Due to the dynamic nature and node mobility,assuring the security of Mobile Ad-hoc Networks(MANET)is one of the difficult and challenging tasks today.In MANET,the Intrusion Detection System(IDS)is crucial because it a...Due to the dynamic nature and node mobility,assuring the security of Mobile Ad-hoc Networks(MANET)is one of the difficult and challenging tasks today.In MANET,the Intrusion Detection System(IDS)is crucial because it aids in the identification and detection of malicious attacks that impair the network’s regular operation.Different machine learning and deep learning methodologies are used for this purpose in the conventional works to ensure increased security of MANET.However,it still has significant flaws,including increased algorithmic complexity,lower system performance,and a higher rate of misclassification.Therefore,the goal of this paper is to create an intelligent IDS framework for significantly enhancing MANET security through the use of deep learning models.Here,the min-max normalization model is applied to preprocess the given cyber-attack datasets for normalizing the attributes or fields,which increases the overall intrusion detection performance of classifier.Then,a novel Adaptive Marine Predator Optimization Algorithm(AOMA)is implemented to choose the optimal features for improving the speed and intrusion detection performance of classifier.Moreover,the Deep Supervise Learning Classification(DSLC)mechanism is utilized to predict and categorize the type of intrusion based on proper learning and training operations.During evaluation,the performance and results of the proposed AOMA-DSLC based IDS methodology is validated and compared using various performance measures and benchmarking datasets.展开更多
To solve the problem that the existing ciphertext domain image retrieval system is challenging to balance security,retrieval efficiency,and retrieval accuracy.This research suggests a searchable encryption and deep ha...To solve the problem that the existing ciphertext domain image retrieval system is challenging to balance security,retrieval efficiency,and retrieval accuracy.This research suggests a searchable encryption and deep hashing-based secure image retrieval technique that extracts more expressive image features and constructs a secure,searchable encryption scheme.First,a deep learning framework based on residual network and transfer learn-ing model is designed to extract more representative image deep features.Secondly,the central similarity is used to quantify and construct the deep hash sequence of features.The Paillier homomorphic encryption encrypts the deep hash sequence to build a high-security and low-complexity searchable index.Finally,according to the additive homomorphic property of Paillier homomorphic encryption,a similarity measurement method suitable for com-puting in the retrieval system’s security is ensured by the encrypted domain.The experimental results,which were obtained on Web Image Database from the National University of Singapore(NUS-WIDE),Microsoft Common Objects in Context(MS COCO),and ImageNet data sets,demonstrate the system’s robust security and precise retrieval,the proposed scheme can achieve efficient image retrieval without revealing user privacy.The retrieval accuracy is improved by at least 37%compared to traditional hashing schemes.At the same time,the retrieval time is saved by at least 9.7%compared to the latest deep hashing schemes.展开更多
With an increasing number of services connected to the internet,including cloud computing and Internet of Things(IoT)systems,the prevention of cyberattacks has become more challenging due to the high dimensionality of...With an increasing number of services connected to the internet,including cloud computing and Internet of Things(IoT)systems,the prevention of cyberattacks has become more challenging due to the high dimensionality of the network traffic data and access points.Recently,researchers have suggested deep learning(DL)algorithms to define intrusion features through training empirical data and learning anomaly patterns of attacks.However,due to the high dynamics and imbalanced nature of the data,the existing DL classifiers are not completely effective at distinguishing between abnormal and normal behavior line connections for modern networks.Therefore,it is important to design a self-adaptive model for an intrusion detection system(IDS)to improve the detection of attacks.Consequently,in this paper,a novel hybrid weighted deep belief network(HW-DBN)algorithm is proposed for building an efficient and reliable IDS(DeepIoT.IDS)model to detect existing and novel cyberattacks.The HW-DBN algorithm integrates an improved Gaussian–Bernoulli restricted Boltzmann machine(Deep GB-RBM)feature learning operator with a weighted deep neural networks(WDNN)classifier.The CICIDS2017 dataset is selected to evaluate the DeepIoT.IDS model as it contains multiple types of attacks,complex data patterns,noise values,and imbalanced classes.We have compared the performance of the DeepIoT.IDS model with three recent models.The results show the DeepIoT.IDS model outperforms the three other models by achieving a higher detection accuracy of 99.38%and 99.99%for web attack and bot attack scenarios,respectively.Furthermore,it can detect the occurrence of low-frequency attacks that are undetectable by other models.展开更多
