Clinical, morphologic and molecular heterogeneity of HPV-associated oropharyngeal cancer

Fully automated 3D machine learning model for HPV status characterization in oropharyngeal squamous cell carcinomas based on CT images

BACKGROUND

Human papillomavirus (HPV) status plays a major role in predicting oropharyngeal squamous cell carcinoma (OPSCC) survival. This study assesses the accuracy of a fully automated 3D convolutional neural network (CNN) in predicting HPV status using CT images.

METHODS

Pretreatment CT images from OPSCC patients were used to train a 3D DenseNet-121 model to predict HPV-p16 status. Performance was evaluated by the ROC Curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score.

RESULTS

The network achieved a mean AUC of 0.80 ± 0.06. The best-preforming fold had a sensitivity of 0.86 and specificity of 0.92 at the Youden's index. The PPV, NPV, and F1 scores are 0.97, 0.71, and 0.82, respectively.

CONCLUSIONS

A fully automated CNN can characterize the HPV status of OPSCC patients with high sensitivity and specificity. Further refinement of this algorithm has the potential to provide a non-invasive tool to guide clinical management.

HPV-associated oropharyngeal cancer: in search of surrogate biomarkers for early lesions

The incidence of oropharyngeal cancer (OPSCC) has escalated in the past few decades; this has largely been triggered by high-risk human papillomavirus (HPV). Early cancer screening is needed for timely clinical intervention and may reduce mortality and morbidity, but the lack of knowledge about premalignant lesions for OPSCC poses a significant challenge to early detection. Biomarkers that identify individuals at high risk for OPSCC may act as surrogate markers for precancer but these are limited as only a few studies decipher the multistep progression from HPV infection to OPSCC development. Here, we summarize the current literature describing the multistep progression from oral HPV infection, persistence, and tumor development in the oropharynx. We also examine key challenges that hinder the identification of premalignant lesions in the oropharynx and discuss potential biomarkers for oropharyngeal precancer. Finally, we evaluate novel strategies to improve investigations of the biological process that drives oral HPV persistence and OPSCC, highlighting new developments in the establishment of a genetic progression model for HPV + OPSCC and in vivo models that mimic HPV + OPSCC pathogenesis.