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

Automatic and accurate lesion segmentation is critical for clinicallyestimating the lesion statuses of stroke diseases and developing appropriatediagnostic systems. Although existing methods have achieved remarkable results,further adoption of the models is hindered by: (1) inter-class indistinction,the normal brain tissue resembles the lesion in appearance. (2) intra-classinconsistency, large variability exists between different areas of the lesion.To solve these challenges in stroke segmentation, we propose a novel method,namely Attention Guided Multiscale Recovery framework (AGMR-Net) in this paper.Firstly, a coarse-grained patch attention module in the encoding is adopted toget a patch-based coarse-grained attention map in a multi-stage explicitlysupervised way, enabling target spatial context saliency representation with apatch-based weighting technique that eliminates the effect of intra-classinconsistency. Secondly, to obtain a more detailed boundary partitioning tosolve the challenge of the inter-class indistinction, a newly designedcross-dimensional feature fusion module is used to capture global contextualinformation to further guide the selective aggregation of 2D and 3D features,which can compensate for the lack of boundary learning capability of 2Dconvolution. Lastly, in the decoding stage, an innovative designed multi-scaledeconvolution upsampling instead of linear interpolation enhances the recoveryof target space and boundary information. The AGMR-Net is evaluated on the opendataset Anatomical Tracings of Lesions-After-Stroke (ATLAS), achieving thehighest dice similarity coefficient (DSC) score of 0.594, Hausdorff distance of27.005 mm, and average symmetry surface distance of 7.137 mm, which demonstratethat our proposed method outperforms other state-of-the-art methods and hasgreat potential in the diagnosis of stroke.

AGMR-Net: Attention Guided Multiscale Recovery framework for stroke segmentation