Morphologic and topographic radiologic features of human papillomavirus-related and -unrelated oropharyngeal carcinoma

Update on Pathologic Conditions, Imaging Findings, Prevention, and Management of Human Papillomavirus-related Neoplasms

Human papillomavirus (HPV) is the most common sexually transmitted infection that proliferates in the squamous epithelium and is the most common source of viral-related neoplasms. Low-risk subtypes (HPV-6 and -11) cause respiratory papillomas (laryngeal, tracheal, and bronchial) and condyloma acuminata of the penis, anus, and perineal region (anogenital warts). High-risk subtypes (HPV-16, -18, -31, and -33) are responsible for oropharyngeal squamous cell carcinoma (SCC) that involves the tongue base, tonsils, posterior pharyngeal wall, and larynx and malignancies of the anogenital region (cancers of the cervix, vagina, vulva, penis, and anal canal). Recent studies have increasingly shown a favorable treatment response and substantial differences in the overall prognosis associated with HPV-associated oropharyngeal cancers. Given this fact, oropharyngeal, cervical, and penile SCCs are classified as HPV-associated and HPV-independent cancers in the current World Health Organization classification. Imaging is essential in the early detection, diagnosis, and staging of HPV-associated cancers. Imaging also helps assess treatment response and postoperative complications and is used for long-term surveillance. HPV-associated oropharyngeal SCCs have well-defined borders and solid and cystic nodal metastases at imaging. Updated screening and vaccination guidelines are currently available that have great potential to decrease the overall disease burden and help control this worldwide public health concern. Novel therapeutic strategies, such as immunotherapies, are being explored, and imaging biomarkers that can predict treatment response and prognosis are being investigated; radiologists play a pivotal role in these efforts. ©RSNA, 2024 Supplemental material is available for this article.

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.

Explainable prediction model for the human papillomavirus status in patients with oropharyngeal squamous cell carcinoma using CNN on CT images

Several studies have emphasised how positive and negative human papillomavirus (HPV+  and HPV-, respectively) oropharyngeal squamous cell carcinoma (OPSCC) has distinct molecular profiles, tumor characteristics, and disease outcomes. Different radiomics-based prediction models have been proposed, by also using innovative techniques such as Convolutional Neural Networks (CNNs). Although some of these models reached encouraging predictive performances, there evidence explaining the role of radiomic features in achieving a specific outcome is scarce. In this paper, we propose some preliminary results related to an explainable CNN-based model to predict HPV status in OPSCC patients. We extracted the Gross Tumor Volume (GTV) of pre-treatment CT images related to 499 patients (356 HPV+ and 143 HPV-) included into the OPC-Radiomics public dataset to train an end-to-end Inception-V3 CNN architecture. We also collected a multicentric dataset consisting of 92 patients (43 HPV+ , 49 HPV-), which was employed as an independent test set. Finally, we applied Gradient-weighted Class Activation Mapping (Grad-CAM) technique to highlight the most informative areas with respect to the predicted outcome. The proposed model reached an AUC value of 73.50% on the independent test. As a result of the Grad-CAM algorithm, the most informative areas related to the correctly classified HPV+ patients were located into the intratumoral area. Conversely, the most important areas referred to the tumor edges. Finally, since the proposed model provided additional information with respect to the accuracy of the classification given by the visualization of the areas of greatest interest for predictive purposes for each case examined, it could contribute to increase confidence in using computer-based predictive models in the actual clinical practice.

MRI for Differentiation between HPV-Positive and HPV-Negative Oropharyngeal Squamous Cell Carcinoma: A Systematic Review

Human papillomavirus (HPV) is an important risk factor for oropharyngeal squamous cell carcinoma (OPSCC). HPV-positive (HPV+) cases are associated with a different pathophysiology, microstructure, and prognosis compared to HPV-negative (HPV-) cases. This review aimed to investigate the potential of magnetic resonance imaging (MRI) to discriminate between HPV+ and HPV- tumours and predict HPV status in OPSCC patients. A systematic literature search was performed on 15 December 2022 on EMBASE, MEDLINE ALL, Web of Science, and Cochrane according to PRISMA guidelines. Twenty-eight studies (n = 2634 patients) were included. Five, nineteen, and seven studies investigated structural MRI (e.g., T1, T2-weighted), diffusion-weighted MRI, and other sequences, respectively. Three out of four studies found that HPV+ tumours were significantly smaller in size, and their lymph node metastases were more cystic in structure than HPV- ones. Eleven out of thirteen studies found that the mean apparent diffusion coefficient was significantly higher in HPV- than HPV+ primary tumours. Other sequences need further investigation. Fourteen studies used MRI to predict HPV status using clinical, radiological, and radiomics features. The reported areas under the curve (AUC) values ranged between 0.697 and 0.944. MRI can potentially be used to find differences between HPV+ and HPV- OPSCC patients and predict HPV status with reasonable accuracy. Larger studies with external model validation using independent datasets are needed before clinical implementation.

Multiparametric MRI-based radiomics model for predicting human papillomavirus status in oropharyngeal squamous cell carcinoma: optimization using oversampling and machine learning techniques

OBJECTIVES

To develop and validate a multiparametric MRI-based radiomics model with optimal oversampling and machine learning techniques for predicting human papillomavirus (HPV) status in oropharyngeal squamous cell carcinoma (OPSCC).

