Sage Journals: Discover world-class research

Abstract

French

Background and Purpose: Human papillomavirus-associated oropharyngeal squamous cell carcinoma (OPSCC) is increasingly prevalent. Despite the overall more favorable outcome, the observed heterogeneous treatment response within this patient group highlights the need for additional means to prognosticate and guide clinical decision-making. Promising prediction models using radiomics from primary OPSCC have been derived. However, no model/s using metastatic lymphadenopathy exist to allow prognostication in those instances when the primary tumor is not seen. The aim of our study was to evaluate whether radiomics using metastatic lymphadenopathy allows for the development of a useful risk assessment model comparable to the primary tumor and whether additional knowledge of the HPV status further improves its prognostic efficacy. Materials and Methods: 80 consecutive patients diagnosed with stage III-IV OPSCC between February 2009 and October 2015, known human papillomavirus status, and pre-treatment CT images were retrospectively identified. Manual segmentation of primary tumor and metastatic lymphadenopathy was performed and the extracted texture features were used to develop multivariate assessment models to prognosticate treatment response. Results: Texture analysis of either the primary or metastatic lymphadenopathy from pre-treatment enhanced CT images can be used to develop models for the stratification of treatment outcomes in OPSCC patients. AUCs range from .78 to .85 for the various OPSCC groups tested, indicating high predictive capability of the models. Conclusions: This preliminary study can form the basis multi-centre trial that may help optimize treatment and improve quality of life in patients with OPSCC in the era of personalized medicine.

Visual Abstract

Keywords

human papilloma virus oropharyngeal squamous cell carcinoma texture analysis lymph node logistic regression

Introduction

Head and neck cancer is the sixth most common cancer worldwide, with oropharyngeal squamous cell carcinoma (OPSCC) arising from the base of tongue and tonsils comprising the most common histologic subtype and anatomic subsites.¹ Traditional risk factors include smoking and alcohol consumption, and affected patients most commonly are white men between 40-55 years of age. In recent years, human papillomavirus (HPV)-associated oropharyngeal squamous cell carcinoma related to infection with high-risk HPV genotypes, most notably HPV-16, has emerged as a distinct entity. It differs from the HPV-negative disease in patient demographics, molecular profiles and more importantly, in its markedly more favorable prognosis. This is reflected in the most recent eighth edition of the American Joint Committee on Cancer (AJCC) staging guideline for oropharyngeal cancer from 2017 which provides distinct staging criteria based on HPV status, and immunohistochemistry of p16 protein as a marker for HPV status has been incorporated into the routine workup for OPSCC.^2,3

Treatment options for both HPV-negative and HPV-positive OPSCC patient populations include primary surgery and/or radiation therapy with or without chemotherapy. Multiple treatment de-intensification trials are ongoing with the aim to minimize acute and long-term treatment complications and improve patient quality of life without adversely affecting survival.^4-7 Despite the overall more favorable outcome for the HPV-positive OPSCC patient population, there is heterogeneity in the treatment response with a substantial risk of disease recurrence [.26 Hazard Ratio (HR)] and death (.24 HR) among these patients.⁸ Therefore, identification of additional parameters in addition to HPV status to predict treatment response in OPSCC patients would be beneficial for personalization of care and selection of candidates for potential de-intensification treatment.

Radiomics is a rapidly emerging field of imaging analysis that employs high-throughput quantitative mapping of features from standard of care medical images to develop models that assist in clinical decision making by improving diagnostic, prognostic and predictive accuracy. So far, oncologic applications include screening, staging and prognosis; in particular, prediction of survival and the development of distant metastatic disease.^9,10 With regards to OPSCC, radiomics based on CT, MRI and FDG PET-CT images have been used in the prediction of HPV or p53 status, local treatment control and tumor type differentiation.^11-18 Advanced analysis methods to estimate the mean intracellular water molecular lifetime and volume transfer constant in MRI have been utilized to prognosticate overall survival in patients with head and neck SCC.^19,20 Ou et al. have developed a model to stratify patients with locally advanced head and neck SCC on chemoradiotherapy treatment.¹⁵ In a meticulous study using pre-treatment enhanced CT imaging, the M.D. Anderson Cancer Centre Head and Neck Quantitative Imaging Working Group consortium used radiomics based on primary tumor in oropharyngeal squamous cell carcinoma to predict local recurrence at 55 months.²¹ However, in some cases, the primary tumor remains occult on imaging and endoscopic examinations, and diagnosis in these cases relies on biopsy of metastatic lymph nodes.

