Devising novel imaging biomarkers for Human Papillomavirus (HPV) status in oropharyngeal squamous cell carcinoma (OPSCC): applying radiomics and machine learning algorithms

Purpose HPV-positive and HPV-negative OPSCC are biologically distinct entities, with different prognosis and divergent AJCC/UICC staging schemes. Radiomics refers to automated extraction of shape, intensity and texture features from target lesions on medical images – inaccessible to visual interpretation. We applied machine learning classifiers to devise radiomics signatures to determine the HPV-status in OPSCC.

Methods Imaging data was retrieved form The Cancer Imaging Archive and our institutional archives. Patients with OPSCC, known HPV/p16-status, and pre-treatment FDG‑PET / non‑contrast CT were included.

The primary tumors were delineated on PET and CT scans. 1040 radiomics features describing texture, shape and signal intensity characteristics were extracted from each tumor and per imaging modality.

For HPV-status prediction, LASSO regression feature selection (LASSO) and random forest (RF) machine learning classifiers were applied in 10-fold cross validation, repeated 10x. The area under the receiver operating characteristic curve (AUC-ROC) averaged across validation folds is reported.

Conclusions A total of 244 HPV-positive and 82 HPV-negative OPSCC patients were included: 46 T1, 119 T2, 107 T3, and 54 T4 UICC/AJCC stage primary tumors were analyzed. The LASSO / RF machine learning algorithm achieved an averaged AUC-ROC of 0.79 (PET/CT), 0.74 (CT) and 0.70 (PET).

Conclusion Radiomics feature extraction from PET and CT scans, combined with machine learning classifiers can generate imaging biomarkers for HPV in OPSCC primary tumors, which may aid in HPV-classification if standard immunohistochemical staining is equivocal, or supplement the immunohistochemical tests in subjects requiring second-line testing.

Poster-PDF A-1164.PDF

Publication History

Article published online:
10 June 2020