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

Automatic segmentation of medical images based on multi-modality is animportant topic for disease diagnosis. Although the convolutional neuralnetwork (CNN) has been proven to have excellent performance in imagesegmentation tasks, it is difficult to obtain global information. The lack ofglobal information will seriously affect the accuracy of the segmentationresults of the lesion area. In addition, there are visual representationdifferences between multimodal data of the same patient. These differences willaffect the results of the automatic segmentation methods. To solve theseproblems, we propose a segmentation method suitable for multimodal medicalimages that can capture global information, named TranSiam. TranSiam is a 2Ddual path network that extracts features of different modalities. In each path,we utilize convolution to extract detailed information in low level stage, anddesign a ICMT block to extract global information in high level stage. ICMTblock embeds convolution in the transformer, which can extract globalinformation while retaining spatial and detailed information. Furthermore, wedesign a novel fusion mechanism based on cross attention and selfattention,called TMM block, which can effectively fuse features between differentmodalities. On the BraTS 2019 and BraTS 2020 multimodal datasets, we have asignificant improvement in accuracy over other popular methods.

TranSiam: Fusing Multimodal Visual Features Using Transformer for Medical Image Segmentation