TY - JOUR
T1 - Non-invasive imaging prediction of tumor hypoxia: A novel developed and externally validated CT and FDG-PET-based radiomic signatures
AU - Sanduleanu, Sebastian
AU - Jochems, Arthur
AU - Upadhaya, Taman
AU - Even, Aniek J. G.
AU - Leijenaar, Ralph T. H.
AU - Dankers, Frank J. W. M.
AU - Klaassen, Remy
AU - Woodruff, Henry C.
AU - Hatt, Mathieu
AU - Kaanders, Hans J. A. M.
AU - Hamming-Vrieze, Olga
AU - van Laarhoven, Hanneke W. M.
AU - Subramiam, Rathan M.
AU - Huang, Shao Hui
AU - O'Sullivan, Brian
AU - Bratman, Scott V.
AU - Dubois, Ludwig J.
AU - Miclea, Razvan L.
AU - di Perri, Dario
AU - Geets, Xavier
AU - Crispin-Ortuzar, Mireia
AU - Apte, Aditya
AU - Deasy, Joseph O.
AU - Oh, Jung Hun
AU - Lee, Nancy Y.
AU - Humm, John L.
AU - Schöder, Heiko
AU - de Ruysscher, Dirk
AU - Hoebers, Frank
AU - Lambin, Philippe
PY - 2020/12/1
Y1 - 2020/12/1
N2 - 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.
AB - 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.
KW - Radiomics
KW - Tumor hypoxia
UR - https://www.scopus.com/pages/publications/85097729232
U2 - 10.1016/j.radonc.2020.10.016
DO - 10.1016/j.radonc.2020.10.016
M3 - Article
C2 - 33137396
SN - 0167-8140
VL - 153
SP - 97
EP - 105
JO - Radiotherapy and oncology
JF - Radiotherapy and oncology
ER -