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

Population imaging studies rely upon good quality medical imagery beforedownstream image quantification. This study provides an automated approach toassess image quality from cardiovascular magnetic resonance (CMR) imaging atscale. We identify four common CMR imaging artefacts, including respiratorymotion, cardiac motion, Gibbs ringing, and aliasing. The model can deal withimages acquired in different views, including two, three, and four-chamberlong-axis and short-axis cine CMR images. Two deep learning-based models inspatial and frequency domains are proposed. Besides recognising theseartefacts, the proposed models are suitable to the common challenges of nothaving access to data labels. An unsupervised domain adaptation method and aFourier-based convolutional neural network are proposed to overcome thesechallenges. We show that the proposed models reliably allow for CMR imagequality assessment. The accuracies obtained for the spatial model in supervisedand weakly supervised learning are 99.41+0.24 and 96.37+0.66 for the UK Biobankdataset, respectively. Using unsupervised domain adaptation can somewhatovercome the challenge of not having access to the data labels. The maximumachieved domain gap coverage in unsupervised domain adaptation is 16.86%.Domain adaptation can significantly improve a 5-class classification task anddeal with considerable domain shift without data labels. Increasing the speedof training and testing can be achieved with the proposed model in thefrequency domain. The frequency-domain model can achieve the same accuracy yet1.548 times faster than the spatial model. This model can also be used directlyon k-space data, and there is no need for image reconstruction.

Automatic Multi-Class Cardiovascular Magnetic Resonance Image Quality  Assessment using Unsupervised Domain Adaptation in Spatial and Frequency  Domains