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

Accurate segmentation of colonoscopic polyps is considered a fundamental stepin medical image analysis and surgical interventions. Many recent studies havemade improvements based on the encoder-decoder framework, which can effectivelysegment diverse polyps. Such improvements mainly aim to enhance local featuresby using global features and applying attention methods. However, relying onlyon the global information of the final encoder block can result in losing localregional features in the intermediate layer. In addition, determining the edgesbetween benign regions and polyps could be a challenging task. To address theaforementioned issues, we propose a novel separated edge-guidance transformer(SegT) network that aims to build an effective polyp segmentation model. Atransformer encoder that learns a more robust representation than existingCNN-based approaches was specifically applied. To determine the precisesegmentation of polyps, we utilize a separated edge-guidance module consistingof separator and edge-guidance blocks. The separator block is a two-streamoperator to highlight edges between the background and foreground, whereas theedge-guidance block lies behind both streams to strengthen the understanding ofthe edge. Lastly, an innovative cascade fusion module was used and fused therefined multi-level features. To evaluate the effectiveness of SegT, weconducted experiments with five challenging public datasets, and the proposedmodel achieved state-of-the-art performance.

SegT: A Novel Separated Edge-guidance Transformer Network for Polyp Segmentation