METHODS

This retrospective, multicenter study included consecutive patients with newly diagnosed and pathologically confirmed OPSCC between January 2017 and December 2020 (110 patients in the training set, 44 patients in the external validation set). A total of 293 radiomics features were extracted from three sequences (T2-weighted images [T2WI], contrast-enhanced T1-weighted images [CE-T1WI], and ADC). Combinations of three feature selection, five oversampling, and 12 machine learning techniques were evaluated to optimize its diagnostic performance. The area under the receiver operating characteristic curve (AUC) of the top five models was validated in the external validation set.

RESULTS

A total of 154 patients (59.2 ± 9.1 years; 132 men [85.7%]) were included, and oversampling was employed to account for data imbalance between HPV-positive and HPV-negative OPSCC (86.4% [133/154] vs. 13.6% [21/154]). For the ADC radiomics model, the combination of random oversampling and ridge showed the highest diagnostic performance in the external validation set (AUC, 0.791; 95% CI, 0.775-0.808). The ADC radiomics model showed a higher trend in diagnostic performance compared to the radiomics model using CE-T1WI (AUC, 0.604; 95% CI, 0.590-0.618), T2WI (AUC, 0.695; 95% CI, 0.673-0.717), and a combination of both (AUC, 0.642; 95% CI, 0.626-0.657).

CONCLUSIONS

The ADC radiomics model using random oversampling and ridge showed the highest diagnostic performance in predicting the HPV status of OPSCC in the external validation set.

CLINICAL RELEVANCE STATEMENT

Among multiple sequences, the ADC radiomics model has a potential for generalizability and applicability in clinical practice. Exploring multiple oversampling and machine learning techniques was a valuable strategy for optimizing radiomics model performance.

KEY POINTS

• Previous radiomics studies using multiparametric MRI were conducted at single centers without external validation and had unresolved data imbalances. • Among the ADC, CE-T1WI, and T2WI radiomics models and the ADC histogram models, the ADC radiomics model was the best-performing model for predicting human papillomavirus status in oropharyngeal squamous cell carcinoma. • The ADC radiomics model with the combination of random oversampling and ridge showed the highest diagnostic performance.

Radiomics analysis for the prediction of locoregional recurrence of locally advanced oropharyngeal cancer and hypopharyngeal cancer

PURPOSE

By radiomic analysis of the postcontrast CT images, this study aimed to predict locoregional recurrence (LR) of locally advanced oropharyngeal cancer (OPC) and hypopharyngeal cancer (HPC).

METHODS

A total of 192 patients with stage III-IV OPC or HPC from two independent cohort were randomly split into a training cohort with 153 cases and a testing cohort with 39 cases. Only primary tumor mass was manually segmented. Radiomic features were extracted using PyRadiomics, and then the support vector machine was used to build the radiomic model with fivefold cross-validation process in the training data set. For each case, a radiomics score was generated to indicate the probability of LR.

RESULTS

There were 94 patients with LR assigned in the progression group and 98 patients without LR assigned in the stable group. There was no significant difference of TNM staging, treatment strategies and common risk factors between these two groups. For the training data set, the radiomics model to predict LR showed 83.7% accuracy and 0.832 (95% CI 0.72, 0.87) area under the ROC curve (AUC). For the test data set, the accuracy and AUC slightly declined to 79.5% and 0.770 (95% CI 0.64, 0.80), respectively. The sensitivity/specificity of training and test data set for LR prediction were 77.6%/89.6%, and 66.7%/90.5%, respectively.

CONCLUSIONS

The image-based radiomic approach could provide a reliable LR prediction model in locally advanced OPC and HPC. Early identification of those prone to post-treatment recurrence would be helpful for appropriate adjustments to treatment strategies and post-treatment surveillance.

Imaging of human papilloma virus (HPV) related oropharynx tumour: what we know to date

The tumours of head and neck district are around 3% of all malignancies and squamous cell carcinoma is the most frequent histotype, with rapid increase during the last two decades because of the increment of the infection due to human papilloma virus (HPV). Even if the gold standard for the diagnosis is histological examination, including the detection of viral DNA and transcription products, imaging plays a fundamental role in the detection and staging of HPV + tumours, in order to assess the primary tumour, to establish the extent of disease and for follow-up. The main diagnostic tools are Computed Tomography (CT), Positron Emission Tomography-Computed Tomography (PET-CT) and Magnetic Resonance Imaging (MRI), but also Ultrasound (US) and the use of innovative techniques such as Radiomics have an important role. Aim of our review is to illustrate the main imaging features of HPV + tumours of the oropharynx, in US, CT and MRI imaging. In particular, we will outline the main limitations and strengths of the various imaging techniques, the main uses in the diagnosis, staging and follow-up of disease and the fundamental differential diagnoses of this type of tumour. Finally, we will focus on the innovative technique of texture analysis, which is increasingly gaining importance as a diagnostic tool in aid of the radiologist.

Interpretable radiomics method for predicting human papillomavirus status in oropharyngeal cancer using Bayesian networks

OBJECTIVES

To develop a simple interpretable Bayesian Network (BN) to classify HPV status in patients with oropharyngeal cancer.

