Updates are available Correction dated 2021-05-04

Article History

Received: 22 May 2020

Revised: 2 December 2020

Accepted: 16 December 2020

First Online: 17 March 2021

Change Date: 4 May 2021

Change Type: Correction

Change Details: A Correction to this paper has been published:

Change Details: https://doi.org/10.1007/s00330-021-07995-7

Compliance with ethical standards

:

: The scientific guarantor of this publication is Prof. Dr. Helmut Prosch.

: The authors of this manuscript declare relationships with the following companies: S.R.: Consulting activities for contextflow GmbH; J.H.: Speaker fees: Boehringer-Ingelheim; L.N.: no relationships with any companies, whose products or services may be related to the subject matter of the article; G.L.: Shareholder/Co-Founder contextflow GmbH; Speaker fees: Roche, Siemens; H.P.: Speakers fees: Boehringer-Ingelheim, Roche, Novartis, MSD, BMS, GSK, Chiesi, AstraZeneca.

: One of the authors has significant statistical expertise.

: Written informed consent was obtained from all patients in this study.

: Institutional Review Board approval was obtained.

: The imaging and clinical data acquired for this study were collected in the framework of a prospective study which aimed to evaluate manual volumetry of parenchymal lung injury in initial and follow-up CT scans to predict ARDS in polytraumatized patients (Title: “The clinical benefit of a follow-up thoracic computed tomography scan regarding parenchymal lung injury and acute respiratory distress syndrome in polytraumatized patients”); please also see the attached PDF. The previous study reported on the usefulness of a follow-up chest CT scan for manual volumetry of lung parenchymal injuries compared to the initial scan at admission whereas the present study evaluated the possibility of deep learning–based prediction of ARDS in the initial scan.

: • prospective• diagnostic or prognostic study• performed at one institution