A multicenter evaluation of a deep learning software (LungQuant) for lung parenchyma characterization in COVID-19 pneumonia.
Camilla ScapicchioAndrea ChincariniElena BallanteLuca BertaEleonora BicciChandra BortolottoFrancesca BreroRaffaella Fiamma CabiniGiuseppe CristofaloSalvatore Claudio FanniMaria Evelina FantacciSilvia FiginiMassimo GaliaPietro GemmaEmanuele GrassedonioAlessandro LascialfariCristina LenardiAlice LionettiFrancesca LizziMaurizio MarraleMassimo MidiriCosimo NardiPiernicola OlivaNoemi PerilloIan PostumaLorenzo PredaVieri RastrelliFrancesco RizzettoNicola SpinaCinzia TalamontiAlberto TorresinAngelo VanzulliFederica VolpiEmanuele NeriAlessandra ReticoPublished in: European radiology experimental (2023)
We conducted a multicenter evaluation of the deep learning-based LungQuant automated software. We translated qualitative assessments into quantifiable metrics to characterize coronavirus disease 2019 (COVID-19) pneumonia lesions. Comparing the software output to the clinical evaluations, results were satisfactory despite heterogeneity of the clinical evaluations. An automatic quantification tool may contribute to improve the clinical workflow of COVID-19 pneumonia.