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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The coronavirus disease (COVID-19) has resulted in a pandemic crippling the abreadth of services critical to daily life. Segmentation of lung infections incomputerized tomography (CT) slices could be be used to improve diagnosis andunderstanding of COVID-19 in patients. Deep learning systems lackinterpretability because of their black box nature. Inspired by humancommunication of complex ideas through language, we propose a symbolicframework based on emergent languages for the segmentation of COVID-19infections in CT scans of lungs. We model the cooperation between twoartificial agents - a Sender and a Receiver. These agents synergisticallycooperate using emergent symbolic language to solve the task of semanticsegmentation. Our game theoretic approach is to model the cooperation betweenagents unlike Generative Adversarial Networks (GANs). The Sender retrievesinformation from one of the higher layers of the deep network and generates asymbolic sentence sampled from a categorical distribution of vocabularies. TheReceiver ingests the stream of symbols and cogenerates the segmentation mask. Aprivate emergent language is developed that forms the communication channelused to describe the task of segmentation of COVID infections. We augmentexisting state of the art semantic segmentation architectures with our symbolicgenerator to form symbolic segmentation models. Our symbolic segmentationframework achieves state of the art performance for segmentation of lunginfections caused by COVID-19. Our results show direct interpretation ofsymbolic sentences to discriminate between normal and infected regions,infection morphology and image characteristics. We show state of the artresults for segmentation of COVID-19 lung infections in CT.

Symbolic Semantic Segmentation and Interpretation of COVID-19 Lung Infections in Chest CT volumes based on Emergent Languages