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

Curvilinear structure segmentation is important in medical imaging,quantifying structures such as vessels, airways, neurons, or organ boundariesin 2D slices. Segmentation via pixel-wise classification often fails to capturethe small and low-contrast curvilinear structures. Prior topologicalinformation is typically used to address this problem, often at an expensivecomputational cost, and sometimes requiring prior knowledge of the expectedtopology.  We present DTU-Net, a data-driven approach to topology-preserving curvilinearstructure segmentation. DTU-Net consists of two sequential, lightweight U-Nets,dedicated to texture and topology, respectively. While the texture net makes acoarse prediction using image texture information, the topology net learnstopological information from the coarse prediction by employing a triplet losstrained to recognize false and missed splits in the structure. We conductexperiments on a challenging multi-class ultrasound scan segmentation datasetas well as a well-known retinal imaging dataset. Results show that our modeloutperforms existing approaches in both pixel-wise segmentation accuracy andtopological continuity, with no need for prior topological knowledge.

DTU-Net: Learning Topological Similarity for Curvilinear Structure Segmentation