March 11, 2021
In response to the evolving COVID-19 pandemic, Fandango consortium members allocate technologies and data to support research that will provide insights during these challenging times.
CERTH (The Centre for Research and Technology - Hellas) has contributed to and published a new paper that uses concepts and knowledge from Fandango’s research in video processing for deep-fakes for effective and efficient Computed Tomography (CT)-based risk assessment to improve treatment patient care. This article introduces a data-driven approach built on top of volume-of-interest aware deep neural networks for automatic COVID-19 patient risk assessment (discharged, hospitalized, intensive care unit) based on lung infection quantization through segmentation and, subsequently, CT classification.
This article belongs to the Special Issue Deep Learning: AI Steps Up in Battle against COVID-19. It has been partially funded by Fandango and private funds of the Humanitas Research Hospital.
Chatzitofis, A.; Cancian, P.; Gkitsas, V.; Carlucci, A.; Stalidis, P.; Albanis, G.; Karakottas, A.; Semertzidis, T.; Daras, P.; Giannitto, C.; Casiraghi, E.; Sposta, F.M.; Vatteroni, G.; Ammirabile, A.; Lofino, L.; Ragucci, P.; Laino, M.E.; Voza, A.; Desai, A.; Cecconi, M.; Balzarini, L.; Chiti, A.; Zarpalas, D.; Savevski, V. Volume-of-Interest Aware Deep Neural Networks for Rapid Chest CT-Based COVID-19 Patient Risk Assessment. Int. J. Environ. Res. Public Health 2021, 18, 2842. https://doi.org/10.3390/ijerph18062842