Automatic identification and segmentation of lesions in medical images has become a focus area for researchers.Segmentation for medical image provides professionals with a clearer and more detailed view by accurately ...Automatic identification and segmentation of lesions in medical images has become a focus area for researchers.Segmentation for medical image provides professionals with a clearer and more detailed view by accurately identifying and isolating specific tissues,organs,or lesions from complex medical images,which is crucial for early diagnosis of diseases,treatment planning,and efficacy tracking.This paper introduces a deep network based on dendritic learning and missing region detection(DMNet),a new approach to medical image segmentation.DMNet combines a dendritic neuron model(DNM)with an improved SegNet framework to improve segmentation accuracy,especially in challenging tasks such as breast lesion and COVID-19 CT scan analysis.This work provides a new approach to medical image segmentation and confirms its effectiveness.Experiments have demonstrated that DMNet outperforms classic and latest methods in various performance metrics,proving its effectiveness and stability in medical image segmentation tasks.展开更多
Coronavirus has infected more than 753 million people,ranging in severity from one person to another,where more than six million infected people died worldwide.Computer-aided diagnostic(CAD)with artificial intelligenc...Coronavirus has infected more than 753 million people,ranging in severity from one person to another,where more than six million infected people died worldwide.Computer-aided diagnostic(CAD)with artificial intelligence(AI)showed outstanding performance in effectively diagnosing this virus in real-time.Computed tomography is a complementary diagnostic tool to clarify the damage of COVID-19 in the lungs even before symptoms appear in patients.This paper conducts a systematic literature review of deep learning methods for classifying the segmentation of COVID-19 infection in the lungs.We used the methodology of systematic reviews and meta-analyses(PRISMA)flow method.This research aims to systematically analyze the supervised deep learning methods,open resource datasets,data augmentation methods,and loss functions used for various segment shapes of COVID-19 infection from computerized tomography(CT)chest images.We have selected 56 primary studies relevant to the topic of the paper.We have compared different aspects of the algorithms used to segment infected areas in the CT images.Limitations to deep learning in the segmentation of infected areas still need to be developed to predict smaller regions of infection at the beginning of their appearance.展开更多
The objective of this study is to address semantic misalignment and insufficient accuracy in edge detail and discrimination detection,which are common issues in deep learning-based change detection methods relying on ...The objective of this study is to address semantic misalignment and insufficient accuracy in edge detail and discrimination detection,which are common issues in deep learning-based change detection methods relying on encoding and decoding frameworks.In response to this,we propose a model called FlowDual-PixelClsObjectMec(FPCNet),which innovatively incorporates dual flow alignment technology in the decoding stage to rectify semantic discrepancies through streamlined feature correction fusion.Furthermore,the model employs an object-level similarity measurement coupled with pixel-level classification in the PixelClsObjectMec(PCOM)module during the final discrimination stage,significantly enhancing edge detail detection and overall accuracy.Experimental evaluations on the change detection dataset(CDD)and building CDD demonstrate superior performance,with F1 scores of 95.1%and 92.8%,respectively.Our findings indicate that the FPCNet outperforms the existing algorithms in stability,robustness,and other key metrics.展开更多
Accurate prognosis prediction is essential for guiding cancer treatment and improving patient outcomes.While recent studies have demonstrated the potential of histopathological images in survival analysis,existing mod...Accurate prognosis prediction is essential for guiding cancer treatment and improving patient outcomes.While recent studies have demonstrated the potential of histopathological images in survival analysis,existing models are typically developed in a cancerspecific manner,lack extensive external validation,and often rely on molecular data that are not routinely available in clinical practice.To address these limitations,we present PROGPATH,a unified model capable of integrating histopathological image features with routinely collected clinical variables to achieve pancancer prognosis prediction.PROGPATH employs a weakly supervised deep learning architecture built upon the foundation model for image encoding.Morphological features are aggregated through an attention-guided multiple instance learning module and fused with clinical information via