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

Magnetic resonance angiography (MRA) is an imaging modality for visualisingblood vessels. It is useful for several diagnostic applications and forassessing the risk of adverse events such as haemorrhagic stroke (resultingfrom the rupture of aneurysms in blood vessels). However, MRAs are not acquiredroutinely, hence, an approach to synthesise blood vessel segmentations frommore routinely acquired MR contrasts such as T1 and T2, would be useful. Wepresent an encoder-decoder model for synthesising segmentations of the maincerebral arteries in the circle of Willis (CoW) from only T2 MRI. We propose atwo-phase multi-objective learning approach, which captures both global andlocal features. It uses learned local attention maps generated by dilating thesegmentation labels, which forces the network to only extract information fromthe T2 MRI relevant to synthesising the CoW. Our synthetic vessel segmentationsgenerated from only T2 MRI achieved a mean Dice score of $0.79 \pm 0.03$ intesting, compared to state-of-the-art segmentation networks such as transformerU-Net ($0.71 \pm 0.04$) and nnU-net($0.68 \pm 0.05$), while using only afraction of the parameters. The main qualitative difference between oursynthetic vessel segmentations and the comparative models was in the sharperresolution of the CoW vessel segments, especially in the posterior circulation.

Learned Local Attention Maps for Synthesising Vessel Segmentations