Cargando…

Volume-of-Interest Aware Deep Neural Networks for Rapid Chest CT-Based COVID-19 Patient Risk Assessment

Since December 2019, the world has been devastated by the Coronavirus Disease 2019 (COVID-19) pandemic. Emergency Departments have been experiencing situations of urgency where clinical experts, without long experience and mature means in the fight against COVID-19, have to rapidly decide the most p...

Descripción completa

Detalles Bibliográficos
Autores principales: Chatzitofis, Anargyros, Cancian, Pierandrea, Gkitsas, Vasileios, Carlucci, Alessandro, Stalidis, Panagiotis, Albanis, Georgios, Karakottas, Antonis, Semertzidis, Theodoros, Daras, Petros, Giannitto, Caterina, Casiraghi, Elena, Sposta, Federica Mrakic, Vatteroni, Giulia, Ammirabile, Angela, Lofino, Ludovica, Ragucci, Pasquala, Laino, Maria Elena, Voza, Antonio, Desai, Antonio, Cecconi, Maurizio, Balzarini, Luca, Chiti, Arturo, Zarpalas, Dimitrios, Savevski, Victor
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7998401/
https://www.ncbi.nlm.nih.gov/pubmed/33799509
http://dx.doi.org/10.3390/ijerph18062842
_version_ 1783670543495462912
author Chatzitofis, Anargyros
Cancian, Pierandrea
Gkitsas, Vasileios
Carlucci, Alessandro
Stalidis, Panagiotis
Albanis, Georgios
Karakottas, Antonis
Semertzidis, Theodoros
Daras, Petros
Giannitto, Caterina
Casiraghi, Elena
Sposta, Federica Mrakic
Vatteroni, Giulia
Ammirabile, Angela
Lofino, Ludovica
Ragucci, Pasquala
Laino, Maria Elena
Voza, Antonio
Desai, Antonio
Cecconi, Maurizio
Balzarini, Luca
Chiti, Arturo
Zarpalas, Dimitrios
Savevski, Victor
author_facet Chatzitofis, Anargyros
Cancian, Pierandrea
Gkitsas, Vasileios
Carlucci, Alessandro
Stalidis, Panagiotis
Albanis, Georgios
Karakottas, Antonis
Semertzidis, Theodoros
Daras, Petros
Giannitto, Caterina
Casiraghi, Elena
Sposta, Federica Mrakic
Vatteroni, Giulia
Ammirabile, Angela
Lofino, Ludovica
Ragucci, Pasquala
Laino, Maria Elena
Voza, Antonio
Desai, Antonio
Cecconi, Maurizio
Balzarini, Luca
Chiti, Arturo
Zarpalas, Dimitrios
Savevski, Victor
author_sort Chatzitofis, Anargyros
collection PubMed
description Since December 2019, the world has been devastated by the Coronavirus Disease 2019 (COVID-19) pandemic. Emergency Departments have been experiencing situations of urgency where clinical experts, without long experience and mature means in the fight against COVID-19, have to rapidly decide the most proper patient treatment. In this context, we introduce an artificially intelligent tool for effective and efficient Computed Tomography (CT)-based risk assessment to improve treatment and patient care. In this paper, we introduce 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. We tackle the high and varying dimensionality of the CT input by detecting and analyzing only a sub-volume of the CT, the Volume-of-Interest (VoI). Differently from recent strategies that consider infected CT slices without requiring any spatial coherency between them, or use the whole lung volume by applying abrupt and lossy volume down-sampling, we assess only the “most infected volume” composed of slices at its original spatial resolution. To achieve the above, we create, present and publish a new labeled and annotated CT dataset with 626 CT samples from COVID-19 patients. The comparison against such strategies proves the effectiveness of our VoI-based approach. We achieve remarkable performance on patient risk assessment evaluated on balanced data by reaching 88.88%, 89.77%, 94.73% and 88.88% accuracy, sensitivity, specificity and F1-score, respectively.
format Online
Article
Text
id pubmed-7998401
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-79984012021-03-28 Volume-of-Interest Aware Deep Neural Networks for Rapid Chest CT-Based COVID-19 Patient Risk Assessment Chatzitofis, Anargyros Cancian, Pierandrea Gkitsas, Vasileios Carlucci, Alessandro Stalidis, Panagiotis Albanis, Georgios Karakottas, Antonis Semertzidis, Theodoros Daras, Petros Giannitto, Caterina Casiraghi, Elena Sposta, Federica Mrakic Vatteroni, Giulia Ammirabile, Angela Lofino, Ludovica Ragucci, Pasquala Laino, Maria Elena Voza, Antonio Desai, Antonio Cecconi, Maurizio Balzarini, Luca Chiti, Arturo Zarpalas, Dimitrios Savevski, Victor Int J Environ Res Public Health Article Since December 2019, the world has been devastated by the Coronavirus Disease 2019 (COVID-19) pandemic. Emergency Departments have been experiencing situations of urgency where clinical experts, without long experience and mature means in the fight against COVID-19, have to rapidly decide the