Skip to main navigation Skip to search Skip to main content

Non-invasive imaging prediction of tumor hypoxia: A novel developed and externally validated CT and FDG-PET-based radiomic signatures

  • Sebastian Sanduleanu*
  • , Arthur Jochems
  • , Taman Upadhaya
  • , Aniek J. G. Even
  • , Ralph T. H. Leijenaar
  • , Frank J. W. M. Dankers
  • , Remy Klaassen
  • , Henry C. Woodruff
  • , Mathieu Hatt
  • , Hans J. A. M. Kaanders
  • , Olga Hamming-Vrieze
  • , Hanneke W. M. van Laarhoven
  • , Rathan M. Subramiam
  • , Shao Hui Huang
  • , Brian O'Sullivan
  • , Scott V. Bratman
  • , Ludwig J. Dubois
  • , Razvan L. Miclea
  • , Dario di Perri
  • , Xavier Geets
  • Mireia Crispin-Ortuzar, Aditya Apte, Joseph O. Deasy, Jung Hun Oh, Nancy Y. Lee, John L. Humm, Heiko Schöder, Dirk de Ruysscher, Frank Hoebers, Philippe Lambin
*Corresponding author for this work
  • Maastricht University
  • Université de Bretagne Occidentale
  • University of California at San Francisco
  • Radboud University Medical Center
  • Antoni van Leeuwenhoek, Surgical Oncology, Amsterdam, Netherlands;
  • Boston University
  • Johns Hopkins University
  • University of Toronto
  • Université catholique de Louvain
  • Memorial Sloan-Kettering Cancer Center
  • University of Cambridge

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Background: Tumor hypoxia increases resistance to radiotherapy and systemic therapy. Our aim was to develop and validate a disease-agnostic and disease-specific CT (+FDG-PET) based radiomics hypoxia classification signature. Material and methods: A total of 808 patients with imaging data were included: N = 100 training/N = 183 external validation cases for a disease-agnostic CT hypoxia classification signature, N = 76 training/N = 39 validation cases for the H&N CT signature and N = 62 training/N = 36 validation cases for the Lung CT signature. The primary gross tumor volumes (GTV) were manually defined by experts on CT. In order to dichotomize between hypoxic/well-oxygenated tumors a threshold of 20% was used for the [18F]-HX4-derived hypoxic fractions (HF). A random forest (RF)-based machine-learning classifier/regressor was trained to classify patients as hypoxia-positive/ negative based on radiomic features. Results: A 11 feature “disease-agnostic CT model” reached AUC's of respectively 0.78 (95% confidence interval [CI], 0.62–0.94), 0.82 (95% CI, 0.67–0.96) and 0.78 (95% CI, 0.67–0.89) in three external validation datasets. A “disease-agnostic FDG-PET model” reached an AUC of 0.73 (0.95% CI, 0.49–0.97) in validation by combining 5 features. The highest “lung-specific CT model” reached an AUC of 0.80 (0.95% CI, 0.65–0.95) in validation with 4 CT features, while the “H&N-specific CT model” reached an AUC of 0.84 (0.95% CI, 0.64–1.00) in validation with 15 CT features. A tumor volume-alone model was unable to significantly classify patients as hypoxia-positive/ negative. A significant survival split (P = 0.037) was found between CT-classified hypoxia strata in an external H&N cohort (n = 517), while 117 significant hypoxia gene-CT signature feature associations were found in an external lung cohort (n = 80). Conclusion: The disease-specific radiomics signatures perform better than the disease agnostic ones. By identifying hypoxic patients our signatures have the potential to enrich interventional hypoxia-targeting trials.
Original languageEnglish
Pages (from-to)97-105
Number of pages9
JournalRadiotherapy and oncology
Volume153
DOIs
Publication statusPublished - 1 Dec 2020

Keywords

  • Radiomics
  • Tumor hypoxia

Fingerprint

Dive into the research topics of 'Non-invasive imaging prediction of tumor hypoxia: A novel developed and externally validated CT and FDG-PET-based radiomic signatures'. Together they form a unique fingerprint.

Cite this