Automatic segmentation of medical images provides a reliable scientific basis for disease diagnosis and analysis.Notably,most existing methods that combine the strengths of convolutional neural networks(CNNs)and Trans...Automatic segmentation of medical images provides a reliable scientific basis for disease diagnosis and analysis.Notably,most existing methods that combine the strengths of convolutional neural networks(CNNs)and Transformers have made significant progress.However,there are some limitations in the current integration of CNN and Transformer technology in two key aspects.Firstly,most methods either overlook or fail to fully incorporate the complementary nature between local and global features.Secondly,the significance of integrating the multiscale encoder features from the dual-branch network to enhance the decoding features is often disregarded in methods that combine CNN and Transformer.To address this issue,we present a groundbreaking dual-branch cross-attention fusion network(DCFNet),which efficiently combines the power of Swin Transformer and CNN to generate complementary global and local features.We then designed the Feature Cross-Fusion(FCF)module to efficiently fuse local and global features.In the FCF,the utilization of the Channel-wise Cross-fusion Transformer(CCT)serves the purpose of aggregatingmulti-scale features,and the Feature FusionModule(FFM)is employed to effectively aggregate dual-branch prominent feature regions from the spatial perspective.Furthermore,within the decoding phase of the dual-branch network,our proposed Channel Attention Block(CAB)aims to emphasize the significance of the channel features between the up-sampled features and the features generated by the FCFmodule to enhance the details of the decoding.Experimental results demonstrate that DCFNet exhibits enhanced accuracy in segmentation performance.Compared to other state-of-the-art(SOTA)methods,our segmentation framework exhibits a superior level of competitiveness.DCFNet’s accurate segmentation of medical images can greatly assist medical professionals in making crucial diagnoses of lesion areas in advance.展开更多
This paper presents a concurrent dual-band branch-line coupler with an independently tunable center frequency. In the proposed architecture, the quarter-wavelength lines, which work at two separated bands concurrently...This paper presents a concurrent dual-band branch-line coupler with an independently tunable center frequency. In the proposed architecture, the quarter-wavelength lines, which work at two separated bands concurrently and can be tuned in one of them, are key components. Based on the analysis of ABCD-matrix, a novel hybrid structure and a pair of varactors topology are utilized to achieve concurrent dual-band operation and independent tunability, respectively. Using this configuration, it is convenient to tune the center frequency of the upper band, while the responses of the lower band remain unaltered. To verify the proposed idea, a demonstration is implemented and the simulated results are presented.展开更多
In this work, the performance of free-space optical(FSO) communication system based on maximal ratio combining using binary phase shift keying subcarrier intensity modulation over Gamma-Gamma fading channels has been ...In this work, the performance of free-space optical(FSO) communication system based on maximal ratio combining using binary phase shift keying subcarrier intensity modulation over Gamma-Gamma fading channels has been studied systematically. Under identically or non-identically distributed branches, the analytical expressions for the bit error rate function of signal-to-noise are derived by expressing the modified Bessel function of second kind with Meijer G-function for dualand triple-branch systems, respectively. In terms of H-fox function, the new expressions have more general forms and are more efficient for computation. It is found that the dual-and triple-branch systems significantly outperform the direct link system under weak, moderate and strong turbulence conditions. Monte Carlo simulation is also provided to confirm the accuracy of the proposed model.展开更多
A tunable dual-broad-band branch-line coupler (BLC) utilizing composite right/left-handed (CRLH) transmission lines is presented. Two λ/4 segments consisting of CRLH transmission lines are added to each port to broad...A tunable dual-broad-band branch-line coupler (BLC) utilizing composite right/left-handed (CRLH) transmission lines is presented. Two λ/4 segments consisting of CRLH transmission lines are added to each port to broaden the dual bands of the branch-line coupler. Numerical simulation and optimal design of the novel coupler are presented. The dual bands of the novel coupler are tunable and broad. The 1-dB bandwidth of each pass band is more than 16% of the central frequency.展开更多
基金supported by the National Key R&D Program of China(2018AAA0102100)the National Natural Science Foundation of China(No.62376287)+3 种基金the International Science and Technology Innovation Joint Base of Machine Vision and Medical Image Processing in Hunan Province(2021CB1013)the Key Research and Development Program of Hunan Province(2022SK2054)the Natural Science Foundation of Hunan Province(No.2022JJ30762,2023JJ70016)the 111 Project under Grant(No.B18059).
