Due to the inability of manufacturing a single monolithic mirror at the 10-meter scales,segmented mirrors have become indispensable tools in modern astronomical research.However,to match the imaging performance of the...Due to the inability of manufacturing a single monolithic mirror at the 10-meter scales,segmented mirrors have become indispensable tools in modern astronomical research.However,to match the imaging performance of the monolithic counterpart,the sub-mirrors must maintain precise co-phasing.Piston error critically degrades segmented mirror imaging quality,necessitating efficient and precise detection.To ad-dress the limitations that the conventional circular-aperture diffraction with two-wavelength algorithm is sus-ceptible to decentration errors,and the traditional convolutional neural networks(CNNs)struggle to capture global features under large-range piston errors due to their restricted local receptive fields,this paper pro-poses a method that integrates extended Young’s interference principles with a Vision Transformer(ViT)to detect piston error.By suppressing decentration error interference through two symmetrically arranged aper-tures and extending the measurement range to±7.95μm via a two-wavelength(589 nm/600 nm)algorithm.This approach exploits ViT’s self-attention mechanism to model global characteristics of interference fringes.Unlike CNNs constrained by local convolutional kernels,the ViT significantly improves sensitivity to inter-ferogram periodicity.The simulation results demonstrate that the proposed method achieves a measurement accuracy of 5 nm(0.0083λ0)across the range of±7.95μm,while maintaining an accuracy exceeding 95%in the presence of Gaussian noise(SNR≥15 dB),Poisson noise(λ≥9 photons/pixel),and sub-mirror gap er-ror(Egap≤0.2)interference.Moreover,the detection speed shows significant improvement compared to the cross-correlation algorithm.This study establishes an accurate,robust framework for segmented mirror error detection,advancing high-precision astronomical observation.展开更多
High-resolution remote sensing images(HRSIs)are now an essential data source for gathering surface information due to advancements in remote sensing data capture technologies.However,their significant scale changes an...High-resolution remote sensing images(HRSIs)are now an essential data source for gathering surface information due to advancements in remote sensing data capture technologies.However,their significant scale changes and wealth of spatial details pose challenges for semantic segmentation.While convolutional neural networks(CNNs)excel at capturing local features,they are limited in modeling long-range dependencies.Conversely,transformers utilize multihead self-attention to integrate global context effectively,but this approach often incurs a high computational cost.This paper proposes a global-local multiscale context network(GLMCNet)to extract both global and local multiscale contextual information from HRSIs.A detail-enhanced filtering module(DEFM)is proposed at the end of the encoder to refine the encoder outputs further,thereby enhancing the key details extracted by the encoder and effectively suppressing redundant information.In addition,a global-local multiscale transformer block(GLMTB)is proposed in the decoding stage to enable the modeling of rich multiscale global and local information.We also design a stair fusion mechanism to transmit deep semantic information from deep to shallow layers progressively.Finally,we propose the semantic awareness enhancement module(SAEM),which further enhances the representation of multiscale semantic features through spatial attention and covariance channel attention.Extensive ablation analyses and comparative experiments were conducted to evaluate the performance of the proposed method.Specifically,our method achieved a mean Intersection over Union(mIoU)of 86.89%on the ISPRS Potsdam dataset and 84.34%on the ISPRS Vaihingen dataset,outperforming existing models such as ABCNet and BANet.展开更多
Advanced traffic monitoring systems encounter substantial challenges in vehicle detection and classification due to the limitations of conventional methods,which often demand extensive computational resources and stru...Advanced traffic monitoring systems encounter substantial challenges in vehicle detection and classification due to the limitations of conventional methods,which often demand extensive computational resources and struggle with diverse data acquisition techniques.This research presents a novel approach for vehicle classification and recognition in aerial image sequences,integrating multiple advanced techniques to enhance detection accuracy.The proposed model begins with preprocessing using Multiscale Retinex(MSR)to enhance image quality,followed by Expectation-Maximization(EM)Segmentation for precise foreground object identification.Vehicle detection is performed using the state-of-the-art YOLOv10 framework,while feature extraction incorporates Maximally Stable Extremal Regions(MSER),Dense Scale-Invariant Feature Transform(Dense SIFT),and Zernike Moments Features to capture distinct object characteristics.Feature optimization is further refined through a Hybrid Swarm-based Optimization algorithm,ensuring optimal feature selection for improved classification performance.The final classification is conducted using a Vision Transformer,leveraging its robust learning capabilities for enhanced accuracy.Experimental evaluations on benchmark datasets,including UAVDT and the Unmanned Aerial Vehicle Intruder Dataset(UAVID),demonstrate the superiority of the proposed approach,achieving an accuracy of 94.40%on UAVDT and 93.57%on UAVID.The results highlight the efficacy of the model in significantly enhancing vehicle detection and classification in aerial imagery,outperforming existing methodologies and offering a statistically validated improvement for intelligent traffic monitoring systems compared to existing approaches.展开更多
Polyurethane elastomers exhibit high dielectric constants owing to their polar groups,and can be used as energy storage capacitors.Energy storage depends not only on the dielectric constant but also on the dielectric ...Polyurethane elastomers exhibit high dielectric constants owing to their polar groups,and can be used as energy storage capacitors.Energy storage depends not only on the dielectric constant but also on the dielectric loss.However,the relationship between chain structure and dielectric properties is not yet clear.Ketal-containing crosslinked polyurethane elastomers were prepared using cyclic ketal diol as a chain extender.The effect of the soft segment length on the dielectric properties and energy storage was investigated.The cause of the change in the dipolar polarization with the soft segment length was analyzed.As the soft segment length increased,the hard-soft hydrogen bonding decreased,whereas the hard-hard hydrogen bonding increased.Under the action of an electric field,the polar bonds in the ketal-containing polyurethane elastomer overcome the hydrogen bonding between hard-soft segments to produce polarization;meanwhile,they also experience crankshaft motions to generate polarization.The former has a relatively high relaxation activation energy of approximately 10-20 k J·mol^(-1),resulting in a large dielectric loss.The latter has a relatively low relaxation activation energy,approximately 0.7-1.7 kJ·mol^(-1),leading to low dielectric loss.As a result,the dielectric constant showed a decreasing trend,and the dielectric loss gradually decreased.This study provides a theoretical foundation for improving the dielectric properties of polyurethane elastomers.展开更多
