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

Automated methods for Cobb angle estimation are of high demand for scoliosisassessment. Existing methods typically calculate the Cobb angle from landmarkestimation, or simply combine the low-level task (e.g., landmark detection andspine segmentation) with the Cobb angle regression task, without fullyexploring the benefits from each other. In this study, we propose a novelmulti-task framework, named Seg4Reg+, which jointly optimizes the segmentationand regression networks. We thoroughly investigate both local and globalconsistency and knowledge transfer between each other. Specifically, we proposean attention regularization module leveraging class activation maps (CAMs) fromimage-segmentation pairs to discover additional supervision in the regressionnetwork, and the CAMs can serve as a region-of-interest enhancement gate tofacilitate the segmentation task in turn. Meanwhile, we design a novel triangleconsistency learning to train the two networks jointly for global optimization.The evaluations performed on the public AASCE Challenge dataset demonstrate theeffectiveness of each module and superior performance of our model to thestate-of-the-art methods.

Seg4Reg+: Consistency Learning between Spine Segmentation and Cobb Angle Regression