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

Vessel segmentation and centerline extraction are two crucial preliminarytasks for many computer-aided diagnosis tools dealing with vascular diseases.Recently, deep-learning based methods have been widely applied to these tasks.However, classic deep-learning approaches struggle to capture the complexgeometry and specific topology of vascular networks, which is of the utmostimportance in most applications. To overcome these limitations, the clDiceloss, a topological loss that focuses on the vessel centerlines, has beenrecently proposed. This loss requires computing, with a proposed soft-skeletonalgorithm, the skeletons of both the ground truth and the predictedsegmentation. However, the soft-skeleton algorithm provides suboptimal resultson 3D images, which makes the clDice hardly suitable on 3D images. In thispaper, we propose to replace the soft-skeleton algorithm by a U-Net whichcomputes the vascular skeleton directly from the segmentation. We show that ourmethod provides more accurate skeletons than the soft-skeleton algorithm. Wethen build upon this network a cascaded U-Net trained with the clDice loss toembed topological constraints during the segmentation. The resulting model isable to predict both the vessel segmentation and centerlines with a moreaccurate topology.

Cascaded multitask U-Net using topological loss for vessel segmentation and centerline extraction