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

This paper presents a method for automatic segmentation, localization, andidentification of vertebrae in arbitrary 3D CT images. Many previous works donot perform the three tasks simultaneously even though requiring a prioriknowledge of which part of the anatomy is visible in the 3D CT images. Ourmethod tackles all these tasks in a single multi-stage framework without anyassumptions. In the first stage, we train a 3D Fully Convolutional Networks tofind the bounding boxes of the cervical, thoracic, and lumbar vertebrae. In thesecond stage, we train an iterative 3D Fully Convolutional Networks to segmentindividual vertebrae in the bounding box. The input to the second networks havean auxiliary channel in addition to the 3D CT images. Given the segmentedvertebra regions in the auxiliary channel, the networks output the nextvertebra. The proposed method is evaluated in terms of segmentation,localization, and identification accuracy with two public datasets of 15 3D CTimages from the MICCAI CSI 2014 workshop challenge and 302 3D CT images withvarious pathologies introduced in [1]. Our method achieved a mean Dice score of96%, a mean localization error of 8.3 mm, and a mean identification rate of84%. In summary, our method achieved better performance than all existing worksin all the three metrics.

Automatic Segmentation, Localization, and Identification of Vertebrae in 3D CT Images Using Cascaded Convolutional Neural Networks