%0 Journal Article
%A Klein, Sebastian
%A Wuerdemann, Nora
%A Demers, Imke
%A Kopp, Christopher
%A Quantius, Jennifer
%A Charpentier, Arthur
%A Tolkach, Yuri
%A Brinker, Klaus
%A Sharma, Shachi Jenny
%A George, Julie
%A Hess, Jochen
%A Stögbauer, Fabian
%A Lacko, Martin
%A Struijlaart, Marijn
%A van den Hout, Mari F C M
%A Wagner, Steffen
%A Wittekindt, Claus
%A Langer, Christine
%A Arens, Christoph
%A Buettner, Reinhard
%A Quaas, Alexander
%A Reinhardt, Hans Christian
%A Speel, Ernst-Jan
%A Klussmann, Jens Peter
%T Predicting HPV association using deep learning and regular H</td><td width="150">
%T amp;E stains allows granular stratification of oropharyngeal cancer patients.
%J npj digital medicine
%V 6
%N 1
%@ 2398-6352
%C [Basingstoke]
%I Macmillan Publishers Limited
%M DKFZ-2023-01684
%P 152
%D 2023
%X Human Papilloma Virus (HPV)-associated oropharyngeal squamous cell cancer (OPSCC) represents an OPSCC subgroup with an overall good prognosis with a rising incidence in Western countries. Multiple lines of evidence suggest that HPV-associated tumors are not a homogeneous tumor entity, underlining the need for accurate prognostic biomarkers. In this retrospective, multi-institutional study involving 906 patients from four centers and one database, we developed a deep learning algorithm (OPSCCnet), to analyze standard H</td><td width="150">
%X E stains for the calculation of a patient-level score associated with prognosis, comparing it to combined HPV-DNA and p16-status. When comparing OPSCCnet to HPV-status, the algorithm showed a good overall performance with a mean area under the receiver operator curve (AUROC) = 0.83 (95
%F PUB:(DE-HGF)16
%9 Journal Article
%$ pmid:37598255
%2 pmc:PMC10439941
%R 10.1038/s41746-023-00901-z
%U https://inrepo02.dkfz.de/record/278640