Defect detection in printed circuit boards(PCB)remains challenging due to the difficulty of identifying small-scale defects,the inefficiency of conventional approaches,and the interference from complex backgrounds.To ...Defect detection in printed circuit boards(PCB)remains challenging due to the difficulty of identifying small-scale defects,the inefficiency of conventional approaches,and the interference from complex backgrounds.To address these issues,this paper proposes SIM-Net,an enhanced detection framework derived from YOLOv11.The model integrates SPDConv to preserve fine-grained features for small object detection,introduces a novel convolutional partial attention module(C2PAM)to suppress redundant background information and highlight salient regions,and employs a multi-scale fusion network(MFN)with a multi-grain contextual module(MGCT)to strengthen contextual representation and accelerate inference.Experimental evaluations demonstrate that SIM-Net achieves 92.4%mAP,92%accuracy,and 89.4%recall with an inference speed of 75.1 FPS,outperforming existing state-of-the-art methods.These results confirm the robustness and real-time applicability of SIM-Net for PCB defect inspection.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
This paper aims to develop a nonrigid registration method of preoperative and intraoperative thoracoabdominal CT images in computer-assisted interventional surgeries for accurate tumor localization and tissue visualiz...This paper aims to develop a nonrigid registration method of preoperative and intraoperative thoracoabdominal CT images in computer-assisted interventional surgeries for accurate tumor localization and tissue visualization enhancement.However,fine structure registration of complex thoracoabdominal organs and large deformation registration caused by respiratory motion is challenging.To deal with this problem,we propose a 3D multi-scale attention VoxelMorph(MAVoxelMorph)registration network.To alleviate the large deformation problem,a multi-scale axial attention mechanism is utilized by using a residual dilated pyramid pooling for multi-scale feature extraction,and position-aware axial attention for long-distance dependencies between pixels capture.To further improve the large deformation and fine structure registration results,a multi-scale context channel attention mechanism is employed utilizing content information via adjacent encoding layers.Our method was evaluated on four public lung datasets(DIR-Lab dataset,Creatis dataset,Learn2Reg dataset,OASIS dataset)and a local dataset.Results proved that the proposed method achieved better registration performance than current state-of-the-art methods,especially in handling the registration of large deformations and fine structures.It also proved to be fast in 3D image registration,using about 1.5 s,and faster than most methods.Qualitative and quantitative assessments proved that the proposed MA-VoxelMorph has the potential to realize precise and fast tumor localization in clinical interventional surgeries.展开更多
We propose a hierarchical multi-scale attention mechanism-based model in response to the low accuracy and inefficient manual classification of existing oceanic biological image classification methods. Firstly, the hie...We propose a hierarchical multi-scale attention mechanism-based model in response to the low accuracy and inefficient manual classification of existing oceanic biological image classification methods. Firstly, the hierarchical efficient multi-scale attention(H-EMA) module is designed for lightweight feature extraction, achieving outstanding performance at a relatively low cost. Secondly, an improved EfficientNetV2 block is used to integrate information from different scales better and enhance inter-layer message passing. Furthermore, introducing the convolutional block attention module(CBAM) enhances the model's perception of critical features, optimizing its generalization ability. Lastly, Focal Loss is introduced to adjust the weights of complex samples to address the issue of imbalanced categories in the dataset, further improving the model's performance. The model achieved 96.11% accuracy on the intertidal marine organism dataset of Nanji Islands and 84.78% accuracy on the CIFAR-100 dataset, demonstrating its strong generalization ability to meet the demands of oceanic biological image classification.展开更多
Whole brain functional connectivity(FC)patterns obtained from resting-state functional magnetic resonance imaging(rs-fMRI)have been widely used in the diagnosis of brain disorders such as autism spectrum disorder(ASD)...Whole brain functional connectivity(FC)patterns obtained from resting-state functional magnetic resonance imaging(rs-fMRI)have been widely used in the diagnosis of brain disorders such as autism spectrum disorder(ASD).Recently,an increasing number of studies have focused on employing deep learning techniques to analyze FC patterns for brain disease classification.However,the high dimensionality of the FC features and the interpretation of deep learning results are issues that need to be addressed in the FC-based brain disease classification.In this paper,we proposed a multi-scale attention-based deep neural network(MSA-DNN)model to classify FC patterns for the ASD diagnosis.The model was implemented by adding a flexible multi-scale attention(MSA)module to the auto-encoder based backbone DNN,which can extract multi-scale features of the FC patterns and change the level of attention for different FCs by continuous learning.Our model will reinforce the weights of important FC features while suppress the unimportant FCs to ensure the sparsity of the model weights and enhance the model interpretability.We performed systematic experiments on the large multi-sites ASD dataset with both ten-fold and leaveone-site-out cross-validations.Results showed that our model outperformed classical methods in brain disease classification and revealed robust intersite prediction performance.We also localized important FC features and brain regions associated with ASD classification.Overall,our study further promotes the biomarker detection and computer-aided classification for ASD diagnosis,and the proposed MSA module is flexible and easy to implement in other classification networks.展开更多
The goal of street-to-aerial cross-view image geo-localization is to determine the location of the query street-view image by retrieving the aerial-view image from the same place.The drastic viewpoint and appearance g...The goal of street-to-aerial cross-view image geo-localization is to determine the location of the query street-view image by retrieving the aerial-view image from the same place.The drastic viewpoint and appearance gap between the aerial-view and the street-view images brings a huge challenge against this task.In this paper,we propose a novel multiscale attention encoder to capture the multiscale contextual information of the aerial/street-view images.To bridge the domain gap between these two view images,we first use an inverse polar transform to make the street-view images approximately aligned with the aerial-view images.Then,the explored multiscale attention encoder is applied to convert the image into feature representation with the guidance of the learnt multiscale information.Finally,we propose a novel global mining strategy to enable the network to pay more attention to hard negative exemplars.Experiments on standard benchmark datasets show that our approach obtains 81.39%top-1 recall rate on the CVUSA dataset and 71.52%on the CVACT dataset,achieving the state-of-the-art performance and outperforming most of the existing methods significantly.展开更多