a cross-attention transformer.A router-based classification strategy further refines the prediction performance.PROGPATH was trained on 7999 whole-slide images(WSIs)from 6,670 patients across 15 cancer types,and extensively validated on 17 external cohorts with a total of 7374 WSIs from 4441 patients,covering 12 cancer types from 8 consortia and institutions across three continents.PROGPATH achieved consistently superior performance compared with state-of-the-art multimodal prognosis prediction models.It demonstrated strong generalizability across cancer types and robustness in stratified subgroups,including early-and advancedstage patients,treatment cohorts(radiotherapy and pharmaceutical therapy),and biomarker-defined subsets.We further provide model interpretability by identifying pathological patterns critical to PROGPATH’s risk predictions,such as the degree of cell differentiation and extent of necrosis.Together,these results highlight the potential of PROGPATH to support pancancer outcome prediction and inform personalized cancer management strategies.展开更多
Liver cancer has the second highest incidence rate among all types of malignant tumors,and currently,its diagnosis heavily depends on doctors’manual labeling of CT scan images,a process that is time-consuming and sus...Liver cancer has the second highest incidence rate among all types of malignant tumors,and currently,its diagnosis heavily depends on doctors’manual labeling of CT scan images,a process that is time-consuming and susceptible to subjective errors.To address the aforementioned issues,we propose an automatic segmentation model for liver and tumors called Res2Swin Unet,which is based on the Unet architecture.The model combines Attention-Res2 and Swin Transformer modules for liver and tumor segmentation,respectively.Attention-Res2 merges multiple feature map parts with an Attention gate via skip connections,while Swin Transformer captures long-range dependencies and models the input globally.And the model uses deep supervision and a hybrid loss function for faster convergence.On the LiTS2017 dataset,it achieves better segmentation performance than other models,with an average Dice coefficient of 97.0%for liver segmentation and 81.2%for tumor segmentation.展开更多
Deep convolutional neural network (CNN) greatly promotes the automatic segmentation of medical images. However, due to the inherent properties of convolution operations, CNN usually cannot establish long-distance inte...Deep convolutional neural network (CNN) greatly promotes the automatic segmentation of medical images. However, due to the inherent properties of convolution operations, CNN usually cannot establish long-distance interdependence, which limits the segmentation performance. Transformer has been successfully applied to various computer vision, using self-attention mechanism to simulate long-distance interaction, so as to capture global information. However, self-attention lacks spatial location and high-performance computing. In order to solve the above problems, we develop a new medical transformer, which has a multi-scale context fusion function and can be used for medical image segmentation. The proposed model combines convolution operation and attention mechanism to form a u-shaped framework, which can capture both local and global information. First, the traditional converter module is improved to an advanced converter module, which uses post-layer normalization to obtain mild activation values, and uses scaled cosine attention with a moving window to obtain accurate spatial information. Secondly, we also introduce a deep supervision strategy to guide the model to fuse multi-scale feature information. It further enables the proposed model to effectively propagate feature information across layers, Thanks to this, it can achieve better segmentation performance while being more robust and efficient. The proposed model is evaluated on multiple medical image segmentation datasets. Experimental results demonstrate that the proposed model achieves better performance on a challenging dataset (ETIS) compared to existing methods that rely only on convolutional neural networks, transformers, or a combination of both. The mDice and mIou indicators increased by 2.74% and 3.3% respectively.展开更多
Salient object detection(SOD)has garnered significant interest because of its pivotal role in numerous computer vision and graphics applications.Deep convolutional neural networks have been widely applied in salient o...Salient object detection(SOD)has garnered significant interest because of its pivotal role in numerous computer vision and graphics applications.Deep convolutional neural networks have been widely applied in salient object detection and have achieved remarkable results in this field.To enhance the network representation ability,a very important means is to increase the depth of the neural network to learn as many hierarchical features as possible.However,the information related to the input image features will be lost with the increase in network depth,and existing models suffer from information distortion caused by interpolation during up-sampling and downsampling.In response to this drawback,this article focuses on the feature level and label level to address this significant challenge.On the one hand,a novel cascaded interaction network with a guidance module named global-local aligned attention(GAA)is designed to reduce the negative impact of interpolation on the feature side.On the other hand,a deep supervision strategy based on edge erosion is proposed to reduce the negative guidance of label interpolation on lateral output.Extensive experiments on five popular datasets demonstrate the superiority of our method.展开更多
