English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The U-shaped architecture has emerged as a crucial paradigm in the design ofmedical image segmentation networks. However, due to the inherent locallimitations of convolution, a fully convolutional segmentation network withU-shaped architecture struggles to effectively extract global contextinformation, which is vital for the precise localization of lesions. Whilehybrid architectures combining CNNs and Transformers can address these issues,their application in real medical scenarios is limited due to the computationalresource constraints imposed by the environment and edge devices. In addition,the convolutional inductive bias in lightweight networks adeptly fits thescarce medical data, which is lacking in the Transformer based network. Inorder to extract global context information while taking advantage of theinductive bias, we propose CMUNeXt, an efficient fully convolutionallightweight medical image segmentation network, which enables fast and accurateauxiliary diagnosis in real scene scenarios. CMUNeXt leverages large kernel andinverted bottleneck design to thoroughly mix distant spatial and locationinformation, efficiently extracting global context information. We alsointroduce the Skip-Fusion block, designed to enable smooth skip-connections andensure ample feature fusion. Experimental results on multiple medical imagedatasets demonstrate that CMUNeXt outperforms existing heavyweight andlightweight medical image segmentation networks in terms of segmentationperformance, while offering a faster inference speed, lighter weights, and areduced computational cost. The code is available athttps://github.com/FengheTan9/CMUNeXt.

CMUNeXt: An Efficient Medical Image Segmentation Network based on Large Kernel and Skip Fusion