DCFNet:An Effective Dual-Branch Cross-Attention Fusion Network for Medical Image Segmentation

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.

A large-current, highly integrated switched-capacitor divider with a dual-branch interleaved topology and light load efficiency improvement

Because it is magnet-free and can achieve a high integration level,the switched-capacitor(SC)converter acting as a direct current transformer has many promising applications in modern electronics.However,designing an SC converter with large current capability and high power efficiency is still challenging.This paper proposes a dual-branch SC voltage divider and presents its integrated circuit(IC)implementation.The designed SC converter is capable of driving large current load,thus widening the use of SC converters to high-power applications.This SC converter has a constant conversion ratio of 1/2 and its dual-branch interleaved operation ensures a continuous input current.An effective on-chip gate-driving method using a capacitively coupled floating-voltage level shifter is proposed to drive the all-NMOS power train.Due to the self-powered structure,the flying capacitor itself is also a bootstrap capacitor for gate driving and thus reduces the number of needed components.A digital frequency modulation method is adopted and the switching frequency decreases automatically at light load to improve light load efficiency.The converter IC is implemented using a 180 nm triple-well BCD process.Experimental results verify the effectiveness of the dual-branch interleaved operation and the self-powered gate-driving method.The proposed SC divider can drive up to 4 A load current with 5–12 V input voltage and its power efficiency is as high as 96.5%.At light load,using the proposed optimization method,the power efficiency is improved by 30%.