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

This paper proposes a novel framework for lung segmentation in chest X-rays.It consists of two key contributions, a criss-cross attention basedsegmentation network and radiorealistic chest X-ray image synthesis (i.e. asynthesized radiograph that appears anatomically realistic) for dataaugmentation. The criss-cross attention modules capture rich global contextualinformation in both horizontal and vertical directions for all the pixels thusfacilitating accurate lung segmentation. To reduce the manual annotation burdenand to train a robust lung segmentor that can be adapted to pathological lungswith hazy lung boundaries, an image-to-image translation module is employed tosynthesize radiorealistic abnormal CXRs from the source of normal ones for dataaugmentation. The lung masks of synthetic abnormal CXRs are propagated from thesegmentation results of their normal counterparts, and then serve as pseudomasks for robust segmentor training. In addition, we annotate 100 CXRs withlung masks on a more challenging NIH Chest X-ray dataset containing bothposterioranterior and anteroposterior views for evaluation. Extensiveexperiments validate the robustness and effectiveness of the proposedframework. The code and data can be found fromhttps://github.com/rsummers11/CADLab/tree/master/Lung_Segmentation_XLSor .

XLSor: A Robust and Accurate Lung Segmentor on Chest X-Rays Using Criss-Cross Attention and Customized Radiorealistic Abnormalities Generation