Background:Diabetic macular edema is a prevalent retinal condition and a leading cause of visual impairment among diabetic patients’Early detection of affected areas is beneficial for effective diagnosis and treatmen...Background:Diabetic macular edema is a prevalent retinal condition and a leading cause of visual impairment among diabetic patients’Early detection of affected areas is beneficial for effective diagnosis and treatment.Traditionally,diagnosis relies on optical coherence tomography imaging technology interpreted by ophthalmologists.However,this manual image interpretation is often slow and subjective.Therefore,developing automated segmentation for macular edema images is essential to enhance to improve the diagnosis efficiency and accuracy.Methods:In order to improve clinical diagnostic efficiency and accuracy,we proposed a SegNet network structure integrated with a convolutional block attention module(CBAM).This network introduces a multi-scale input module,the CBAM attention mechanism,and jump connection.The multi-scale input module enhances the network’s perceptual capabilities,while the lightweight CBAM effectively fuses relevant features across channels and spatial dimensions,allowing for better learning of varying information levels.Results:Experimental results demonstrate that the proposed network achieves an IoU of 80.127%and an accuracy of 99.162%.Compared to the traditional segmentation network,this model has fewer parameters,faster training and testing speed,and superior performance on semantic segmentation tasks,indicating its highly practical applicability.Conclusion:The C-SegNet proposed in this study enables accurate segmentation of Diabetic macular edema lesion images,which facilitates quicker diagnosis for healthcare professionals.展开更多
This systematic review aims to comprehensively examine and compare deep learning methods for brain tumor segmentation and classification using MRI and other imaging modalities,focusing on recent trends from 2022 to 20...This systematic review aims to comprehensively examine and compare deep learning methods for brain tumor segmentation and classification using MRI and other imaging modalities,focusing on recent trends from 2022 to 2025.The primary objective is to evaluate methodological advancements,model performance,dataset usage,and existing challenges in developing clinically robust AI systems.We included peer-reviewed journal articles and highimpact conference papers published between 2022 and 2025,written in English,that proposed or evaluated deep learning methods for brain tumor segmentation and/or classification.Excluded were non-open-access publications,books,and non-English articles.A structured search was conducted across Scopus,Google Scholar,Wiley,and Taylor&Francis,with the last search performed in August 2025.Risk of bias was not formally quantified but considered during full-text screening based on dataset diversity,validation methods,and availability of performance metrics.We used narrative synthesis and tabular benchmarking to compare performance metrics(e.g.,accuracy,Dice score)across model types(CNN,Transformer,Hybrid),imaging modalities,and datasets.A total of 49 studies were included(43 journal articles and 6 conference papers).These studies spanned over 9 public datasets(e.g.,BraTS,Figshare,REMBRANDT,MOLAB)and utilized a range of imaging modalities,predominantly MRI.Hybrid models,especially ResViT and UNetFormer,consistently achieved high performance,with classification accuracy exceeding 98%and segmentation Dice scores above 0.90 across multiple studies.Transformers and hybrid architectures showed increasing adoption post2023.Many studies lacked external validation and were evaluated only on a few benchmark datasets,raising concerns about generalizability and dataset bias.Few studies addressed clinical interpretability or uncertainty quantification.Despite promising results,particularly for hybrid deep learning models,widespread clinical adoption remains limited due to lack of validation,interpretability concerns,and real-world deployment barriers.展开更多
Brain tumors require precise segmentation for diagnosis and treatment plans due to their complex morphology and heterogeneous characteristics.While MRI-based automatic brain tumor segmentation technology reduces the b...Brain tumors require precise segmentation for diagnosis and treatment plans due to their complex morphology and heterogeneous characteristics.While MRI-based automatic brain tumor segmentation technology reduces the burden on medical staff and provides quantitative information,existing methodologies and recent models still struggle to accurately capture and classify the fine boundaries and diverse morphologies of tumors.In order to address these challenges and maximize the performance of brain tumor segmentation,this research introduces a novel SwinUNETR-based model by integrating a new decoder block,the Hierarchical Channel-wise Attention Decoder(HCAD),into a powerful SwinUNETR encoder.The HCAD decoder block utilizes hierarchical features and channelspecific attention mechanisms to further fuse information at different scales transmitted from the encoder and preserve spatial details throughout the reconstruction phase.Rigorous evaluations on the recent BraTS GLI datasets demonstrate that the proposed SwinHCAD model achieved superior and improved segmentation accuracy on both the Dice score and HD95 metrics across all tumor subregions(WT,TC,and ET)compared to baseline models.In particular,the rationale and contribution of the model design were clarified through ablation studies to verify the effectiveness of the proposed HCAD decoder block.The results of this study are expected to greatly contribute to enhancing the efficiency of clinical diagnosis and treatment planning by increasing the precision of automated brain tumor segmentation.展开更多
