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

Digital subtraction angiography (DSA) is universally acknowledged as the goldstandard for examining lesion angioarchitecture, elucidating arterial bloodsupply dynamics, and guiding endovascular interventions. The automaticsegmentation of intracranial arteries (IA) in DSA, which is pivotal forquantifying vascular morphology, plays an essential role in computer-assistedstroke research and clinical practices. Nevertheless, research in this specificdomain remains constrained, primarily owing to the unavailability of publiclydatasets for IA segmentation within the research community. Currently, thepredominant focus of methodologies lies in the segmentation of single-frame DSAusing in-house datasets. These methods, limited by the partial inclusion ofcontrast in single-frame DSA, encounters challenges in rendering a preciserepresentation of vascular structures. In this paper, we introduces DIAS, adataset specifically developed for IA segmentation in DSA sequences. Acomprehensive benchmark has been established for evaluating DIAS, coveringfully, weakly, and semi-supervised segmentation methods. Specifically, wepropose a vessel sequence segmentation network that captures the spatiotemporalrepresentation of intravascular contrast for segmenting vessels in DSAsequences. For weakly-supervised learning, we propose a novel scribblelearning-based image segmentation framework, incorporating both scribblesupervision and consistency regularization. Furthermore, we introduce a randompatch-based self-training framework that harnesses unlabeled DSA sequences toimprove segmentation performance. Our extensive experiments on the DIAS datasetdemonstrate the effectiveness of these methods as potential baselines forfuture research and clinical applications.

DIAS: A Dataset and Benchmark for Intracranial Artery Segmentation in DSA sequences