-B48 by 1.83% in segmentation accuracy with minimal complexity overhead.The model also shows strong cross-dataset generalization,achieving 60.01%mIoU and 66.22%F1 on Asphalt3k without fine-tuning.These results highlight CW-HRNet’s favorable accuracyefficiency trade-off for real-world crack segmentation tasks.
文摘Ownership is an increasingly important conflict in outer space at this moment in time.Despite the principle in the Outer Space Treaty(1967),that emphasizes the importance of all states'free access to outer space based on equality for exploration and use.Moreover,outer space including the Moon and other celestial bodies is not subject to national appropriation by claim of sovereignty,by means of use or occupation,or by any other means.However,outer space activity is not free from sovereignty and jurisdiction after all.Anyway,the legal situation relating to space resource exploitation and utilization activities under the adoption of United Nations is a challenge.Some scholars implied that the Outer Space Treaty(1967)clearly prohibits appropriation of whole celestial bodies but is far less clear concerning the rights of over-extracted resources.Nevertheless,the Moon Agreement(1979)promotes the idea of property ownership of over-extracted resources.It permits states to collect and remove samples of lunar minerals and other substances for further interest in scientific investigation.The application of the Moon Agreement(1979)is not only to the Moon itself but to other celestial bodies,thus potentially covering the planets and asteroids where the mining potential is considered to be limitless.Under this circumstance,numerous countries,such as the United States,Luxembourg,The United Arab Emirates,and Japan have enacted legal regimes that glorify the rights of their entities in mineral resources in outer space.However,these regimes could be disputed under the international legal framework if countries have merely interpreted and applied their rights and obligations on a national level as they understand them.Therefore,this paper purports to clarify the ownership rights in outer space and analyze the purpose of the legal situation relating to space resource exploitation and utilization activities under the adoption of the United States,Luxembourg,The United Arab Emirates,and Japan.
基金supported by Natural Science Research Project of Tianjin Education Commission(Grant 2020KJ124)National Natural Science Foundation of China(Grant 11601372)National Key Research and Development Program of China(Grant 2022YFF0706003).
文摘The segmentation of retinal vessels and coronary angiographs is essential for diagnosing conditions such as glaucoma,diabetes,hypertension,and coronary artery disease.However,retinal vessels and coronary angiographs are characterized by low contrast and complex structures,posing challenges for vessel segmentation.Moreover,CNN-based approaches are limited in capturing long-range pixel relationships due to their focus on local feature extraction,while ViT-based approaches struggle to capture fine local details,impacting tasks like vessel segmentation that require precise boundary detection.To address these issues,in this paper,we propose a Global–Local Hybrid Modulation Network(GLHM-Net),a dual-encoder architecture that combines the strengths of CNNs and ViTs for vessel segmentation.First,the Hybrid Non-Local Transformer Block(HNLTB)is proposed to efficiently consolidate long-range spatial dependencies into a compact feature representation,providing a global perspective while significantly reducing computational overhead.Second,the Collaborative Attention Fusion Block(CAFB)is proposed to more effectively integrate local and global vessel features at the same hierarchical level during the encoding phase.Finally,the proposed Feature Cross-Modulation Block(FCMB)better complements the local and global features in the decoding stage,effectively enhancing feature learning and minimizing information loss.The experiments conducted on the DRIVE,CHASEDB1,DCA1,and XCAD datasets,achieving AUC values of 0.9811,0.9864,0.9915,and 0.9919,F1 scores of 0.8288,0.8202,0.8040,and 0.8150,and IOU values of 0.7076,0.6952,0.6723,and 0.6878,respectively,demonstrate the strong performance of our proposed network for vessel segmentation.
基金supported by funding from the following sources:National Natural Science Foundation of China(U1904119)Research Programs of Henan Science and Technology Department(232102210033,232102210054)+3 种基金Chongqing Natural Science Foundation(CSTB2023NSCQ-MSX0070)Henan Province Key Research and Development Project(231111212000)Aviation Science Foundation(20230001055002)supported by Henan Center for Outstanding Overseas Scientists(GZS2022011).
文摘The key to the success of few-shot semantic segmentation(FSS)depends on the efficient use of limited annotated support set to accurately segment novel classes in the query set.Due to the few samples in the support set,FSS faces challenges such as intra-class differences,background(BG)mismatches between query and support sets,and ambiguous segmentation between the foreground(FG)and BG in the query set.To address these issues,The paper propose a multi-module network called CAMSNet,which includes four modules:the General Information Module(GIM),the Class Activation Map Aggregation(CAMA)module,the Self-Cross Attention(SCA)Block,and the Feature Fusion Module(FFM).In CAMSNet,The GIM employs an improved triplet loss,which concatenates word embedding vectors and support prototypes as anchors,and uses local support features of FG and BG as positive and negative samples to help solve the problem of intra-class differences.Then for the first time,the Class Activation Map(CAM)from the Weakly Supervised Semantic Segmentation(WSSS)is applied to FSS within the CAMA module.This method replaces the traditional use of cosine similarity to locate query information.Subsequently,the SCA Block processes the support and query features aggregated by the CAMA module,significantly enhancing the understanding of input information,leading to more accurate predictions and effectively addressing BG mismatch and ambiguous FG-BG segmentation.Finally,The FFM combines general class information with the enhanced query information to achieve accurate segmentation of the query image.Extensive Experiments on PASCAL and COCO demonstrate that-5i-20ithe CAMSNet yields superior performance and set a state-of-the-art.
