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

Multi-sequence cardiac magnetic resonance (CMR) provides essential pathologyinformation (scar and edema) to diagnose myocardial infarction. However,automatic pathology segmentation can be challenging due to the difficulty ofeffectively exploring the underlying information from the multi-sequence CMRdata. This paper aims to tackle the scar and edema segmentation frommulti-sequence CMR with a novel auto-weighted supervision framework, where theinteractions among different supervised layers are explored under atask-specific objective using reinforcement learning. Furthermore, we design acoarse-to-fine framework to boost the small myocardial pathology regionsegmentation with shape prior knowledge. The coarse segmentation modelidentifies the left ventricle myocardial structure as a shape prior, while thefine segmentation model integrates a pixel-wise attention strategy with anauto-weighted supervision model to learn and extract salient pathologicalstructures from the multi-sequence CMR data. Extensive experimental results ona publicly available dataset from Myocardial pathology segmentation combiningmulti-sequence CMR (MyoPS 2020) demonstrate our method can achieve promisingperformance compared with other state-of-the-art methods. Our method ispromising in advancing the myocardial pathology assessment on multi-sequenceCMR data. To motivate the community, we have made our code publicly availablevia https://github.com/soleilssss/AWSnet/tree/master.

AWSnet: An Auto-weighted Supervision Attention Network for Myocardial  Scar and Edema Segmentation in Multi-sequence Cardiac Magnetic Resonance  Images