Automatic extraction of tailing ponds from Very High-Resolution(VHR)remotely sensed images is vital for mineral resource management.This study proposes a Pseudo-Siamese Visual Geometry Group Encoder-Decoder network(PS...Automatic extraction of tailing ponds from Very High-Resolution(VHR)remotely sensed images is vital for mineral resource management.This study proposes a Pseudo-Siamese Visual Geometry Group Encoder-Decoder network(PSVED)to achieve high accuracy tailing ponds extraction from VHR images.First,handcrafted feature(HCF)images are calculated from VHR images based on the index calculation algorithm,highlighting the tailing ponds'signals.Second,considering the information gap between VHR images and HCF images,the Pseudo-Siamese Visual Geometry Group(Pseudo-Siamese VGG)is utilized to extract independent and representative deep semantic features from VHR images and HCF images,respectively.Third,the deep supervision mechanism is attached to handle the optimization problem of gradients vanishing or exploding.A self-made tailing ponds extraction dataset(TPSet)produced with the Gaofen-6 images of part of Hebei province,China,was employed to conduct experiments.The results show that the proposed'method_achieves the best visual performance and accuracy for tailing ponds extraction in all the tested methods,whereas the running time of the proposed method maintains at the same level as other methods.This study has practical significance in automatically extracting tailing ponds from VHR images which is beneficial to tailing ponds management and monitoring.展开更多
文摘Due to the dynamic nature and node mobility,assuring the security of Mobile Ad-hoc Networks(MANET)is one of the difficult and challenging tasks today.In MANET,the Intrusion Detection System(IDS)is crucial because it aids in the identification and detection of malicious attacks that impair the network’s regular operation.Different machine learning and deep learning methodologies are used for this purpose in the conventional works to ensure increased security of MANET.However,it still has significant flaws,including increased algorithmic complexity,lower system performance,and a higher rate of misclassification.Therefore,the goal of this paper is to create an intelligent IDS framework for significantly enhancing MANET security through the use of deep learning models.Here,the min-max normalization model is applied to preprocess the given cyber-attack datasets for normalizing the attributes or fields,which increases the overall intrusion detection performance of classifier.Then,a novel Adaptive Marine Predator Optimization Algorithm(AOMA)is implemented to choose the optimal features for improving the speed and intrusion detection performance of classifier.Moreover,the Deep Supervise Learning Classification(DSLC)mechanism is utilized to predict and categorize the type of intrusion based on proper learning and training operations.During evaluation,the performance and results of the proposed AOMA-DSLC based IDS methodology is validated and compared using various performance measures and benchmarking datasets.
基金supported by the National Natural Science Foundation of China(No.61862041).
文摘To solve the problem that the existing ciphertext domain image retrieval system is challenging to balance security,retrieval efficiency,and retrieval accuracy.This research suggests a searchable encryption and deep hashing-based secure image retrieval technique that extracts more expressive image features and constructs a secure,searchable encryption scheme.First,a deep learning framework based on residual network and transfer learn-ing model is designed to extract more representative image deep features.Secondly,the central similarity is used to quantify and construct the deep hash sequence of features.The Paillier homomorphic encryption encrypts the deep hash sequence to build a high-security and low-complexity searchable index.Finally,according to the additive homomorphic property of Paillier homomorphic encryption,a similarity measurement method suitable for com-puting in the retrieval system’s security is ensured by the encrypted domain.The experimental results,which were obtained on Web Image Database from the National University of Singapore(NUS-WIDE),Microsoft Common Objects in Context(MS COCO),and ImageNet data sets,demonstrate the system’s robust security and precise retrieval,the proposed scheme can achieve efficient image retrieval without revealing user privacy.The retrieval accuracy is improved by at least 37%compared to traditional hashing schemes.At the same time,the retrieval time is saved by at least 9.7%compared to the latest deep hashing schemes.
