The SARS-CoV-2 is quickly spreading worldwide resulting in millions of infection and death cases. As a consequence, it is increasingly important to diagnose the presence of COVID-19 infection regardless of the technique applied. To this end, this work deals with the problem of COVID-19 classification using Computed Tomography (CT) images. Precisely, a new feature-based approach is proposed by exploiting axial CT lung acquisitions in order to differentiate COVID-19 versus healthy Computed Tomography (CT) images. In particular, first-order statistical measures as well as numerical quantities extracted from the autocorrelation function are investigated with the aim to provide an efficient classification process ensuring satisfactory performance results.

COVID-19 Lung CT Images Recognition: A Feature-Based Approach

Pallotta L.;
2021-01-01

Abstract

The SARS-CoV-2 is quickly spreading worldwide resulting in millions of infection and death cases. As a consequence, it is increasingly important to diagnose the presence of COVID-19 infection regardless of the technique applied. To this end, this work deals with the problem of COVID-19 classification using Computed Tomography (CT) images. Precisely, a new feature-based approach is proposed by exploiting axial CT lung acquisitions in order to differentiate COVID-19 versus healthy Computed Tomography (CT) images. In particular, first-order statistical measures as well as numerical quantities extracted from the autocorrelation function are investigated with the aim to provide an efficient classification process ensuring satisfactory performance results.
2021
978-3-030-93419-4
978-3-030-93420-0
File in questo prodotto:
File Dimensione Formato  
59_Losquadro_Ciarp_2021_Covid-19_Lung_CT_Images.pdf

accesso aperto

Descrizione: articolo principale
Tipologia: Documento in Post-print
Licenza: Creative commons
Dimensione 460.93 kB
Formato Adobe PDF
460.93 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11563/160788
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact