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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Cardiac magnetic resonance imaging improves on diagnosis of cardiovasculardiseases by providing images at high spatiotemporal resolution. Manualevaluation of these time-series, however, is expensive and prone to biased andnon-reproducible outcomes. In this paper, we present a method that addressesnamed limitations by integrating segmentation and disease classification into afully automatic processing pipeline. We use an ensemble of UNet inspiredarchitectures for segmentation of cardiac structures such as the left and rightventricular cavity (LVC, RVC) and the left ventricular myocardium (LVM) on eachtime instance of the cardiac cycle. For the classification task, information isextracted from the segmented time-series in form of comprehensive featureshandcrafted to reflect diagnostic clinical procedures. Based on these featureswe train an ensemble of heavily regularized multilayer perceptrons (MLP) and arandom forest classifier to predict the pathologic target class. We evaluatedour method on the ACDC dataset (4 pathology groups, 1 healthy group) andachieve dice scores of 0.945 (LVC), 0.908 (RVC) and 0.905 (LVM) in across-validation over the training set (100 cases) and 0.950 (LVC), 0.923 (RVC)and 0.911 (LVM) on the test set (50 cases). We report a classification accuracyof 94% on a training set cross-validation and 92% on the test set. Our resultsunderpin the potential of machine learning methods for accurate, fast andreproducible segmentation and computer-assisted diagnosis (CAD).

Automatic Cardiac Disease Assessment on cine-MRI via Time-Series Segmentation and Domain Specific Features