基金This work was partially funded by the Industry Grant Scheme from Jaycorp Berhad in cooperation with UNITAR International University.The authors would like to thank INSFORNET,the Center for Advanced Computing Technology(C-ACT)at Universiti Teknikal Malaysia Melaka(UTeM),and the Center of Intelligent and Autonomous Systems(CIAS)at Universiti Tun Hussein Onn Malaysia(UTHM)for supporting this work.
文摘With an increasing number of services connected to the internet,including cloud computing and Internet of Things(IoT)systems,the prevention of cyberattacks has become more challenging due to the high dimensionality of the network traffic data and access points.Recently,researchers have suggested deep learning(DL)algorithms to define intrusion features through training empirical data and learning anomaly patterns of attacks.However,due to the high dynamics and imbalanced nature of the data,the existing DL classifiers are not completely effective at distinguishing between abnormal and normal behavior line connections for modern networks.Therefore,it is important to design a self-adaptive model for an intrusion detection system(IDS)to improve the detection of attacks.Consequently,in this paper,a novel hybrid weighted deep belief network(HW-DBN)algorithm is proposed for building an efficient and reliable IDS(DeepIoT.IDS)model to detect existing and novel cyberattacks.The HW-DBN algorithm integrates an improved Gaussian–Bernoulli restricted Boltzmann machine(Deep GB-RBM)feature learning operator with a weighted deep neural networks(WDNN)classifier.The CICIDS2017 dataset is selected to evaluate the DeepIoT.IDS model as it contains multiple types of attacks,complex data patterns,noise values,and imbalanced classes.We have compared the performance of the DeepIoT.IDS model with three recent models.The results show the DeepIoT.IDS model outperforms the three other models by achieving a higher detection accuracy of 99.38%and 99.99%for web attack and bot attack scenarios,respectively.Furthermore,it can detect the occurrence of low-frequency attacks that are undetectable by other models.
基金supported by the Japan Society for the Promotion of Science(JSPS)KAKENHI under Grant JP22H03643Japan Science and Technology Agency(JST)Support for Pioneering Research Initiated by the Next Generation(SPRING)under Grant JPMJSP2145JST through the Establishment of University Fellowships towards the Creation of Science Technology Innovation under Grant JPMJFS2115.
文摘Automatic identification and segmentation of lesions in medical images has become a focus area for researchers.Segmentation for medical image provides professionals with a clearer and more detailed view by accurately identifying and isolating specific tissues,organs,or lesions from complex medical images,which is crucial for early diagnosis of diseases,treatment planning,and efficacy tracking.This paper introduces a deep network based on dendritic learning and missing region detection(DMNet),a new approach to medical image segmentation.DMNet combines a dendritic neuron model(DNM)with an improved SegNet framework to improve segmentation accuracy,especially in challenging tasks such as breast lesion and COVID-19 CT scan analysis.This work provides a new approach to medical image segmentation and confirms its effectiveness.Experiments have demonstrated that DMNet outperforms classic and latest methods in various performance metrics,proving its effectiveness and stability in medical image segmentation tasks.
文摘Coronavirus has infected more than 753 million people,ranging in severity from one person to another,where more than six million infected people died worldwide.Computer-aided diagnostic(CAD)with artificial intelligence(AI)showed outstanding performance in effectively diagnosing this virus in real-time.Computed tomography is a complementary diagnostic tool to clarify the damage of COVID-19 in the lungs even before symptoms appear in patients.This paper conducts a systematic literature review of deep learning methods for classifying the segmentation of COVID-19 infection in the lungs.We used the methodology of systematic reviews and meta-analyses(PRISMA)flow method.This research aims to systematically analyze the supervised deep learning methods,open resource datasets,data augmentation methods,and loss functions used for various segment shapes of COVID-19 infection from computerized tomography(CT)chest images.We have selected 56 primary studies relevant to the topic of the paper.We have compared different aspects of the algorithms used to segment infected areas in the CT images.Limitations to deep learning in the segmentation of infected areas still need to be developed to predict smaller regions of infection at the beginning of their appearance.
