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

Segmentation of cardiac images, particularly late gadolinium-enhancedmagnetic resonance imaging (LGE-MRI) widely used for visualizing diseasedcardiac structures, is a crucial first step for clinical diagnosis andtreatment. However, direct segmentation of LGE-MRIs is challenging due to itsattenuated contrast. Since most clinical studies have relied on manual andlabor-intensive approaches, automatic methods are of high interest,particularly optimized machine learning approaches. To address this, weorganized the "2018 Left Atrium Segmentation Challenge" using 154 3D LGE-MRIs,currently the world's largest cardiac LGE-MRI dataset, and associated labels ofthe left atrium segmented by three medical experts, ultimately attracting theparticipation of 27 international teams. In this paper, extensive analysis ofthe submitted algorithms using technical and biological metrics was performedby undergoing subgroup analysis and conducting hyper-parameter analysis,offering an overall picture of the major design choices of convolutional neuralnetworks (CNNs) and practical considerations for achieving state-of-the-artleft atrium segmentation. Results show the top method achieved a dice score of93.2% and a mean surface to a surface distance of 0.7 mm, significantlyoutperforming prior state-of-the-art. Particularly, our analysis demonstratedthat double, sequentially used CNNs, in which a first CNN is used for automaticregion-of-interest localization and a subsequent CNN is used for refinedregional segmentation, achieved far superior results than traditional methodsand pipelines containing single CNNs. This large-scale benchmarking study makesa significant step towards much-improved segmentation methods for cardiacLGE-MRIs, and will serve as an important benchmark for evaluating and comparingthe future works in the field.

A Global Benchmark of Algorithms for Segmenting Late Gadolinium-Enhanced Cardiac Magnetic Resonance Imaging