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

Recently, U-shaped networks have dominated the field of medical imagesegmentation due to their simple and easily tuned structure. However, existingU-shaped segmentation networks: 1) mostly focus on designing complexself-attention modules to compensate for the lack of long-term dependence basedon convolution operation, which increases the overall number of parameters andcomputational complexity of the network; 2) simply fuse the features of encoderand decoder, ignoring the connection between their spatial locations. In thispaper, we rethink the above problem and build a lightweight medical imagesegmentation network, called SegNetr. Specifically, we introduce a novelSegNetr block that can perform local-global interactions dynamically at anystage and with only linear complexity. At the same time, we design a generalinformation retention skip connection (IRSC) to preserve the spatial locationinformation of encoder features and achieve accurate fusion with the decoderfeatures. We validate the effectiveness of SegNetr on four mainstream medicalimage segmentation datasets, with 59\% and 76\% fewer parameters and GFLOPsthan vanilla U-Net, while achieving segmentation performance comparable tostate-of-the-art methods. Notably, the components proposed in this paper can beapplied to other U-shaped networks to improve their segmentation performance.

SegNetr: Rethinking the local-global interactions and skip connections in U-shaped networks