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

Understanding chest CT imaging of the coronavirus disease 2019 (COVID-19)will help detect infections early and assess the disease progression.Especially, automated severity assessment of COVID-19 in CT images plays anessential role in identifying cases that are in great need of intensiveclinical care. However, it is often challenging to accurately assess theseverity of this disease in CT images, due to variable infection regions in thelungs, similar imaging biomarkers, and large inter-case variations. To thisend, we propose a synergistic learning framework for automated severityassessment of COVID-19 in 3D CT images, by jointly performing lung lobesegmentation and multi-instance classification. Considering that only a fewinfection regions in a CT image are related to the severity assessment, wefirst represent each input image by a bag that contains a set of 2D imagepatches (with each cropped from a specific slice). A multi-task multi-instancedeep network (called M$^2$UNet) is then developed to assess the severity ofCOVID-19 patients and also segment the lung lobe simultaneously. Our M$^2$UNetconsists of a patch-level encoder, a segmentation sub-network for lung lobesegmentation, and a classification sub-network for severity assessment (with aunique hierarchical multi-instance learning strategy). Here, the contextinformation provided by segmentation can be implicitly employed to improve theperformance of severity assessment. Extensive experiments were performed on areal COVID-19 CT image dataset consisting of 666 chest CT images, with resultssuggesting the effectiveness of our proposed method compared to severalstate-of-the-art methods.

Synergistic Learning of Lung Lobe Segmentation and Hierarchical  Multi-Instance Classification for Automated Severity Assessment of COVID-19  in CT Images