Definition and validation of a radiomics signature for loco-regional tumour control in patients with locally advanced head and neck squamous cell carcinoma

Research output: Contribution to journalResearch articleContributedpeer-review

Contributors

  • Asier Rabasco Meneghetti - , OncoRay - National Center for Radiation Research in Oncology, Helmholtz-Zentrum Dresden-Rossendorf, TUD Dresden University of Technology (Author)
  • Alex Zwanenburg - , TUD Dresden University of Technology, German Cancer Research Center (DKFZ) (Author)
  • Stefan Leger - , OncoRay - National Center for Radiation Research in Oncology, TUD Dresden University of Technology, German Cancer Research Center (DKFZ) (Author)
  • Karoline Leger - , Department of Radiotherapy and Radiooncology, TUD Dresden University of Technology, German Cancer Research Center (DKFZ), University Hospital Carl Gustav Carus Dresden (Author)
  • Esther G.C. Troost - , University Medicine (Faculty of Medicine and University Hospital), School of Medicine, Helmholtz-Zentrum Dresden-Rossendorf, TUD Dresden University of Technology, German Cancer Research Center (DKFZ), University Hospital Carl Gustav Carus Dresden (Author)
  • Annett Linge - , Department of Radiotherapy and Radiooncology, TUD Dresden University of Technology, German Cancer Research Center (DKFZ), University Hospital Carl Gustav Carus Dresden (Author)
  • Fabian Lohaus - , Department of Radiotherapy and Radiooncology, TUD Dresden University of Technology, German Cancer Research Center (DKFZ), University Hospital Carl Gustav Carus Dresden (Author)
  • Andreas Schreiber - , Municipal Hospital Dresden (Author)
  • Goda Kalinauskaite - , German Cancer Research Center (DKFZ), Charité – Universitätsmedizin Berlin (Author)
  • Inge Tinhofer - , German Cancer Research Center (DKFZ), Charité – Universitätsmedizin Berlin (Author)
  • Nika Guberina - , German Cancer Research Center (DKFZ), University of Duisburg-Essen (Author)
  • Maja Guberina - , German Cancer Research Center (DKFZ), University of Duisburg-Essen (Author)
  • Panagiotis Balermpas - , German Cancer Research Center (DKFZ), University Hospital Frankfurt (Author)
  • Jens von der Grün - , German Cancer Research Center (DKFZ), University Hospital Frankfurt (Author)
  • Ute Ganswindt - , German Cancer Research Center (DKFZ), Ludwig Maximilian University of Munich, Innsbruck Medical University, Helmholtz Zentrum München - German Research Center for Environmental Health (Author)
  • Claus Belka - , German Cancer Research Center (DKFZ), Ludwig Maximilian University of Munich, Helmholtz Zentrum München - German Research Center for Environmental Health (Author)
  • Jan C. Peeken - , German Cancer Research Center (DKFZ), Technical University of Munich, Helmholtz Zentrum München - German Research Center for Environmental Health (Author)
  • Stephanie E. Combs - , German Cancer Research Center (DKFZ), Technical University of Munich, Helmholtz Zentrum München - German Research Center for Environmental Health (Author)
  • Simon Böke - , German Cancer Research Center (DKFZ), University of Tübingen (Author)
  • Daniel Zips - , German Cancer Research Center (DKFZ) (Author)
  • Mechthild Krause - , Department of Radiotherapy and Radiooncology, Helmholtz-Zentrum Dresden-Rossendorf, TUD Dresden University of Technology, German Cancer Research Center (DKFZ), University Hospital Carl Gustav Carus Dresden (Author)
  • Michael Baumann - , Department of Radiotherapy and Radiooncology, Helmholtz-Zentrum Dresden-Rossendorf, TUD Dresden University of Technology, German Cancer Research Center (DKFZ), University Hospital Carl Gustav Carus Dresden (Author)
  • Steffen Löck - , OncoRay - National Center for Radiation Research in Oncology, TUD Dresden University of Technology, German Cancer Research Center (DKFZ), University Hospital Carl Gustav Carus Dresden (Author)

Abstract

Purpose: To develop and validate a CT-based radiomics signature for the prognosis of loco-regional tumour control (LRC) in patients with locally advanced head and neck squamous cell carcinoma (HNSCC) treated by primary radiochemotherapy (RCTx) based on retrospective data from 6 partner sites of the German Cancer Consortium - Radiation Oncology Group (DKTK-ROG). Material and methods: Pre-treatment CT images of 318 patients with locally advanced HNSCC were collected. Four-hundred forty-six features were extracted from each primary tumour volume and then filtered through stability analysis and clustering. First, a baseline signature was developed from demographic and tumour-associated clinical parameters. This signature was then supplemented by CT imaging features. A final signature was derived using repeated 3-fold cross-validation on the discovery cohort. Performance in external validation was assessed by the concordance index (C-Index). Furthermore, calibration and patient stratification in groups with low and high risk for loco-regional recurrence were analysed. Results: For the clinical baseline signature, only the primary tumour volume was selected. The final signature combined the tumour volume with two independent radiomics features. It achieved moderately good discriminatory performance (C-Index [95% confidence interval]: 0.66 [0.55–0.75]) on the validation cohort along with significant patient stratification (p = 0.005) and good calibration. Conclusion: We identified and validated a clinical-radiomics signature for LRC of locally advanced HNSCC using a multi-centric retrospective dataset. Prospective validation will be performed on the primary cohort of the HNprädBio trial of the DKTK-ROG once follow-up is completed.

Details

Original languageEnglish
Pages (from-to)62-70
Number of pages9
JournalClinical and translational radiation oncology
Volume26
Publication statusPublished - Jan 2021
Peer-reviewedYes

External IDs

ORCID /0000-0002-7017-3738/work/146646042
ORCID /0000-0003-1776-9556/work/171065753

Keywords

Sustainable Development Goals

Keywords

  • Biomarker, HNSCC, Loco-regional control, Machine learning, Radiomics, Validation