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 convolutional-based methods provide good segmentation performance in themedical image segmentation task. However, those methods have the followingchallenges when dealing with the edges of the medical images: (1) Previousconvolutional-based methods do not focus on the boundary relationship betweenforeground and background around the segmentation edge, which leads to thedegradation of segmentation performance when the edge changes complexly. (2)The inductive bias of the convolutional layer cannot be adapted to complex edgechanges and the aggregation of multiple-segmented areas, resulting in itsperformance improvement mostly limited to segmenting the body of segmentedareas instead of the edge. To address these challenges, we propose the CM-MLPframework on MFI (Multi-scale Feature Interaction) block and ACRE (AxialContext Relation Encoder) block for accurate segmentation of the edge ofmedical image. In the MFI block, we propose the cascade multi-scale MLP(Cascade MLP) to process all local information from the deeper layers of thenetwork simultaneously and utilize a cascade multi-scale mechanism to fusediscrete local information gradually. Then, the ACRE block is used to make thedeep supervision focus on exploring the boundary relationship betweenforeground and background to modify the edge of the medical image. Thesegmentation accuracy (Dice) of our proposed CM-MLP framework reaches 96.96%,96.76%, and 82.54% on three benchmark datasets: CVC-ClinicDB dataset,sub-Kvasir dataset, and our in-house dataset, respectively, which significantlyoutperform the state-of-the-art method. The source code and trained models willbe available at https://github.com/ProgrammerHyy/CM-MLP.

CM-MLP: Cascade Multi-scale MLP with Axial Context Relation Encoder for Edge Segmentation of Medical Image