文摘The objective of this study is to address semantic misalignment and insufficient accuracy in edge detail and discrimination detection,which are common issues in deep learning-based change detection methods relying on encoding and decoding frameworks.In response to this,we propose a model called FlowDual-PixelClsObjectMec(FPCNet),which innovatively incorporates dual flow alignment technology in the decoding stage to rectify semantic discrepancies through streamlined feature correction fusion.Furthermore,the model employs an object-level similarity measurement coupled with pixel-level classification in the PixelClsObjectMec(PCOM)module during the final discrimination stage,significantly enhancing edge detail detection and overall accuracy.Experimental evaluations on the change detection dataset(CDD)and building CDD demonstrate superior performance,with F1 scores of 95.1%and 92.8%,respectively.Our findings indicate that the FPCNet outperforms the existing algorithms in stability,robustness,and other key metrics.
基金supported in part by the National Cancer Institute under award numbers R01CA268287A1,U01CA269181,R01CA26820701A1,R01CA249992-01A1,R01CA202752-01A1,R01CA208236-01A1,R01CA216579-01A1,R01CA220581-01A1,R01CA257612-01A1,1U01CA239055-01,1U01CA248226-01,1U54CA254566-01National Heart,Lung and Blood Institute 1R01HL15127701A1,R01HL15807101A1+8 种基金National Institute of Biomedical Imaging and Bioengineering 1R43EB028736-01VA Merit Review Award IBX004121A from the United States Department of Veterans Affairs Biomedical Laboratory Research and Development Service the Office of the Assistant Secretary of Defense for Health Affairs,through the Breast Cancer Research Program(W81XWH-19-1-0668)the Prostate Cancer Research Program(W81XWH-20-1-0851)the Lung Cancer Research Program(W81XWH-18-1-0440,W81XWH-20-1-0595)the Peer Reviewed Cancer Research Program(W81XWH-18-1-0404,W81XWH-21-1-0345,W81XWH-211-0160)the Kidney Precision Medicine Project(KPMP)Glue Grant and sponsored research agreements from Bristol Myers-Squibb,Boehringer-Ingelheim,Eli-Lilly and Astrazenecasupported in part by the National Natural Science Foundation of China general program(No.61571314)the Sichuan University-Yibin City Strategic Cooperation Special Fund(No.2020CDYB-27)Support Program of Sichuan Science and Technology Department(No.2023YFS0327-LH).
文摘Accurate prognosis prediction is essential for guiding cancer treatment and improving patient outcomes.While recent studies have demonstrated the potential of histopathological images in survival analysis,existing models are typically developed in a cancerspecific manner,lack extensive external validation,and often rely on molecular data that are not routinely available in clinical practice.To address these limitations,we present PROGPATH,a unified model capable of integrating histopathological image features with routinely collected clinical variables to achieve pancancer prognosis prediction.PROGPATH employs a weakly supervised deep learning architecture built upon the foundation model for image encoding.Morphological features are aggregated through an attention-guided multiple instance learning module and fused with clinical information via a cross-attention transformer.A router-based classification strategy further refines the prediction performance.PROGPATH was trained on 7999 whole-slide images(WSIs)from 6,670 patients across 15 cancer types,and extensively validated on 17 external cohorts with a total of 7374 WSIs from 4441 patients,covering 12 cancer types from 8 consortia and institutions across three continents.PROGPATH achieved consistently superior performance compared with state-of-the-art multimodal prognosis prediction models.It demonstrated strong generalizability across cancer types and robustness in stratified subgroups,including early-and advancedstage patients,treatment cohorts(radiotherapy and pharmaceutical therapy),and biomarker-defined subsets.We further provide model interpretability by identifying pathological patterns critical to PROGPATH’s risk predictions,such as the degree of cell differentiation and extent of necrosis.Together,these results highlight the potential of PROGPATH to support pancancer outcome prediction and inform personalized cancer management strategies.
文摘Liver cancer has the second highest incidence rate among all types of malignant tumors,and currently,its diagnosis heavily depends on doctors’manual labeling of CT scan images,a process that is time-consuming and susceptible to subjective errors.To address the aforementioned issues,we propose an automatic segmentation model for liver and tumors called Res2Swin Unet,which is based on the Unet architecture.The model combines Attention-Res2 and Swin Transformer modules for liver and tumor segmentation,respectively.Attention-Res2 merges multiple feature map parts with an Attention gate via skip connections,while Swin Transformer captures long-range dependencies and models the input globally.And the model uses deep supervision and a hybrid loss function for faster convergence.On the LiTS2017 dataset,it achieves better segmentation performance than other models,with an average Dice coefficient of 97.0%for liver segmentation and 81.2%for tumor segmentation.