Bone age assessment(BAA)helps doctors determine how a child’s bones grow and develop in clinical medicine.Traditional BAA methods rely on clinician expertise,leading to time-consuming predictions and inaccurate resul...Bone age assessment(BAA)helps doctors determine how a child’s bones grow and develop in clinical medicine.Traditional BAA methods rely on clinician expertise,leading to time-consuming predictions and inaccurate results.Most deep learning-based BAA methods feed the extracted critical points of images into the network by providing additional annotations.This operation is costly and subjective.To address these problems,we propose a multi-scale attentional densely connected network(MSADCN)in this paper.MSADCN constructs a multi-scale dense connectivity mechanism,which can avoid overfitting,obtain the local features effectively and prevent gradient vanishing even in limited training data.First,MSADCN designs multi-scale structures in the densely connected network to extract fine-grained features at different scales.Then,coordinate attention is embedded to focus on critical features and automatically locate the regions of interest(ROI)without additional annotation.In addition,to improve the model’s generalization,transfer learning is applied to train the proposed MSADCN on the public dataset IMDB-WIKI,and the obtained pre-trained weights are loaded onto the Radiological Society of North America(RSNA)dataset.Finally,label distribution learning(LDL)and expectation regression techniques are introduced into our model to exploit the correlation between hand bone images of different ages,which can obtain stable age estimates.Extensive experiments confirm that our model can converge more efficiently and obtain a mean absolute error(MAE)of 4.64 months,outperforming some state-of-the-art BAA methods.展开更多
Accurate valve nozzle detection is an important component of industrial visual inspection systems;however,structural complexity,scale variation,illumination fluctuation,and partial occlusion remain challenging factors...Accurate valve nozzle detection is an important component of industrial visual inspection systems;however,structural complexity,scale variation,illumination fluctuation,and partial occlusion remain challenging factors that affect detection stability.This study presents YOLOv12-Enhanced,a refined singlestage detection framework developed for industrial valve nozzle scenarios.The proposed approach incorporates three architectural modifications:a RepViT backbone to enhance hierarchical feature representation through structural re-parameterization and global–local modeling,a Spatial Pyramid Pooling Fast(SPPF)module combined with C2PSA attention to strengthen multi-scale contextual feature extraction,and a Global Edge Information Fusion(GEIF)module to integrate shallow edge information with deep semantic features for improved boundary alignment.Experimental evaluation on the Pascal Visual Object Classes(VOC)dataset shows that the proposed model achieves 71.0%mAP50 and 54.4%mAP50–95 under identical training conditions,exceeding the baseline YOLOv12n.Ablation experiments further demonstrate that each module contributes incremental performance gains.Evaluation on a self-constructed valve nozzle dataset consisting of 500 real industrial images indicates stable detection behavior under varying illumination and partial occlusion conditions.The experimental findings suggest that the proposed structural refinements provide a balanced enhancement in feature representation and localization precision while maintaining comparable computational complexity.展开更多
Tomato is a major economic crop worldwide,and diseases on tomato leaves can significantly reduce both yield and quality.Traditional manual inspection is inefficient and highly subjective,making it difficult to meet th...Tomato is a major economic crop worldwide,and diseases on tomato leaves can significantly reduce both yield and quality.Traditional manual inspection is inefficient and highly subjective,making it difficult to meet the requirements of early disease identification in complex natural environments.To address this issue,this study proposes an improved YOLO11-based model,YOLO-SPDNet(Scale Sequence Fusion,Position-Channel Attention,and Dual Enhancement Network).The model integrates the SEAM(Self-Ensembling Attention Mechanism)semantic enhancement module,the MLCA(Mixed Local Channel Attention)lightweight attention mechanism,and the SPA(Scale-Position-Detail Awareness)module composed of SSFF(Scale Sequence Feature Fusion),TFE(Triple Feature Encoding),and CPAM(Channel and Position Attention Mechanism).These enhancements strengthen fine-grained lesion detection while maintaining model lightweightness.Experimental results show that YOLO-SPDNet achieves an accuracy of 91.8%,a recall of 86.5%,and an mAP@0.5 of 90.6%on the test set,with a computational complexity of 12.5 GFLOPs.Furthermore,the model reaches a real-time inference speed of 987 FPS,making it suitable for deployment on mobile agricultural terminals and online monitoring systems.Comparative analysis and ablation studies further validate the reliability and practical applicability of the proposed model in complex natural scenes.展开更多
Images taken in dim environments frequently exhibit issues like insufficient brightness,noise,color shifts,and loss of detail.These problems pose significant challenges to dark image enhancement tasks.Current approach...Images taken in dim environments frequently exhibit issues like insufficient brightness,noise,color shifts,and loss of detail.These problems pose significant challenges to dark image enhancement tasks.Current approaches,while effective in global illumination modeling,often struggle to simultaneously suppress noise and preserve structural details,especially under heterogeneous lighting.Furthermore,misalignment between luminance and color channels introduces additional challenges to accurate enhancement.In response to the aforementioned difficulties,we introduce a single-stage framework,M2ATNet,using the multi-scale multi-attention and Transformer architecture.First,to address the problems of texture blurring and residual noise,we design a multi-scale multi-attention denoising module(MMAD),which is applied separately to the luminance and color channels to enhance the structural and texture modeling capabilities.Secondly,to solve the non-alignment problem of the luminance and color channels,we introduce the multi-channel feature fusion Transformer(CFFT)module,which effectively recovers the dark details and corrects the color shifts through cross-channel alignment and deep feature interaction.To guide the model to learn more stably and efficiently,we also fuse multiple types of loss functions to form a hybrid loss term.We extensively evaluate the proposed method on various standard datasets,including LOL-v1,LOL-v2,DICM,LIME,and NPE.Evaluation in terms of numerical metrics and visual quality demonstrate that M2ATNet consistently outperforms existing advanced approaches.Ablation studies further confirm the critical roles played by the MMAD and CFFT modules to detail preservation and visual fidelity under challenging illumination-deficient environments.展开更多
Fine-grained visual classification(FGVC)is a very challenging task due to distinguishing subcategories under the same super-category.Recent works mainly localize discriminative image regions and capture subtle inter-c...Fine-grained visual classification(FGVC)is a very challenging task due to distinguishing subcategories under the same super-category.Recent works mainly localize discriminative image regions and capture subtle inter-class differences by utilizing attention-based methods.However,at the same layer,most attention-based works only consider large-scale attention blocks with the same size as feature maps,and they ignore small-scale attention blocks that are smaller than feature maps.To distinguish subcategories,it is important to exploit small local regions.In this work,a novel multi-scale attention network(MSANet)is proposed to capture large and small regions at the same layer in fine-grained visual classification.Specifically,a novel multi-scale attention layer(MSAL)is proposed,which generates multiple groups in each feature maps to capture different-scale discriminative regions.The groups based on large-scale regions can exploit global features and the groups based on the small-scale regions can extract local subtle features.Then,a simple feature fusion strategy is utilized to fully integrate global features and local subtle features to mine information that are more conducive to FGVC.Comprehensive experiments in Caltech-UCSD Birds-200-2011(CUB),FGVC-Aircraft(AIR)and Stanford Cars(Cars)datasets show that our method achieves the competitive performances,which demonstrate its effectiveness.展开更多
