This site exploits session and third parties cookies. Pressing on 'Accept' button, you accept cookie usage. For further information click Cookie Policy button

  • Banner


An optimised path for the data flow and the clinical management of COVID-19 patients

Funded under: Regione Toscana Bando COVID 19

Start date 26 February 2021     End date 25 February 2023

Keywords: COVID-19, Deep Learning, Computed Tomography, Radiomics

The uniqueness and complexity of the SARS-CoV-2 disease still pose many critical challenges for the clinical care and management of COVID-19 patients. Many hospitals have struggled to find effective approaches to treat the infected citizens, as there were no tools to predict the evolution and the impact of the disease. The diagnostic test, based on the detection of the viral RNA by real-time PCR, does not provide any piece of information on the severity and the effects of the disease. In addition, the lack of “solid” evidence on the pathology has led to fragmented and inhomogeneous patients management. In some sites, as for instance at the Emergency Department of the Azienda USL Toscana Centro, the clinical and laboratory evaluation was coupled with a standard chest X-ray, whilst in other sites, as for instance at the University Hospital of Pisa, patients underwent also a chest computed tomography and a lung ultrasound exam. These diverse diagnostic approaches have jeopardized the collection of data on the regional territories, and now pose the need for a careful analysis of the most effective procedure with respect to the clinical manifestation of the disease.

In this complex scenario, OPTIMISED will work to create a path for managing the data flow of COVID-19 patients, based on a careful analysis of the retrospective imaging and clinical data. The analysis will serve to determine the potential and limits of the different imaging techniques as well as the role of innovative blood parameters. The knowledge acquired and integrated during the project will lead to a prognostic model based on risk stratification and to effective recommendations for healthcare professionals about the most suitable patient management procedures.

The OPTIMISED path will be conceived to be easily exportable to other hospitals both in Tuscany and other regions, thus supporting the management of the current peaks of COVID-19, but also in anticipation of other future pandemics.

ISTI-CNR is involved with the Signals & Images Lab. The team will work to design and train deep learning models able to segment and label computed tomography images of COVID-19 patients. Further to this, the SILab researchers will contribute to the radiomics analysis of the imaging data and to the definition of the risk stratification model.