文摘Deep convolutional neural network (CNN) greatly promotes the automatic segmentation of medical images. However, due to the inherent properties of convolution operations, CNN usually cannot establish long-distance interdependence, which limits the segmentation performance. Transformer has been successfully applied to various computer vision, using self-attention mechanism to simulate long-distance interaction, so as to capture global information. However, self-attention lacks spatial location and high-performance computing. In order to solve the above problems, we develop a new medical transformer, which has a multi-scale context fusion function and can be used for medical image segmentation. The proposed model combines convolution operation and attention mechanism to form a u-shaped framework, which can capture both local and global information. First, the traditional converter module is improved to an advanced converter module, which uses post-layer normalization to obtain mild activation values, and uses scaled cosine attention with a moving window to obtain accurate spatial information. Secondly, we also introduce a deep supervision strategy to guide the model to fuse multi-scale feature information. It further enables the proposed model to effectively propagate feature information across layers, Thanks to this, it can achieve better segmentation performance while being more robust and efficient. The proposed model is evaluated on multiple medical image segmentation datasets. Experimental results demonstrate that the proposed model achieves better performance on a challenging dataset (ETIS) compared to existing methods that rely only on convolutional neural networks, transformers, or a combination of both. The mDice and mIou indicators increased by 2.74% and 3.3% respectively.
基金supported in part by Shenzhen Science and Technology Program,China(No.GXWD20231129140908002).
文摘Salient object detection(SOD)has garnered significant interest because of its pivotal role in numerous computer vision and graphics applications.Deep convolutional neural networks have been widely applied in salient object detection and have achieved remarkable results in this field.To enhance the network representation ability,a very important means is to increase the depth of the neural network to learn as many hierarchical features as possible.However,the information related to the input image features will be lost with the increase in network depth,and existing models suffer from information distortion caused by interpolation during up-sampling and downsampling.In response to this drawback,this article focuses on the feature level and label level to address this significant challenge.On the one hand,a novel cascaded interaction network with a guidance module named global-local aligned attention(GAA)is designed to reduce the negative impact of interpolation on the feature side.On the other hand,a deep supervision strategy based on edge erosion is proposed to reduce the negative guidance of label interpolation on lateral output.Extensive experiments on five popular datasets demonstrate the superiority of our method.
基金supported by the National Key Research and Development Program[grant number:2022YFF1303301]The Open Foundation of the Key Laboratory of Coupling Process and Effect of Natural Resources Elements[grant number:2022KFKTC001]+1 种基金The National Natural Science Foundation of China[grant number:42271480]The Fundamental Research Funds for the Central Universities[grant number:2023ZKPYDC10,BBJ2023026].
文摘Automatic extraction of tailing ponds from Very High-Resolution(VHR)remotely sensed images is vital for mineral resource management.This study proposes a Pseudo-Siamese Visual Geometry Group Encoder-Decoder network(PSVED)to achieve high accuracy tailing ponds extraction from VHR images.First,handcrafted feature(HCF)images are calculated from VHR images based on the index calculation algorithm,highlighting the tailing ponds'signals.Second,considering the information gap between VHR images and HCF images,the Pseudo-Siamese Visual Geometry Group(Pseudo-Siamese VGG)is utilized to extract independent and representative deep semantic features from VHR images and HCF images,respectively.Third,the deep supervision mechanism is attached to handle the optimization problem of gradients vanishing or exploding.A self-made tailing ponds extraction dataset(TPSet)produced with the Gaofen-6 images of part of Hebei province,China,was employed to conduct experiments.The results show that the proposed'method_achieves the best visual performance and accuracy for tailing ponds extraction in all the tested methods,whereas the running time of the proposed method maintains at the same level as other methods.This study has practical significance in automatically extracting tailing ponds from VHR images which is beneficial to tailing ponds management and monitoring.