基金supported by the STI2030-Major-Projects(No.2021ZD0200104)the National Natural Science Foundations of China under Grant 61771437.
文摘Neuronal soma segmentation plays a crucial role in neuroscience applications.However,the fine structure,such as boundaries,small-volume neuronal somata and fibers,are commonly present in cell images,which pose a challenge for accurate segmentation.In this paper,we propose a 3D semantic segmentation network for neuronal soma segmentation to address this issue.Using an encoding-decoding structure,we introduce a Multi-Scale feature extraction and Adaptive Weighting fusion module(MSAW)after each encoding block.The MSAW module can not only emphasize the fine structures via an upsampling strategy,but also provide pixel-wise weights to measure the importance of the multi-scale features.Additionally,a dynamic convolution instead of normal convolution is employed to better adapt the network to input data with different distributions.The proposed MSAW-based semantic segmentation network(MSAW-Net)was evaluated on three neuronal soma images from mouse brain and one neuronal soma image from macaque brain,demonstrating the efficiency of the proposed method.It achieved an F1 score of 91.8%on Fezf2-2A-CreER dataset,97.1%on LSL-H2B-GFP dataset,82.8%on Thy1-EGFP-Mline dataset,and 86.9%on macaque dataset,achieving improvements over the 3D U-Net model by 3.1%,3.3%,3.9%,and 2.3%,respectively.
文摘The use of AI technologies in remote sensing(RS)tasks has been the focus of many individuals in both the professional and academic domains.Having more accessible interfaces and tools that allow people of little or no experience to intuitively interact with RS data of multiple formats is a potential provided by this integration.However,the use of AI and AI agents to help automate RS-related tasks is still in its infancy stage,with some frameworks and interfaces built on top of well-known vision language models(VLM)such as GPT-4,segment anything model(SAM),and grounding DINO.These tools do promise and draw guidelines on the potentials and limitations of existing solutions concerning the use of said models.In this work,the state of the art AI foundation models(FM)are reviewed and used in a multi-modal manner to ingest RS imagery input and perform zero-shot object detection using natural language.The natural language input is then used to define the classes or labels the model should look for,then,both inputs are fed to the pipeline.The pipeline presented in this work makes up for the shortcomings of the general knowledge FMs by stacking pre-processing and post-processing applications on top of the FMs;these applications include tiling to produce uniform patches of the original image for faster detection,outlier rejection of redundant bounding boxes using statistical and machine learning methods.The pipeline was tested with UAV,aerial and satellite images taken over multiple areas.The accuracy for the semantic segmentation showed improvement from the original 64%to approximately 80%-99%by utilizing the pipeline and techniques proposed in this work.GitHub Repository:MohanadDiab/LangRS.
基金supported by the National Natural Science Foundation of China(Grant No.42130312)。
文摘The complexity of the seismicity pattern for the subduction zone along the oceanic plate triggered the outer rise events and revealed cyclic tectonic deformation conditions along the plate subduction zones.The outer rise earthquakes have been observed along the Sunda arc,following the estimated rupture area of the 2005 M_(W)8.6 Nias earthquakes.Here,we used kinematic waveform inversion(KIWI)to obtain the source parameters of the 14 May 2021 M_(W)6.6 event off the west coast of northern Sumatra and to define the fault plane that triggered this outer rise event.The KIWI algorithm allows two types of seismic source to be configured:the moment tensor model to describe the type of shear with six moment tensor components and the Eikonal model for the rupture of pure double-couple sources.This method was chosen for its flexibility to be applied for different sources of seismicity and also for the automated full-moment tensor solution with real-time monitoring.We used full waveform traces from 8 broadband seismic stations within 1000 km epicentral distances sourced from the Incorporated Research Institutions for Seismology(IRIS-IDA)and Geofon GFZ seismic record databases.The initial origin time and hypocenter values are obtained from the IRIS-IDA.The synthetic seismograms used in the inversion process are based on the existing regional green function database model and were accessed from the KIWI Tools Green's Function Database.The obtained scalar seismic moment value is 1.18×10^(19)N·m,equivalent to a moment magnitude M_(W)6.6.The source parameters are 140°,44°,and−99°for the strike,dip,and rake values at a centroid depth of 10.2 km,indicating that this event is a normal fault earthquake that occurred in the outer rise area.The outer rise events with normal faults typically occur at the shallow part of the plate,with nodal-plane dips predominantly in the range of 30°-60°on the weak oceanic lithosphere due to hydrothermal alteration.The stress regime around the plate subduction zone varies both temporally and spatially due to the cyclic influences of megathrust earthquakes.Tensional outer rise earthquakes tend to occur after the megathrust events.The relative timing of these events is not known due to the viscous relaxation of the down going slab and poroelastic response in the trench slope region.The occurrence of the 14 May 2021 earthquake shows the seismicity in the outer rise region in the strongly coupled Sunda arc subduction zone due to elastic bending stress within the duration of the seismic cycle.
