In medical image segmentation task,convolutional neural networks(CNNs)are difficult to capture long-range dependencies,but transformers can model the long-range dependencies effectively.However,transformers have a fle...In medical image segmentation task,convolutional neural networks(CNNs)are difficult to capture long-range dependencies,but transformers can model the long-range dependencies effectively.However,transformers have a flexible structure and seldom assume the structural bias of input data,so it is difficult for transformers to learn positional encoding of the medical images when using fewer images for training.To solve these problems,a dual branch structure is proposed.In one branch,Mix-Feed-Forward Network(Mix-FFN)and axial attention are adopted to capture long-range dependencies and keep the translation invariance of the model.Mix-FFN whose depth-wise convolutions can provide position information is better than ordinary positional encoding.In the other branch,traditional convolutional neural networks(CNNs)are used to extract different features of fewer medical images.In addition,the attention fusion module BiFusion is used to effectively integrate the information from the CNN branch and Transformer branch,and the fused features can effectively capture the global and local context of the current spatial resolution.On the public standard datasets Gland Segmentation(GlaS),Colorectal adenocarcinoma gland(CRAG)and COVID-19 CT Images Segmentation,the F1-score,Intersection over Union(IoU)and parameters of the proposed TC-Fuse are superior to those by Axial Attention U-Net,U-Net,Medical Transformer and other methods.And F1-score increased respectively by 2.99%,3.42%and 3.95%compared with Medical Transformer.展开更多
The growth trajectory of hailstones in clouds determines the ground intensity and spatial distribution of hailfall.A systematic study of hail trajectories can help improve the current scientific understanding of the m...The growth trajectory of hailstones in clouds determines the ground intensity and spatial distribution of hailfall.A systematic study of hail trajectories can help improve the current scientific understanding of the mechanisms by which hail forms in semi-arid regions of China and,in doing so,improve the quality of hail forecasts and warnings and help to prevent and mitigate disasters.In this study,the WRFv3.7.1 model was employed to provide the background field to drive the hailstone trajectory model.Cluster analysis was then used to classify hail trajectories to investigate the characteristics of different types of hail trajectories and the microphysical characteristics of hail formation.The differences in hail trajectories might be mainly due to differences in the background flow fields and microphysical fields of hail clouds in different regions.Comparative analysis revealed that as the maximum particle size of ground hailfall increased,the maximum supercooled cloud water content and the maximum updraft velocity for the formation and growth of hailstone increased.The larger the size when the hailstone reaches its maximum height,the larger the ground hailstone formed.Overall,the formation and growth of hailstone are caused by the joint action of the dynamical flow field and cloud microphysical processes.The physical processes of hailstone growth and main growth regions differ for different types of hail trajectories.Therefore,different catalytic schemes should be adopted in artificial hail prevention operations for different hail clouds and trajectories due to differences in hail formation processes and ground hailfall characteristics.展开更多
Retinal vessel segmentation in fundus images plays an essential role in the screening,diagnosis,and treatment of many diseases.The acquired fundus images generally have the following problems:uneven illumination,high ...Retinal vessel segmentation in fundus images plays an essential role in the screening,diagnosis,and treatment of many diseases.The acquired fundus images generally have the following problems:uneven illumination,high noise,and complex structure.It makes vessel segmentation very challenging.Previous methods of retinal vascular segmentation mainly use convolutional neural networks on U Network(U-Net)models,and they have many limitations and shortcomings,such as the loss of microvascular details at the end of the vessels.We address the limitations of convolution by introducing the transformer into retinal vessel segmentation.Therefore,we propose a hybrid method for retinal vessel segmentation based on modulated deformable convolution and the transformer,named DT-Net.Firstly,multi-scale image features are extracted by deformable convolution and multi-head selfattention(MHSA).Secondly,image information is recovered,and vessel morphology is refined by the proposed transformer decoder block.Finally,the local prediction results are obtained by the side output layer.The accuracy of the vessel segmentation is improved by the hybrid loss function.Experimental results show that our method obtains good segmentation performance on Specificity(SP),Sensitivity(SE),Accuracy(ACC),Curve(AUC),and F1-score on three publicly available fundus datasets such as DRIVE,STARE,and CHASE_DB1.展开更多
基金supported in part by the National Natural Science Foundation of China under Grant 61972267the National Natural Science Foundation of Hebei Province under Grant F2018210148+1 种基金the University Science Research Project of Hebei Province under Grant ZD2021334the Science and Technology Project of Hebei Education Department(ZD2022098).
