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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The Cobb angle that quantitatively evaluates the spinal curvature plays animportant role in the scoliosis diagnosis and treatment. Conventionalmeasurement of these angles suffers from huge variability and low reliabilitydue to intensive manual intervention. However, since there exist high ambiguityand variability around boundaries of vertebrae, it is challenging to obtainCobb angles automatically. In this paper, we formulate the estimation of theCobb angles from spinal X-rays as a multi-output regression task. We proposestructured support vector regression (S^2VR) to jointly estimate Cobb anglesand landmarks of the spine in X-rays in one single framework. The proposedS^2VR can faithfully handle the nonlinear relationship between input images andquantitative outputs, while explicitly capturing the intrinsic correlation ofoutputs. We introduce the manifold regularization to exploit the geometry ofthe output space. We propose learning the kernel in S2VR by kernel targetalignment to enhance its discriminative ability. The proposed method isevaluated on the spinal X-rays dataset of 439 scoliosis subjects, whichachieves the inspiring correlation coefficient of 92.76% with ground truthobtained manually by human experts and outperforms two baseline methods. Ourmethod achieves the direct estimation of Cobb angles with high accuracy, whichindicates its great potential in clinical use.

Direct Estimation of Spinal Cobb Angles by Structured Multi-Output Regression