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

Training deep learning models on cardiac magnetic resonance imaging (CMR) canbe a challenge due to the small amount of expert generated labels and inherentcomplexity of data source. Self-supervised contrastive learning (SSCL) hasrecently been shown to boost performance in several medical imaging tasks.However, it is unclear how much the pre-trained representation reflects theprimary organ of interest compared to spurious surrounding tissue. In thiswork, we evaluate the optimal method of incorporating prior knowledge ofanatomy into a SSCL training paradigm. Specifically, we evaluate using asegmentation network to explicitly local the heart in CMR images, followed bySSCL pretraining in multiple diagnostic tasks. We find that using a prioriknowledge of anatomy can greatly improve the downstream diagnostic performance.Furthermore, SSCL pre-training with in-domain data generally improveddownstream performance and more human-like saliency compared to end-to-endtraining and ImageNet pre-trained networks. However, introducing anatomicknowledge to pre-training generally does not have significant impact.

Interaction of a priori Anatomic Knowledge with Self-Supervised Contrastive Learning in Cardiac Magnetic Resonance Imaging