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

Detailed pulmonary airway segmentation is a clinically important task forendobronchial intervention and treatment of peripheral located lung cancerlesions. Convolutional Neural Networks (CNNs) are promising tools for medicalimage analysis but have been performing poorly for cases when existing asignificant imbalanced feature distribution, which is true for the airway dataas the trachea and principal bronchi dominate most of the voxels whereas thelobar bronchi and distal segmental bronchi occupy a small proportion. In thispaper, we propose a Differentiable Topology-Preserved Distance Transform(DTPDT) framework to improve the performance of airway segmentation. ATopology-Preserved Surrogate (TPS) learning strategy is first proposed tobalance the training progress within-class distribution. Furthermore, aConvolutional Distance Transform (CDT) is designed to identify the breakagephenomenon with superior sensitivity and minimize the variation of the distancemap between the predictionand ground-truth. The proposed method is validatedwith the publically available reference airway segmentation datasets. Thedetected rate of branch and length on public EXACT'09 and BAS datasets are82.1%/79.6% and 96.5%/91.5% respectively, demonstrating the reliability andefficiency of the method in terms of improving the topology completeness of thesegmentation performance while maintaining the overall topology accuracy.

Differentiable Topology-Preserved Distance Transform for Pulmonary Airway Segmentation