METHODS

Two hundred forty-six patients, 216 of whom were HPV positive, were used in this study. We extracted 851 radiomics markers from patients' contrast-enhanced Computed Tomography (CT) images. Mens eX Machina (MXM) approach selected two most relevant predictors: sphericity and max2DDiameterRow. The area under the curve (AUC) demonstrated BN model performance in 30% of the data reserved for testing. A Support Vector Machine (SVM) based method was also implemented for comparison purposes.

RESULTS

The Mens eX Machina (MXM) approach selected two most relevant predictors: sphericity and max2DDiameterRow. Areas under the Curves (AUC) were found 0.78 and 0.72 on the training and test data, respectively. When using support vector machine (SVM) and 25 features, the AUC was found 0.83 on the test data.

CONCLUSIONS

The straightforward structure and power of interpretability of our BN model will help clinicians make treatment decisions and enable the non-invasive detection of HPV status from contrast-enhanced CT images. Higher accuracy can be obtained using more complex structures at the expense of lower interpretability.

ADVANCES IN KNOWLEDGE

Radiomics is being studied lately as a simple imaging data based HPV status detection technique which can be an alternative to laboratory approaches. However, it generally lacks interpretability. This work demonstrated the feasibility of using Bayesian networks based radiomics for predicting HPV positivity in an interpretable way.

Artificial intelligence for HPV status prediction based on disease-specific images in head and neck cancer: A systematic review and meta-analysis

Accurate early detection of the human papillomavirus (HPV) status in head and neck cancer (HNC) is crucial to identify at-risk populations, stratify patients, personalized treatment options, and predict prognosis. Artificial intelligence (AI) is an emerging tool to dissect imaging features. This systematic review and meta-analysis aimed to evaluate the performance of AI to predict the HPV positivity through the HPV-associated diseased images in HNC patients. A systematic literature search was conducted in databases including Ovid-MEDLINE, Embase, and Web of Science Core Collection for studies continuously published from inception up to October 30, 2022. Search strategies included keywords such as "artificial intelligence," "head and neck cancer," "HPV," and "sensitivity & specificity." Duplicates, articles without HPV predictions, letters, scientific reports, conference abstracts, or reviews were excluded. Binary diagnostic data were then extracted to generate contingency tables and then used to calculate the pooled sensitivity (SE), specificity (SP), area under the curve (AUC), and their 95% confidence interval (CI). A random-effects model was used for meta-analysis, four subgroup analyses were further explored. Totally, 22 original studies were included in the systematic review, 15 of which were eligible to generate 33 contingency tables for meta-analysis. The pooled SE and SP for all studies were 79% (95% CI: 75-82%) and 74% (95% CI: 69-78%) respectively, with an AUC of 0.83 (95% CI: 0.79-0.86). When only selecting one contingency table with the highest accuracy from each study, our analysis revealed a pooled SE of 79% (95% CI: 75-83%), SP of 75% (95% CI: 69-79%), and an AUC of 0.84 (95% CI: 0.81-0.87). The respective heterogeneities were moderate (I2 for SE and SP were 51.70% and 51.01%) and only low (35.99% and 21.44%). This evidence-based study showed an acceptable and promising performance for AI algorithms to predict HPV status in HNC but was not comparable to the routine p16 immunohistochemistry. The exploitation and optimization of AI algorithms warrant further research. Compared with previous studies, future studies anticipate to make progress in the selection of databases, improvement of international reporting guidelines, and application of high-quality deep learning algorithms.

Imaging of Neck Nodes in Head and Neck Cancers - a Comprehensive Update

Cervical lymph node metastases from head and neck squamous cell cancers significantly reduce disease-free survival and worsen overall prognosis and, hence, deserve more aggressive management and follow-up. As per the eighth edition of the American Joint Committee on Cancer staging manual, extranodal extension, especially in human papillomavirus-negative cancers, has been incorporated in staging as it is important in deciding management and significantly impacts the outcome of head and neck squamous cell cancer. Lymph node imaging with various radiological modalities, including ultrasound, computed tomography and magnetic resonance imaging, has been widely used, not only to demonstrate nodal involvement but also for guided histopathological evaluation and therapeutic intervention. Computed tomography and magnetic resonance imaging, together with positron emission tomography, are used widely for the follow-up of treated patients. Finally, there is an emerging role for artificial intelligence in neck node imaging that has shown promising results, increasing the accuracy of detection of nodal involvement, especially normal-appearing nodes. The aim of this review is to provide a comprehensive overview of the diagnosis and management of involved neck nodes with a focus on sentinel node anatomy, pathogenesis, imaging correlates (including radiogenomics and artificial intelligence) and the role of image-guided interventions.

External validation of a radiomic signature to predict p16 (HPV) status from standard CT images of anal cancer patients

The paper deals with the evaluation of the performance of an existing and previously validated CT based radiomic signature, developed in oropharyngeal cancer to predict human papillomavirus (HPV) status, in the context of anal cancer. For the validation in anal cancer, a dataset of 59 patients coming from two different centers was collected. The primary endpoint was HPV status according to p16 immunohistochemistry. Predefined statistical tests were performed to evaluate the performance of the model. The AUC obtained here in anal cancer is 0.68 [95% CI (0.32-1.00)] with F1 score of 0.78. This signature is TRIPOD level 4 (57%) with an RQS of 61%. This study provides proof of concept that this radiomic signature has the potential to identify a clinically relevant molecular phenotype (i.e., the HPV-ness) across multiple cancers and demonstrates potential for this radiomic signature as a CT imaging biomarker of p16 status.

