ESTRO 2022 - Abstract Book

S1622

Abstract book

ESTRO 2022

PO-1824 Regression and deep learning for transcriptome-based HPV-status prediction in head and neck cancer

K. Unger 1,2,3 , E. Lombardo 3,6 , J. Hess 4,5,3 , C. Kurz 3,6 , M. Riboldi 6 , S. Marschner 3,2 , P. Baumeister 7,2 , K. Lauber 3,2 , U. Pflugradt 3,2 , A. Walch 8,2 , M. Canis 7,2 , F. Klauschen 9,10 , H. Zitzelsberger 11,2,3 , C. Belka 3,2,10 , G. Landry 3,12 1 Helmholtz Zentrum München, German Research Center for Environmental Health GmbH, Radiation Cytogenetics, Neuherberg, Germany; 2 Helmholtz Zentrum München, German Research Center for Environmental Health GmbH, Clinical Cooperation Group "Personalized Radiotherapy in Head and Neck Cancer", Neuherberg, Germany; 3 University Hospital, LMU Munich, Department of Radiation Oncology, München, Germany; 4 Helmholtz Zentrum München, German Research Center for Environmental Health GmbH, German Research Center for Environmental Health GmbH, Neuherberg, Germany; 5 Helmholtz Zentrum München, German Research Center for Environmental Health GmbH, Clinical Cooperation Group "Personalized Radiotherapy in Head and Neck Cancer", Neuherberg, Germany; 6 Faculty of Physics, Ludwig-Maximilians- Universität München, Department of Medical Physics, Garching, Germany; 7 University Hospital, LMU Munich, Department of Otorhinolaryngology, München, Germany; 8 Helmholtz Zentrum München, German Research Center for Environmental Health GmbH, Research Unit Analytical Pathology, Neuherberg, Germany; 9 Faculty of Medicine, Ludwig-Maximilians- University of Munich, Institute of Pathology, München, Germany; 10 German Cancer Consortium (DKTK), Partner Site Munich, München, Germany; 11 Helmholtz Zentrum München, German Research Center for Environmental Health GmbH, Research Unit Radiation Cytogenetics, Neuherberg, Germany; 12 Faculty of Physics, Ludwig-Maximilians-Universität München, Department of Medical Physics, München, Germany Materials and Methods In this study we used transcriptome data of 348 patients with known HPV-status to build and compare the performance of regression-based and 2D Convolutional Neural Network (CNN) models for HPV prediction. For the CNN, transcriptome data was reorganized as 2D treemap images representing MSigDB Hallmark pathways. The treemaps were built three times in three different ways to assess the stability of the 2D-CNN. The features for the linear regression model were selected using Lasso on the training set. Results Applied on an unseen testing set comprising 25 % of the full patient dataset, the CNN achieved test ROC-AUCs/PR-AUCs of 0.95/0.87, 0.93/0.82 and 0.93/0.81 for the three variants of input treemaps respectively, while the regression model achieved a ROC-AUC/PR-AUC of 0.92/0.81. Conclusion Therefore, we conclude that accurate predictions of HPV-status can be made with both models. However, the advantage over linear regression is that the deep learning model allows for functional interpretation through visualization of saliency maps computed using the Grad-CAM method. Purpose or Objective HPV-status is a known prognostic factor for therapy outcome of head and neck squamous cell carcinomas.

PO-1825 Metabolic background affects radiation response more than metabolic therapy, in GBM models.

O. Furman 1 , K. Porper 1 , Y. Shpatz 1 , Y. Lawrence 1 , L. Zach 1