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

Current standard protocols used in the clinic for diagnosing COVID-19 includemolecular or antigen tests, generally complemented by a plain chest X-Ray. Thecombined analysis aims to reduce the significant number of false negatives ofthese tests, but also to provide complementary evidence about the presence andseverity of the disease. However, the procedure is not free of errors, and theinterpretation of the chest X-Ray is only restricted to radiologists due to itscomplexity. With the long term goal to provide new evidence for the diagnosis,this paper presents an evaluation of different methods based on a deep neuralnetwork. These are the first steps to develop an automatic COVID-19 diagnosistool using chest X-Ray images, that would additionally differentiate betweencontrols, pneumonia or COVID-19 groups. The paper describes the processfollowed to train a Convolutional Neural Network with a dataset of more than79,500 X-Ray images compiled from different sources, including more than 8,500COVID-19 examples. For the sake of evaluation and comparison of the modelsdeveloped, three different experiments were carried out following threepreprocessing schemes. The aim is to evaluate how preprocessing the dataaffects the results and improves its explainability. Likewise, a criticalanalysis is carried out about different variability issues that mightcompromise the system and the effects on the performance. With the employedmethodology, a 91.5% classification accuracy is obtained, with a 87.4% averagerecall for the worst but most explainable experiment, which requires a previousautomatic segmentation of the lungs region.

Artificial Intelligence applied to chest X-Ray images for the automatic detection of COVID-19. A thoughtful evaluation approach