Imaging of human papilloma virus associated oropharyngeal squamous cell carcinoma and its impact on diagnosis, prognostication, and response assessment

The clinical behaviour and outcomes of patients with oropharyngeal cancer (OPC) may be dichotomised according to their association with human papilloma virus (HPV) infection. Patients with HPV-associated disease (HPV+OPC) have a distinct demographic profile, clinical phenotype and demonstrate considerably better responses to chemoradiotherapy. This has led to a reappraisal of staging and treatment strategies for HPV+OPC, which are underpinned by radiological data. Structural modalities, such as CT and MRI can provide accurate staging information. These can be combined with ultrasound-guided tissue sampling and functional techniques (such as diffusion-weighted MRI and 18F-fludeoxyglucose positron emission tomography-CT) to monitor response to treatment, derive prognostic information, and to identify individuals who might benefit from intensification or deintensification strategies. Furthermore, advanced MRI techniques, such as intravoxel incoherent motion and perfusion MRI as well as application of artificial intelligence and radiomic techniques, have shown promise in treatment response monitoring and prognostication. The following review will consider the contemporary role and knowledge on imaging in HPV+OPC.

Primary tumor volume and prognosis for patients with p16-positive and p16-negative oropharyngeal squamous cell carcinoma treated with radiation therapy

BACKGROUND

The prescribed radiation dose to patients with oropharyngeal squamous cell carcinoma (OPSCC) is standardized, even if the prognosis for individual patients may differ. Easy-at-hand pre-treatment risk stratification methods are valuable to individualize therapy. In the current study we assessed the prognostic impact of primary tumor volume for p16-positive and p16-negative tumors and in relationship to other prognostic factors for outcome in patients with OPSCC treated with primary radiation therapy (RT).

METHODS

Five hundred twenty-three OPSCC patients with p16-status treated with primary RT (68.0 Gy to 73.1 Gy in 7 weeks, or 68.0 Gy in 4.5 weeks), with or without concurrent chemotherapy, within three prospective trials were included in the study. Local failure (LF), progression free survival (PFS) and overall survival (OS) in relationship to the size of the primary gross tumor volume (GTV-T) and other prognostic factors were investigated. Efficiency of intensified RT (RT with total dose 73.1 Gy or given within 4.5 weeks) was analyzed in relationship to tumor volume.

RESULTS

The volume of GTV-T and p16-status were found to be the strongest prognostic markers for LF, PFS and OS. For p16-positive tumors, an increase in tumor volume had a significantly higher negative prognostic impact compared with p16-negative tumors. Within a T-classification, patients with a smaller tumor, compared with a larger tumor, had a better prognosis. The importance of tumor volume remained after adjusting for nodal status, age, performance status, smoking status, sex, and hemoglobin-level. The adjusted hazard ratio for OS per cm³ increase in tumor volume was 2.3% (95% CI 0-4.9) for p16-positive and 1.3% (95% 0.3-2.2) for p16-negative. Exploratory analyses suggested that intensified RT could mitigate the negative impact of a large tumor volume.

CONCLUSIONS

Outcome for patients with OPSCC treated with RT is largely determined by tumor volume, even when adjusting for other established prognostic factors. Tumor volume is significantly more influential for patients with p16-positive tumors. Patients with large tumor volumes might benefit by intensified RT to improve survival.

Comparison of the Seventh and Eighth Edition of American Joint Committee on Cancer (AJCC) Staging for Selected and Nonselected Oropharyngeal Squamous Cell Carcinomas

OBJECTIVES

The eighth edition American Joint Committee on Cancer (AJCC) Staging incorporates significant changes to the seventh edition in the staging of oropharyngeal squamous cell carcinomas (OPSCC). An important change was the inclusion of OPSCC associated with the human papilloma virus (HPV). Our goal is to compare the performance of both staging systems for patients with HPV-selected and unselected clinical characteristics for OPSCC.

METHODS

Using the Surveillance, Epidemiology, and End Results (SEER) database, 2004-2016, we identified patients with likely HPV-associated OPSCC based on surrogate markers (white males aged <65 years old with squamous cell carcinomas of the tonsil and base of tongue), excluding those who underwent surgery. We re-classified these patients using seventh and eighth edition staging for HPV-selected OPSCC and compared the prediction performance of both staging editions for overall survival (OS) and disease-specific survival (DSS). We performed the same analysis for clinically unselected patients with OPSCC.

RESULTS

Our analysis included 9554 patients with a median follow-up of 67 months. Comparing the eighth versus seventh edition for our HPV-selected cohort, clinical staging changed for 92.3% of patients and 10-year OS was 62.2%, 61.2%, 35.3%, and 15.5% for Stage I, II, III, and IV, versus 52.9%, 59.2%, 61.6%, 55.1%, 38.3%, and 15.5% for stage I, II, III, IVA, IVB, and IVC, respectively. A similar pattern was observed for 10-year DSS. The concordance statistics for our HPV-selected cohort were improved for both AJCC 7 (0.6260) and AJCC 8 (0.6846) compared with the unselected cohort, 0.5860 and 0.6457 for AJCC 7 and 8, respectively.

