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

A "heart attack" or myocardial infarction (MI), occurs when an arterysupplying blood to the heart is abruptly occluded. The "gold standard" methodfor imaging MI is Cardiovascular Magnetic Resonance Imaging (MRI), withintravenously administered gadolinium-based contrast (late gadoliniumenhancement). However, no "gold standard" fully automated method for thequantification of MI exists. In this work, we propose an end-to-end fullyautomatic system (MyI-Net) for the detection and quantification of MI in MRIimages. This has the potential to reduce the uncertainty due to the technicalvariability across labs and inherent problems of the data and labels. Oursystem consists of four processing stages designed to maintain the flow ofinformation across scales. First, features from raw MRI images are generatedusing feature extractors built on ResNet and MoblieNet architectures. This isfollowed by the Atrous Spatial Pyramid Pooling (ASPP) to produce spatialinformation at different scales to preserve more image context. High-levelfeatures from ASPP and initial low-level features are concatenated at the thirdstage and then passed to the fourth stage where spatial information isrecovered via up-sampling to produce final image segmentation output into: i)background, ii) heart muscle, iii) blood and iv) scar areas. New models werecompared with state-of-art models and manual quantification. Our models showedfavorable performance in global segmentation and scar tissue detection relativeto state-of-the-art work, including a four-fold better performance in matchingscar pixels to contours produced by clinicians.

MyI-Net: Fully Automatic Detection and Quantification of Myocardial Infarction from Cardiovascular MRI Images