COVID-19 disease is a public health problem worldwide. Different studies proved that Computed Tomography (CT) brings quantitative information facilitating the prediction of the clinical course of the disease. In this work, we exploited the LungQuant software we previously developed to segment COVID-19 lesions on chest CT scans. We built a Machine Learning (ML) pipeline that, from the radiomic features extracted from lesions, can predict the evolution of the disease for the patient, by distinguishing severe (intubated/died) from not severe outcomes.
COVID-19 SEVERITY PREDICTION BASED ON RADIOMIC FEATURES EXTRACTED FROM LUNG CT SCANS USING THE LUNGQUANT SEGMENTATION SOFTWARE
Scapicchio, C.
Primo
;Fanni, S. C.;Fantacci, M. E.;Lascialfari, A.;Lizzi, F.;Ubaldi, L.;
2023-01-01
Abstract
COVID-19 disease is a public health problem worldwide. Different studies proved that Computed Tomography (CT) brings quantitative information facilitating the prediction of the clinical course of the disease. In this work, we exploited the LungQuant software we previously developed to segment COVID-19 lesions on chest CT scans. We built a Machine Learning (ML) pipeline that, from the radiomic features extracted from lesions, can predict the evolution of the disease for the patient, by distinguishing severe (intubated/died) from not severe outcomes.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