文摘In medical image segmentation task,convolutional neural networks(CNNs)are difficult to capture long-range dependencies,but transformers can model the long-range dependencies effectively.However,transformers have a flexible structure and seldom assume the structural bias of input data,so it is difficult for transformers to learn positional encoding of the medical images when using fewer images for training.To solve these problems,a dual branch structure is proposed.In one branch,Mix-Feed-Forward Network(Mix-FFN)and axial attention are adopted to capture long-range dependencies and keep the translation invariance of the model.Mix-FFN whose depth-wise convolutions can provide position information is better than ordinary positional encoding.In the other branch,traditional convolutional neural networks(CNNs)are used to extract different features of fewer medical images.In addition,the attention fusion module BiFusion is used to effectively integrate the information from the CNN branch and Transformer branch,and the fused features can effectively capture the global and local context of the current spatial resolution.On the public standard datasets Gland Segmentation(GlaS),Colorectal adenocarcinoma gland(CRAG)and COVID-19 CT Images Segmentation,the F1-score,Intersection over Union(IoU)and parameters of the proposed TC-Fuse are superior to those by Axial Attention U-Net,U-Net,Medical Transformer and other methods.And F1-score increased respectively by 2.99%,3.42%and 3.95%compared with Medical Transformer.
基金supported by the National Natural Science Foundation of China (Grant Nos. 41975176, 42061134009)the High Performance Computing Center of Nanjing University of Information Science and Technology for their support of this work
文摘The growth trajectory of hailstones in clouds determines the ground intensity and spatial distribution of hailfall.A systematic study of hail trajectories can help improve the current scientific understanding of the mechanisms by which hail forms in semi-arid regions of China and,in doing so,improve the quality of hail forecasts and warnings and help to prevent and mitigate disasters.In this study,the WRFv3.7.1 model was employed to provide the background field to drive the hailstone trajectory model.Cluster analysis was then used to classify hail trajectories to investigate the characteristics of different types of hail trajectories and the microphysical characteristics of hail formation.The differences in hail trajectories might be mainly due to differences in the background flow fields and microphysical fields of hail clouds in different regions.Comparative analysis revealed that as the maximum particle size of ground hailfall increased,the maximum supercooled cloud water content and the maximum updraft velocity for the formation and growth of hailstone increased.The larger the size when the hailstone reaches its maximum height,the larger the ground hailstone formed.Overall,the formation and growth of hailstone are caused by the joint action of the dynamical flow field and cloud microphysical processes.The physical processes of hailstone growth and main growth regions differ for different types of hail trajectories.Therefore,different catalytic schemes should be adopted in artificial hail prevention operations for different hail clouds and trajectories due to differences in hail formation processes and ground hailfall characteristics.
基金supported in part by the National Natural Science Foundation of China under Grant 61972267the National Natural Science Foundation of Hebei Province under Grant F2018210148the University Science Research Project of Hebei Province under Grant ZD2021334.
文摘Retinal vessel segmentation in fundus images plays an essential role in the screening,diagnosis,and treatment of many diseases.The acquired fundus images generally have the following problems:uneven illumination,high noise,and complex structure.It makes vessel segmentation very challenging.Previous methods of retinal vascular segmentation mainly use convolutional neural networks on U Network(U-Net)models,and they have many limitations and shortcomings,such as the loss of microvascular details at the end of the vessels.We address the limitations of convolution by introducing the transformer into retinal vessel segmentation.Therefore,we propose a hybrid method for retinal vessel segmentation based on modulated deformable convolution and the transformer,named DT-Net.Firstly,multi-scale image features are extracted by deformable convolution and multi-head selfattention(MHSA).Secondly,image information is recovered,and vessel morphology is refined by the proposed transformer decoder block.Finally,the local prediction results are obtained by the side output layer.The accuracy of the vessel segmentation is improved by the hybrid loss function.Experimental results show that our method obtains good segmentation performance on Specificity(SP),Sensitivity(SE),Accuracy(ACC),Curve(AUC),and F1-score on three publicly available fundus datasets such as DRIVE,STARE,and CHASE_DB1.
