Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Multicenter Study
. 2023 May 2;18(5):e0285121.
doi: 10.1371/journal.pone.0285121. eCollection 2023.

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

Laurens Topff  1   2 , José Sánchez-García  3 , Rafael López-González  3 , Ana Jiménez Pastor  3 , Jacob J Visser  4 , Merel Huisman  5 , Julien Guiot  6 , Regina G H Beets-Tan  1   2 , Angel Alberich-Bayarri  3 , Almudena Fuster-Matanzo  3 , Erik R Ranschaert  7   8 ; Imaging COVID-19 AI initiative
Affiliations
Multicenter Study

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

Laurens Topff et al. PLoS One. .

Abstract

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.

PubMed Disclaimer

Conflict of interest statement

I have read the journal’s policy and the authors of this manuscript have the following competing interests: Laurens Topff, Merel Huisman, Regina G.H. Beets-Tan: no disclosures; Jacob J. Visser: medical advisor Noaber Foundation, medical advisor NLC, medical advisor Contextflow GmbH, medical advisor Quibim S.L.; Julien Guiot: personal fees for advisory board, work and lectures from Boehringer Ingelheim, Janssens, GSK, Roche and Chiesi, non-financial support for meeting attendance from Chiesi, Roche, Boehringer Ingelheim and Janssens, permanent SAB of Radiomics (Oncoradiomics SA) for the SALMON trial without any specific consultancy fee for this work, co-inventor of one issued patent on radiomics licensed to Radiomics (Oncoradiomics SA); Erik R. Ranschaert: medical advisor Quibim S.L, medical advisor Robovision BV; Ángel Alberich-Bayarri: CEO and a shareholder of Quibim S.L.; José Sánchez-García, Rafael López-González, Ana Jiménez Pastor, Almudena Fuster-Matanzo: current or past employees of Quibim S.L.

Figures

Fig 1
Fig 1. Custom 3D CNN architecture used for the classification model approach.
C: 3x3x3 Conv + LeakyReLU + MaxPooling + Batch Normalization; FC1: 128 neuron fully connected layer; FC2: 3 neuron fully connected layer. CNN, convolutional neuronal network.
Fig 2
Fig 2. Data flowchart.
COVID-19, coronavirus disease 2019; CT, computed tomography.
Fig 3
Fig 3. Receiver operating characteristic (ROC) curve for the COVID-19 classification model.
AUC, area under the ROC curve.
Fig 4
Fig 4. Confusion matrix for the COVID-19 classification model.
COVID-19, coronavirus disease 2019.
Fig 5
Fig 5. Structured report with analysis results.
A 3D reconstruction of the lungs is generated, together with the most affected transverse CT slice and segmentation masks of the lung opacities. The report includes disease probabilities and quantitative analysis results. COVID-19, coronavirus disease 2019; CT, computed tomography.
See this image and copyright information in PMC

References

    1. Mallah SI, Ghorab OK, Al-Salmi S, Abdellatif OS, Tharmaratnam T, Iskandar MA, et al.. COVID-19: breaking down a global health crisis. Ann Clin Microbiol Antimicrob. 2021;20(1):35. doi: 10.1186/s12941-021-00438-7 - DOI - PMC - PubMed
    1. Huang C, Wang Y, Li X, Ren L, Zhao J, Hu Y, et al.. Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China. The Lancet. 2020;395(10223):497–506. - PMC - PubMed
    1. Mercer TR, Salit M. Testing at scale during the COVID-19 pandemic. Nat Rev Genet. 2021;22(7):415–426. doi: 10.1038/s41576-021-00360-w - DOI - PMC - PubMed
    1. Filchakova O, Dossym D, Ilyas A, Kuanysheva T, Abdizhamil A, Bukasov R. Review of COVID-19 testing and diagnostic methods. Talanta. 2022;244:123409. doi: 10.1016/j.talanta.2022.123409 - DOI - PMC - PubMed
    1. Sharma S, Shrivastava S, Kausley SB, Rai B, Pandit AB. Coronavirus: a comparative analysis of detection technologies in the wake of emerging variants. Infection. 2022:1–19. doi: 10.1007/s15010-022-01819-6 - DOI - PMC - PubMed

Publication types