Fractures are critical to subsurface activities such as oil and gas extraction,geothermal energy production,and carbon storage.Hydraulic fracturing,a technique that enhances fluid production,creates complex fracture n...Fractures are critical to subsurface activities such as oil and gas extraction,geothermal energy production,and carbon storage.Hydraulic fracturing,a technique that enhances fluid production,creates complex fracture networks within rock formations containing natural discontinuities.Accurately distinguishing between hydraulically induced fractures and pre-existing discontinuities is essential for understanding hydraulic fracture mechanisms.However,this remains challenging due to the interconnected nature of fractures in three-dimensional(3D)space.Manual segmentation,while adaptive,is both labor-intensive and subjective,making it impractical for large-scale 3D datasets.This study introduces a deep learning-based progressive cross-sectional segmentation method to automate the classification of 3D fracture volumes.The proposed method was applied to a 3D hydraulic fracture network in a Montney cube sample,successfully segmenting natural fractures,parted bedding planes,and hydraulic fractures with minimal user intervention.The automated approach achieves a 99.6%reduction in manual image processing workload while maintaining high segmentation accuracy,with test accuracy exceeding 98%and F1-score over 84%.This approach generalizes well to Brazilian disc samples with different fracture patterns,achieving consistently high accuracy in distinguishing between bedding and non-bedding fractures.This automated fracture segmentation method offers an effective tool for enhanced quantitative characterization of fracture networks,which would contribute to a deeper understanding of hydraulic fracturing processes.展开更多
Segmenting vegetation in color images is a complex task, especially when the background and lighting conditions of the environment are uncontrolled. This paper proposes a vegetation segmentation algorithm that combine...Segmenting vegetation in color images is a complex task, especially when the background and lighting conditions of the environment are uncontrolled. This paper proposes a vegetation segmentation algorithm that combines a supervised and an unsupervised learning method to segment healthy and diseased plant images from the background. During the training stage, a Self-Organizing Map (SOM) neural network is applied to create different color groups from a set of images containing vegetation, acquired from a tomato greenhouse. The color groups are labeled as vegetation and non-vegetation and then used to create two color histogram models corresponding to vegetation and non-vegetation. In the online mode, input images are segmented by a Bayesian classifier using the two histogram models. This algorithm has provided a qualitatively better segmentation rate of images containing plants’ foliage in uncontrolled environments than the segmentation rate obtained by a color index technique, resulting in the elimination of the background and the preservation of important color information. This segmentation method will be applied in disease diagnosis of tomato plants in greenhouses as future work.展开更多
Acting as a pilot of the Square Kilometer Array (SKA), a Five hundred meter Aperture Spherical Telescope (FAST) project puts forward many innovative ideas, among which the design of the active main reflector shows fas...Acting as a pilot of the Square Kilometer Array (SKA), a Five hundred meter Aperture Spherical Telescope (FAST) project puts forward many innovative ideas, among which the design of the active main reflector shows fascinating potential. The main spherical reflector is to be composed of thousands of small spherical panels, which can be adjusted to fit a paraboloid of revolution in real time. For the construction and performance, the rms of the fit must be optimized, and so appropriate dimensional limits for the panels need to be determined. The issue of how to divide the spherical reflector mathematically is addressed in this paper. The advantages and drawbacks of various segmenting methods are discussed and an optimum one is suggested.展开更多
Segmenting Arabic handwritings had been one of the subjects of research in the field of Arabic character recognition for more than 25 years. The majority of reported segmentation techniques share a critical shortcomin...Segmenting Arabic handwritings had been one of the subjects of research in the field of Arabic character recognition for more than 25 years. The majority of reported segmentation techniques share a critical shortcoming, which is over-segmentation. The aim of segmentation is to produce the letters (segments) of a handwritten word. When a resulting letter (segment) is made of more than one piece (stroke) instead of one, this is called over-segmentation. Our objective is to overcome this problem by using an Artificial Neural Networks (ANN) to verify the resulting segment. We propose a set of heuristic-based rules to assemble strokes in order to report the precise segmented letters. Preprocessing phases that include normalization and feature extraction are required as a prerequisite step for the ANN system for recognition and verification. In our previous work [1], we did achieve a segmentation success rate of 86% but without recognition. In this work, our experimental results confirmed a segmentation success rate of no less than 95%.展开更多
The wide availability, low radiation dose and short acquisition time of Cone-Beam CT (CBCT) scans make them an attractive source of data for compiling databases of anatomical structures. However CBCT has higher noise ...The wide availability, low radiation dose and short acquisition time of Cone-Beam CT (CBCT) scans make them an attractive source of data for compiling databases of anatomical structures. However CBCT has higher noise and lower contrast than helical slice CT, which makes segmentation more challenging and the optimal methods are not yet known. This paper evaluates several methods of segmenting airway geometries (nares, nasal cavities and pharynx) from typical dental quality head and neck CBCT data. The nasal cavity has narrow and intricate passages and is separated from the paranasal sinuses by thin walls, making it is susceptible to either over- or under-segmentation. The upper airway was split into two: the nasal cavity and the pharyngeal region (nasopharynx to larynx). Each part was segmented using global thresholding, multi-step level-set, and region competition methods (the latter using thresholding, clustering and classification initialisation and edge attraction techniques). The segmented 3D surfaces were evaluated against a reference manual segmentation using distance-, overlap- and volume-based metrics. Global thresholding, multi-step level-set, and region competition all gave satisfactory results for the lower part of the airway (nasopharynx to larynx). Edge attraction failed completely. A semi-automatic region-growing segmentation with multi-thresholding (or classification) initialization offered the best quality segmentation. With some minimal manual editing, it resulted in an accurate upper airway model, as judged by the similarity and volumetric indices, while being the least time consuming of the semi-automatic methods, and relying the least on the operator’s expertise.展开更多
