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

Vertebral landmark localization is a crucial step for variant spine-relatedclinical applications, which requires detecting the corner points of 17vertebrae. However, the neighbor landmarks often disturb each other for thehomogeneous appearance of vertebrae, which makes vertebral landmarklocalization extremely difficult. In this paper, we propose multi-stagecascaded convolutional neural networks (CNNs) to split the single task into twosequential steps, i.e., center point localization to roughly locate 17 centerpoints of vertebrae, and corner point localization to find 4 corner points foreach vertebra without distracted by others. Landmarks in each step are locatedgradually from a set of initialized points by regressing offsets via cascadedCNNs. Principal Component Analysis (PCA) is employed to preserve a shapeconstraint in offset regression to resist the mutual attraction of vertebrae.We evaluate our method on the AASCE dataset that consists of 609 tight spinalanterior-posterior X-ray images and each image contains 17 vertebrae composedof the thoracic and lumbar spine for spinal shape characterization.Experimental results demonstrate our superior performance of vertebral landmarklocalization over other state-of-the-arts with the relative error decreasingfrom 3.2e-3 to 7.2e-4.

Accurate Scoliosis Vertebral Landmark Localization on X-ray Images via Shape-constrained Multi-stage Cascaded CNNs