Your browser doesn't support javascript.
On the Adoption of Radiomics and Formal Methods for COVID-19 Coronavirus Diagnosis.
Santone, Antonella; Belfiore, Maria Paola; Mercaldo, Francesco; Varriano, Giulia; Brunese, Luca.
  • Santone A; Department of Medicine and Health Sciences "Vincenzo Tiberio", University of Molise, 86100 Campobasso, Italy.
  • Belfiore MP; Department of Precision Medicine, University of Campania "Luigi Vanvitelli", 80138 Napoli, Italy.
  • Mercaldo F; Department of Medicine and Health Sciences "Vincenzo Tiberio", University of Molise, 86100 Campobasso, Italy.
  • Varriano G; Department of Medicine and Health Sciences "Vincenzo Tiberio", University of Molise, 86100 Campobasso, Italy.
  • Brunese L; Department of Medicine and Health Sciences "Vincenzo Tiberio", University of Molise, 86100 Campobasso, Italy.
Diagnostics (Basel) ; 11(2)2021 Feb 12.
Article in English | MEDLINE | ID: covidwho-1085112
ABSTRACT
Considering the current pandemic, caused by the spreading of the novel Coronavirus disease, there is the urgent need for methods to quickly and automatically diagnose infection. To assist pathologists and radiologists in the detection of the novel coronavirus, in this paper we propose a two-tiered method, based on formal methods (to the best of authors knowledge never previously introduced in this context), aimed to (i) detect whether the patient lungs are healthy or present a generic pulmonary infection; (ii) in the case of the previous tier, a generic pulmonary disease is detected to identify whether the patient under analysis is affected by the novel Coronavirus disease. The proposed approach relies on the extraction of radiomic features from medical images and on the generation of a formal model that can be automatically checked using the model checking technique. We perform an experimental analysis using a set of computed tomography medical images obtained by the authors, achieving an accuracy of higher than 81% in disease detection.
Keywords

Full text: Available Collection: International databases Database: MEDLINE Language: English Year: 2021 Document Type: Article Affiliation country: Diagnostics11020293

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Language: English Year: 2021 Document Type: Article Affiliation country: Diagnostics11020293