Visual attention mechanisms allow humans to extract relevant and important information from raw input percepts. Many applications in robotics and computer vision have modeled human visual attention mechanisms using a ...Visual attention mechanisms allow humans to extract relevant and important information from raw input percepts. Many applications in robotics and computer vision have modeled human visual attention mechanisms using a bottom-up data centric approach. In contrast, recent studies in cognitive science highlight advantages of a top-down approach to the attention mechanisms, especially in applications involving goal-directed search. In this paper, we propose a top-down approach for extracting salient objects/regions of space. The top-down methodology first isolates different objects in an unorganized point cloud, and compares each object for uniqueness. A measure of saliency using the properties of geodesic distance on the object’s surface is defined. Our method works on 3D point cloud data, and identifies salient objects of high curvature and unique silhouette. These being the most unique features of a scene, are robust to clutter, occlusions and view point changes. We provide the details of the proposed method and initial experimental results.展开更多
Segmentation of vegetation remote sensing images can minimize the interference of background,thus achieving efficient monitoring and analysis for vegetation information.The segmentation of vegetation poses a significa...Segmentation of vegetation remote sensing images can minimize the interference of background,thus achieving efficient monitoring and analysis for vegetation information.The segmentation of vegetation poses a significant challenge due to the inherently complex environmental conditions.Currently,there is a growing trend of using spectral sensing combined with deep learning for field vegetation segmentation to cope with complex environ-ments.However,two major constraints remain:the high cost of equipment required for field spectral data collection;the availability of field datasets is limited and data annotation is time-consuming and labor-intensive.To address these challenges,we propose a weakly supervised approach for field vegetation segmentation by using spectral reconstruction(SR)techniques as the foundation and drawing on the theory of vegetation index(Ⅵ).Specifically,to reduce the cost of data acquisition,we propose SRCNet and SRANet based on convolution and attention structure to reconstruct multispectral images of fields,respectively.Then,borrowing from theⅥprinciple,we aggregate the reconstructed data to establish the connection of spectral bands,obtaining more salient vegetation information.Finally,we employ the adaptation strategy to segment the fused feature map using a weakly supervised method,which does not require manual labeling to obtain a field vegetation segmentation result.Our segmentation method can achieve a Mean Intersection over Union(MIoU)of 0.853 on real field datasets,which outperforms the existing methods.In addition,we have open-sourced a dataset of unmanned aerial vehicle(UAV)RGB-multispectral images,comprising 2358 pairs of samples,to improve the richness of remote sensing agricultural data.The code and data are available at egment_SR,and.展开更多
Organoids possess immense potential for unraveling the intricate functions of human tissues and facilitating preclinical disease treatment.Their applications span from high-throughput drug screening to the modeling of...Organoids possess immense potential for unraveling the intricate functions of human tissues and facilitating preclinical disease treatment.Their applications span from high-throughput drug screening to the modeling of complex diseases,with some even achieving clinical translation.Changes in the overall size,shape,boundary,and other morphological features of organoids provide a noninvasive method for assessing organoid drug sensitivity.However,the precise segmentation of organoids in bright-field microscopy images is made difficult by the complexity of the organoid morphology and interference,including overlapping organoids,bubbles,dust particles,and cell fragments.This paper introduces the precision organoid segmentation technique(POST),which is a deep-learning algorithm for segmenting challenging organoids under simple bright-field imaging conditions.Unlike existing methods,POST accurately segments each organoid and eliminates various artifacts encountered during organoid culturing and imaging.Furthermore,it is sensitive to and aligns with measurements of organoid activity in drug sensitivity experiments.POST is expected to be a valuable tool for drug screening using organoids owing to its capability of automatically and rapidly eliminating interfering substances and thereby streamlining the organoid analysis and drug screening process.展开更多
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
Detailed individual tree crown segmentation is highly relevant for the detection and monitoring of Fraxinus excelsior L.trees affected by ash dieback,a major threat to common ash populations across Europe.In this stud...Detailed individual tree crown segmentation is highly relevant for the detection and monitoring of Fraxinus excelsior L.trees affected by ash dieback,a major threat to common ash populations across Europe.In this study,both fine and coarse crown segmentation methods were applied to close-range multispectral UAV imagery.The fine tree crown segmentation method utilized a novel unsupervised machine learning approach based on a blended NIR-NDVI image,whereas the coarse segmentation relied on the segment anything model(SAM).Both methods successfully delineated tree crown outlines,however,only the fine segmentation accurately captured internal canopy gaps.Despite these structural differences,mean NDVI values calculated per tree crown revealed no significant differences between the two approaches,indicating that coarse segmentation is sufficient for mean vegetation index assessments.Nevertheless,the fine segmentation revealed increased heterogeneity in NDVI values in more severely damaged trees,underscoring its value for detailed structural and health analyses.Furthermore,the fine segmentation workflow proved transferable to both individual UAV images and orthophotos from broader UAV surveys.For applications focused on structural integrity and spatial variation in canopy health,the fine segmentation approach is recommended.展开更多
Dear Editor,This letter presents techniques to simplify dataset generation for instance segmentation of raw meat products,a critical step toward automating food production lines.Accurate segmentation is essential for ...Dear Editor,This letter presents techniques to simplify dataset generation for instance segmentation of raw meat products,a critical step toward automating food production lines.Accurate segmentation is essential for addressing challenges such as occlusions,indistinct edges,and stacked configurations,which demand large,diverse datasets.To meet these demands,we propose two complementary approaches:a semi-automatic annotation interface using tools like the segment anything model(SAM)and GrabCut and a synthetic data generation pipeline leveraging 3D-scanned models.These methods reduce reliance on real meat,mitigate food waste,and improve scalability.Experimental results demonstrate that incorporating synthetic data enhances segmentation model performance and,when combined with real data,further boosts accuracy,paving the way for more efficient automation in the food industry.展开更多