We hypothesize that using texture signatures from pre-treatment CT images of the metastatic lymph nodes may help in stratification of treatment outcome of OPSCC patients. The aim of this study is therefore to develop a multivariable risk assessment model for OPSCC based on 3D high order texture analysis of both the primary tumor and metastatic lymphadenopathy on pre-treatment CT images, with or without regard to HPV status, and compare their prognostic efficacy. We sought to elucidate whether radiomics of metastatic lymphadenopathy allows for stratification of OPSCC patients, and whether additional knowledge of the HPV status leads to a higher prognostic efficacy of the assessment model.

Materials and Methods

Patient Selection

Retrospective chart review of 299 consecutive patients with head and neck cancer diagnosed between February 2009 and October 2015, and treated at our institution was performed. All patients underwent standard of care treatment (surgery, radiation therapy, and chemotherapy, either as single modalities or in combination). 80 consecutive patients were selected that had biopsy-proven stage III-IV oropharyngeal squamous cell carcinoma (both p16 positive and negative), known HPV status and pre-treatment contrast-enhanced CT scan of the neck that showed both the primary tumor and metastatic lymph nodes. Patient characteristics are summarized in Table 1. Further inclusion criteria included minimum follow-up of 24 months and documented treatment response. Patients with distant metastatic disease at the time of diagnosis, past malignancy, prior chemotherapy or radiotherapy or surgery to the neck region were excluded. Patients with unclear documentation of the treatment protocol or treatment response were also excluded. Favorable treatment response was defined as the absence of regional or distant metastatic disease at 24 months by clinical examination and follow-up imaging. In patients with unfavorable treatment response, regional or distant metastatic disease recurrence secondary to prior OPSCC was confirmed by biopsy. The study was approved by the Conjoint Health Research Ethics Board.
Table 1.
Patient Characteristics.

Characteristics Number Percentage

Sex

Male 70 87.5

Female 10 12.5

Ethnicity

White 77 96.3

Black 0 0

Hispanic 1 1.3

Asian 2 2.5

Smoking status

Current smoker 23 28.8

Former smoker 33 41.3

Never smoker 24 30

Tumor subsite in oropharynx

Base of tongue 36 43.8

Tonsil 44 55

p16/HPV status

Positive 68 85

Negative 12 15

Local control

Responder 53 66.3

Non-responder 27 33.8

Local recurrence 10 37% of non-responders

Distant metastases 16 59.3% of non-responders

Refractory to treatment 1 3.7% of non-responders

CT Imaging and Segmentation

Contrast-enhanced CT examinations of the neck were performed preoperatively. Images were acquired at .625 mm intervals from the supraorbital ridge to the sternoclavicular joints after administration of 125 mL non-ionic iodinated contrast material (Optiray 350) using a split injection technique (50 mL with a 3-minute delay and 75 mL with a 20 second delay) on one of the CT scanners: Lightspeed VCT 64-slice or 16-slice CT scanners (GE Healthcare, Milwaukee, Wisconsin), Revolution 64-slice CT scanner (GE Healthcare) and Somatom 128-slice CT scanner (Siemens Healthcare, Forchheim, Germany). We employed a compensation method to correct for the variations of radiomic features caused by using different CT scanners and reconstruction techniques.²² Using the reformatted soft tissue algorithm axial images with 2.5 mm slice thickness, manual segmentation of either both primary tumor and a representative ipsilateral metastatic lymph node containing cystic and solid components was performed by a senior radiology resident (YS.C.) in a slice-by-slice manner using the OsiriX graphical-user interphase.²³ Image slices with artifact from dental hardware involving the primary tumor or metastatic lymph node were excluded from segmentation. Contouring was validated independently by a senior neuroradiology fellow (J.N.) and a fellowship-trained neuroradiology staff with more than 10 years’ experience in head and neck image interpretation (J.T.L.). Representative images of segmentation are shown in Supplemental Figure 1.