The detection of dust devils on Mars poses significant challenges,primarily due to the substantial variability in target scales,the susceptibility of small-scale features to loss or distortion during feature extractio...The detection of dust devils on Mars poses significant challenges,primarily due to the substantial variability in target scales,the susceptibility of small-scale features to loss or distortion during feature extraction and fusion,and the interference from complex Martian backgrounds.To tackle these issues,we propose the Dynamic Triplet Fusion Attentive Net(DTFA-Net),a framework tailored for Martian dust devil detection.Within DTFA-Net,we design a Multi-Dimensional Dynamic Feature Pyramid Network(MDFPN),which is based on the Bi-directional Feature Pyramid Network(BiFPN)and enhances multi-level feature fusion by incorporating shallow-layer features and employing a cross-scale connection strategy.Additionally,we propose three innovative lightweight and plug-and-play modules:the Local-Channel Cross-Stage Module(LCCS)to boost feature diversity,the Progressive Feature Enhancement Module(PFE)to increase the focus on critical features,and the Triplet-Aware Cross-Stage Module(TACS)for capturing interactions across spatial and channel dimensions.Furthermore,the framework incorporates the Dynamic Head(DyHead),which uses multi-dimensional attention mechanisms to dynamically adjust to various scales,spatial positions,and detection challenges.Experimental results show that DTFA-Net achieved a detection Precision of 94.3%,a Recall of 92.8%,and mAP50 of 96.6%on the Amazonis Planitia dust devil dataset.Its overall performance significantly surpasses that of existing mainstream methods,while also demonstrating strong generalization capability on cross-regional datasets.Beyond detection,this framework was further applied to analyze the seasonal activity and spatial distribution patterns of Martian dust devils in Amazonis Planitia,and the prevailing winds of each season were examined to explore the mechanisms underlying the formation of activity hotspots.In addition,the model was extended to the ten core candidate landing sites of the Tianwen-3 mission to systematically assess dust devil distribution across these regions.Based on the detection results and previous studies,we suggest that four sites—Kasei Valles,Oxia Planum,McLaughlin Crater,and Mawrth Vallis—offer a more balanced trade-off among scientific value,dust-cleaning,and engineering safety,making them relatively ideal landing sites for the Tianwen-3 mission.Overall,this study provides important insights into the spatiotemporal distribution,activity patterns,and potential environmental risks of Martian dust devils,thereby offering valuable references for Mars exploration missions.Furthermore,it provides guidance for the optimized design and safe operation of spacecraft,and contributes scientific support for the planning and implementation of future Mars exploration endeavors.展开更多
Distributed secondary control has been proposed to maintain frequency/voltage synchronization and power sharing for distributed energy sources in AC microgrids(MGs).The cyber layer is susceptible to time delays and cy...Distributed secondary control has been proposed to maintain frequency/voltage synchronization and power sharing for distributed energy sources in AC microgrids(MGs).The cyber layer is susceptible to time delays and cyber failures and thus,a distributed resilient secondary control should be investigated.This paper proposes a distributed multi-scale attention and predictor-based control(DMAPC)strategy to address false data injection attacks and packet loss failures with time delays.The multi-scale attention mechanism enables the system to selectively focus on neighbors'states with higher confidence evaluated in different time scales,while the data-driven predictor compensates for lost neighbors'states in the nonlinear controller.The DMAPC does not impose strict limitations on the number of false communication links or upper bound for false data.Besides,the DMAPC is formulated as an uncertain system with time delays and is proven to be uniformly ultimately bounded.Extensive experiments on a hardware-in-the-loop MG testbed have validated the effectiveness of DMAPC,which successfully relaxes restrictions on cyber failures compared to existing strategies.展开更多
Shadows in document images are undesirable yet inevitable.They can decrease the clarity and readability of the images.The existing methods for removing shadows from documents still face some challenges,such as the tra...Shadows in document images are undesirable yet inevitable.They can decrease the clarity and readability of the images.The existing methods for removing shadows from documents still face some challenges,such as the traditional heuristics lack universality and the optimization goal of subnetworks is not consistent for multistage deep learning methods.In this paper,we introduce an end-to-end direct document shadow removal network(DDSR-Net),where we employ a 3-layer UNet++as the backbone to extract features from diverse scales.To further improve the performance of DDSR-Net,we integrate the multi-scale attention(MSA)blocks into each node.The MSA block allocates different weights to feature vectors at different positions,achieving automatic feature alignment and significantly enhancing the end-to-end network's ability to handle shadow processing.To verify the effectiveness of the proposed DDSR-Net,qualitative and quantitative experiments are conducted on multiple open-source document shadow removal datasets.The experimental results demonstrate that our method outperforms the existing state-of-the-art methods on these datasets.Our code and models will be released to the public.展开更多
Underwater target detection is extensively applied in domains such as underwater search and rescue,environmental monitoring,and marine resource surveys.It is crucial in enabling autonomous underwater robot operations ...Underwater target detection is extensively applied in domains such as underwater search and rescue,environmental monitoring,and marine resource surveys.It is crucial in enabling autonomous underwater robot operations and promoting ocean exploration.Nevertheless,low imaging quality,harsh underwater environments,and obscured objects considerably increase the difficulty of detecting underwater targets,making it difficult for current detection methods to achieve optimal performance.In order to enhance underwater object perception and improve target detection precision,we propose a lightweight underwater target detection method using You Only Look Once(YOLO)v8 with multi-scale cross-channel attention(MSCCA),named YOLOv8-UOD.In the proposed multiscale cross-channel attention module,multi-scale attention(MSA)augments the variety of attentional perception by extracting information from innately diverse sensory fields.The cross-channel strategy utilizes RepVGGbased channel shuffling(RCS)and one-shot aggregation(OSA)to rearrange feature map channels according to specific rules.It aggregates all features only once in the final feature mapping,resulting in the extraction of more comprehensive and valuable feature information.The experimental results show that the proposed YOLOv8-UOD achieves a mAP50 of 95.67%and FLOPs of 23.8 G on the Underwater Robot Picking Contest 2017(URPC2017)dataset,outperforming other methods in terms of detection precision and computational cost-efficiency.展开更多