AIM:To construct an intelligent segmentation scheme for precise localization of central serous chorioretinopathy(CSC)leakage points,thereby enabling ophthalmologists to deliver accurate laser treatment without navigat...AIM:To construct an intelligent segmentation scheme for precise localization of central serous chorioretinopathy(CSC)leakage points,thereby enabling ophthalmologists to deliver accurate laser treatment without navigational laser equipment.METHODS:A dataset with dual labels(point-level and pixel-level)was first established based on fundus fluorescein angiography(FFA)images of CSC and subsequently divided into training(102 images),validation(40 images),and test(40 images)datasets.An intelligent segmentation method was then developed,based on the You Only Look Once version 8 Pose Estimation(YOLOv8-Pose)model and segment anything model(SAM),to segment CSC leakage points.Next,the YOLOv8-Pose model was trained for 200 epochs,and the best-performing model was selected to form the optimal combination with SAM.Additionally,the classic five types of U-Net series models[i.e.,U-Net,recurrent residual U-Net(R2U-Net),attention U-Net(AttU-Net),recurrent residual attention U-Net(R2AttUNet),and nested U-Net(UNet^(++))]were initialized with three random seeds and trained for 200 epochs,resulting in a total of 15 baseline models for comparison.Finally,based on the metrics including Dice similarity coefficient(DICE),intersection over union(IoU),precision,recall,precisionrecall(PR)curve,and receiver operating characteristic(ROC)curve,the proposed method was compared with baseline models through quantitative and qualitative experiments for leakage point segmentation,thereby demonstrating its effectiveness.RESULTS:With the increase of training epochs,the mAP50-95,Recall,and precision of the YOLOv8-Pose model showed a significant increase and tended to stabilize,and it achieved a preliminary localization success rate of 90%(i.e.,36 images)for CSC leakage points in 40 test images.Using manually expert-annotated pixel-level labels as the ground truth,the proposed method achieved outcomes with a DICE of 57.13%,an IoU of 45.31%,a precision of 45.91%,a recall of 93.57%,an area under the PR curve(AUC-PR)of 0.78 and an area under the ROC curve(AUC-ROC)of 0.97,which enables more accurate segmentation of CSC leakage points.CONCLUSION:By combining the precise localization capability of the YOLOv8-Pose model with the robust and flexible segmentation ability of SAM,the proposed method not only demonstrates the effectiveness of the YOLOv8-Pose model in detecting keypoint coordinates of CSC leakage points from the perspective of application innovation but also establishes a novel approach for accurate segmentation of CSC leakage points through the“detect-then-segment”strategy,thereby providing a potential auxiliary means for the automatic and precise realtime localization of leakage points during traditional laser photocoagulation for CSC.展开更多
Over the years,Generative Adversarial Networks(GANs)have revolutionized the medical imaging industry for applications such as image synthesis,denoising,super resolution,data augmentation,and cross-modality translation...Over the years,Generative Adversarial Networks(GANs)have revolutionized the medical imaging industry for applications such as image synthesis,denoising,super resolution,data augmentation,and cross-modality translation.The objective of this review is to evaluate the advances,relevances,and limitations of GANs in medical imaging.An organised literature review was conducted following the guidelines of PRISMA(Preferred Reporting Items for Systematic Reviews and Meta-Analyses).The literature considered included peer-reviewed papers published between 2020 and 2025 across databases including PubMed,IEEE Xplore,and Scopus.The studies related to applications of GAN architectures in medical imaging with reported experimental outcomes and published in English in reputable journals and conferences were considered for the review.Thesis,white papers,communication letters,and non-English articles were not included for the same.CLAIM based quality assessment criteria were applied to the included studies to assess the quality.The study classifies diverse GAN architectures,summarizing their clinical applications,technical performances,and their implementation hardships.Key findings reveal the increasing applications of GANs for enhancing diagnostic accuracy,reducing data scarcity through synthetic data generation,and supporting modality translation.However,concerns such as limited generalizability,lack of clinical validation,and regulatory constraints persist.This review provides a comprehensive study of the prevailing scenario of GANs in medical imaging and highlights crucial research gaps and future directions.Though GANs hold transformative capability for medical imaging,their integration into clinical use demands further validation,interpretability,and regulatory alignment.展开更多
Medical image segmentation is of critical importance in the domain of contemporary medical imaging.However,U-Net and its variants exhibit limitations in capturing complex nonlinear patterns and global contextual infor...Medical image segmentation is of critical importance in the domain of contemporary medical imaging.However,U-Net and its variants exhibit limitations in capturing complex nonlinear patterns and global contextual information.Although the subsequent U-KAN model enhances nonlinear representation capabilities,it still faces challenges such as gradient vanishing during deep network training and spatial detail loss during feature downsampling,resulting in insufficient segmentation accuracy for edge structures and minute lesions.To address these challenges,this paper proposes the RE-UKAN model,which innovatively improves upon U-KAN.Firstly,a residual network is introduced into the encoder to effectively mitigate gradient vanishing through cross-layer identity mappings,thus enhancing modelling capabilities for complex pathological structures.Secondly,Efficient Local Attention(ELA)is integrated to suppress spatial detail loss during downsampling,thereby improving the perception of edge structures and minute lesions.Experimental results on four public datasets demonstrate that RE-UKAN outperforms existing medical image segmentation methods across multiple evaluation metrics,with particularly outstanding performance on the TN-SCUI 2020 dataset,achieving IoU of 88.18%and Dice of 93.57%.Compared to the baseline model,it achieves improvements of 3.05%and 1.72%,respectively.These results fully demonstrate RE-UKAN’s superior detail retention capability and boundary recognition accuracy in complex medical image segmentation tasks,providing a reliable solution for clinical precision segmentation.展开更多
Background:Laparoscopic anatomic hepatectomy of segment 7(LAH-S7)is a challenging surgery.In this study we aimed to investigate surgical and oncological outcomes of various approaches of LAH-S7 in patients with hepato...Background:Laparoscopic anatomic hepatectomy of segment 7(LAH-S7)is a challenging surgery.In this study we aimed to investigate surgical and oncological outcomes of various approaches of LAH-S7 in patients with hepatocellular carcinoma(HCC).A particular focus was placed on identifying the Glissonean pedicle of segment 7(G7)and the intersegmental plane.Given the scarcity of comprehensive reviews or comparative studies on clinical outcomes,we also sought to analyze the experiences and advantages associated with different approaches in relation to the anatomic variations of G7.Methods:The clinical data of 124 patients who underwent LAH-S7 for HCC across seven tertiary referral medical centers in China were retrospectively analyzed.Three surgical approaches were categorized based on the procedures used for G7 identification:the indocyanine green(ICG)fluorescence positive staining approach(IFPA),the Glissonean approach(GA),and the hepatic vein-guided approach(HVGA).Subsequently,the postoperative short-term results and oncological outcomes of the three different approaches were compared.Results:The distribution of surgical approaches among the patients was as follows:IFPA in 16(12.9%),GA in 62(50.0%),and HVGA in 46(37.1%)patients.Complications were observed in 27(21.8%)patients.The 1-,3-,and 5-year overall survival(OS)rates were 99.1%,89.2%,and 84.7%,respectively.The 1-,3-,and 5-year recurrence-free survival(RFS)rates were 99.0%,84.7%,and 69.3%,respectively.The OS and RFS rates were comparable across the three approaches.Conclusions:Following a standardized surgical procedure,LAH-S7 is demonstrated to be safe and yields favorable oncological outcomes.Surgeons performing LAH-S7 should select the appropriate surgical approach based on the anatomical characteristics and variations of G7.展开更多