The northern segment of the North-South Seismic Belt is characterized by intense crustal deformation,well-developed active tectonics,and frequent occurrences of strong earthquakes.Therefore,conducting a Probabilistic ...The northern segment of the North-South Seismic Belt is characterized by intense crustal deformation,well-developed active tectonics,and frequent occurrences of strong earthquakes.Therefore,conducting a Probabilistic Seismic Hazard Analysis(PSHA)for this region is of significant importance for supporting seismic fortification in major engineering projects and formulating disaster prevention and mitigation policies.In this study,a composite seismic source model was constructed by integrating data on historical earthquakes,active faults,and paleoseismicity.Furthermore,a logic tree framework was employed to quantify epistemic uncertainties,enabling a systematic seismic hazard assessment of the region.To more accurately characterize the spatial heterogeneity of seismic activity,improvements were made to both the Circular Spatial Smoothing Model(CSSM)with a fixed radius and the Adaptive Spatial Smoothing Model(ASSM),with full consideration given to the spatiotemporal completeness of historical earthquake magnitudes.Regarding the CSSM,for scenarios involving small sample sizes in earthquake catalogs,the cross-validation method proposed in this study demonstrated higher robustness than the maximum likelihood method in determining the optimal correlation distance.Performance evaluation results indicate that while both models effectively characterize seismic activity,the ASSM exhibits superior overall predictive performance compared to the CSSM,owing to its ability to adaptively adjust the smoothing radius according to seismic density.Significant discrepancies were observed in the Peak Ground Acceleration(PGA)results calculated with a 10%probability of exceedance in 50 years across different combinations of seismic source models.The single spatially smoothed point-source model yielded a maximum PGA of approximately 0.52 g,with high-value areas concentrated near historical epicenters,thereby significantly underestimating the hazard associated with major fault zones.When combined with the simple fault-source model,the maximum PGA increased to 0.8 g,with high-value zones exhibiting a zonal distribution along faults;however,the risk remained underestimated for faults with low slip rates that are nevertheless approaching their recurrence cycles.Following the introduction of the time-dependent characteristic fault-source model,local PGA values for faults in the middle-to-late stages of their recurrence cycles increased by a factor of 2 to 7 compared to the single model.These results demonstrate that the characteristic fault-source model reasonably delineates the time-dependence of large earthquake recurrence,thereby providing a more accurate assessment of imminent seismic risks.By comprehensively applying the improved spatially smoothed pointsource model,the simple fault-source model,and the characteristic fault-source model,the following faults within the region were identified as having high seismic hazard:the Huangxianggou,Zhangxian,and Tianshui segments of the Xiqinling northern edge fault;the Maqin-Maqu segment of the Dongkunlun fault;the Longriqu fault;the Maoergai fault;the Elashan fault;the Riyueshan fault;the eastern segment of the Lenglongling fault;the Maxianshan segment of the Maxianshan northern Margin fault;and the Maomaoshan-Jinqianghe segment of the Laohushan-Maomaoshan fault.As these faults are located within seismic gaps or are approaching the recurrence periods of large earthquakes,they should be prioritized for current and future seismic monitoring as well as disaster prevention and mitigation efforts.展开更多
Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone t...Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.展开更多
Considering the desirable behavior of concrete filled steel tube(CFT)columns and the complicated behavior of segmental double-column piers under cyclic loads,three post-tensioned precast segmental CFT double-column pi...Considering the desirable behavior of concrete filled steel tube(CFT)columns and the complicated behavior of segmental double-column piers under cyclic loads,three post-tensioned precast segmental CFT double-column pier specimens were tested to extend their application in moderate and high seismicity areas.The effects of the number of CFT segments and the steel endplates as energy dissipaters on the seismic behavior of the piers were evaluated.The experimental results show that the segmental piers exhibited stable hysteretic behavior with small residual displacements under cyclic loads.All the tested specimens achieved a drift ratio no less than 13%without significant damage and strength deterioration due to the desirable behavior of CFT columns.Since the deformation of segmental columns was mainly concentrated at the column-footing interfaces,the increase of the segment numbers for each column had no obvious effects on the loading capacity but reduced the initial stiffness of the specimens.The use of steel endplates improved the bearing capacity,stiffness and energy dissipation of segmental piers,but weakened their self-centering capacity.Fiber models were also proposed to simulate the hysteretic behavior of the tested specimens,and the influences of segment numbers and prestress levels on seismic behavior were further studied.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
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
Image segmentation is attracting increasing attention in the field of medical image analysis.Since widespread utilization across various medical applications,ensuring and improving segmentation accuracy has become a c...Image segmentation is attracting increasing attention in the field of medical image analysis.Since widespread utilization across various medical applications,ensuring and improving segmentation accuracy has become a crucial topic of research.With advances in deep learning,researchers have developed numerous methods that combine Transformers and convolutional neural networks(CNNs)to create highly accurate models for medical image segmentation.However,efforts to further enhance accuracy by developing larger and more complex models or training with more extensive datasets,significantly increase computational resource consumption.To address this problem,we propose BiCLIP-nnFormer(the prefix"Bi"refers to the use of two distinct CLIP models),a virtual multimodal instrument that leverages CLIP models to enhance the segmentation performance of a medical segmentation model nnFormer.Since two CLIP models(PMC-CLIP and CoCa-CLIP)are pre-trained on large datasets,they do not require additional training,thus conserving computation resources.These models are used offline to extract image and text embeddings from medical images.These embeddings are then processed by the proposed 3D CLIP adapter,which adapts the CLIP knowledge for segmentation tasks by fine-tuning.Finally,the adapted embeddings are fused with feature maps extracted from the nnFormer encoder for generating predicted masks.This process enriches the representation capabilities of the feature maps by integrating global multimodal information,leading to more precise segmentation predictions.We demonstrate the superiority of BiCLIP-nnFormer and the effectiveness of using CLIP models to enhance nnFormer through experiments on two public datasets,namely the Synapse multi-organ segmentation dataset(Synapse)and the Automatic Cardiac Diagnosis Challenge dataset(ACDC),as well as a self-annotated lung multi-category segmentation dataset(LMCS).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
