Privacy-preserving distributed learning of radiomics to predict overall survival and HPV status in head and neck cancer.

Marta Bogowicz, Arthur Jochems, Timo M. Deist, Stephanie Tanadini-Lang, Shao Hui Huang, Biu Chan, John N. Waldron, Scott Bratman, Brian O'Sullivan, Oliver Riesterer, Gabriela Studer, Jan Unkelbach, Samir Barakat, Ruud H. Brakenhoff, Irene Nauta, Silvia E. Gazzani, Giuseppina Calareso, Kathrin Scheckenbach, Frank Hoebers, Frederik W. R. WesselingSimon Keek, Sebastian Sanduleanu, Ralph T. H. Leijenaar, Marije R. Vergeer, C. René Leemans, Chris H. J. Terhaard, Michiel W. M. van den Brekel, Olga Hamming-Vrieze, Martijn A. van der Heijden, Hesham M. Elhalawani, Clifton D. Fuller, Matthias Guckenberger, Philippe Lambin

Research output: Contribution to journalArticlepeer-review


A major challenge in radiomics is assembling data from multiple centers. Sharing data between hospitals is restricted by legal and ethical regulations. Distributed learning is a technique, enabling training models on multicenter data without data leaving the hospitals ("privacy-preserving" distributed learning). This study tested feasibility of distributed learning of radiomics data for prediction of two year overall survival and HPV status in head and neck cancer (HNC) patients. Pretreatment CT images were collected from 1174 HNC patients in 6 different cohorts. 981 radiomic features were extracted using Z-Rad software implementation. Hierarchical clustering was performed to preselect features. Classification was done using logistic regression. In the validation dataset, the receiver operating characteristics (ROC) were compared between the models trained in the centralized and distributed manner. No difference in ROC was observed with respect to feature selection. The logistic regression coefficients were identical between the methods (absolute difference textless10(-7)). In comparison of the full workflow (feature selection and classification), no significant difference in ROC was found between centralized and distributed models for both studied endpoints (DeLong p textgreater 0.05). In conclusion, both feature selection and classification are feasible in a distributed manner using radiomics data, which opens new possibility for training more reliable radiomics models.
Original languageEnglish
Pages (from-to)4542
Number of pages1
JournalSci. Rep.
Issue number1
Publication statusPublished - Mar 1 2020


  • Humans
  • Survival Rate
  • Prognosis
  • Retrospective Studies
  • ROC Curve
  • *Data Accuracy
  • *Deep Learning
  • *Privacy
  • Head and Neck Neoplasms/diagnostic imaging/*mortality/virology
  • Image Interpretation
  • Computer-Assisted
  • Papillomaviridae/*isolation purification
  • Papillomavirus Infections/*complications/virology
  • Tomography
  • X-Ray Computed/*methods

Fingerprint Dive into the research topics of 'Privacy-preserving distributed learning of radiomics to predict overall survival and HPV status in head and neck cancer.'. Together they form a unique fingerprint.

Cite this