Strontianite-rich carbonatite,containing over 30 vol%carbonate minerals predominantly composed of strontianite(SrCO3),is identified in the Zhengjialiangzi ore segment of the Muluozhai rare earth element(REE)deposit,we...Strontianite-rich carbonatite,containing over 30 vol%carbonate minerals predominantly composed of strontianite(SrCO3),is identified in the Zhengjialiangzi ore segment of the Muluozhai rare earth element(REE)deposit,western Sichuan Province,China.It exhibits a unique mineral assemblage dominated by strontianite,fluorite,bastnäsite,barite,calcite and dolomite,distinguishing it from conventional calcio-,magnesio-,ferro-,or natro-carbonatites.The rock shows extreme enrichment in REEs(ΣREE=47335-64367 ppm),with strong LREE/HREE fractionation[(La/Yb)N=1151-2119]and notably high concentrations of high-value critical REEs(e.g.,Pr,Nd,Tb,Dy),5-10 times greater than those in local calcite-dominated carbonatites.Trace element patterns indicate significant enrichment in REEs,Sr,and Ba,along with depletion in high-field-strength elements(HFSEs;e.g.,Nb,Ta,Zr,Hf).In-situ Sr isotopes of strontianite[(^(87)Sr/^(86)Sr)i=0.706190-0.707305]indicate an enriched mantle source(EMI-EMII).Sr enrichment is attributed to initial mantle source enrichment and extensive fractional crystallization,possibly accompanied by minor wall-rock assimilation.We propose that the strontianite-rich carbonatite formed from a highly evolved,Sr-and REEs-rich carbonatitic magma that intruded into shallow structural breccias,followed by rapid cooling.Its formation is associated with a continuous melt-fluid evolutionary process that is characteristic of carbonatitic systems.展开更多
Weakly Supervised Semantic Segmentation(WSSS),which relies only on image-level labels,has attracted significant attention for its cost-effectiveness and scalability.Existing methods mainly enhance inter-class distinct...Weakly Supervised Semantic Segmentation(WSSS),which relies only on image-level labels,has attracted significant attention for its cost-effectiveness and scalability.Existing methods mainly enhance inter-class distinctions and employ data augmentation to mitigate semantic ambiguity and reduce spurious activations.However,they often neglect the complex contextual dependencies among image patches,resulting in incomplete local representations and limited segmentation accuracy.To address these issues,we propose the Context Patch Fusion with Class Token Enhancement(CPF-CTE)framework,which exploits contextual relations among patches to enrich feature repre-sentations and improve segmentation.At its core,the Contextual-Fusion Bidirectional Long Short-Term Memory(CF-BiLSTM)module captures spatial dependencies between patches and enables bidirectional information flow,yield-ing a more comprehensive understanding of spatial correlations.This strengthens feature learning and segmentation robustness.Moreover,we introduce learnable class tokens that dynamically encode and refine class-specific semantics,enhancing discriminative capability.By effectively integrating spatial and semantic cues,CPF-CTE produces richer and more accurate representations of image content.Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 validate that CPF-CTE consistently surpasses prior WSSS methods.展开更多
Quantitative analysis of aluminum-silicon(Al-Si)alloy microstructure is crucial for evaluating and controlling alloy performance.Conventional analysis methods rely on manual segmentation,which is inefficient and subje...Quantitative analysis of aluminum-silicon(Al-Si)alloy microstructure is crucial for evaluating and controlling alloy performance.Conventional analysis methods rely on manual segmentation,which is inefficient and subjective,while fully supervised deep learning approaches require extensive and expensive pixel-level annotated data.Furthermore,existing semi-supervised methods still face challenges in handling the adhesion of adjacent primary silicon particles and effectively utilizing consistency in unlabeled data.To address these issues,this paper proposes a novel semi-supervised framework for Al-Si alloy microstructure image segmentation.First,we introduce a Rotational Uncertainty Correction Strategy(RUCS).This strategy employs multi-angle rotational perturbations andMonte Carlo sampling to assess prediction consistency,generating a pixel-wise confidence weight map.By integrating this map into the loss function,the model dynamically focuses on high-confidence regions,thereby improving generalization ability while reducing manual annotation pressure.Second,we design a Boundary EnhancementModule(BEM)to strengthen boundary feature extraction through erosion difference and multi-scale dilated convolutions.This module guides the model to focus on the boundary regions of adjacent particles,effectively resolving particle adhesion and improving segmentation accuracy.Systematic experiments were conducted on the Aluminum-Silicon Alloy Microstructure Dataset(ASAD).Results indicate that the proposed method performs exceptionally well with scarce labeled data.Specifically,using only 5%labeled data,our method improves the Jaccard index and Adjusted Rand Index(ARI)by 2.84 and 1.57 percentage points,respectively,and reduces the Variation of Information(VI)by 8.65 compared to stateof-the-art semi-supervised models,approaching the performance levels of 10%labeled data.These results demonstrate that the proposed method significantly enhances the accuracy and robustness of quantitative microstructure analysis while reducing annotation costs.展开更多
Autonomous vehicles rely heavily on accurate and efficient scene segmentation for safe navigation and efficient operations.Traditional Bird’s Eye View(BEV)methods on semantic scene segmentation,which leverage multimo...Autonomous vehicles rely heavily on accurate and efficient scene segmentation for safe navigation and efficient operations.Traditional Bird’s Eye View(BEV)methods on semantic scene segmentation,which leverage multimodal sensor fusion,often struggle with noisy data and demand high-performance GPUs,leading to sensor misalignment and performance degradation.This paper introduces an Enhanced Channel Attention BEV(ECABEV),a novel approach designed to address the challenges under insufficient GPU memory conditions.ECABEV integrates camera and radar data through a de-noise enhanced channel attention mechanism,which utilizes global average and max pooling to effectively filter out noise while preserving discriminative features.Furthermore,an improved fusion approach is proposed to efficiently merge categorical data across modalities.To reduce computational overhead,a bilinear interpolation layer normalizationmethod is devised to ensure spatial feature fidelity.Moreover,a scalable crossentropy loss function is further designed to handle the imbalanced classes with less computational efficiency sacrifice.Extensive experiments on the nuScenes dataset demonstrate that ECABEV achieves state-of-the-art performance with an IoU of 39.961,using a lightweight ViT-B/14 backbone and lower resolution(224×224).Our approach highlights its cost-effectiveness and practical applicability,even on low-end devices.The code is publicly available at:https://github.com/YYF-CQU/ECABEV.git.展开更多
基金supported through the Natural Sciences and Engineering Research Council of Canada(NSERC)Discovery Grants 341275,CRDPJ 543894-19NSERC/Energi Simulation Industrial Research Chair program.