To avoid the laborious annotation process for dense prediction tasks like semantic segmentation,unsupervised domain adaptation(UDA)methods have been proposed to leverage the abundant annotations from a source domain,s...To avoid the laborious annotation process for dense prediction tasks like semantic segmentation,unsupervised domain adaptation(UDA)methods have been proposed to leverage the abundant annotations from a source domain,such as virtual world(e.g.,3D games),and adapt models to the target domain(the real world)by narrowing the domain discrepancies.However,because of the large domain gap,directly aligning two distinct domains without considering the intermediates leads to inefficient alignment and inferior adaptation.To address this issue,we propose a novel learnable evolutionary Category Intermediates(CIs)guided UDA model named Leci,which enables the information transfer between the two domains via two processes,i.e.,Distilling and Blending.Starting from a random initialization,the CIs learn shared category-wise semantics automatically from two domains in the Distilling process.Then,the learned semantics in the CIs are sent back to blend the domain features through a residual attentive fusion(RAF)module,such that the categorywise features of both domains shift towards each other.As the CIs progressively and consistently learn from the varying feature distributions during training,they are evolutionary to guide the model to achieve category-wise feature alignment.Experiments on both GTA5 and SYNTHIA datasets demonstrate Leci's superiority over prior representative methods.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
Convolutional neural networks(CNNs)-based medical image segmentation technologies have been widely used in medical image segmentation because of their strong representation and generalization abilities.However,due to ...Convolutional neural networks(CNNs)-based medical image segmentation technologies have been widely used in medical image segmentation because of their strong representation and generalization abilities.However,due to the inability to effectively capture global information from images,CNNs can easily lead to loss of contours and textures in segmentation results.Notice that the transformer model can effectively capture the properties of long-range dependencies in the image,and furthermore,combining the CNN and the transformer can effectively extract local details and global contextual features of the image.Motivated by this,we propose a multi-branch and multi-scale attention network(M2ANet)for medical image segmentation,whose architecture consists of three components.Specifically,in the first component,we construct an adaptive multi-branch patch module for parallel extraction of image features to reduce information loss caused by downsampling.In the second component,we apply residual block to the well-known convolutional block attention module to enhance the network’s ability to recognize important features of images and alleviate the phenomenon of gradient vanishing.In the third component,we design a multi-scale feature fusion module,in which we adopt adaptive average pooling and position encoding to enhance contextual features,and then multi-head attention is introduced to further enrich feature representation.Finally,we validate the effectiveness and feasibility of the proposed M2ANet method through comparative experiments on four benchmark medical image segmentation datasets,particularly in the context of preserving contours and textures.展开更多
Karst fractures serve as crucial seepage channels and storage spaces for carbonate natural gas reservoirs,and electrical image logs are vital data for visualizing and characterizing such fractures.However,the conventi...Karst fractures serve as crucial seepage channels and storage spaces for carbonate natural gas reservoirs,and electrical image logs are vital data for visualizing and characterizing such fractures.However,the conventional approach of identifying fractures using electrical image logs predominantly relies on manual processes that are not only time-consuming but also highly subjective.In addition,the heterogeneity and strong dissolution tendency of karst carbonate reservoirs lead to complexity and variety in fracture geometry,which makes it difficult to accurately identify fractures.In this paper,the electrical image logs network(EILnet)da deep-learning-based intelligent semantic segmentation model with a selective attention mechanism and selective feature fusion moduledwas created to enable the intelligent identification and segmentation of different types of fractures through electrical logging images.Data from electrical image logs representing structural and induced fractures were first selected using the sliding window technique before image inpainting and data augmentation were implemented for these images to improve the generalizability of the model.Various image-processing tools,including the bilateral filter,Laplace operator,and Gaussian low-pass filter,were also applied to the electrical logging images to generate a multi-attribute dataset to help the model learn the semantic features of the fractures.The results demonstrated that the EILnet model outperforms mainstream deep-learning semantic segmentation models,such as Fully Convolutional Networks(FCN-8s),U-Net,and SegNet,for both the single-channel dataset and the multi-attribute dataset.The EILnet provided significant advantages for the single-channel dataset,and its mean intersection over union(MIoU)and pixel accuracy(PA)were 81.32%and 89.37%,respectively.In the case of the multi-attribute dataset,the identification capability of all models improved to varying degrees,with the EILnet achieving the highest MIoU and PA of 83.43%and 91.11%,respectively.Further,applying the EILnet model to various blind wells demonstrated its ability to provide reliable fracture identification,thereby indicating its promising potential applications.展开更多
