COVID detection and severity prediction with 3D-ConvNeXt and custom pretrainings

  • Since COVID strongly affects the respiratory system, lung CT-scans can be used for the analysis of a patients health. We introduce a neural network for the prediction of the severity of lung damage and the detection of a COVID-infection using three-dimensional CT-data. Therefore, we adapt the recent ConvNeXt model to process three-dimensional data. Furthermore, we design and analyze different pretraining methods specifically designed to improve the models ability to handle three-dimensional CT-data. We rank 2nd in the 1st COVID19 Severity Detection Challenge and 3rd in the 2nd COVID19 Detection Challenge.

Download full text files

Export metadata

Statistics

Number of document requests

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Daniel KienzleGND, Julian LorenzGND, Robin SchönGND, Katja LudwigGND, Rainer LienhartGND
URN:urn:nbn:de:bvb:384-opus4-974807
Frontdoor URLhttps://opus.bibliothek.uni-augsburg.de/opus4/97480
ISBN:978-3-031-25082-8OPAC
Parent Title (English):Computer Vision – ECCV 2022 Workshops: Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part VII
Publisher:Springer
Place of publication:Berlin
Editor:Leonid Karlinsky, Tomer Michaeli, Ko Nishino
Type:Conference Proceeding
Language:English
Year of first Publication:2023
Publishing Institution:Universität Augsburg
Release Date:2022/08/18
First Page:500
Last Page:516
Series:Lecture Notes in Computer Science ; 13807
DOI:https://doi.org/10.1007/978-3-031-25082-8_33
Institutes:Fakultät für Angewandte Informatik
Fakultät für Angewandte Informatik / Institut für Informatik
Fakultät für Angewandte Informatik / Institut für Informatik / Lehrstuhl für Maschinelles Lernen und Maschinelles Sehen
Dewey Decimal Classification:0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Licence (German):Deutsches Urheberrecht