文摘Fractures are critical to subsurface activities such as oil and gas extraction,geothermal energy production,and carbon storage.Hydraulic fracturing,a technique that enhances fluid production,creates complex fracture networks within rock formations containing natural discontinuities.Accurately distinguishing between hydraulically induced fractures and pre-existing discontinuities is essential for understanding hydraulic fracture mechanisms.However,this remains challenging due to the interconnected nature of fractures in three-dimensional(3D)space.Manual segmentation,while adaptive,is both labor-intensive and subjective,making it impractical for large-scale 3D datasets.This study introduces a deep learning-based progressive cross-sectional segmentation method to automate the classification of 3D fracture volumes.The proposed method was applied to a 3D hydraulic fracture network in a Montney cube sample,successfully segmenting natural fractures,parted bedding planes,and hydraulic fractures with minimal user intervention.The automated approach achieves a 99.6%reduction in manual image processing workload while maintaining high segmentation accuracy,with test accuracy exceeding 98%and F1-score over 84%.This approach generalizes well to Brazilian disc samples with different fracture patterns,achieving consistently high accuracy in distinguishing between bedding and non-bedding fractures.This automated fracture segmentation method offers an effective tool for enhanced quantitative characterization of fracture networks,which would contribute to a deeper understanding of hydraulic fracturing processes.
文摘Segmenting vegetation in color images is a complex task, especially when the background and lighting conditions of the environment are uncontrolled. This paper proposes a vegetation segmentation algorithm that combines a supervised and an unsupervised learning method to segment healthy and diseased plant images from the background. During the training stage, a Self-Organizing Map (SOM) neural network is applied to create different color groups from a set of images containing vegetation, acquired from a tomato greenhouse. The color groups are labeled as vegetation and non-vegetation and then used to create two color histogram models corresponding to vegetation and non-vegetation. In the online mode, input images are segmented by a Bayesian classifier using the two histogram models. This algorithm has provided a qualitatively better segmentation rate of images containing plants’ foliage in uncontrolled environments than the segmentation rate obtained by a color index technique, resulting in the elimination of the background and the preservation of important color information. This segmentation method will be applied in disease diagnosis of tomato plants in greenhouses as future work.
文摘Acting as a pilot of the Square Kilometer Array (SKA), a Five hundred meter Aperture Spherical Telescope (FAST) project puts forward many innovative ideas, among which the design of the active main reflector shows fascinating potential. The main spherical reflector is to be composed of thousands of small spherical panels, which can be adjusted to fit a paraboloid of revolution in real time. For the construction and performance, the rms of the fit must be optimized, and so appropriate dimensional limits for the panels need to be determined. The issue of how to divide the spherical reflector mathematically is addressed in this paper. The advantages and drawbacks of various segmenting methods are discussed and an optimum one is suggested.
文摘Segmenting Arabic handwritings had been one of the subjects of research in the field of Arabic character recognition for more than 25 years. The majority of reported segmentation techniques share a critical shortcoming, which is over-segmentation. The aim of segmentation is to produce the letters (segments) of a handwritten word. When a resulting letter (segment) is made of more than one piece (stroke) instead of one, this is called over-segmentation. Our objective is to overcome this problem by using an Artificial Neural Networks (ANN) to verify the resulting segment. We propose a set of heuristic-based rules to assemble strokes in order to report the precise segmented letters. Preprocessing phases that include normalization and feature extraction are required as a prerequisite step for the ANN system for recognition and verification. In our previous work [1], we did achieve a segmentation success rate of 86% but without recognition. In this work, our experimental results confirmed a segmentation success rate of no less than 95%.
文摘The wide availability, low radiation dose and short acquisition time of Cone-Beam CT (CBCT) scans make them an attractive source of data for compiling databases of anatomical structures. However CBCT has higher noise and lower contrast than helical slice CT, which makes segmentation more challenging and the optimal methods are not yet known. This paper evaluates several methods of segmenting airway geometries (nares, nasal cavities and pharynx) from typical dental quality head and neck CBCT data. The nasal cavity has narrow and intricate passages and is separated from the paranasal sinuses by thin walls, making it is susceptible to either over- or under-segmentation. The upper airway was split into two: the nasal cavity and the pharyngeal region (nasopharynx to larynx). Each part was segmented using global thresholding, multi-step level-set, and region competition methods (the latter using thresholding, clustering and classification initialisation and edge attraction techniques). The segmented 3D surfaces were evaluated against a reference manual segmentation using distance-, overlap- and volume-based metrics. Global thresholding, multi-step level-set, and region competition all gave satisfactory results for the lower part of the airway (nasopharynx to larynx). Edge attraction failed completely. A semi-automatic region-growing segmentation with multi-thresholding (or classification) initialization offered the best quality segmentation. With some minimal manual editing, it resulted in an accurate upper airway model, as judged by the similarity and volumetric indices, while being the least time consuming of the semi-automatic methods, and relying the least on the operator’s expertise.
文摘Visual attention mechanisms allow humans to extract relevant and important information from raw input percepts. Many applications in robotics and computer vision have modeled human visual attention mechanisms using a bottom-up data centric approach. In contrast, recent studies in cognitive science highlight advantages of a top-down approach to the attention mechanisms, especially in applications involving goal-directed search. In this paper, we propose a top-down approach for extracting salient objects/regions of space. The top-down methodology first isolates different objects in an unorganized point cloud, and compares each object for uniqueness. A measure of saliency using the properties of geodesic distance on the object’s surface is defined. Our method works on 3D point cloud data, and identifies salient objects of high curvature and unique silhouette. These being the most unique features of a scene, are robust to clutter, occlusions and view point changes. We provide the details of the proposed method and initial experimental results.
基金supported by National Key R&D Program of China(2024YFD2001100,2024YFE0214300)National Natural Science Foundation of China(No.62162008)+3 种基金Guizhou Provincial Science and Technology Projects([2024]002,CXTD[2023]027)Guizhou Province Youth Science and Technology Talent Project([2024]317)Guiyang Guian Science and Technology Talent Training Project([2024]2-15)The Talent Introduction Program of Guizhou University under Grant No.(2021)89.
