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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Melanoma, a dangerous type of skin cancer resulting from abnormal skin cellgrowth, can be treated if detected early. Various approaches using FullyConvolutional Networks (FCNs) have been proposed, with the U-Net architecturebeing prominent To aid in its diagnosis through automatic skin lesionsegmentation. However, the symmetrical U-Net model's reliance on convolutionaloperations hinders its ability to capture long-range dependencies crucial foraccurate medical image segmentation. Several Transformer-based U-Net topologieshave recently been created to overcome this limitation by replacing CNN blockswith different Transformer modules to capture local and global representations.Furthermore, the U-shaped structure is hampered by semantic gaps between theencoder and decoder. This study intends to increase the network's featurere-usability by carefully building the skip connection path. Integrating analready calculated attention affinity within the skip connection path improvesthe typical concatenation process utilized in the conventional skip connectionpath. As a result, we propose a U-shaped hierarchical Transformer-basedstructure for skin lesion segmentation and an Inter-scale Context Fusion (ISCF)method that uses attention correlations in each stage of the encoder toadaptively combine the contexts from each stage to mitigate semantic gaps. Thefindings from two skin lesion segmentation benchmarks support the ISCF module'sapplicability and effectiveness. The code is publicly available at\url{https://github.com/saniaesk/skin-lesion-segmentation}

Skin Lesion Segmentation Improved by Transformer-based Networks with Inter-scale Dependency Modeling