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

Purpose: to optimize a pipeline of clinical data gathering and CT imagesprocessing implemented during the COVID-19 pandemic crisis and to developartificial intelligence model for different of viral pneumonia. Methods: 1028chest CT image of patients with positive swab were segmented automatically forlung extraction. A Gaussian model developed in Python language was applied tocalculate quantitative metrics (QM) describing well-aerated and ill portions ofthe lungs from the histogram distribution of lung CT numbers in both lungs ofeach image and in four geometrical subdivision. Furthermore, radiomic features(RF) of first and second order were extracted from bilateral lungs usingPyRadiomic tools. QM and RF were used to develop 4 different Multi-LayerPerceptron (MLP) classifier to discriminate images of patients with COVID(n=646) and non-COVID (n=382) viral pneumonia. Results: The Gaussian modelapplied to lung CT histogram correctly described healthy parenchyma 94% of thepatients. The resulting accuracy of the models for COVID diagnosis were in therange 0.76-0.87, as the integral of the receiver operating curve. The bestdiagnostic performances were associated to the model based on RF of first andsecond order, with 21 relevant features after LASSO regression and an accuracyof 0.81$\pm$0.02 after 4-fold cross validation Conclusions: Despite theseresults were obtained with CT images from a single center, a platform forextracting useful quantitative metrics from CT images was developed andoptimized. Four artificial intelligence-based models for classifying patientswith COVID and non-COVID viral pneumonia were developed and compared showingoverall good diagnostic performances

A framework for quantitative analysis of Computed Tomography images of viral pneumonitis: radiomic features in COVID and non-COVID patients