The application of image super-resolution(SR)has brought significant assistance in the medical field,aiding doctors to make more precise diagnoses.However,solely relying on a convolutional neural network(CNN)for image...The application of image super-resolution(SR)has brought significant assistance in the medical field,aiding doctors to make more precise diagnoses.However,solely relying on a convolutional neural network(CNN)for image SR may lead to issues such as blurry details and excessive smoothness.To address the limitations,we proposed an algorithm based on the generative adversarial network(GAN)framework.In the generator network,three different sizes of convolutions connected by a residual dense structure were used to extract detailed features,and an attention mechanism combined with dual channel and spatial information was applied to concentrate the computing power on crucial areas.In the discriminator network,using InstanceNorm to normalize tensors sped up the training process while retaining feature information.The experimental results demonstrate that our algorithm achieves higher peak signal-to-noise ratio(PSNR)and structural similarity index measure(SSIM)compared to other methods,resulting in an improved visual quality.展开更多
Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address ...Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address this problem, a Multi-head Self-attention and Spatial-Temporal Graph Convolutional Network (MSSTGCN) for multiscale traffic flow prediction is proposed. Firstly, to capture the hidden traffic periodicity of traffic flow, traffic flow is divided into three kinds of periods, including hourly, daily, and weekly data. Secondly, a graph attention residual layer is constructed to learn the global spatial features across regions. Local spatial-temporal dependence is captured by using a T-GCN module. Thirdly, a transformer layer is introduced to learn the long-term dependence in time. A position embedding mechanism is introduced to label position information for all traffic sequences. Thus, this multi-head self-attention mechanism can recognize the sequence order and allocate weights for different time nodes. Experimental results on four real-world datasets show that the MSSTGCN performs better than the baseline methods and can be successfully adapted to traffic prediction tasks.展开更多
Multimodal image fusion plays an important role in image analysis and applications.Multimodal medical image fusion helps to combine contrast features from two or more input imaging modalities to represent fused inform...Multimodal image fusion plays an important role in image analysis and applications.Multimodal medical image fusion helps to combine contrast features from two or more input imaging modalities to represent fused information in a single image.One of the critical clinical applications of medical image fusion is to fuse anatomical and functional modalities for rapid diagnosis of malignant tissues.This paper proposes a multimodal medical image fusion network(MMIF-Net)based on multiscale hybrid attention.The method first decomposes the original image to obtain the low-rank and significant parts.Then,to utilize the features at different scales,we add amultiscalemechanism that uses three filters of different sizes to extract the features in the encoded network.Also,a hybrid attention module is introduced to obtain more image details.Finally,the fused images are reconstructed by decoding the network.We conducted experiments with clinical images from brain computed tomography/magnetic resonance.The experimental results show that the multimodal medical image fusion network method based on multiscale hybrid attention works better than other advanced fusion methods.展开更多
This paper proposes an automated detection framework for transmission facilities using a featureattention multi-scale robustness network(FAMSR-Net)with high-fidelity virtual images.The proposed framework exhibits thre...This paper proposes an automated detection framework for transmission facilities using a featureattention multi-scale robustness network(FAMSR-Net)with high-fidelity virtual images.The proposed framework exhibits three key characteristics.First,virtual images of the transmission facilities generated using StyleGAN2-ADA are co-trained with real images.This enables the neural network to learn various features of transmission facilities to improve the detection performance.Second,the convolutional block attention module is deployed in FAMSR-Net to effectively extract features from images and construct multi-dimensional feature maps,enabling the neural network to perform precise object detection in various environments.Third,an effective bounding box optimization method called Scylla-IoU is deployed on FAMSR-Net,considering the intersection over union,center point distance,angle,and shape of the bounding box.This enables the detection of power facilities of various sizes accurately.Extensive experiments demonstrated that FAMSRNet outperforms other neural networks in detecting power facilities.FAMSR-Net also achieved the highest detection accuracy when virtual images of the transmission facilities were co-trained in the training phase.The proposed framework is effective for the scheduled operation and maintenance of transmission facilities because an optical camera is currently the most promising tool for unmanned aerial vehicles.This ultimately contributes to improved inspection efficiency,reduced maintenance risks,and more reliable power delivery across extensive transmission facilities.展开更多
Semantic segmentation plays a foundational role in biomedical image analysis, providing precise information about cellular, tissue, and organ structures in both biological and medical imaging modalities. Traditional a...Semantic segmentation plays a foundational role in biomedical image analysis, providing precise information about cellular, tissue, and organ structures in both biological and medical imaging modalities. Traditional approaches often fail in the face of challenges such as low contrast, morphological variability, and densely packed structures. Recent advancements in deep learning have transformed segmentation capabilities through the integration of fine-scale detail preservation, coarse-scale contextual modeling, and multi-scale feature fusion. This work provides a comprehensive analysis of state-of-the-art deep learning models, including U-Net variants, attention-based frameworks, and Transformer-integrated networks, highlighting innovations that improve accuracy, generalizability, and computational efficiency. Key architectural components such as convolution operations, shallow and deep blocks, skip connections, and hybrid encoders are examined for their roles in enhancing spatial representation and semantic consistency. We further discuss the importance of hierarchical and instance-aware segmentation and annotation in interpreting complex biological scenes and multiplexed medical images. By bridging methodological developments with diverse application domains, this paper outlines current trends and future directions for semantic segmentation, emphasizing its critical role in facilitating annotation, diagnosis, and discovery in biomedical research.展开更多
文摘Defect detection in printed circuit boards(PCB)remains challenging due to the difficulty of identifying small-scale defects,the inefficiency of conventional approaches,and the interference from complex backgrounds.To address these issues,this paper proposes SIM-Net,an enhanced detection framework derived from YOLOv11.The model integrates SPDConv to preserve fine-grained features for small object detection,introduces a novel convolutional partial attention module(C2PAM)to suppress redundant background information and highlight salient regions,and employs a multi-scale fusion network(MFN)with a multi-grain contextual module(MGCT)to strengthen contextual representation and accelerate inference.Experimental evaluations demonstrate that SIM-Net achieves 92.4%mAP,92%accuracy,and 89.4%recall with an inference speed of 75.1 FPS,outperforming existing state-of-the-art methods.These results confirm the robustness and real-time applicability of SIM-Net for PCB defect inspection.