CONCLUSION

The overall performance of discrimination improved from AJCC 7 to AJCC 8 for both clinically selected and unselected patients, but more notably for our HPV-selected cohort. Despite the lack of statistically significant differentiation between Stages I and II in AJCC 8 in either groups, markedly improved discrimination was observed between Stages I/II, III, and IV in the HPV-selected cohort.

Inter-rater concordance and operating definitions of radiologic nodal feature assessment in human papillomavirus-positive oropharyngeal carcinoma

BACKGROUND AND PURPOSE

This study aims to evaluate the reliability of radiologic nodal feature assessment in clinical node-positive human papillomavirus-positive oropharyngeal carcinoma.

MATERIALS AND METHODS

Baseline CTs or MRIs of clinical node-positive human papillomavirus-positive oropharyngeal carcinoma diagnosed between 2012 and 2015 were reviewed independently by two neuroradiologists for seven nodal features: radiologic nodal involvement, cystic change, presence of necrosis, clustering, conglomeration, coalescence, and extranodal extension. Consensus operating definitions were derived after discussion. The features were re-reviewed in a randomly selected cohort. Levels of certainty (probability of presence: <25%, ∼50%, ∼75%, and >90%) were recorded. Interrater concordance was calculated using Cohen's kappa coefficient.

RESULTS

A total of 413 patients (826 necks) were eligible. At initial review, the inter-rater kappa values for: radiologic nodal involvement, cystic change, necrosis, clustering, conglomeration, coalescence, and extranodal extension were 0.92, 0.64, 0.48, 0.32, 0.32, 0.62, and 0.56, respectively. A re-review of 94 randomly selected cases (188 necks) after consolidation of operating definitions for nodal features showed that the inter-rater kappa values of these features were 0.83, 0.62, 0.58, 0.32, 0.18, 0.68, and 0.74 when considering ≥50% certainty as positive, and improved to 0.94, 0.66, 0.59, 0.33, 0.19, 0.76, and 0.86 when considering ≥75% certainty as positive.

CONCLUSION

Clearly defined nomenclature results in improved interrater reliability when assessing radiologic nodal features, especially for coalescent adenopathy and extranodal extension. Higher levels of certainty are associated with higher inter-rater agreement. Radiology reporting should include clear definitions of clinically relevant nodal features as well as levels of certainty to serve various needs in clinical care and research.

Radiomics outperforms clinical factors in characterizing human papilloma virus (HPV) for patients with oropharyngeal squamous cell carcinomas

Purpose:To utilize radiomic features extracted from CT images to characterize Human Papilloma Virus (HPV) for patients with oropharyngeal cancer squamous cell carcinoma (OPSCC).Methods:One hundred twenty-eight OPSCC patients with known HPV-status (60-HPV+ and 68-HPV-, confirmed by immunohistochemistry-P16-protein testing) were retrospectively studied. Radiomic features (11 feature-categories) were extracted in 3D from contrast-enhanced (CE)-CT images of gross-tumor-volumes using 'in-house' software ('ROdiomiX') developed and validated following the image-biomarker-standardization-initiative (IBSI) guidelines. Six clinical factors were investigated: Age-at-Diagnosis, Gender, Total-Charlson, Alcohol-Use, Smoking-History, and T-Stage. A Least-Absolute-Shrinkage-and-Selection-Operation (Lasso) technique combined with a Generalized-Linear-Model (Lasso-GLM) were applied to perform regularization in the radiomic and clinical feature spaces to identify the ranking of optimal feature subsets with most representative information for prediction of HPV. Lasso-GLM models/classifiers based on clinical factors only, radiomics only, and combined clinical and radiomics (ensemble/integrated) were constructed using random-permutation-sampling. Tests of significance (One-way ANOVA), average Area-Under-Receiver-Operating-Characteristic (AUC), and Positive and Negative Predictive values (PPV and NPV) were computed to estimate the generalization-error and prediction performance of the classifiers.Results:Five clinical factors, including T-stage, smoking status, and age, and 14 radiomic features, including tumor morphology, and intensity contrast were found to be statistically significant discriminators between HPV positive and negative cohorts. Performances for prediction of HPV for the 3 classifiers were: Radiomics-Lasso-GLM: AUC/PPV/NPV=0.789/0.755/0.805; Clinical-Lasso-GLM: 0.676/0.747/0.672, and Integrated/Ensemble-Lasso-GLM: 0.895/0.874/0.844. Results imply that the radiomics-based classifier enabled better characterization and performance prediction of HPV relative to clinical factors, and that the combination of both radiomics and clinical factors yields even higher accuracy characterization and predictive performance.Conclusion:Albeit subject to confirmation in a larger cohort, this pilot study presents encouraging results in support of the role of radiomic features towards characterization of HPV in patients with OPSCC.

Advances in Imaging for HPV-Related Oropharyngeal Cancer: Applications to Radiation Oncology

While there has been an overall decline of tobacco and alcohol-related head and neck cancer in recent decades, there has been an increased incidence of HPV-associated oropharyngeal cancer (OPC). Recent research studies and clinical trials have revealed that the cancer biology and clinical progression of HPV-positive OPC is unique relative to its HPV-negative counterparts. HPV-positive OPC is associated with higher rates of disease control following definitive treatment when compared to HPV-negative OPC. Thus, these conditions should be considered unique diseases with regards to treatment strategies and survival. In order to sufficiently characterize HPV-positive OPC and guide treatment strategies, there has been a considerable effort to diagnose, prognose, and track the treatment response of HPV-associated OPC through advanced imaging research. Furthermore, HPV-positive OPC patients are prime candidates for radiation de-escalation protocols, which will ideally reduce toxicities associated with radiation therapy and has prompted additional imaging research to detect radiation-induced changes in organs at risk. This manuscript reviews the various imaging modalities and current strategies for tackling these challenges as well as provides commentary on the potential successes and suggested improvements for the optimal treatment of these tumors.

Prognostic Value of Apparent Diffusion Coefficient in Oropharyngeal Carcinoma

Purpose

To investigate clinical and radiological factors predicting worse outcome after (chemo)radiotherapy ([C]RT) in oropharyngeal squamous cell carcinoma (OPSCC) with a focus on apparent diffusion coefficient (ADC).

Methods

This retrospective study included 67 OPSCC patients, treated with (C)RT with curative intent and diagnosed during 2013–2017. Human papilloma virus (HPV) association was detected with p16 immunohistochemistry. Of all 67 tumors, 55 were p16 positive, 9 were p16 negative, and in 3 the p16 status was unknown. Median follow-up time was 38 months. We analyzed pretreatment magnetic resonance imaging (MRI) for factors predicting disease-free survival (DFS) and locoregional recurrence (LRR), including primary tumor volume and the largest metastasis. Crude and p16-adjusted hazard ratios were analyzed using Cox proportional hazards model. Interobserver agreement was evaluated.

Results

Disease recurred in 13 (19.4%) patients. High ADC predicted poor DFS, but not when the analysis was adjusted for p16. A break in RT (hazard ratio, HR = 3.972, 95% confidence interval, CI 1.445–10.917, p = 0.007) and larger metastasis volume (HR = 1.041, 95% CI 1.007–1.077, p = 0.019) were associated with worse DFS. A primary tumor larger than 7 cm³ was associated with increased LRR rate (HR = 4.861, 1.042–22.667, p = 0.044). Among p16-positive tumors, mean ADC was lower in grade 3 tumors compared to lower grade tumors (0.736 vs. 0.883; p = 0.003).

Conclusion

Low tumor ADC seems to be related to p16 positivity and therefore should not be used independently to evaluate disease prognosis or to choose patients for treatment deintensification.

Radiological differences in computed tomography findings and texture analysis between cystic lymph node metastases of human papillomavirus-positive oropharyngeal cancer and second branchial cysts

Purpose

The study aimed to analyse radiological differences in computed tomography (CT) findings and texture analysis between cystic lymph node metastases (CNM) in human papillomavirus (HPV)-positive oropharyngeal cancer (OPC) and second branchial cleft cysts (2^nd BC).

Material and methods

Patients with pathological evidence of CNM-HPV-OPC and 2^nd BC, who underwent contrast-enhanced CT, were retrospectively evaluated. The evaluated characteristics include age, sex, and CT findings. CT findings included the maximum and minimum transverse diameters, maximum caudal diameter, thickness of the peripheral wall, presence of internal septation, presence of surrounding fat stranding, location, and 40 texture parameters.

Results

A total of 13 patients had CNM-HPV-OPC (19 lesions), while 20 patients had 2^nd BC (20 lesions). Patients with 2^nd BC were significantly younger than those with CNM-HPV-OPC (p < 0.001). In terms of diameter, 2^nd BC lesions were significantly larger than the CNM-HPV-OPC lesions (p < 0.001). CNM-HPV OPC lesions had significantly thicker walls than 2^nd BC lesions (p < 0.001). CNM-HPV-OPC lesions had significantly higher association with internal septations than 2^nd BC lesions (p < 0.001). Second BC lesions were significantly less common at level III than CNM-HPV-OPC lesions (p = 0.047). Among the 40 texture parameters measured, 8 had significant differences (p ≤ 0.001).

Conclusions

There were significant differences in CT findings and textural parameters between CNM-HPV-OPC and 2^nd BC lesions. These results may help in differentiating one from the other.

Oropharyngeal squamous cell carcinomas: Can imaging findings predict HPV status?

PURPOSE

This is first Australian population-based retrospective study in HPV-induced OPSCCs utilising CT. Contrast enhanced computed tomography (CECT) was utilised to assess if imaging findings of metastatic cystic lymph nodes (LNs) can predict human papillomavirus (HPV) status, as defined by p16 immunostaining of oropharyngeal squamous cell carcinomas (OPSCCs).

MATERIALS AND METHODS

The location and p16 status of primary tumours and LNs were recorded. Metastatic LNs were assessed for size, shape, margins and cystic changes. Hounsfield Units (HU) value of primary tumours and LNs were measured and tabulated. p16-positive and p16-negative groups were compared with respect to these variables. The two-sample t test and two-sample Mann-Whitney test was used.