Texture Features

326 texture features were extracted from the contoured primary tumor and metastatic lymph node using an in-house developed MATLAB based software.²⁴ These features can be classified into three separate sets: 1) first order statistics (34 features), 2) volume-based statistics (6 features), and 3) higher order statistical textural information (286 features).

First order statistics are calculated from all voxels in the region of interest, and are common measurements such as mean and standard deviation, among others. Volume-based features quantify the size and shape of the region of interest. Texture features are a broad spectrum of higher-order statistical operations that characterize the heterogeneity of the region in 3 dimensions.

Radiomics Features and Machine Learning Modules

Not all 326 features were included in the machine learning models implemented later in this paper. First, the large set of statistical features were reduced to a subset of the most discriminative features. Linear discrimination analysis (LDA) was used to rank each feature individually in terms of its discriminatory importance (Table 2) This list was used to select the number of features included in each machine learning model. These features were then used to train a machine learning algorithm to classify the desired binary groups. The top 15 most distinctive features for each of the binary groups are listed in Table 3. The maximum number of texture features included was determined by maximizing cross-validated accuracy. This value was not the same for each binary group, or each machine learning model. Maximums typically occurred between 5-20 texture features. To make one-to-one comparisons, the average threshold was determined for all models/binary groups. This threshold was 15 +/− 3 texture features, where the error was determined from the standard deviation of all thresholds averaged. This standard deviation was converted into uncertainty when reporting AUCs and cross-validated accuracies.
Table 2.
Texture Features Calculated in the Present Work.

Type Method Number of Features

First-order statistics Characterization of intensity distribution 34

Volume-based statistics Characterizing the size & shape of the ROI 6

Texture features Gray-level co-occurrence matrix 78

Gray-level run length matrix 66

Neighborhood gray-level difference matrix 10

Law textures 105

Local binary pattern 27

Table 3.
Top 15 Selected Features for Each Binary Group.

Group Top-Ranked Features

Primary tumor (OP) 1. Standard deviation of Laws LLS
2. Standard deviation of Laws LLW
3. Absolute mean of Laws LLS
4. Absolute mean of Laws LLW
5. Standard deviation of Laws LLR
6. Mean of Laws EER
7. Mean of Laws EES
8. Absolute mean of Laws LES
9. Mean of Laws EWW
10. Absolute mean of Laws LLE
11. Standard deviation of Laws LLE
12. Homogeneity of GLCM with level number 60 at sagittal orientation
13. Mean of Laws LEW
14. The second moment of GLDM at axial orientation
15. Entropy of GLDM at axial orientation

Lymph node (LN) 1. Proportion of 3 × 3 × 3 kernel LBP with a value of 5 to the total distribution of LBP values
2. Standard deviation of information measure of correlation1 of GLCM at sagittal orientation
3. Proportion of 5 × 5 × 5 kernel LBP with a value of 8 to the total distribution of LBP values
4. Mean of information measure of correlation1 of GLCM at axial orientation
5. Proportion of 5 × 5 × 5 kernel LBP with a value of 10 to the total distribution of LBP values
6. Proportion of 5 × 5 × 5 kernel LBP with a value of 4 to the total distribution of LBP values
7. Mean of 5 × 5 × 5 kernel LBP
8. Mean of information measure of correlation2 of GLCM at axial orientation
9. Run length of non-uniformity of GLRL at level of 120 at coronal orientation
10. Proportion of 5 × 5 × 5 kernel LBP with a value of 11 to the total distribution of LBP values
11. Proportion of 3 × 3 × 3 kernel LBP with a value of 4 to the total distribution of LBP values
12. Mean of information measure of correlation2 of GLCM at axial orientation
13. GLCM_axial_NL60_inf1h_m
14. Coarseness of NGTDM at level of600
15. Coarseness of NGTDM at level of 60