文摘Due to the inability of manufacturing a single monolithic mirror at the 10-meter scales,segmented mirrors have become indispensable tools in modern astronomical research.However,to match the imaging performance of the monolithic counterpart,the sub-mirrors must maintain precise co-phasing.Piston error critically degrades segmented mirror imaging quality,necessitating efficient and precise detection.To ad-dress the limitations that the conventional circular-aperture diffraction with two-wavelength algorithm is sus-ceptible to decentration errors,and the traditional convolutional neural networks(CNNs)struggle to capture global features under large-range piston errors due to their restricted local receptive fields,this paper pro-poses a method that integrates extended Young’s interference principles with a Vision Transformer(ViT)to detect piston error.By suppressing decentration error interference through two symmetrically arranged aper-tures and extending the measurement range to±7.95μm via a two-wavelength(589 nm/600 nm)algorithm.This approach exploits ViT’s self-attention mechanism to model global characteristics of interference fringes.Unlike CNNs constrained by local convolutional kernels,the ViT significantly improves sensitivity to inter-ferogram periodicity.The simulation results demonstrate that the proposed method achieves a measurement accuracy of 5 nm(0.0083λ0)across the range of±7.95μm,while maintaining an accuracy exceeding 95%in the presence of Gaussian noise(SNR≥15 dB),Poisson noise(λ≥9 photons/pixel),and sub-mirror gap er-ror(Egap≤0.2)interference.Moreover,the detection speed shows significant improvement compared to the cross-correlation algorithm.This study establishes an accurate,robust framework for segmented mirror error detection,advancing high-precision astronomical observation.
基金provided by the Science Research Project of Hebei Education Department under grant No.BJK2024115.
文摘High-resolution remote sensing images(HRSIs)are now an essential data source for gathering surface information due to advancements in remote sensing data capture technologies.However,their significant scale changes and wealth of spatial details pose challenges for semantic segmentation.While convolutional neural networks(CNNs)excel at capturing local features,they are limited in modeling long-range dependencies.Conversely,transformers utilize multihead self-attention to integrate global context effectively,but this approach often incurs a high computational cost.This paper proposes a global-local multiscale context network(GLMCNet)to extract both global and local multiscale contextual information from HRSIs.A detail-enhanced filtering module(DEFM)is proposed at the end of the encoder to refine the encoder outputs further,thereby enhancing the key details extracted by the encoder and effectively suppressing redundant information.In addition,a global-local multiscale transformer block(GLMTB)is proposed in the decoding stage to enable the modeling of rich multiscale global and local information.We also design a stair fusion mechanism to transmit deep semantic information from deep to shallow layers progressively.Finally,we propose the semantic awareness enhancement module(SAEM),which further enhances the representation of multiscale semantic features through spatial attention and covariance channel attention.Extensive ablation analyses and comparative experiments were conducted to evaluate the performance of the proposed method.Specifically,our method achieved a mean Intersection over Union(mIoU)of 86.89%on the ISPRS Potsdam dataset and 84.34%on the ISPRS Vaihingen dataset,outperforming existing models such as ABCNet and BANet.
文摘Advanced traffic monitoring systems encounter substantial challenges in vehicle detection and classification due to the limitations of conventional methods,which often demand extensive computational resources and struggle with diverse data acquisition techniques.This research presents a novel approach for vehicle classification and recognition in aerial image sequences,integrating multiple advanced techniques to enhance detection accuracy.The proposed model begins with preprocessing using Multiscale Retinex(MSR)to enhance image quality,followed by Expectation-Maximization(EM)Segmentation for precise foreground object identification.Vehicle detection is performed using the state-of-the-art YOLOv10 framework,while feature extraction incorporates Maximally Stable Extremal Regions(MSER),Dense Scale-Invariant Feature Transform(Dense SIFT),and Zernike Moments Features to capture distinct object characteristics.Feature optimization is further refined through a Hybrid Swarm-based Optimization algorithm,ensuring optimal feature selection for improved classification performance.The final classification is conducted using a Vision Transformer,leveraging its robust learning capabilities for enhanced accuracy.Experimental evaluations on benchmark datasets,including UAVDT and the Unmanned Aerial Vehicle Intruder Dataset(UAVID),demonstrate the superiority of the proposed approach,achieving an accuracy of 94.40%on UAVDT and 93.57%on UAVID.The results highlight the efficacy of the model in significantly enhancing vehicle detection and classification in aerial imagery,outperforming existing methodologies and offering a statistically validated improvement for intelligent traffic monitoring systems compared to existing approaches.
基金financially supported by the Hubei Key Laboratory of Pollutant Analysis&Reuse Technology(No.PA230102)。
文摘Polyurethane elastomers exhibit high dielectric constants owing to their polar groups,and can be used as energy storage capacitors.Energy storage depends not only on the dielectric constant but also on the dielectric loss.However,the relationship between chain structure and dielectric properties is not yet clear.Ketal-containing crosslinked polyurethane elastomers were prepared using cyclic ketal diol as a chain extender.The effect of the soft segment length on the dielectric properties and energy storage was investigated.The cause of the change in the dipolar polarization with the soft segment length was analyzed.As the soft segment length increased,the hard-soft hydrogen bonding decreased,whereas the hard-hard hydrogen bonding increased.Under the action of an electric field,the polar bonds in the ketal-containing polyurethane elastomer overcome the hydrogen bonding between hard-soft segments to produce polarization;meanwhile,they also experience crankshaft motions to generate polarization.The former has a relatively high relaxation activation energy of approximately 10-20 k J·mol^(-1),resulting in a large dielectric loss.The latter has a relatively low relaxation activation energy,approximately 0.7-1.7 kJ·mol^(-1),leading to low dielectric loss.As a result,the dielectric constant showed a decreasing trend,and the dielectric loss gradually decreased.This study provides a theoretical foundation for improving the dielectric properties of polyurethane elastomers.