RESULTS

A total of 364 CECT scans were reviewed with 209 patients (187 p16 positive and 22 p16 negative). Primary sites of OPSCCs were tonsils (58.8%), base of tongue (37.4%) and other oropharyngeal sites (3.8%). The HU values of p16-positive OPSCCs with mean of 78.6HU; 95% CI (76.5-80.8) were lower for p16-negative tumours, mean 96.0 HU CI 95% (85.5-106.6) for all oropharyngeal sub-sites. The mean HU values of p16-positive and p16-negative metastatic LNs were 38.8 HU 95% CI: (13-103 HU) versus 88.7 HU 95% CI: (54-131) (P < 0.0001).

CONCLUSIONS

The association between p16-positive status and the tonsillar cancer site is very high. Imaging features of p16-positive metastatic LNs include relatively large cystic neck nodes with low HU values. This is an imaging signature of p16-positive OPSCCs and can potentially influence patient's early diagnosis and prognosis.

Differences in clinical and imaging characteristics between p16-positive non-smokers and p16-positive smokers or p16-negative patients in oropharyngeal carcinoma

The eighth edition of the TNM classifies oropharyngeal squamous cell carcinomas (OSCCs) depending on p16 status. Some imaging features are reportedly associated more frequently with p16-positive (P16+) OSCC than p16-negative (p16−) OSCC. However, classical risk factors such as tobacco use were not specifically considered when assessing these imaging features. We aimed to evaluate whether P16+ OSCCs have different epidemiological, clinical, prognostic and imaging features depending on smoking status, and to compare P16+ and p16− groups. A retrospective study of data from 85 patients with P16+ OSCC (41 non-smokers, 44 smokers) and 36 with p16− OSCC from 2011 to 2020 was carried out, assessing epidemiological data, clinical aspects of the tumour and presence of adenopathy. Staging was assessed according to the seventh and eighth editions of the TNM. Compared with P16+ OSCC non-smokers, P16+ OSCC smokers had tumours that were less well-defined (36.6% vs 77.8%, p < 0.001), more ulcerated (85.4% vs 44.4%, p < 0.001) and more necrotic (53.7% vs 25%, p = 0.012). There was also less downstaging from N2 or N3 of the seventh edition of the TNM to N1 of the eighth edition for smokers than non-smokers (22.7% vs 43.9%, p = 0.042). Compared with p16− tumours, more P16+ tumours had well-defined contours (55.8% vs 22.2%, p = 0.001), were exophytic (89.6% vs 72.2%, p = 0.023), less necrotic (40.3% vs 80.6%, p < 0.001), less ulcerated (97.2% vs 66.2%, p = 0.006) and involved less muscle tissue (26.0% vs 47.2%, p = 0.027).P16+ OSCCs of smokers show clinical, imaging and prognostic differences with P16+ OSCCs of non-smokers.

Oropharyngeal squamous cell carcinoma: radiomic machine-learning classifiers from multiparametric MR images for determination of HPV infection status

We investigated the ability of machine-learning classifiers on radiomics from pre-treatment multiparametric magnetic resonance imaging (MRI) to accurately predict human papillomavirus (HPV) status in patients with oropharyngeal squamous cell carcinoma (OPSCC). This retrospective study collected data of 60 patients (48 HPV-positive and 12 HPV-negative) with newly diagnosed histopathologically proved OPSCC, who underwent head and neck MRIs consisting of axial T1WI, T2WI, CE-T1WI, and apparent diffusion coefficient (ADC) maps from diffusion-weighted imaging (DWI). The median age was 59 years (the range being 35 to 85 years), and 83.3% of patients were male. The imaging data were randomised into a training set (32 HPV-positive and 8 HPV-negative OPSCC) and a test set (16 HPV-positive and 4 HPV-negative OPSCC) in each fold. 1618 quantitative features were extracted from manually delineated regions-of-interest of primary tumour and one definite lymph node in each sequence. After feature selection by using the least absolute shrinkage and selection operator (LASSO), three different machine-learning classifiers (logistic regression, random forest, and XG boost) were trained and compared in the setting of various combinations between four sequences. The highest diagnostic accuracies were achieved when using all sequences, and the difference was significant only when the combination did not include the ADC map. Using all sequences, logistic regression and the random forest classifier yielded higher accuracy compared with the that of the XG boost classifier, with mean area under curve (AUC) values of 0.77, 0.76, and 0.71, respectively. The machine-learning classifier of non-invasive and quantitative radiomics signature could guide the classification of the HPV status.

Machine Learning Based Radiomic HPV Phenotyping of Oropharyngeal SCC: A Feasibility Study Using MRI

OBJECTIVES

To investigate whether a radiomic MRI feature-based prediction model can differentiate oropharyngeal squamous cell carcinoma (SCC) according to the human papillomavirus (HPV) status.

STUDY DESIGN

Retrospective cohort study.

METHODS

Pretreatment MRI data from 62 consecutive patients with oropharyngeal SCC were retrospectively reviewed, and chronologically allocated to training (n = 43) and test sets (n = 19). Enhancing tumors were semi-automatically segmented on each slice of the postcontrast T1WI to span the entire tumor volume, after registration of T2WI to postcontrast T1WI; 170 radiomic features were extracted from the entire tumor volume. Relevant features were selected and radiomics models were trained using least absolute shrinkage and selection operator (LASSO) logistic regression model with 10-fold cross-validation, after subsampling of training sets using synthetic minority over-sampling technique to mitigate data imbalance. The selected features, weighted by their respective coefficients, were combined linearly to yield a radiomics score. The diagnostic performance of the radiomic score was evaluated using the area under the receiver operating characteristic curve (AUC).

