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

Accurate identification and localization of the vertebrae in CT scans is acritical and standard preprocessing step for clinical spinal diagnosis andtreatment. Existing methods are mainly based on the integration of multipleneural networks, and most of them use the Gaussian heat map to locate thevertebrae's centroid. However, the process of obtaining the vertebrae'scentroid coordinates using heat maps is non-differentiable, so it is impossibleto train the network to label the vertebrae directly. Therefore, for end-to-enddifferential training of vertebra coordinates on CT scans, a robust andaccurate automatic vertebral labeling algorithm is proposed in this study.Firstly, a novel residual-based multi-label classification and localizationnetwork is developed, which can capture multi-scale features, but also utilizethe residual module and skip connection to fuse the multi-level features.Secondly, to solve the problem that the process of finding coordinates isnon-differentiable and the spatial structure is not destructible, integralregression module is used in the localization network. It combines theadvantages of heat map representation and direct regression coordinates toachieve end-to-end training, and can be compatible with any key point detectionmethods of medical image based on heat map. Finally, multi-label classificationof vertebrae is carried out, which use bidirectional long short term memory(Bi-LSTM) to enhance the learning of long contextual information to improve theclassification performance. The proposed method is evaluated on a challengingdataset and the results are significantly better than the state-of-the-artmethods (mean localization error <3mm).

Residual Block-based Multi-Label Classification and Localization Network with Integral Regression for Vertebrae Labeling