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supported in part by the National Natural Science Foundation of China[62301374]Hubei Provincial Natural Science Foundation of China[2022CFB804]+2 种基金Hubei Provincial Education Research Project[B2022057]the Youths Science Foundation of Wuhan Institute of Technology[K202240]the 15th Graduate Education Innovation Fund of Wuhan Institute of Technology[CX2023295].
文摘This paper aims to develop a nonrigid registration method of preoperative and intraoperative thoracoabdominal CT images in computer-assisted interventional surgeries for accurate tumor localization and tissue visualization enhancement.However,fine structure registration of complex thoracoabdominal organs and large deformation registration caused by respiratory motion is challenging.To deal with this problem,we propose a 3D multi-scale attention VoxelMorph(MAVoxelMorph)registration network.To alleviate the large deformation problem,a multi-scale axial attention mechanism is utilized by using a residual dilated pyramid pooling for multi-scale feature extraction,and position-aware axial attention for long-distance dependencies between pixels capture.To further improve the large deformation and fine structure registration results,a multi-scale context channel attention mechanism is employed utilizing content information via adjacent encoding layers.Our method was evaluated on four public lung datasets(DIR-Lab dataset,Creatis dataset,Learn2Reg dataset,OASIS dataset)and a local dataset.Results proved that the proposed method achieved better registration performance than current state-of-the-art methods,especially in handling the registration of large deformations and fine structures.It also proved to be fast in 3D image registration,using about 1.5 s,and faster than most methods.Qualitative and quantitative assessments proved that the proposed MA-VoxelMorph has the potential to realize precise and fast tumor localization in clinical interventional surgeries.
基金supported by the National Natural Science Foundation of China (Nos.61806107 and 61702135)。
文摘We propose a hierarchical multi-scale attention mechanism-based model in response to the low accuracy and inefficient manual classification of existing oceanic biological image classification methods. Firstly, the hierarchical efficient multi-scale attention(H-EMA) module is designed for lightweight feature extraction, achieving outstanding performance at a relatively low cost. Secondly, an improved EfficientNetV2 block is used to integrate information from different scales better and enhance inter-layer message passing. Furthermore, introducing the convolutional block attention module(CBAM) enhances the model's perception of critical features, optimizing its generalization ability. Lastly, Focal Loss is introduced to adjust the weights of complex samples to address the issue of imbalanced categories in the dataset, further improving the model's performance. The model achieved 96.11% accuracy on the intertidal marine organism dataset of Nanji Islands and 84.78% accuracy on the CIFAR-100 dataset, demonstrating its strong generalization ability to meet the demands of oceanic biological image classification.
基金This work was supported by the National Natural Science Foundation of China(No.61906006).
文摘Whole brain functional connectivity(FC)patterns obtained from resting-state functional magnetic resonance imaging(rs-fMRI)have been widely used in the diagnosis of brain disorders such as autism spectrum disorder(ASD).Recently,an increasing number of studies have focused on employing deep learning techniques to analyze FC patterns for brain disease classification.However,the high dimensionality of the FC features and the interpretation of deep learning results are issues that need to be addressed in the FC-based brain disease classification.In this paper,we proposed a multi-scale attention-based deep neural network(MSA-DNN)model to classify FC patterns for the ASD diagnosis.The model was implemented by adding a flexible multi-scale attention(MSA)module to the auto-encoder based backbone DNN,which can extract multi-scale features of the FC patterns and change the level of attention for different FCs by continuous learning.Our model will reinforce the weights of important FC features while suppress the unimportant FCs to ensure the sparsity of the model weights and enhance the model interpretability.We performed systematic experiments on the large multi-sites ASD dataset with both ten-fold and leaveone-site-out cross-validations.Results showed that our model outperformed classical methods in brain disease classification and revealed robust intersite prediction performance.We also localized important FC features and brain regions associated with ASD classification.Overall,our study further promotes the biomarker detection and computer-aided classification for ASD diagnosis,and the proposed MSA module is flexible and easy to implement in other classification networks.
基金National Natural Science Foundation of China,Grant/Award Number:62106177supported by the Central University Basic Research Fund of China(No.2042020KF0016)supported by the supercomputing system in the Supercomputing Center of Wuhan University.
文摘The goal of street-to-aerial cross-view image geo-localization is to determine the location of the query street-view image by retrieving the aerial-view image from the same place.The drastic viewpoint and appearance gap between the aerial-view and the street-view images brings a huge challenge against this task.In this paper,we propose a novel multiscale attention encoder to capture the multiscale contextual information of the aerial/street-view images.To bridge the domain gap between these two view images,we first use an inverse polar transform to make the street-view images approximately aligned with the aerial-view images.Then,the explored multiscale attention encoder is applied to convert the image into feature representation with the guidance of the learnt multiscale information.Finally,we propose a novel global mining strategy to enable the network to pay more attention to hard negative exemplars.Experiments on standard benchmark datasets show that our approach obtains 81.39%top-1 recall rate on the CVUSA dataset and 71.52%on the CVACT dataset,achieving the state-of-the-art performance and outperforming most of the existing methods significantly.
基金This research is partially supported by grant from the National Natural Science Foundation of China(No.72071019)grant from the Natural Science Foundation of Chongqing(No.cstc2021jcyj-msxmX0185)grant from the Chongqing Graduate Education and Teaching Reform Research Project(No.yjg193096).
文摘Bone age assessment(BAA)helps doctors determine how a child’s bones grow and develop in clinical medicine.Traditional BAA methods rely on clinician expertise,leading to time-consuming predictions and inaccurate results.Most deep learning-based BAA methods feed the extracted critical points of images into the network by providing additional annotations.This operation is costly and subjective.To address these problems,we propose a multi-scale attentional densely connected network(MSADCN)in this paper.MSADCN constructs a multi-scale dense connectivity mechanism,which can avoid overfitting,obtain the local features effectively and prevent gradient vanishing even in limited training data.First,MSADCN designs multi-scale structures in the densely connected network to extract fine-grained features at different scales.Then,coordinate attention is embedded to focus on critical features and automatically locate the regions of interest(ROI)without additional annotation.In addition,to improve the model’s generalization,transfer learning is applied to train the proposed MSADCN on the public dataset IMDB-WIKI,and the obtained pre-trained weights are loaded onto the Radiological Society of North America(RSNA)dataset.Finally,label distribution learning(LDL)and expectation regression techniques are introduced into our model to exploit the correlation between hand bone images of different ages,which can obtain stable age estimates.Extensive experiments confirm that our model can converge more efficiently and obtain a mean absolute error(MAE)of 4.64 months,outperforming some state-of-the-art BAA methods.