P16 1. Mean of LAWS LES
2. Mean of LAWS LEE
3. Proportion of pixel numbers with 25 – 50 HU to the total number of ROI pixels
4. Proportion of pixel numbers with 0 -25 HU to the total number of ROI pixels
5. Mean of LAWS SSW
6. Mean of GLDM in sagittal orientation
7. Standard deviation of LAWS EEE
8. Angular second moment of GLDM at sagittal orientation
9. Standard deviation of LAWS EES
10. Standard deviation of HU distribution for ROI
11. Standard deviation of GFB blurred at .16 mm
12. Standard deviation of GFB blurred at .32 mm
13. Standard deviation of GFB blurred at .64 mm
14. Standard deviation of LAWS EEW
15. Mean of LAWS SWW

OP + P16 positive 1. Mean of LAWS EEW
2. Mean of LAWS EER
3. Standard deviation of LAWS LLS
4. Mean of LAWS EWW
5. Standard deviation of LAWS LLR
6. Standard deviation of information measure of correlation2 of GLCM at axial orientation
7. Standard deviation of LAWS LLW
8. Absolute mean of LAWS LLS
9. Absolute mean of LAWS LLW
10. Run length of non-uniformity of GLRL at level of 30 at coronal orientation
11. Standard deviation of sum of entropy of GLCM at sagittal orientation
12. Absolute mean of LAWS LLR
13. Proportion of pixel numbers with 75 - 100 HU to the total number of ROI pixels
14. Proportion of LBP length of 2 with kernel size of 3
15. Angular second moment of GLDM at axial orientation

LN + P16 positive 1. Proportion of 5 × 5 × 5 kernel LBP with a value of 10 to the total distribution of LBP values
2. Proportion of 5 × 5 × 5 kernel LBP with a value of 11 to the total distribution of LBP values
3. Proportion of 5 × 5 × 5 kernel LBP with a value of 8 to the total distribution of LBP values
4. Standard deviation of maximum proportion of GLCM at axial orientation
5. Proportion of 3 × 3 × 3 kernel LBP with a value of 4 to the total distribution of LBP values
6. Mean of information measure of correlation1 of GLCM at axial orientation
7. Standard deviation of information measure of correlation1 of GLCM at sagittal orientation
8. Run length of non-uniformity of GLRL at level of 120 at coronal orientation
9. Proportion of 3 × 3 × 3 kernel LBP with a value of 5 to the total distribution of LBP values
10. Proportion of 5 × 5 × 5 kernel LBP with a value of 8 to the total distribution of LBP values
11. Coarseness of NGTDM at level of 600
12. Coarseness of NGTDM at level of 60
13. Run length of non-uniformity of GLRL at level of 120 at sagittal orientation
14. Mean of information measure of correlation2 of GLCM at axial orientation
15. Short run of high gray level emphasis of GLRL at level of 120 at sagittal orientation

Abbreviation: LAWS – E, edge; L, level, S, spot; R, ripple; W, Wave;²⁶ LBP, local binary pattern;^27,28 GLRL, gray-level run length, GLCM, gray- level co-occurrence matrix^29,30; NGTDM, neighboring gray tone difference matrix; GFB, gabor filter bank.

Logistic regression (LR) is often used in small data sets due to their resistivity to overfitting. Due to the small sample size of our study, LR minimized overfitting and provided reliable cross-validated accuracy and AUC. In our study, LR was implemented to discriminate between 5 binary groups. For each binary group, the data sets were trained with increasing numbers of texture features, taken from the rank list created from LDA. The optimal number of features was determined by maximizing cross-validated accuracy.

Oversampling

Due to the asymmetry between the positive and negative binary groups, a correction was required to ensure the models were not biased towards a certain binary subgroup. This was corrected by oversampling each group, to equalize the positive and negative groups.

ROC Analysis and Leave-One-Out Cross Validation

The Area Under the Curve (AUC) of a Receiver Operating Characteristic (ROC) curve was used to evaluate the performance of the derived machine learning model. To minimize overfitting, leave-one-out cross validation (LOOCV) strategy was used to train the machine learning models. Specifically, the model is constructed with the one less than the patient population. Then, that one patient is tested with the fitted model to determine if it can accurately classify the patient into the correct binary class. This is completed for all patients in the data set, “leaving one out” for each iteration. The accuracy, sensitivity and specificity was then calculated considering results from all iterations. This accuracy tests the variance in the model by assessing overfitting. This was the primary statistic used when determining a texture feature dimensionality threshold.