文摘Automatic segmentation of medical images provides a reliable scientific basis for disease diagnosis and analysis.Notably,most existing methods that combine the strengths of convolutional neural networks(CNNs)and Transformers have made significant progress.However,there are some limitations in the current integration of CNN and Transformer technology in two key aspects.Firstly,most methods either overlook or fail to fully incorporate the complementary nature between local and global features.Secondly,the significance of integrating the multiscale encoder features from the dual-branch network to enhance the decoding features is often disregarded in methods that combine CNN and Transformer.To address this issue,we present a groundbreaking dual-branch cross-attention fusion network(DCFNet),which efficiently combines the power of Swin Transformer and CNN to generate complementary global and local features.We then designed the Feature Cross-Fusion(FCF)module to efficiently fuse local and global features.In the FCF,the utilization of the Channel-wise Cross-fusion Transformer(CCT)serves the purpose of aggregatingmulti-scale features,and the Feature FusionModule(FFM)is employed to effectively aggregate dual-branch prominent feature regions from the spatial perspective.Furthermore,within the decoding phase of the dual-branch network,our proposed Channel Attention Block(CAB)aims to emphasize the significance of the channel features between the up-sampled features and the features generated by the FCFmodule to enhance the details of the decoding.Experimental results demonstrate that DCFNet exhibits enhanced accuracy in segmentation performance.Compared to other state-of-the-art(SOTA)methods,our segmentation framework exhibits a superior level of competitiveness.DCFNet’s accurate segmentation of medical images can greatly assist medical professionals in making crucial diagnoses of lesion areas in advance.
基金Supported by the Provincial Natural Science Foundation of Zhejiang(No.Y1101270)the National Natural Science Foundation of China(No.61171040)+1 种基金Ningbo University Disciplinary Project(No.XKL141038)Agilent Technologies Inc.Research Project(No.3110)
文摘This paper presents a concurrent dual-band branch-line coupler with an independently tunable center frequency. In the proposed architecture, the quarter-wavelength lines, which work at two separated bands concurrently and can be tuned in one of them, are key components. Based on the analysis of ABCD-matrix, a novel hybrid structure and a pair of varactors topology are utilized to achieve concurrent dual-band operation and independent tunability, respectively. Using this configuration, it is convenient to tune the center frequency of the upper band, while the responses of the lower band remain unaltered. To verify the proposed idea, a demonstration is implemented and the simulated results are presented.
基金supported by the National Natural Science Foundation of China (Grant No. 61671347)the Fundamental ResearchFunds for the Central Universities (Grant No. 20106151859 & 20106161859)supported by 111 Project of China (B08038)
文摘In this work, the performance of free-space optical(FSO) communication system based on maximal ratio combining using binary phase shift keying subcarrier intensity modulation over Gamma-Gamma fading channels has been studied systematically. Under identically or non-identically distributed branches, the analytical expressions for the bit error rate function of signal-to-noise are derived by expressing the modified Bessel function of second kind with Meijer G-function for dualand triple-branch systems, respectively. In terms of H-fox function, the new expressions have more general forms and are more efficient for computation. It is found that the dual-and triple-branch systems significantly outperform the direct link system under weak, moderate and strong turbulence conditions. Monte Carlo simulation is also provided to confirm the accuracy of the proposed model.
基金Project (No. 2004CB719802) supported by the National Basic Re-search Program (973) of China
文摘A tunable dual-broad-band branch-line coupler (BLC) utilizing composite right/left-handed (CRLH) transmission lines is presented. Two λ/4 segments consisting of CRLH transmission lines are added to each port to broaden the dual bands of the branch-line coupler. Numerical simulation and optimal design of the novel coupler are presented. The dual bands of the novel coupler are tunable and broad. The 1-dB bandwidth of each pass band is more than 16% of the central frequency.