EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access · CC BY 4.0

A deep learning-based application for COVID-19 diagnosis on CT: The Imaging COVID-19 AI initiative

Laurens Topff iD, José Sánchez-García, Rafael López-González, Ana Jiménez Pastor, Jacob J Visser iD, Merel Huisman, Julien Guiot iD, Regina G H Beets-Tan, Angel Alberich-Bayarri, Almudena Fuster-Matanzo, Erik R Ranschaert, Imaging COVID-19 AI initiative

PLOS ONE · 2023

DOI: 10.1371/journal.pone.0285121 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift PLOS ONE, 2023. Verfasst von Laurens Topff und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Netherlands Cancer Institute, Amsterdam, The Netherlands. Hauptthemen laut MEDLINE: COVID-19, Deep Learning. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

COVID-19Deep LearningHumansFemaleMaleMiddle AgedArtificial IntelligenceLungCOVID-19 TestingCohort StudiesSARS-CoV-2Tomography, X-Ray Computed

Autor:innen und Institutionen

  • Department of Radiology, Netherlands Cancer Institute, Amsterdam, The Netherlands.
  • GROW School for Oncology and Reproduction, Maastricht University, Maastricht, The Netherlands.
  • Quantitative Imaging Biomarkers in Medicine (Quibim), Valencia, Spain.
  • Department of Radiology and Nuclear Medicine, Erasmus MC, University Medical Center Rotterdam, Rotterdam, The Netherlands.
  • Department of Radiology and Nuclear Medicine, Radboud University Medical Center, Nijmegen, The Netherlands.
  • Department of Pneumology, University Hospital of Liège (CHU Liège), Liège, Belgium.

ORCID-Profile: Laurens Topff, Jacob J Visser, Julien Guiot

Zitieren

APA

Topff, L., Sánchez-García, J., López-González, R., Pastor, A. J., Visser, J. J., Huisman, M., Guiot, J., Beets-Tan, R. G. H., Alberich-Bayarri, A., Fuster-Matanzo, A., Ranschaert, E. R., & Imaging COVID-19 AI initiative (2023). A deep learning-based application for COVID-19 diagnosis on CT: The Imaging COVID-19 AI initiative. PLOS ONE. https://doi.org/10.1371/journal.pone.0285121

Vancouver

Topff L, Sánchez-García J, López-González R, Pastor AJ, Visser JJ, Huisman M, et al. A deep learning-based application for COVID-19 diagnosis on CT: The Imaging COVID-19 AI initiative. PLOS ONE. 2023. doi:10.1371/journal.pone.0285121

BibTeX
@article{Topff2023,
  author = {Topff, Laurens and Sánchez-García, José and López-González, Rafael and Pastor, Ana Jiménez and Visser, Jacob J and Huisman, Merel and Guiot, Julien and Beets-Tan, Regina G H and Alberich-Bayarri, Angel and Fuster-Matanzo, Almudena and Ranschaert, Erik R and Imaging COVID-19 AI initiative, Imaging COVID-19 AI initiative},
  title = {A deep learning-based application for COVID-19 diagnosis on CT: The Imaging COVID-19 AI initiative},
  journal = {PLOS ONE},
  year = {2023},
  doi = {10.1371/journal.pone.0285121}
}
Kostenlos starten →