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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Automatically identifying the structural substrates underlying cardiacabnormalities can potentially provide real-time guidance for interventionalprocedures. With the knowledge of cardiac tissue substrates, the treatment ofcomplex arrhythmias such as atrial fibrillation and ventricular tachycardia canbe further optimized by detecting arrhythmia substrates to target for treatment(i.e., adipose) and identifying critical structures to avoid. Optical coherencetomography (OCT) is a real-time imaging modality that aids in addressing thisneed. Existing approaches for cardiac image analysis mainly rely on fullysupervised learning techniques, which suffer from the drawback of workload onlabor-intensive annotation process of pixel-wise labeling. To lessen the needfor pixel-wise labeling, we develop a two-stage deep learning framework forcardiac adipose tissue segmentation using image-level annotations on OCT imagesof human cardiac substrates. In particular, we integrate class activationmapping with superpixel segmentation to solve the sparse tissue seed challengeraised in cardiac tissue segmentation. Our study bridges the gap between thedemand on automatic tissue analysis and the lack of high-quality pixel-wiseannotations. To the best of our knowledge, this is the first study thatattempts to address cardiac tissue segmentation on OCT images via weaklysupervised learning techniques. Within an in-vitro human cardiac OCT dataset,we demonstrate that our weakly supervised approach on image-level annotationsachieves comparable performance as fully supervised methods trained onpixel-wise annotations.

Cardiac Adipose Tissue Segmentation via Image-Level Annotations