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

Assessment of cardiovascular disease (CVD) with cine magnetic resonanceimaging (MRI) has been used to non-invasively evaluate detailed cardiacstructure and function. Accurate segmentation of cardiac structures from cineMRI is a crucial step for early diagnosis and prognosis of CVD, and has beengreatly improved with convolutional neural networks (CNN). There, however, area number of limitations identified in CNN models, such as limitedinterpretability and high complexity, thus limiting their use in clinicalpractice. In this work, to address the limitations, we propose a lightweightand interpretable machine learning model, successive subspace learning with thesubspace approximation with adjusted bias (Saab) transform, for accurate andefficient segmentation from cine MRI. Specifically, our segmentation frameworkis comprised of the following steps: (1) sequential expansion of near-to-farneighborhood at different resolutions; (2) channel-wise subspace approximationusing the Saab transform for unsupervised dimension reduction; (3) class-wiseentropy guided feature selection for supervised dimension reduction; (4)concatenation of features and pixel-wise classification with gradient boost;and (5) conditional random field for post-processing. Experimental results onthe ACDC 2017 segmentation database, showed that our framework performed betterthan state-of-the-art U-Net models with 200$\times$ fewer parameters indelineating the left ventricle, right ventricle, and myocardium, thus showingits potential to be used in clinical practice.

Segmentation of Cardiac Structures via Successive Subspace Learning with Saab Transform from Cine MRI