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

The shape and motion of the heart provide essential clues to understandingthe mechanisms of cardiovascular disease. With the advent of large-scalecardiac imaging data, statistical atlases become a powerful tool to provideautomated and precise quantification of the status of patient-specific heartgeometry with respect to reference populations. The Multi-Ethnic Study ofAtherosclerosis (MESA), begun in 2000, was the first large cohort study toincorporate cardiovascular MRI in over 5000 participants, and there is now awealth of follow-up data over 20 years. Building a machine learning basedautomated analysis is necessary to extract the additional imaging informationnecessary for expanding original manual analyses. However, machine learningtools trained on MRI datasets with different pulse sequences fail on suchlegacy datasets. Here, we describe an automated atlas construction pipelineusing deep learning methods applied to the legacy cardiac MRI data in MESA. Fordetection of anatomical cardiac landmark points, a modified VGGNetconvolutional neural network architecture was used in conjunction with atransfer learning sequence between two-chamber, four-chamber, and short-axisMRI views. A U-Net architecture was used for detection of the endocardial andepicardial boundaries in short axis images. Both network architectures resultedin good segmentation and landmark detection accuracies compared withinter-observer variations. Statistical relationships with common risk factorswere similar between atlases derived from automated vs manual annotations. Theautomated atlas can be employed in future studies to examine the relationshipsbetween cardiac morphology and future events.

Deep Learning Analysis of Cardiac MRI in Legacy Datasets: Multi-Ethnic Study of Atherosclerosis