基金supported by the Guangdong Pharmaceutical University 2024 Higher Education Research Projects(GKP202403,GMP202402)the Guangdong Pharmaceutical University College Students’Innovation and Entrepreneurship Training Programs(Grant No.202504302033,202504302034,202504302036,and 202504302244).
文摘Background:Diabetic macular edema is a prevalent retinal condition and a leading cause of visual impairment among diabetic patients’Early detection of affected areas is beneficial for effective diagnosis and treatment.Traditionally,diagnosis relies on optical coherence tomography imaging technology interpreted by ophthalmologists.However,this manual image interpretation is often slow and subjective.Therefore,developing automated segmentation for macular edema images is essential to enhance to improve the diagnosis efficiency and accuracy.Methods:In order to improve clinical diagnostic efficiency and accuracy,we proposed a SegNet network structure integrated with a convolutional block attention module(CBAM).This network introduces a multi-scale input module,the CBAM attention mechanism,and jump connection.The multi-scale input module enhances the network’s perceptual capabilities,while the lightweight CBAM effectively fuses relevant features across channels and spatial dimensions,allowing for better learning of varying information levels.Results:Experimental results demonstrate that the proposed network achieves an IoU of 80.127%and an accuracy of 99.162%.Compared to the traditional segmentation network,this model has fewer parameters,faster training and testing speed,and superior performance on semantic segmentation tasks,indicating its highly practical applicability.Conclusion:The C-SegNet proposed in this study enables accurate segmentation of Diabetic macular edema lesion images,which facilitates quicker diagnosis for healthcare professionals.
文摘This systematic review aims to comprehensively examine and compare deep learning methods for brain tumor segmentation and classification using MRI and other imaging modalities,focusing on recent trends from 2022 to 2025.The primary objective is to evaluate methodological advancements,model performance,dataset usage,and existing challenges in developing clinically robust AI systems.We included peer-reviewed journal articles and highimpact conference papers published between 2022 and 2025,written in English,that proposed or evaluated deep learning methods for brain tumor segmentation and/or classification.Excluded were non-open-access publications,books,and non-English articles.A structured search was conducted across Scopus,Google Scholar,Wiley,and Taylor&Francis,with the last search performed in August 2025.Risk of bias was not formally quantified but considered during full-text screening based on dataset diversity,validation methods,and availability of performance metrics.We used narrative synthesis and tabular benchmarking to compare performance metrics(e.g.,accuracy,Dice score)across model types(CNN,Transformer,Hybrid),imaging modalities,and datasets.A total of 49 studies were included(43 journal articles and 6 conference papers).These studies spanned over 9 public datasets(e.g.,BraTS,Figshare,REMBRANDT,MOLAB)and utilized a range of imaging modalities,predominantly MRI.Hybrid models,especially ResViT and UNetFormer,consistently achieved high performance,with classification accuracy exceeding 98%and segmentation Dice scores above 0.90 across multiple studies.Transformers and hybrid architectures showed increasing adoption post2023.Many studies lacked external validation and were evaluated only on a few benchmark datasets,raising concerns about generalizability and dataset bias.Few studies addressed clinical interpretability or uncertainty quantification.Despite promising results,particularly for hybrid deep learning models,widespread clinical adoption remains limited due to lack of validation,interpretability concerns,and real-world deployment barriers.
基金supported by Institute of Information&Communications Technology Planning&Evaluation(IITP)under the Metaverse Support Program to Nurture the Best Talents(IITP-2024-RS-2023-00254529)grant funded by the Korea government(MSIT).
文摘Brain tumors require precise segmentation for diagnosis and treatment plans due to their complex morphology and heterogeneous characteristics.While MRI-based automatic brain tumor segmentation technology reduces the burden on medical staff and provides quantitative information,existing methodologies and recent models still struggle to accurately capture and classify the fine boundaries and diverse morphologies of tumors.In order to address these challenges and maximize the performance of brain tumor segmentation,this research introduces a novel SwinUNETR-based model by integrating a new decoder block,the Hierarchical Channel-wise Attention Decoder(HCAD),into a powerful SwinUNETR encoder.The HCAD decoder block utilizes hierarchical features and channelspecific attention mechanisms to further fuse information at different scales transmitted from the encoder and preserve spatial details throughout the reconstruction phase.Rigorous evaluations on the recent BraTS GLI datasets demonstrate that the proposed SwinHCAD model achieved superior and improved segmentation accuracy on both the Dice score and HD95 metrics across all tumor subregions(WT,TC,and ET)compared to baseline models.In particular,the rationale and contribution of the model design were clarified through ablation studies to verify the effectiveness of the proposed HCAD decoder block.The results of this study are expected to greatly contribute to enhancing the efficiency of clinical diagnosis and treatment planning by increasing the precision of automated brain tumor segmentation.
基金supported by the National Key R&D Program of China(No.2022YFC3003502).
