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

Late gadolinium enhancement magnetic resonance imaging (LGE MRI) appears tobe a promising alternative for scar assessment in patients with atrialfibrillation (AF). Automating the quantification and analysis of atrial scarscan be challenging due to the low image quality. In this work, we propose afully automated method based on the graph-cuts framework, where the potentialsof the graph are learned on a surface mesh of the left atrium (LA) using amulti-scale convolutional neural network (MS-CNN). For validation, we haveemployed fifty-eight images with manual delineations. MS-CNN, which canefficiently incorporate both the local and global texture information of theimages, has been shown to evidently improve the segmentation accuracy of theproposed graph-cuts based method. The segmentation could be further improvedwhen the contribution between the t-link and n-link weights of the graph isbalanced. The proposed method achieves a mean accuracy of 0.856 +- 0.033 andmean Dice score of 0.702 +- 0.071 for LA scar quantification. Compared with theconventional methods, which are based on the manual delineation of LA forinitialization, our method is fully automatic and has demonstratedsignificantly better Dice score and accuracy (p < 0.01). The method ispromising and can be useful in diagnosis and prognosis of AF.

Atrial Scar Quantification via Multi-scale CNN in the Graph-cuts Framework