文摘Segmentation of vegetation remote sensing images can minimize the interference of background,thus achieving efficient monitoring and analysis for vegetation information.The segmentation of vegetation poses a significant challenge due to the inherently complex environmental conditions.Currently,there is a growing trend of using spectral sensing combined with deep learning for field vegetation segmentation to cope with complex environ-ments.However,two major constraints remain:the high cost of equipment required for field spectral data collection;the availability of field datasets is limited and data annotation is time-consuming and labor-intensive.To address these challenges,we propose a weakly supervised approach for field vegetation segmentation by using spectral reconstruction(SR)techniques as the foundation and drawing on the theory of vegetation index(Ⅵ).Specifically,to reduce the cost of data acquisition,we propose SRCNet and SRANet based on convolution and attention structure to reconstruct multispectral images of fields,respectively.Then,borrowing from theⅥprinciple,we aggregate the reconstructed data to establish the connection of spectral bands,obtaining more salient vegetation information.Finally,we employ the adaptation strategy to segment the fused feature map using a weakly supervised method,which does not require manual labeling to obtain a field vegetation segmentation result.Our segmentation method can achieve a Mean Intersection over Union(MIoU)of 0.853 on real field datasets,which outperforms the existing methods.In addition,we have open-sourced a dataset of unmanned aerial vehicle(UAV)RGB-multispectral images,comprising 2358 pairs of samples,to improve the richness of remote sensing agricultural data.The code and data are available at egment_SR,and.
基金supported by the National Key R&D Program of China(No.2022YFC2504403)the National Natural Science Foundation of China(No.62172202)+1 种基金the Experiment Project of China Manned Space Program(No.HYZHXM01019)the Fundamental Research Funds for the Central Universities from Southeast University(No.3207032101C3)。
文摘Organoids possess immense potential for unraveling the intricate functions of human tissues and facilitating preclinical disease treatment.Their applications span from high-throughput drug screening to the modeling of complex diseases,with some even achieving clinical translation.Changes in the overall size,shape,boundary,and other morphological features of organoids provide a noninvasive method for assessing organoid drug sensitivity.However,the precise segmentation of organoids in bright-field microscopy images is made difficult by the complexity of the organoid morphology and interference,including overlapping organoids,bubbles,dust particles,and cell fragments.This paper introduces the precision organoid segmentation technique(POST),which is a deep-learning algorithm for segmenting challenging organoids under simple bright-field imaging conditions.Unlike existing methods,POST accurately segments each organoid and eliminates various artifacts encountered during organoid culturing and imaging.Furthermore,it is sensitive to and aligns with measurements of organoid activity in drug sensitivity experiments.POST is expected to be a valuable tool for drug screening using organoids owing to its capability of automatically and rapidly eliminating interfering substances and thereby streamlining the organoid analysis and drug screening process.
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This study was conducted within the project FraxVir“Detection,characterisation and analyses of the occurrence of viruses and ash dieback in special stands of Fraxinus excelsior-a supplementary study to the FraxForFuture demonstration project”and receives funding via the Waldklimafonds(WKF)funded by the German Federal Ministry of Food and Agriculture(BMEL)and Federal Ministry for the Environment,Nature Conservation,Nuclear Safety and Consumer Protection(BMUV)administrated by the Agency for Renewable Resources(FNR)under grant agreement 2220WK40A4.
文摘Detailed individual tree crown segmentation is highly relevant for the detection and monitoring of Fraxinus excelsior L.trees affected by ash dieback,a major threat to common ash populations across Europe.In this study,both fine and coarse crown segmentation methods were applied to close-range multispectral UAV imagery.The fine tree crown segmentation method utilized a novel unsupervised machine learning approach based on a blended NIR-NDVI image,whereas the coarse segmentation relied on the segment anything model(SAM).Both methods successfully delineated tree crown outlines,however,only the fine segmentation accurately captured internal canopy gaps.Despite these structural differences,mean NDVI values calculated per tree crown revealed no significant differences between the two approaches,indicating that coarse segmentation is sufficient for mean vegetation index assessments.Nevertheless,the fine segmentation revealed increased heterogeneity in NDVI values in more severely damaged trees,underscoring its value for detailed structural and health analyses.Furthermore,the fine segmentation workflow proved transferable to both individual UAV images and orthophotos from broader UAV surveys.For applications focused on structural integrity and spatial variation in canopy health,the fine segmentation approach is recommended.
基金supported by European Union’s Horizon Europe research and innovation programme,project AGILEHAND(Smart Grading,Handling and Packaging Solutions for Soft and Deformable Products in Agile and Reconfigurable Lines)(101092043).
文摘Dear Editor,This letter presents techniques to simplify dataset generation for instance segmentation of raw meat products,a critical step toward automating food production lines.Accurate segmentation is essential for addressing challenges such as occlusions,indistinct edges,and stacked configurations,which demand large,diverse datasets.To meet these demands,we propose two complementary approaches:a semi-automatic annotation interface using tools like the segment anything model(SAM)and GrabCut and a synthetic data generation pipeline leveraging 3D-scanned models.These methods reduce reliance on real meat,mitigate food waste,and improve scalability.Experimental results demonstrate that incorporating synthetic data enhances segmentation model performance and,when combined with real data,further boosts accuracy,paving the way for more efficient automation in the food industry.
基金Supported by the Shenzhen Science and Technology Program(No.JCYJ20240813152704006)the National Natural Science Foundation of China(No.62401259)+2 种基金the Fundamental Research Funds for the Central Universities(No.NZ2024036)the Postdoctoral Fellowship Program of CPSF(No.GZC20242228)High Performance Computing Platform of Nanjing University of Aeronautics and Astronautics。
文摘AIM:To construct an intelligent segmentation scheme for precise localization of central serous chorioretinopathy(CSC)leakage points,thereby enabling ophthalmologists to deliver accurate laser treatment without navigational laser equipment.METHODS:A dataset with dual labels(point-level and pixel-level)was first established based on fundus fluorescein angiography(FFA)images of CSC and subsequently divided into training(102 images),validation(40 images),and test(40 images)datasets.An intelligent segmentation method was then developed,based on the You Only Look Once version 8 Pose Estimation(YOLOv8-Pose)model and segment anything model(SAM),to segment CSC leakage points.Next,the YOLOv8-Pose model was trained for 200 epochs,and the best-performing model was selected to form the optimal combination with SAM.Additionally,the classic five types of U-Net series models[i.e.,U-Net,recurrent residual U-Net(R2U-Net),attention U-Net(AttU-Net),recurrent residual attention U-Net(R2AttUNet),and nested U-Net(UNet^(++))]were initialized with three random seeds and trained for 200 epochs,resulting in a total of 15 baseline models for comparison.Finally,based on the metrics including Dice similarity coefficient(DICE),intersection over union(IoU),precision,recall,precisionrecall(PR)curve,and receiver operating characteristic(ROC)curve,the proposed method was compared with baseline models through quantitative and qualitative experiments for leakage point segmentation,thereby demonstrating its effectiveness.RESULTS:With the increase of training epochs,the mAP50-95,Recall,and precision of the YOLOv8-Pose model showed a significant increase and tended to stabilize,and it achieved a preliminary localization success rate of 90%(i.e.,36 images)for CSC leakage points in 40 test images.Using manually expert-annotated pixel-level labels as the ground truth,the proposed method achieved outcomes with a DICE of 57.13%,an IoU of 45.31%,a precision of 45.91%,a recall of 93.57%,an area under the PR curve(AUC-PR)of 0.78 and an area under the ROC curve(AUC-ROC)of 0.97,which enables more accurate segmentation of CSC leakage points.CONCLUSION:By combining the precise localization capability of the YOLOv8-Pose model with the robust and flexible segmentation ability of SAM,the proposed method not only demonstrates the effectiveness of the YOLOv8-Pose model in detecting keypoint coordinates of CSC leakage points from the perspective of application innovation but also establishes a novel approach for accurate segmentation of CSC leakage points through the“detect-then-segment”strategy,thereby providing a potential auxiliary means for the automatic and precise realtime localization of leakage points during traditional laser photocoagulation for CSC.
