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 Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Precise segmentation and anatomical identification of the vertebrae providesthe basis for automatic analysis of the spine, such as detection of vertebralcompression fractures or other abnormalities. Most dedicated spine CT and MRscans as well as scans of the chest, abdomen or neck cover only part of thespine. Segmentation and identification should therefore not rely on thevisibility of certain vertebrae or a certain number of vertebrae. We propose aniterative instance segmentation approach that uses a fully convolutional neuralnetwork to segment and label vertebrae one after the other, independently ofthe number of visible vertebrae. This instance-by-instance segmentation isenabled by combining the network with a memory component that retainsinformation about already segmented vertebrae. The network iteratively analyzesimage patches, using information from both image and memory to search for thenext vertebra. To efficiently traverse the image, we include the priorknowledge that the vertebrae are always located next to each other, which isused to follow the vertebral column. This method was evaluated with fivediverse datasets, including multiple modalities (CT and MR), various fields ofview and coverages of different sections of the spine, and a particularlychallenging set of low-dose chest CT scans. The proposed iterative segmentationmethod compares favorably with state-of-the-art methods and is fast, flexibleand generalizable.

Iterative fully convolutional neural networks for automatic vertebra segmentation and identification