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

Accurate and robust segmentation of abdominal organs on CT is essential formany clinical applications such as computer-aided diagnosis and computer-aidedsurgery. But this task is challenging due to the weak boundaries of organs, thecomplexity of the background, and the variable sizes of different organs. Toaddress these challenges, we introduce a novel framework for multi-organsegmentation by using organ-attention networks with reverse connections(OAN-RCs) which are applied to 2D views, of the 3D CT volume, and outputestimates which are combined by statistical fusion exploiting structuralsimilarity. OAN is a two-stage deep convolutional network, where deep networkfeatures from the first stage are combined with the original image, in a secondstage, to reduce the complex background and enhance the discriminativeinformation for the target organs. RCs are added to the first stage to give thelower layers semantic information thereby enabling them to adapt to the sizesof different organs. Our networks are trained on 2D views enabling us to useholistic information and allowing efficient computation. To compensate for thelimited cross-sectional information of the original 3D volumetric CT,multi-sectional images are reconstructed from the three different 2D viewdirections. Then we combine the segmentation results from the different viewsusing statistical fusion, with a novel term relating the structural similarityof the 2D views to the original 3D structure. To train the network and evaluateresults, 13 structures were manually annotated by four human raters andconfirmed by a senior expert on 236 normal cases. We tested our algorithm andcomputed Dice-Sorensen similarity coefficients and surface distances forevaluating our estimates of the 13 structures. Our experiments show that theproposed approach outperforms 2D- and 3D-patch based state-of-the-art methods.

Abdominal multi-organ segmentation with organ-attention networks and statistical fusion