文摘The northern segment of the North-South Seismic Belt is characterized by intense crustal deformation,well-developed active tectonics,and frequent occurrences of strong earthquakes.Therefore,conducting a Probabilistic Seismic Hazard Analysis(PSHA)for this region is of significant importance for supporting seismic fortification in major engineering projects and formulating disaster prevention and mitigation policies.In this study,a composite seismic source model was constructed by integrating data on historical earthquakes,active faults,and paleoseismicity.Furthermore,a logic tree framework was employed to quantify epistemic uncertainties,enabling a systematic seismic hazard assessment of the region.To more accurately characterize the spatial heterogeneity of seismic activity,improvements were made to both the Circular Spatial Smoothing Model(CSSM)with a fixed radius and the Adaptive Spatial Smoothing Model(ASSM),with full consideration given to the spatiotemporal completeness of historical earthquake magnitudes.Regarding the CSSM,for scenarios involving small sample sizes in earthquake catalogs,the cross-validation method proposed in this study demonstrated higher robustness than the maximum likelihood method in determining the optimal correlation distance.Performance evaluation results indicate that while both models effectively characterize seismic activity,the ASSM exhibits superior overall predictive performance compared to the CSSM,owing to its ability to adaptively adjust the smoothing radius according to seismic density.Significant discrepancies were observed in the Peak Ground Acceleration(PGA)results calculated with a 10%probability of exceedance in 50 years across different combinations of seismic source models.The single spatially smoothed point-source model yielded a maximum PGA of approximately 0.52 g,with high-value areas concentrated near historical epicenters,thereby significantly underestimating the hazard associated with major fault zones.When combined with the simple fault-source model,the maximum PGA increased to 0.8 g,with high-value zones exhibiting a zonal distribution along faults;however,the risk remained underestimated for faults with low slip rates that are nevertheless approaching their recurrence cycles.Following the introduction of the time-dependent characteristic fault-source model,local PGA values for faults in the middle-to-late stages of their recurrence cycles increased by a factor of 2 to 7 compared to the single model.These results demonstrate that the characteristic fault-source model reasonably delineates the time-dependence of large earthquake recurrence,thereby providing a more accurate assessment of imminent seismic risks.By comprehensively applying the improved spatially smoothed pointsource model,the simple fault-source model,and the characteristic fault-source model,the following faults within the region were identified as having high seismic hazard:the Huangxianggou,Zhangxian,and Tianshui segments of the Xiqinling northern edge fault;the Maqin-Maqu segment of the Dongkunlun fault;the Longriqu fault;the Maoergai fault;the Elashan fault;the Riyueshan fault;the eastern segment of the Lenglongling fault;the Maxianshan segment of the Maxianshan northern Margin fault;and the Maomaoshan-Jinqianghe segment of the Laohushan-Maomaoshan fault.As these faults are located within seismic gaps or are approaching the recurrence periods of large earthquakes,they should be prioritized for current and future seismic monitoring as well as disaster prevention and mitigation efforts.
文摘Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.
基金National Natural Science Foundation of China under Grant Nos.51978656 and 51478459the Key Research and Development Project of Xuzhou under Grant No.KC22282the Open Fund of Jiangsu Key Laboratory of Environmental Impact and Structural Safety in Civil Engineering,China University of Mining and Technology under Grant No.KFJJ202004。
文摘Considering the desirable behavior of concrete filled steel tube(CFT)columns and the complicated behavior of segmental double-column piers under cyclic loads,three post-tensioned precast segmental CFT double-column pier specimens were tested to extend their application in moderate and high seismicity areas.The effects of the number of CFT segments and the steel endplates as energy dissipaters on the seismic behavior of the piers were evaluated.The experimental results show that the segmental piers exhibited stable hysteretic behavior with small residual displacements under cyclic loads.All the tested specimens achieved a drift ratio no less than 13%without significant damage and strength deterioration due to the desirable behavior of CFT columns.Since the deformation of segmental columns was mainly concentrated at the column-footing interfaces,the increase of the segment numbers for each column had no obvious effects on the loading capacity but reduced the initial stiffness of the specimens.The use of steel endplates improved the bearing capacity,stiffness and energy dissipation of segmental piers,but weakened their self-centering capacity.Fiber models were also proposed to simulate the hysteretic behavior of the tested specimens,and the influences of segment numbers and prestress levels on seismic behavior were further studied.
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.
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.
基金funded by the National Natural Science Foundation of China(Grant No.6240072655)the Hubei Provincial Key Research and Development Program(Grant No.2023BCB151)+1 种基金the Wuhan Natural Science Foundation Exploration Program(Chenguang Program,Grant No.2024040801020202)the Natural Science Foundation of Hubei Province of China(Grant No.2025AFB148).