基金supported by Deanship of Research and Graduate Studies at King Khalid University for funding this work through Large Research Project under grant number RGP2/540/46.
文摘Over the years,Generative Adversarial Networks(GANs)have revolutionized the medical imaging industry for applications such as image synthesis,denoising,super resolution,data augmentation,and cross-modality translation.The objective of this review is to evaluate the advances,relevances,and limitations of GANs in medical imaging.An organised literature review was conducted following the guidelines of PRISMA(Preferred Reporting Items for Systematic Reviews and Meta-Analyses).The literature considered included peer-reviewed papers published between 2020 and 2025 across databases including PubMed,IEEE Xplore,and Scopus.The studies related to applications of GAN architectures in medical imaging with reported experimental outcomes and published in English in reputable journals and conferences were considered for the review.Thesis,white papers,communication letters,and non-English articles were not included for the same.CLAIM based quality assessment criteria were applied to the included studies to assess the quality.The study classifies diverse GAN architectures,summarizing their clinical applications,technical performances,and their implementation hardships.Key findings reveal the increasing applications of GANs for enhancing diagnostic accuracy,reducing data scarcity through synthetic data generation,and supporting modality translation.However,concerns such as limited generalizability,lack of clinical validation,and regulatory constraints persist.This review provides a comprehensive study of the prevailing scenario of GANs in medical imaging and highlights crucial research gaps and future directions.Though GANs hold transformative capability for medical imaging,their integration into clinical use demands further validation,interpretability,and regulatory alignment.
文摘Medical image segmentation is of critical importance in the domain of contemporary medical imaging.However,U-Net and its variants exhibit limitations in capturing complex nonlinear patterns and global contextual information.Although the subsequent U-KAN model enhances nonlinear representation capabilities,it still faces challenges such as gradient vanishing during deep network training and spatial detail loss during feature downsampling,resulting in insufficient segmentation accuracy for edge structures and minute lesions.To address these challenges,this paper proposes the RE-UKAN model,which innovatively improves upon U-KAN.Firstly,a residual network is introduced into the encoder to effectively mitigate gradient vanishing through cross-layer identity mappings,thus enhancing modelling capabilities for complex pathological structures.Secondly,Efficient Local Attention(ELA)is integrated to suppress spatial detail loss during downsampling,thereby improving the perception of edge structures and minute lesions.Experimental results on four public datasets demonstrate that RE-UKAN outperforms existing medical image segmentation methods across multiple evaluation metrics,with particularly outstanding performance on the TN-SCUI 2020 dataset,achieving IoU of 88.18%and Dice of 93.57%.Compared to the baseline model,it achieves improvements of 3.05%and 1.72%,respectively.These results fully demonstrate RE-UKAN’s superior detail retention capability and boundary recognition accuracy in complex medical image segmentation tasks,providing a reliable solution for clinical precision segmentation.
基金supported by grants from the Scientific Research Fund of Education Department of Yunnan Province(2023J767)the National Natural Science Foundation of China(82272963 and 82472718)+6 种基金Health Research Project of Hunan Provincial Health Commission(W20242019)Hunan Provincial Health High-Level Talent Scientific Research Project(R2023096)Hunan Provincial Department of Science and Technology Health Industry Joint Fund(2024JJ9479)Guangdong Province Basic and Applied Basic Research Foundation Project-Guangdong Province Natural Science Foundation(2024A1515220154)"Leading Goose"Project of the Science and Technology Department of Zhejiang Province(2024C03049)Major Project of Health Science and Technology Program of Zhejiang Province(WKJ-ZJ-2407)the National Key Research and Development Program(2024YFB331170204).
文摘Background:Laparoscopic anatomic hepatectomy of segment 7(LAH-S7)is a challenging surgery.In this study we aimed to investigate surgical and oncological outcomes of various approaches of LAH-S7 in patients with hepatocellular carcinoma(HCC).A particular focus was placed on identifying the Glissonean pedicle of segment 7(G7)and the intersegmental plane.Given the scarcity of comprehensive reviews or comparative studies on clinical outcomes,we also sought to analyze the experiences and advantages associated with different approaches in relation to the anatomic variations of G7.Methods:The clinical data of 124 patients who underwent LAH-S7 for HCC across seven tertiary referral medical centers in China were retrospectively analyzed.Three surgical approaches were categorized based on the procedures used for G7 identification:the indocyanine green(ICG)fluorescence positive staining approach(IFPA),the Glissonean approach(GA),and the hepatic vein-guided approach(HVGA).Subsequently,the postoperative short-term results and oncological outcomes of the three different approaches were compared.Results:The distribution of surgical approaches among the patients was as follows:IFPA in 16(12.9%),GA in 62(50.0%),and HVGA in 46(37.1%)patients.Complications were observed in 27(21.8%)patients.The 1-,3-,and 5-year overall survival(OS)rates were 99.1%,89.2%,and 84.7%,respectively.The 1-,3-,and 5-year recurrence-free survival(RFS)rates were 99.0%,84.7%,and 69.3%,respectively.The OS and RFS rates were comparable across the three approaches.Conclusions:Following a standardized surgical procedure,LAH-S7 is demonstrated to be safe and yields favorable oncological outcomes.Surgeons performing LAH-S7 should select the appropriate surgical approach based on the anatomical characteristics and variations of G7.
