TY - JOUR
T1 - Clinical variables and magnetic resonance imaging-based radiomics predict human papillomavirus status of oropharyngeal cancer
AU - Bos, Paula
AU - van den Brekel, Michiel W M
AU - Gouw, Zeno A R
AU - Al-Mamgani, Abrahim
AU - Waktola, Selam
AU - Aerts, Hugo J W L
AU - Beets-Tan, Regina G H
AU - Castelijns, Jonas A
AU - Jasperse, Bas
N1 - Funding Information: We thank the Verwelius Foundation for their financial support. Publisher Copyright: © 2020 The Authors. Head & Neck published by Wiley Periodicals LLC.
PY - 2021/2
Y1 - 2021/2
N2 - BACKGROUND: Human papillomavirus (HPV)-positive oropharyngeal squamous cell carcinoma (OPSCC) have better prognosis and treatment response compared to HPV-negative OPSCC. This study aims to noninvasively predict HPV status of OPSCC using clinical and/or radiological variables.METHODS: Seventy-seven magnetic resonance radiomic features were extracted from T1-weighted postcontrast images of the primary tumor of 153 patients. Logistic regression models were created to predict HPV status, determined with immunohistochemistry, based on clinical variables, radiomic features, and its combination. Model performance was evaluated using area under the curve (AUC).RESULTS: Model performance showed AUCs of 0.794, 0.764, and 0.871 for the clinical, radiomic, and combined models, respectively. Smoking, higher T-classification (T3 and T4), larger, less round, and heterogeneous tumors were associated with HPV-negative tumors.CONCLUSION: Models based on clinical variables and/or radiomic tumor features can predict HPV status in OPSCC patients with good performance and can be considered when HPV testing is not available.
AB - BACKGROUND: Human papillomavirus (HPV)-positive oropharyngeal squamous cell carcinoma (OPSCC) have better prognosis and treatment response compared to HPV-negative OPSCC. This study aims to noninvasively predict HPV status of OPSCC using clinical and/or radiological variables.METHODS: Seventy-seven magnetic resonance radiomic features were extracted from T1-weighted postcontrast images of the primary tumor of 153 patients. Logistic regression models were created to predict HPV status, determined with immunohistochemistry, based on clinical variables, radiomic features, and its combination. Model performance was evaluated using area under the curve (AUC).RESULTS: Model performance showed AUCs of 0.794, 0.764, and 0.871 for the clinical, radiomic, and combined models, respectively. Smoking, higher T-classification (T3 and T4), larger, less round, and heterogeneous tumors were associated with HPV-negative tumors.CONCLUSION: Models based on clinical variables and/or radiomic tumor features can predict HPV status in OPSCC patients with good performance and can be considered when HPV testing is not available.
KW - head and neck cancer
KW - human papillomavirus
KW - machine learning
KW - radiomics
UR - http://www.scopus.com/inward/record.url?scp=85092183080&partnerID=8YFLogxK
U2 - https://doi.org/10.1002/hed.26505
DO - https://doi.org/10.1002/hed.26505
M3 - Article
C2 - 33029923
SN - 1043-3074
VL - 43
SP - 485
EP - 495
JO - Head & neck
JF - Head & neck
IS - 2
ER -