Value and prognostic impact of a deep learning segmentation model of COVID-19 lung lesions on low-dose chest CT

Value and prognostic impact of a deep learning segmentation model of COVID-19 lung lesions on low-dose chest CT

•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: les...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Research in Diagnostic and Interventional Imaging (Online) 2022-03, Vol.1, p.100003-100003, Article 100003
Hauptverfasser: Bartoli, Axel, Fournel, Joris, Maurin, Arnaud, Marchi, Baptiste, Habert, Paul, Castelli, Maxime, Gaubert, Jean-Yves, Cortaredona, Sebastien, Lagier, Jean-Christophe, Million, Matthieu, Raoult, Didier, Ghattas, Badih, Jacquier, Alexis
Format: Artikel
Sprache:eng
Schlagworte:
Artificial intelligence
COVID-19
Deep learning
Diagnostic imaging
Multidetector computed tomography
Original
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•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
ISSN:2772-6525
2772-6525
DOI:10.1016/j.redii.2022.100003