Article (Scientific journals)
A deep learning-based application for COVID-19 diagnosis on CT: The Imaging COVID-19 AI initiative.
Topff, Laurens; Sánchez-García, José; López-González, Rafael et al.
2023In PLoS ONE, 18 (5), p. 0285121
Peer Reviewed verified by ORBi
 

Files


Full Text
20230503_journal.pone.0285121.pdf
Author postprint (1.34 MB) Creative Commons License - Attribution
Download

All documents in ORBi are protected by a user license.

Send to



Details



Abstract :
[en] [en] BACKGROUND: Recently, artificial intelligence (AI)-based applications for chest imaging have emerged as potential tools to assist clinicians in the diagnosis and management of patients with coronavirus disease 2019 (COVID-19). OBJECTIVES: To develop a deep learning-based clinical decision support system for automatic diagnosis of COVID-19 on chest CT scans. Secondarily, to develop a complementary segmentation tool to assess the extent of lung involvement and measure disease severity. METHODS: The Imaging COVID-19 AI initiative was formed to conduct a retrospective multicentre cohort study including 20 institutions from seven different European countries. Patients with suspected or known COVID-19 who underwent a chest CT were included. The dataset was split on the institution-level to allow external evaluation. Data annotation was performed by 34 radiologists/radiology residents and included quality control measures. A multi-class classification model was created using a custom 3D convolutional neural network. For the segmentation task, a UNET-like architecture with a backbone Residual Network (ResNet-34) was selected. RESULTS: A total of 2,802 CT scans were included (2,667 unique patients, mean [standard deviation] age = 64.6 [16.2] years, male/female ratio 1.3:1). The distribution of classes (COVID-19/Other type of pulmonary infection/No imaging signs of infection) was 1,490 (53.2%), 402 (14.3%), and 910 (32.5%), respectively. On the external test dataset, the diagnostic multiclassification model yielded high micro-average and macro-average AUC values (0.93 and 0.91, respectively). The model provided the likelihood of COVID-19 vs other cases with a sensitivity of 87% and a specificity of 94%. The segmentation performance was moderate with Dice similarity coefficient (DSC) of 0.59. An imaging analysis pipeline was developed that returned a quantitative report to the user. CONCLUSION: We developed a deep learning-based clinical decision support system that could become an efficient concurrent reading tool to assist clinicians, utilising a newly created European dataset including more than 2,800 CT scans.
Disciplines :
Cardiovascular & respiratory systems
Radiology, nuclear medicine & imaging
Author, co-author :
Topff, Laurens ;  Department of Radiology, Netherlands Cancer Institute, Amsterdam, The Netherlands ; GROW School for Oncology and Reproduction, Maastricht University, Maastricht, The Netherlands
Sánchez-García, José;  Quantitative Imaging Biomarkers in Medicine (Quibim), Valencia, Spain
López-González, Rafael;  Quantitative Imaging Biomarkers in Medicine (Quibim), Valencia, Spain
Pastor, Ana Jiménez;  Quantitative Imaging Biomarkers in Medicine (Quibim), Valencia, Spain
Visser, Jacob J ;  Department of Radiology and Nuclear Medicine, Erasmus MC, University Medical Center Rotterdam, Rotterdam, The Netherlands
Huisman, Merel;  Department of Radiology and Nuclear Medicine, Radboud University Medical Center, Nijmegen, The Netherlands
Guiot, Julien  ;  Centre Hospitalier Universitaire de Liège - CHU > > Service de pneumologie - allergologie
Beets-Tan, Regina G H;  Department of Radiology, Netherlands Cancer Institute, Amsterdam, The Netherlands ; GROW School for Oncology and Reproduction, Maastricht University, Maastricht, The Netherlands
Alberich-Bayarri, Angel;  Quantitative Imaging Biomarkers in Medicine (Quibim), Valencia, Spain
Fuster-Matanzo, Almudena;  Quantitative Imaging Biomarkers in Medicine (Quibim), Valencia, Spain
Ranschaert, Erik R;  Department of Radiology, St. Nikolaus Hospital, Eupen, Belgium ; Ghent University, Ghent, Belgium
Imaging COVID-19 AI initiative
Language :
English
Title :
A deep learning-based application for COVID-19 diagnosis on CT: The Imaging COVID-19 AI initiative.
Publication date :
02 May 2023
Journal title :
PLoS ONE
eISSN :
1932-6203
Publisher :
Public Library of Science (PLoS), United States
Volume :
18
Issue :
5
Pages :
e0285121
Peer reviewed :
Peer Reviewed verified by ORBi
Available on ORBi :
since 03 May 2023

Statistics


Number of views
51 (3 by ULiège)
Number of downloads
33 (1 by ULiège)

Scopus citations®
 
3
Scopus citations®
without self-citations
2
OpenCitations
 
0

Bibliography


Similar publications



Contact ORBi