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/

Zendy Plus

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

Zendy Tools

Zendy Open

As an important upstream task for many medical applications, supervisedlandmark localization still requires non-negligible annotation costs to achievedesirable performance. Besides, due to cumbersome collection procedures, thelimited size of medical landmark datasets impacts the effectiveness oflarge-scale self-supervised pre-training methods. To address these challenges,we propose a two-stage framework for one-shot medical landmark localization,which first infers landmarks by unsupervised registration from the labeledexemplar to unlabeled targets, and then utilizes these noisy pseudo labels totrain robust detectors. To handle the significant structure variations, welearn an end-to-end cascade of global alignment and local deformations, underthe guidance of novel loss functions which incorporate edge information. Instage II, we explore self-consistency for selecting reliable pseudo labels andcross-consistency for semi-supervised learning. Our method achievesstate-of-the-art performances on public datasets of different body parts, whichdemonstrates its general applicability.

One-Shot Medical Landmark Localization by Edge-Guided Transform and Noisy Landmark Refinement