基金the National Natural Science Foundation of China(Grant No.42203073 and 41472072)Basic Scientific Research Fund of the Institute of Geology,CAGS(Grant No.J2317)Sichuan Science and Technology Program(Grant No.2023NSFSC0272).
文摘Strontianite-rich carbonatite,containing over 30 vol%carbonate minerals predominantly composed of strontianite(SrCO3),is identified in the Zhengjialiangzi ore segment of the Muluozhai rare earth element(REE)deposit,western Sichuan Province,China.It exhibits a unique mineral assemblage dominated by strontianite,fluorite,bastnäsite,barite,calcite and dolomite,distinguishing it from conventional calcio-,magnesio-,ferro-,or natro-carbonatites.The rock shows extreme enrichment in REEs(ΣREE=47335-64367 ppm),with strong LREE/HREE fractionation[(La/Yb)N=1151-2119]and notably high concentrations of high-value critical REEs(e.g.,Pr,Nd,Tb,Dy),5-10 times greater than those in local calcite-dominated carbonatites.Trace element patterns indicate significant enrichment in REEs,Sr,and Ba,along with depletion in high-field-strength elements(HFSEs;e.g.,Nb,Ta,Zr,Hf).In-situ Sr isotopes of strontianite[(^(87)Sr/^(86)Sr)i=0.706190-0.707305]indicate an enriched mantle source(EMI-EMII).Sr enrichment is attributed to initial mantle source enrichment and extensive fractional crystallization,possibly accompanied by minor wall-rock assimilation.We propose that the strontianite-rich carbonatite formed from a highly evolved,Sr-and REEs-rich carbonatitic magma that intruded into shallow structural breccias,followed by rapid cooling.Its formation is associated with a continuous melt-fluid evolutionary process that is characteristic of carbonatitic systems.
文摘Weakly Supervised Semantic Segmentation(WSSS),which relies only on image-level labels,has attracted significant attention for its cost-effectiveness and scalability.Existing methods mainly enhance inter-class distinctions and employ data augmentation to mitigate semantic ambiguity and reduce spurious activations.However,they often neglect the complex contextual dependencies among image patches,resulting in incomplete local representations and limited segmentation accuracy.To address these issues,we propose the Context Patch Fusion with Class Token Enhancement(CPF-CTE)framework,which exploits contextual relations among patches to enrich feature repre-sentations and improve segmentation.At its core,the Contextual-Fusion Bidirectional Long Short-Term Memory(CF-BiLSTM)module captures spatial dependencies between patches and enables bidirectional information flow,yield-ing a more comprehensive understanding of spatial correlations.This strengthens feature learning and segmentation robustness.Moreover,we introduce learnable class tokens that dynamically encode and refine class-specific semantics,enhancing discriminative capability.By effectively integrating spatial and semantic cues,CPF-CTE produces richer and more accurate representations of image content.Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 validate that CPF-CTE consistently surpasses prior WSSS methods.
基金funded by the National Natural Science Foundation of China (52061020).
文摘Quantitative analysis of aluminum-silicon(Al-Si)alloy microstructure is crucial for evaluating and controlling alloy performance.Conventional analysis methods rely on manual segmentation,which is inefficient and subjective,while fully supervised deep learning approaches require extensive and expensive pixel-level annotated data.Furthermore,existing semi-supervised methods still face challenges in handling the adhesion of adjacent primary silicon particles and effectively utilizing consistency in unlabeled data.To address these issues,this paper proposes a novel semi-supervised framework for Al-Si alloy microstructure image segmentation.First,we introduce a Rotational Uncertainty Correction Strategy(RUCS).This strategy employs multi-angle rotational perturbations andMonte Carlo sampling to assess prediction consistency,generating a pixel-wise confidence weight map.By integrating this map into the loss function,the model dynamically focuses on high-confidence regions,thereby improving generalization ability while reducing manual annotation pressure.Second,we design a Boundary EnhancementModule(BEM)to strengthen boundary feature extraction through erosion difference and multi-scale dilated convolutions.This module guides the model to focus on the boundary regions of adjacent particles,effectively resolving particle adhesion and improving segmentation accuracy.Systematic experiments were conducted on the Aluminum-Silicon Alloy Microstructure Dataset(ASAD).Results indicate that the proposed method performs exceptionally well with scarce labeled data.Specifically,using only 5%labeled data,our method improves the Jaccard index and Adjusted Rand Index(ARI)by 2.84 and 1.57 percentage points,respectively,and reduces the Variation of Information(VI)by 8.65 compared to stateof-the-art semi-supervised models,approaching the performance levels of 10%labeled data.These results demonstrate that the proposed method significantly enhances the accuracy and robustness of quantitative microstructure analysis while reducing annotation costs.
基金funded by the National Natural Science Foundation of China,grant number 62262045the Fundamental Research Funds for the Central Universities,grant number 2023CDJYGRH-YB11the Open Funding of SUGON Industrial Control and Security Center,grant number CUIT-SICSC-2025-03.
文摘Autonomous vehicles rely heavily on accurate and efficient scene segmentation for safe navigation and efficient operations.Traditional Bird’s Eye View(BEV)methods on semantic scene segmentation,which leverage multimodal sensor fusion,often struggle with noisy data and demand high-performance GPUs,leading to sensor misalignment and performance degradation.This paper introduces an Enhanced Channel Attention BEV(ECABEV),a novel approach designed to address the challenges under insufficient GPU memory conditions.ECABEV integrates camera and radar data through a de-noise enhanced channel attention mechanism,which utilizes global average and max pooling to effectively filter out noise while preserving discriminative features.Furthermore,an improved fusion approach is proposed to efficiently merge categorical data across modalities.To reduce computational overhead,a bilinear interpolation layer normalizationmethod is devised to ensure spatial feature fidelity.Moreover,a scalable crossentropy loss function is further designed to handle the imbalanced classes with less computational efficiency sacrifice.Extensive experiments on the nuScenes dataset demonstrate that ECABEV achieves state-of-the-art performance with an IoU of 39.961,using a lightweight ViT-B/14 backbone and lower resolution(224×224).Our approach highlights its cost-effectiveness and practical applicability,even on low-end devices.The code is publicly available at:https://github.com/YYF-CQU/ECABEV.git.
