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

COVID-19 infection caused by SARS-CoV-2 pathogen is a catastrophic pandemicoutbreak all over the world with exponential increasing of confirmed cases and,unfortunately, deaths. In this work we propose an AI-powered pipeline, based onthe deep-learning paradigm, for automated COVID-19 detection and lesioncategorization from CT scans. We first propose a new segmentation module aimedat identifying automatically lung parenchyma and lobes. Next, we combined suchsegmentation network with classification networks for COVID-19 identificationand lesion categorization. We compare the obtained classification results withthose obtained by three expert radiologists on a dataset consisting of 162 CTscans. Results showed a sensitivity of 90\% and a specificity of 93.5% forCOVID-19 detection, outperforming those yielded by the expert radiologists, andan average lesion categorization accuracy of over 84%. Results also show that asignificant role is played by prior lung and lobe segmentation that allowed usto enhance performance by over 20 percent points. The interpretation of thetrained AI models, moreover, reveals that the most significant areas forsupporting the decision on COVID-19 identification are consistent with thelesions clinically associated to the virus, i.e., crazy paving, consolidationand ground glass. This means that the artificial models are able todiscriminate a positive patient from a negative one (both controls and patientswith interstitial pneumonia tested negative to COVID) by evaluating thepresence of those lesions into CT scans. Finally, the AI models are integratedinto a user-friendly GUI to support AI explainability for radiologists, whichis publicly available at http://perceivelab.com/covid-ai.

An Explainable AI System for Automated COVID-19 Assessment and Lesion Categorization from CT-scans