文摘Accurate valve nozzle detection is an important component of industrial visual inspection systems;however,structural complexity,scale variation,illumination fluctuation,and partial occlusion remain challenging factors that affect detection stability.This study presents YOLOv12-Enhanced,a refined singlestage detection framework developed for industrial valve nozzle scenarios.The proposed approach incorporates three architectural modifications:a RepViT backbone to enhance hierarchical feature representation through structural re-parameterization and global–local modeling,a Spatial Pyramid Pooling Fast(SPPF)module combined with C2PSA attention to strengthen multi-scale contextual feature extraction,and a Global Edge Information Fusion(GEIF)module to integrate shallow edge information with deep semantic features for improved boundary alignment.Experimental evaluation on the Pascal Visual Object Classes(VOC)dataset shows that the proposed model achieves 71.0%mAP50 and 54.4%mAP50–95 under identical training conditions,exceeding the baseline YOLOv12n.Ablation experiments further demonstrate that each module contributes incremental performance gains.Evaluation on a self-constructed valve nozzle dataset consisting of 500 real industrial images indicates stable detection behavior under varying illumination and partial occlusion conditions.The experimental findings suggest that the proposed structural refinements provide a balanced enhancement in feature representation and localization precision while maintaining comparable computational complexity.
基金Tianmin Tianyuan Boutique Vegetable Industry Technology Service Station(Grant No.2024120011003081)Development of Environmental Monitoring and Traceability System for Wuqing Agricultural Production Areas(Grant No.2024120011001866)。
文摘Tomato is a major economic crop worldwide,and diseases on tomato leaves can significantly reduce both yield and quality.Traditional manual inspection is inefficient and highly subjective,making it difficult to meet the requirements of early disease identification in complex natural environments.To address this issue,this study proposes an improved YOLO11-based model,YOLO-SPDNet(Scale Sequence Fusion,Position-Channel Attention,and Dual Enhancement Network).The model integrates the SEAM(Self-Ensembling Attention Mechanism)semantic enhancement module,the MLCA(Mixed Local Channel Attention)lightweight attention mechanism,and the SPA(Scale-Position-Detail Awareness)module composed of SSFF(Scale Sequence Feature Fusion),TFE(Triple Feature Encoding),and CPAM(Channel and Position Attention Mechanism).These enhancements strengthen fine-grained lesion detection while maintaining model lightweightness.Experimental results show that YOLO-SPDNet achieves an accuracy of 91.8%,a recall of 86.5%,and an mAP@0.5 of 90.6%on the test set,with a computational complexity of 12.5 GFLOPs.Furthermore,the model reaches a real-time inference speed of 987 FPS,making it suitable for deployment on mobile agricultural terminals and online monitoring systems.Comparative analysis and ablation studies further validate the reliability and practical applicability of the proposed model in complex natural scenes.
基金funded by the National Natural Science Foundation of China,grant numbers 52374156 and 62476005。
文摘Images taken in dim environments frequently exhibit issues like insufficient brightness,noise,color shifts,and loss of detail.These problems pose significant challenges to dark image enhancement tasks.Current approaches,while effective in global illumination modeling,often struggle to simultaneously suppress noise and preserve structural details,especially under heterogeneous lighting.Furthermore,misalignment between luminance and color channels introduces additional challenges to accurate enhancement.In response to the aforementioned difficulties,we introduce a single-stage framework,M2ATNet,using the multi-scale multi-attention and Transformer architecture.First,to address the problems of texture blurring and residual noise,we design a multi-scale multi-attention denoising module(MMAD),which is applied separately to the luminance and color channels to enhance the structural and texture modeling capabilities.Secondly,to solve the non-alignment problem of the luminance and color channels,we introduce the multi-channel feature fusion Transformer(CFFT)module,which effectively recovers the dark details and corrects the color shifts through cross-channel alignment and deep feature interaction.To guide the model to learn more stably and efficiently,we also fuse multiple types of loss functions to form a hybrid loss term.We extensively evaluate the proposed method on various standard datasets,including LOL-v1,LOL-v2,DICM,LIME,and NPE.Evaluation in terms of numerical metrics and visual quality demonstrate that M2ATNet consistently outperforms existing advanced approaches.Ablation studies further confirm the critical roles played by the MMAD and CFFT modules to detail preservation and visual fidelity under challenging illumination-deficient environments.
基金jointly supported by the National Science and Technology Major Project(2022ZD0117103)the National Natural Science Foundations of China(62272364)+2 种基金the provincial Key Research and Development Program of Shaanxi(2024GH-ZDXM-47)the Research Project on Higher Education Teaching Reform of Shaanxi Province(23JG003)the Natural Science Basic Research Program of Shaanxi(2024JC-YBQN0639).
文摘Fine-grained visual classification(FGVC)is a very challenging task due to distinguishing subcategories under the same super-category.Recent works mainly localize discriminative image regions and capture subtle inter-class differences by utilizing attention-based methods.However,at the same layer,most attention-based works only consider large-scale attention blocks with the same size as feature maps,and they ignore small-scale attention blocks that are smaller than feature maps.To distinguish subcategories,it is important to exploit small local regions.In this work,a novel multi-scale attention network(MSANet)is proposed to capture large and small regions at the same layer in fine-grained visual classification.Specifically,a novel multi-scale attention layer(MSAL)is proposed,which generates multiple groups in each feature maps to capture different-scale discriminative regions.The groups based on large-scale regions can exploit global features and the groups based on the small-scale regions can extract local subtle features.Then,a simple feature fusion strategy is utilized to fully integrate global features and local subtle features to mine information that are more conducive to FGVC.Comprehensive experiments in Caltech-UCSD Birds-200-2011(CUB),FGVC-Aircraft(AIR)and Stanford Cars(Cars)datasets show that our method achieves the competitive performances,which demonstrate its effectiveness.