RESULTS

Six radiomic features, which revealed strong association with HPV status of oropharyngeal SCC, were selected using LASSO. The radiomics model yielded excellent performance on the training set (AUC, 0.982 [95% CI, 0.942-1.000]) and moderate performance on the test set (AUC, 0.744 [95% CI, 0.496-0.991]) for differentiating oropharyngeal SCC according to HPV status.

CONCLUSIONS

Radiomics-based MRI phenotyping differentiates oropharyngeal SCC according to HPV status, and thus, is a potential imaging biomarker.

LEVEL OF EVIDENCE

3 Laryngoscope, 131:E851-E856, 2021.

Multiple imputation and clinico-serological models to predict human papillomavirus status in oropharyngeal carcinoma: An alternative when tissue is unavailable

In cancer epidemiological studies, determination of human papillomavirus (HPV) in oropharyngeal squamous cell carcinoma (OPSCC) typically depends on the availability of tumor tissue testing, and/or tumor tissue access. Identifying alternative methods for estimating HPV status can improve the quality of such studies when tissue is unavailable. We developed multiple predictive models for tumor HPV status and prognosis by combining both clinico-epidemiological variables and either serological multiplex assays of HPV or multiple imputation of HPV status (HPV_mi ). Sensitivity, specificity and accuracy of these methods compared to either p16 immunostaining (p16 IHC) or survival were assessed. When compared to a reference of tumor tissue p16 IHC in 783 OPSCC patients, the clinic-HPV_sero model incorporating a composite of 20 HPV serological antibodies (HPV_sero ) and 4 clinical factors (c-index: 0.96) performed better than using HPV_sero (c-index: 0.92) or HPV_mi (c-index: 0.76) alone. However, the model that contained a single HPV16 E6 antibody combined with four clinical variables, performed extremely well (clinic-s1-16E6; c-index: 0.95). When defining HPV status by HPV_sero , s1-16E6, HPV_mi or through p16 IHC, each of these definitions demonstrated improved overall and disease-free survival in HPV-positive OPSCC patients, when compared to HPV-negative patients (adjusted hazard ratios between 0.25 and 0.63). Our study demonstrates that when blood samples are available, a model that utilizes a single s1-16E6 antibody combined with several clinical features has excellent test performance characteristics to estimate HPV status and prognosis. When neither blood nor tumor tissue is available, multiple imputation, calibrated on local population characteristics, remains a viable, but suboptimal option.

Development and validation of a radiomic signature to predict HPV (p16) status from standard CT imaging: a multicenter study

OBJECTIVES

Human papillomavirus (HPV) positive oropharyngeal cancer (oropharyngeal squamous cell carcinoma, OPSCC) is biologically and clinically different from HPV negative OPSCC. Here, we evaluate the use of a radiomic approach to identify the HPV status of OPSCC.

METHODS

Four independent cohorts, totaling 778 OPSCC patients with HPV determined by p16 were collected. We randomly assigned 80% of all data for model training (N = 628) and 20% for validation (N = 150). On the pre-treatment CT images, 902 radiomic features were calculated from the gross tumor volume. Multivariable modeling was performed using least absolute shrinkage and selection operator. To assess the impact of CT artifacts in predicting HPV (p16), a model was developed on all training data (Mall) and on the artifact-free subset of training data (Mno art). Models were validated on all validation data (Vall), and the subgroups with (Vart) and without (Vno art) artifacts. Kaplan-Meier survival analysis was performed to compare HPV status based on p16 and radiomic model predictions.

RESULTS

The area under the receiver operator curve for Mall and Mno art ranged between 0.70 and 0.80 and was not significantly different for all validation data sets. There was a consistent and significant split between survival curves with HPV status determined by p16 [p = 0.007; hazard ratio (HR): 0.46], Mall (p = 0.036; HR: 0.55) and Mno art (p = 0.027; HR: 0.49).

CONCLUSION

This study provides proof of concept that molecular information can be derived from standard medical images and shows potential for radiomics as imaging biomarker of HPV status. Advances in knowledge: Radiomics has the potential to identify clinically relevant molecular phenotypes.

Radiomic analysis in prediction of Human Papilloma Virus status

Human Papilloma Virus (HPV) has been associated with oropharyngeal cancer prognosis. Traditionally the HPV status is tested through invasive lab test. Recently, the rapid development of statistical image analysis techniques has enabled precise quantitative analysis of medical images. The quantitative analysis of Computed Tomography (CT) provides a non-invasive way to assess HPV status for oropharynx cancer patients. We designed a statistical radiomics approach analyzing CT images to predict HPV status. Various radiomics features were extracted from CT scans, and analyzed using statistical feature selection and prediction methods. Our approach ranked the highest in the 2016 Medical Image Computing and Computer Assisted Intervention (MICCAI) grand challenge: Oropharynx Cancer (OPC) Radiomics Challenge, Human Papilloma Virus (HPV) Status Prediction. Further analysis on the most relevant radiomic features distinguishing HPV positive and negative subjects suggested that HPV positive patients usually have smaller and simpler tumors.