文摘Image segmentation is attracting increasing attention in the field of medical image analysis.Since widespread utilization across various medical applications,ensuring and improving segmentation accuracy has become a crucial topic of research.With advances in deep learning,researchers have developed numerous methods that combine Transformers and convolutional neural networks(CNNs)to create highly accurate models for medical image segmentation.However,efforts to further enhance accuracy by developing larger and more complex models or training with more extensive datasets,significantly increase computational resource consumption.To address this problem,we propose BiCLIP-nnFormer(the prefix"Bi"refers to the use of two distinct CLIP models),a virtual multimodal instrument that leverages CLIP models to enhance the segmentation performance of a medical segmentation model nnFormer.Since two CLIP models(PMC-CLIP and CoCa-CLIP)are pre-trained on large datasets,they do not require additional training,thus conserving computation resources.These models are used offline to extract image and text embeddings from medical images.These embeddings are then processed by the proposed 3D CLIP adapter,which adapts the CLIP knowledge for segmentation tasks by fine-tuning.Finally,the adapted embeddings are fused with feature maps extracted from the nnFormer encoder for generating predicted masks.This process enriches the representation capabilities of the feature maps by integrating global multimodal information,leading to more precise segmentation predictions.We demonstrate the superiority of BiCLIP-nnFormer and the effectiveness of using CLIP models to enhance nnFormer through experiments on two public datasets,namely the Synapse multi-organ segmentation dataset(Synapse)and the Automatic Cardiac Diagnosis Challenge dataset(ACDC),as well as a self-annotated lung multi-category segmentation dataset(LMCS).
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Australian Research Council Project(FL-170100117).
文摘To avoid the laborious annotation process for dense prediction tasks like semantic segmentation,unsupervised domain adaptation(UDA)methods have been proposed to leverage the abundant annotations from a source domain,such as virtual world(e.g.,3D games),and adapt models to the target domain(the real world)by narrowing the domain discrepancies.However,because of the large domain gap,directly aligning two distinct domains without considering the intermediates leads to inefficient alignment and inferior adaptation.To address this issue,we propose a novel learnable evolutionary Category Intermediates(CIs)guided UDA model named Leci,which enables the information transfer between the two domains via two processes,i.e.,Distilling and Blending.Starting from a random initialization,the CIs learn shared category-wise semantics automatically from two domains in the Distilling process.Then,the learned semantics in the CIs are sent back to blend the domain features through a residual attentive fusion(RAF)module,such that the categorywise features of both domains shift towards each other.As the CIs progressively and consistently learn from the varying feature distributions during training,they are evolutionary to guide the model to achieve category-wise feature alignment.Experiments on both GTA5 and SYNTHIA datasets demonstrate Leci's superiority over prior representative methods.
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 the Natural Science Foundation of the Anhui Higher Education Institutions of China(Grant Nos.2023AH040149 and 2024AH051915)the Anhui Provincial Natural Science Foundation(Grant No.2208085MF168)+1 种基金the Science and Technology Innovation Tackle Plan Project of Maanshan(Grant No.2024RGZN001)the Scientific Research Fund Project of Anhui Medical University(Grant No.2023xkj122).
文摘Convolutional neural networks(CNNs)-based medical image segmentation technologies have been widely used in medical image segmentation because of their strong representation and generalization abilities.However,due to the inability to effectively capture global information from images,CNNs can easily lead to loss of contours and textures in segmentation results.Notice that the transformer model can effectively capture the properties of long-range dependencies in the image,and furthermore,combining the CNN and the transformer can effectively extract local details and global contextual features of the image.Motivated by this,we propose a multi-branch and multi-scale attention network(M2ANet)for medical image segmentation,whose architecture consists of three components.Specifically,in the first component,we construct an adaptive multi-branch patch module for parallel extraction of image features to reduce information loss caused by downsampling.In the second component,we apply residual block to the well-known convolutional block attention module to enhance the network’s ability to recognize important features of images and alleviate the phenomenon of gradient vanishing.In the third component,we design a multi-scale feature fusion module,in which we adopt adaptive average pooling and position encoding to enhance contextual features,and then multi-head attention is introduced to further enrich feature representation.Finally,we validate the effectiveness and feasibility of the proposed M2ANet method through comparative experiments on four benchmark medical image segmentation datasets,particularly in the context of preserving contours and textures.
基金the National Natural Science Foundation of China(42472194,42302153,and 42002144)the Fundamental Research Funds for the Central Univer-sities(22CX06002A).
文摘Karst fractures serve as crucial seepage channels and storage spaces for carbonate natural gas reservoirs,and electrical image logs are vital data for visualizing and characterizing such fractures.However,the conventional approach of identifying fractures using electrical image logs predominantly relies on manual processes that are not only time-consuming but also highly subjective.In addition,the heterogeneity and strong dissolution tendency of karst carbonate reservoirs lead to complexity and variety in fracture geometry,which makes it difficult to accurately identify fractures.In this paper,the electrical image logs network(EILnet)da deep-learning-based intelligent semantic segmentation model with a selective attention mechanism and selective feature fusion moduledwas created to enable the intelligent identification and segmentation of different types of fractures through electrical logging images.Data from electrical image logs representing structural and induced fractures were first selected using the sliding window technique before image inpainting and data augmentation were implemented for these images to improve the generalizability of the model.Various image-processing tools,including the bilateral filter,Laplace operator,and Gaussian low-pass filter,were also applied to the electrical logging images to generate a multi-attribute dataset to help the model learn the semantic features of the fractures.The results demonstrated that the EILnet model outperforms mainstream deep-learning semantic segmentation models,such as Fully Convolutional Networks(FCN-8s),U-Net,and SegNet,for both the single-channel dataset and the multi-attribute dataset.The EILnet provided significant advantages for the single-channel dataset,and its mean intersection over union(MIoU)and pixel accuracy(PA)were 81.32%and 89.37%,respectively.In the case of the multi-attribute dataset,the identification capability of all models improved to varying degrees,with the EILnet achieving the highest MIoU and PA of 83.43%and 91.11%,respectively.Further,applying the EILnet model to various blind wells demonstrated its ability to provide reliable fracture identification,thereby indicating its promising potential applications.