基金supported by the National Natural Science Foundation of China(Grant Nos.12103020&12363009)the Science and Technology Development Fund(FDCT)of Macao(Grant Nos.0021/2024/RIA1,0158/2024/AFJ and 0034/2024/AMJ)+4 种基金the Open Project Program of State Key Laboratory of Lunar and Planetary Sciences(Macao University of Science and Technology)(Grant No.002/2024/SKL)the Key Technology Research Project of TW-3(Grant No.TW3004)the Youth Talent Project of the Science and Technology Plan of Ganzhou(Grant No.2023CYZ26970)the Graduate Innovation Special Fund Project of Jiangxi University of Science and Technology(Grant No.XY2024-S213)the Key Laboratory of Low Dimensional Quantum Materials and Sensor Devices of Jiangxi Education Institutes(Grant No.Gan Jiao Ke Zi-20241301)。
文摘The detection of dust devils on Mars poses significant challenges,primarily due to the substantial variability in target scales,the susceptibility of small-scale features to loss or distortion during feature extraction and fusion,and the interference from complex Martian backgrounds.To tackle these issues,we propose the Dynamic Triplet Fusion Attentive Net(DTFA-Net),a framework tailored for Martian dust devil detection.Within DTFA-Net,we design a Multi-Dimensional Dynamic Feature Pyramid Network(MDFPN),which is based on the Bi-directional Feature Pyramid Network(BiFPN)and enhances multi-level feature fusion by incorporating shallow-layer features and employing a cross-scale connection strategy.Additionally,we propose three innovative lightweight and plug-and-play modules:the Local-Channel Cross-Stage Module(LCCS)to boost feature diversity,the Progressive Feature Enhancement Module(PFE)to increase the focus on critical features,and the Triplet-Aware Cross-Stage Module(TACS)for capturing interactions across spatial and channel dimensions.Furthermore,the framework incorporates the Dynamic Head(DyHead),which uses multi-dimensional attention mechanisms to dynamically adjust to various scales,spatial positions,and detection challenges.Experimental results show that DTFA-Net achieved a detection Precision of 94.3%,a Recall of 92.8%,and mAP50 of 96.6%on the Amazonis Planitia dust devil dataset.Its overall performance significantly surpasses that of existing mainstream methods,while also demonstrating strong generalization capability on cross-regional datasets.Beyond detection,this framework was further applied to analyze the seasonal activity and spatial distribution patterns of Martian dust devils in Amazonis Planitia,and the prevailing winds of each season were examined to explore the mechanisms underlying the formation of activity hotspots.In addition,the model was extended to the ten core candidate landing sites of the Tianwen-3 mission to systematically assess dust devil distribution across these regions.Based on the detection results and previous studies,we suggest that four sites—Kasei Valles,Oxia Planum,McLaughlin Crater,and Mawrth Vallis—offer a more balanced trade-off among scientific value,dust-cleaning,and engineering safety,making them relatively ideal landing sites for the Tianwen-3 mission.Overall,this study provides important insights into the spatiotemporal distribution,activity patterns,and potential environmental risks of Martian dust devils,thereby offering valuable references for Mars exploration missions.Furthermore,it provides guidance for the optimized design and safe operation of spacecraft,and contributes scientific support for the planning and implementation of future Mars exploration endeavors.
基金supported by the Science and Technology Project of State Grid Corporation of China(No.5100202119559A-0-5-SF)。
文摘Distributed secondary control has been proposed to maintain frequency/voltage synchronization and power sharing for distributed energy sources in AC microgrids(MGs).The cyber layer is susceptible to time delays and cyber failures and thus,a distributed resilient secondary control should be investigated.This paper proposes a distributed multi-scale attention and predictor-based control(DMAPC)strategy to address false data injection attacks and packet loss failures with time delays.The multi-scale attention mechanism enables the system to selectively focus on neighbors'states with higher confidence evaluated in different time scales,while the data-driven predictor compensates for lost neighbors'states in the nonlinear controller.The DMAPC does not impose strict limitations on the number of false communication links or upper bound for false data.Besides,the DMAPC is formulated as an uncertain system with time delays and is proven to be uniformly ultimately bounded.Extensive experiments on a hardware-in-the-loop MG testbed have validated the effectiveness of DMAPC,which successfully relaxes restrictions on cyber failures compared to existing strategies.
基金supported by the National Natural Science Foundation of China,Youth Fund,China(No.62102318)the Basic Research Programs of Taicang,China,2023(No.TC2023JC23)+2 种基金funded in part by the National Natural Science Foundation of China(No.92267203)in part by the Science and Technology Major Project of Guangzhou,China(No.202007030006)in part by the Program for Guangdong Introducing Innovative and Entrepreneurial Teams,China(No.2019ZT08X214).
文摘Shadows in document images are undesirable yet inevitable.They can decrease the clarity and readability of the images.The existing methods for removing shadows from documents still face some challenges,such as the traditional heuristics lack universality and the optimization goal of subnetworks is not consistent for multistage deep learning methods.In this paper,we introduce an end-to-end direct document shadow removal network(DDSR-Net),where we employ a 3-layer UNet++as the backbone to extract features from diverse scales.To further improve the performance of DDSR-Net,we integrate the multi-scale attention(MSA)blocks into each node.The MSA block allocates different weights to feature vectors at different positions,achieving automatic feature alignment and significantly enhancing the end-to-end network's ability to handle shadow processing.To verify the effectiveness of the proposed DDSR-Net,qualitative and quantitative experiments are conducted on multiple open-source document shadow removal datasets.The experimental results demonstrate that our method outperforms the existing state-of-the-art methods on these datasets.Our code and models will be released to the public.
基金supported in part by the National Natural Science Foundation of China Grants 62402085,61972062,62306060the Liaoning Doctoral Research Start-Up Fund 2023-BS-078+1 种基金the Dalian Youth Science and Technology Star Project 2023RQ023the Liaoning Basic Research Project 2023JH2/101300191.
文摘Underwater target detection is extensively applied in domains such as underwater search and rescue,environmental monitoring,and marine resource surveys.It is crucial in enabling autonomous underwater robot operations and promoting ocean exploration.Nevertheless,low imaging quality,harsh underwater environments,and obscured objects considerably increase the difficulty of detecting underwater targets,making it difficult for current detection methods to achieve optimal performance.In order to enhance underwater object perception and improve target detection precision,we propose a lightweight underwater target detection method using You Only Look Once(YOLO)v8 with multi-scale cross-channel attention(MSCCA),named YOLOv8-UOD.In the proposed multiscale cross-channel attention module,multi-scale attention(MSA)augments the variety of attentional perception by extracting information from innately diverse sensory fields.The cross-channel strategy utilizes RepVGGbased channel shuffling(RCS)and one-shot aggregation(OSA)to rearrange feature map channels according to specific rules.It aggregates all features only once in the final feature mapping,resulting in the extraction of more comprehensive and valuable feature information.The experimental results show that the proposed YOLOv8-UOD achieves a mAP50 of 95.67%and FLOPs of 23.8 G on the Underwater Robot Picking Contest 2017(URPC2017)dataset,outperforming other methods in terms of detection precision and computational cost-efficiency.
