Value and prognostic impact of a deep learning segmentation model of COVID-19 lung lesions on low-dose chest CT - 21/09/22
, Joris Fournel a, b, 1, Arnaud Maurin, MD a, Baptiste Marchi, MD a, Paul Habert, MD a, d, e, Maxime Castelli, MD a, Jean-Yves Gaubert, MD a, d, e, Sebastien Cortaredona, MD f, g, Jean-Christophe Lagier, MD, PhD f, h, Matthieu Million, MD, PhD f, h, Didier Raoult, MD, PhD f, h, Badih Ghattas, MCU c, Alexis Jacquier, MD, PhD a, b
Bienvenue sur EM-consulte, la référence des professionnels de santé.
Article gratuit.
Connectez-vous pour en bénéficier!
Highlights |
• | Deep Learning (DL) pipeline, based on supervised convolutionnal neural networks achieve Dice coefficient of overall COVID-19 lesions on low-dose chest CT (ground-glass opacity and consolidation) of 0.75 ± 0.08 on low-dose computed tomography. |
• | The developed pipeline computes clinical parameters: lesion volume (cm3) and extend (%). Lesion extent automatic quantification had a mean absolute error of 2.1% ± 2.4 with good correlation to manual ground-truth reference (r = 0.947: p<0.001). |
• | After stepwise selection and adjustment on clinical characteristics of 1621 patients, DL driven automatic quantification was shown to be a strong prognostic marker of adverse events during COVID-19 infection (prognosis accuracy of the model from 0.82 without DL to 0.90 with DL-driven quantification (p<0.0001)). |
Abstract |
Objectives |
1) To develop a deep learning (DL) pipeline allowing quantification of COVID-19 pulmonary lesions on low-dose computed tomography (LDCT). 2) To assess the prognostic value of DL-driven lesion quantification.
Methods |
This monocentric retrospective study included training and test datasets taken from 144 and 30 patients, respectively. The reference was the manual segmentation of 3 labels: normal lung, ground-glass opacity(GGO) and consolidation(Cons). Model performance was evaluated with technical metrics, disease volume and extent. Intra- and interobserver agreement were recorded. The prognostic value of DL-driven disease extent was assessed in 1621 distinct patients using C-statistics. The end point was a combined outcome defined as death, hospitalization>10 days, intensive care unit hospitalization or oxygen therapy.
Results |
The Dice coefficients for lesion (GGO+Cons) segmentations were 0.75±0.08, exceeding the values for human interobserver (0.70±0.08; 0.70±0.10) and intraobserver measures (0.72±0.09). DL-driven lesion quantification had a stronger correlation with the reference than inter- or intraobserver measures. After stepwise selection and adjustment for clinical characteristics, quantification significantly increased the prognostic accuracy of the model (0.82 vs. 0.90; p<0.0001).
Conclusions |
A DL-driven model can provide reproducible and accurate segmentation of COVID-19 lesions on LDCT. Automatic lesion quantification has independent prognostic value for the identification of high-risk patients.
Le texte complet de cet article est disponible en PDF.Keywords : COVID-19, Artificial intelligence, Multidetector computed tomography, Deep learning, Diagnostic imaging
Abbreviations : ACE, BMI, Cons, CNN, COVID-19, CT-SS, DL, DSC, GGO, ICU, LDCT, MAE, MVSF, ROC
Plan
| Institution from which the work originated: Department of Radiology, Hôpital de la Timone Adultes, AP-HM. 264, rue Saint-Pierre 13385 Marseille Cedex 05, France. |
Vol 1
Article 100003- mars 2022 Retour au numéro
Article précédent
- Abdominal imaging in ICU patients with viral pneumonia: Are findings in COVID-19 patients really different from those observed with non-SARS-CoV-2 viral pneumonia?
- Edouard Reizine, Sebastien Mule, Nicolas De Prost, Nicolas Mongardon, Jean-François Deux, Hicham Kobeiter, Alain Luciani
- Investigating of the role of CT scan for cancer patients during the first wave of COVID-19 pandemic
- Sylvain Bourdoncle, Thomas Eche, Jeremy McGale, Kevin Yiu, Ephraïm Partouche, Randy Yeh, Samy Ammari, Hervé Rousseau, Laurent Dercle, Fatima-Zohra Mokrane
Bienvenue sur EM-consulte, la référence des professionnels de santé.