most proper patient treatment. In this context, we introduce an artificially intelligent tool for effective and efficient Computed Tomography (CT)-based risk assessment to improve treatment and patient care. In this paper, we introduce 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. We tackle the high and varying dimensionality of the CT input by detecting and analyzing only a sub-volume of the CT, the Volume-of-Interest (VoI). Differently from recent strategies that consider infected CT slices without requiring any spatial coherency between them, or use the whole lung volume by applying abrupt and lossy volume down-sampling, we assess only the “most infected volume” composed of slices at its original spatial resolution. To achieve the above, we create, present and publish a new labeled and annotated CT dataset with 626 CT samples from COVID-19 patients. The comparison against such strategies proves the effectiveness of our VoI-based approach. We achieve remarkable performance on patient risk assessment evaluated on balanced data by reaching 88.88%, 89.77%, 94.73% and 88.88% accuracy, sensitivity, specificity and F1-score, respectively. MDPI 2021-03-11 /pmc/articles/PMC7998401/ /pubmed/33799509 http://dx.doi.org/10.3390/ijerph18062842 Text en © 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Chatzitofis, Anargyros
Cancian, Pierandrea
Gkitsas, Vasileios
Carlucci, Alessandro
Stalidis, Panagiotis
Albanis, Georgios
Karakottas, Antonis
Semertzidis, Theodoros
Daras, Petros
Giannitto, Caterina
Casiraghi, Elena
Sposta, Federica Mrakic
Vatteroni, Giulia
Ammirabile, Angela
Lofino, Ludovica
Ragucci, Pasquala
Laino, Maria Elena
Voza, Antonio
Desai, Antonio
Cecconi, Maurizio
Balzarini, Luca
Chiti, Arturo
Zarpalas, Dimitrios
Savevski, Victor
Volume-of-Interest Aware Deep Neural Networks for Rapid Chest CT-Based COVID-19 Patient Risk Assessment
title Volume-of-Interest Aware Deep Neural Networks for Rapid Chest CT-Based COVID-19 Patient Risk Assessment
title_full Volume-of-Interest Aware Deep Neural Networks for Rapid Chest CT-Based COVID-19 Patient Risk Assessment
title_fullStr Volume-of-Interest Aware Deep Neural Networks for Rapid Chest CT-Based COVID-19 Patient Risk Assessment
title_full_unstemmed Volume-of-Interest Aware Deep Neural Networks for Rapid Chest CT-Based COVID-19 Patient Risk Assessment
title_short Volume-of-Interest Aware Deep Neural Networks for Rapid Chest CT-Based COVID-19 Patient Risk Assessment
title_sort volume-of-interest aware deep neural networks for rapid chest ct-based covid-19 patient risk assessment
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7998401/
https://www.ncbi.nlm.nih.gov/pubmed/33799509
http://dx.doi.org/10.3390/ijerph18062842
work_keys_str_mv AT chatzitofisanargyros volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT cancianpierandrea volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT gkitsasvasileios volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT carluccialessandro volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT stalidispanagiotis volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT albanisgeorgios volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT karakottasantonis volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT semertzidistheodoros volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT daraspetros volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT giannittocaterina volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT casiraghielena volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT spostafedericamrakic volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT vatteronigiulia volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT ammirabileangela volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT lofinoludovica volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT raguccipasquala volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT lainomariaelena volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT vozaantonio volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT desaiantonio volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT cecconimaurizio volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT balzariniluca volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT chitiarturo volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT zarpalasdimitrios volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment
AT savevskivictor volumeofinterestawaredeepneuralnetworksforrapidchestctbasedcovid19patientriskassessment