文摘The application of image super-resolution(SR)has brought significant assistance in the medical field,aiding doctors to make more precise diagnoses.However,solely relying on a convolutional neural network(CNN)for image SR may lead to issues such as blurry details and excessive smoothness.To address the limitations,we proposed an algorithm based on the generative adversarial network(GAN)framework.In the generator network,three different sizes of convolutions connected by a residual dense structure were used to extract detailed features,and an attention mechanism combined with dual channel and spatial information was applied to concentrate the computing power on crucial areas.In the discriminator network,using InstanceNorm to normalize tensors sped up the training process while retaining feature information.The experimental results demonstrate that our algorithm achieves higher peak signal-to-noise ratio(PSNR)and structural similarity index measure(SSIM)compared to other methods,resulting in an improved visual quality.
基金supported by the National Natural Science Foundation of China(Grant Nos.62472149,62376089,62202147)Hubei Provincial Science and Technology Plan Project(2023BCB04100).
文摘Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address this problem, a Multi-head Self-attention and Spatial-Temporal Graph Convolutional Network (MSSTGCN) for multiscale traffic flow prediction is proposed. Firstly, to capture the hidden traffic periodicity of traffic flow, traffic flow is divided into three kinds of periods, including hourly, daily, and weekly data. Secondly, a graph attention residual layer is constructed to learn the global spatial features across regions. Local spatial-temporal dependence is captured by using a T-GCN module. Thirdly, a transformer layer is introduced to learn the long-term dependence in time. A position embedding mechanism is introduced to label position information for all traffic sequences. Thus, this multi-head self-attention mechanism can recognize the sequence order and allocate weights for different time nodes. Experimental results on four real-world datasets show that the MSSTGCN performs better than the baseline methods and can be successfully adapted to traffic prediction tasks.
基金supported by Qingdao Huanghai University School-Level ScientificResearch Project(2023KJ14)Undergraduate Teaching Reform Research Project of Shandong Provincial Department of Education(M2022328)+1 种基金National Natural Science Foundation of China under Grant(42472324)Qingdao Postdoctoral Foundation under Grant(QDBSH202402049).
文摘Multimodal image fusion plays an important role in image analysis and applications.Multimodal medical image fusion helps to combine contrast features from two or more input imaging modalities to represent fused information in a single image.One of the critical clinical applications of medical image fusion is to fuse anatomical and functional modalities for rapid diagnosis of malignant tissues.This paper proposes a multimodal medical image fusion network(MMIF-Net)based on multiscale hybrid attention.The method first decomposes the original image to obtain the low-rank and significant parts.Then,to utilize the features at different scales,we add amultiscalemechanism that uses three filters of different sizes to extract the features in the encoded network.Also,a hybrid attention module is introduced to obtain more image details.Finally,the fused images are reconstructed by decoding the network.We conducted experiments with clinical images from brain computed tomography/magnetic resonance.The experimental results show that the multimodal medical image fusion network method based on multiscale hybrid attention works better than other advanced fusion methods.
基金supported by the Korea Electric Power Corporation(R22TA14,Development of Drone Systemfor Diagnosis of Porcelain Insulators in Overhead Transmission Lines)the National Fire Agency of Korea(RS-2024-00408270,Fire Hazard Analysis and Fire Safety Standards Development for Transportation and Storage Stage of Reuse Battery)the Ministry of the Interior and Safety of Korea(RS-2024-00408982,Development of Intelligent Fire Detection and Sprinkler Facility Technology Reflecting the Characteristics of Logistics Facilities).
文摘This paper proposes an automated detection framework for transmission facilities using a featureattention multi-scale robustness network(FAMSR-Net)with high-fidelity virtual images.The proposed framework exhibits three key characteristics.First,virtual images of the transmission facilities generated using StyleGAN2-ADA are co-trained with real images.This enables the neural network to learn various features of transmission facilities to improve the detection performance.Second,the convolutional block attention module is deployed in FAMSR-Net to effectively extract features from images and construct multi-dimensional feature maps,enabling the neural network to perform precise object detection in various environments.Third,an effective bounding box optimization method called Scylla-IoU is deployed on FAMSR-Net,considering the intersection over union,center point distance,angle,and shape of the bounding box.This enables the detection of power facilities of various sizes accurately.Extensive experiments demonstrated that FAMSRNet outperforms other neural networks in detecting power facilities.FAMSR-Net also achieved the highest detection accuracy when virtual images of the transmission facilities were co-trained in the training phase.The proposed framework is effective for the scheduled operation and maintenance of transmission facilities because an optical camera is currently the most promising tool for unmanned aerial vehicles.This ultimately contributes to improved inspection efficiency,reduced maintenance risks,and more reliable power delivery across extensive transmission facilities.
基金Open Access funding provided by the National Institutes of Health(NIH)The funding for this project was provided by NCATS Intramural Fund.
文摘Semantic segmentation plays a foundational role in biomedical image analysis, providing precise information about cellular, tissue, and organ structures in both biological and medical imaging modalities. Traditional approaches often fail in the face of challenges such as low contrast, morphological variability, and densely packed structures. Recent advancements in deep learning have transformed segmentation capabilities through the integration of fine-scale detail preservation, coarse-scale contextual modeling, and multi-scale feature fusion. This work provides a comprehensive analysis of state-of-the-art deep learning models, including U-Net variants, attention-based frameworks, and Transformer-integrated networks, highlighting innovations that improve accuracy, generalizability, and computational efficiency. Key architectural components such as convolution operations, shallow and deep blocks, skip connections, and hybrid encoders are examined for their roles in enhancing spatial representation and semantic consistency. We further discuss the importance of hierarchical and instance-aware segmentation and annotation in interpreting complex biological scenes and multiplexed medical images. By bridging methodological developments with diverse application domains, this paper outlines current trends and future directions for semantic segmentation, emphasizing its critical role in facilitating annotation, diagnosis, and discovery in biomedical research.