Results

Patient Characteristics

Of the 80 patients with biopsy-proven OPSCC and known HPV status that fulfilled the selection criteria, 53 patients had favorable response to chemo radiation treatment (“responders”), and 27 patients demonstrated regional or distant metastatic disease (“non-responders”) at 24 months following treatment. 68 patients were HPV-positive as confirmed with p16 immunohistochemistry staining. Of these, 46 patients were responders, and 22 patients were non-responders.

The patients were divided into five binary groups, and their texture features used by the machine learning model to further stratify each group into responders and non-responders. The first four groups were: primary OPSCC (HPV-positive and HPV-negative combined; “OP”), metastatic lymph node (HPV-positive and HPV-negative combined; “LN”), HPV-positive only primary OPSCC and HPV-positive only metastatic lymph node. The fifth group comprised primary OPSCC texture features from 68 HPV-positive and 12 HPV-negative patients and served as an internal control for the efficacy of the machine learning model utilized to determine the p16/HPV status (Figure 1).
Figure 1.
Workflow chart.

As stated earlier, we determined the p16/HPV status based on primary OPSCC texture features of our patients as an internal control (“Primary tumor HPV status” group of Figs.), and the results are shown in Figure 2. The AUC measures .91 ± .06, indicating a robust discrimination of the HPV status by LR. AUC for the primary OPSCC binary group (“Primary tumor combined” group of Figure 1) was .86 ± .03 and .78 ± .03 for the metastatic lymphadenopathy group (“Metastatic LN combined” group in Figure 1), irrespective of HPV status (Figure 3).
Figure 2.
Comparison of HPV status binary for the primary tumor. Brackets indicate uncertainty.
Figure 3.
Comparison between lymph node and primary tumor binaries. Brackets indicate uncertainty.

We proceeded to analyze radiomics features of primary OPSCC and metastatic lymph nodes within the HPV-positive patient group to elucidate whether knowledge of HPV status provided added information in the stratification process (Figure 4). For the HPV-positive primary OPSCC group (“Primary tumor HPV (+)-only” in Figure 1), AUC measured .84 ± .05, slightly lower compared to .86 ± .03 for the general primary OPSCC group. However, AUC for the HPV-positive metastatic lymph node group (“Metastatic LN HPV (+)-only” in Figure 1) measuring .80 ± .02 was slightly higher when compared to .78 ± .03 for the general metastatic lymph node group. The AUC, Accuracy, Sensitivity and Specificity for all models have been summarized in Figures 2, 3 and 4.
Figure 4.
Comparison between lymph node and primary tumor binaries for HPV-positive patients. Brackets indicate uncertainty.

Discussion

Radiomics has emerged as a promising tool to advance clinical decision making by extracting quantitative information based on texture features from medical imaging. In the era of personalized medicine, stratification of OPSCC patient population based on pre-treatment imaging studies harbors the prospect of decreasing treatment-associated side effects and improving the quality of life of patients.

The use of radiomics to stratify treatment response based on texture features derived from pre-treatment CT images of primary OPSCC has been elucidated meticulously in the study from M.D. Anderson Cancer Centre.²¹ Bogowicz et al. showed that expanding radiomics analysis with LN radiomic features improves model performance for prediction of the more complex and clinically more relevant endpoint loco regional control.²⁵

In our study, we showed that texture analysis of either the primary tumor or metastatic lymphadenopathy from pre-treatment enhanced CT images can be used to develop models for the stratification of OPSCC patient treatment outcome. Our models using texture features from primary OPSCC are in keeping with results from M.D. Anderson Cancer Centre, albeit the lower sensitivity and specificity in our study is likely due to our considerably lower patient number. In addition, we showed that models using primary tumor are consistently slightly superior compared to the ones using texture features from metastatic lymph nodes, irrespective of HPV status. However, combination of texture features of the metastatic lymph nodes with additional knowledge of positive HPV status is superior to texture features alone. This is of importance, as sometimes the primary tumor cannot be found either on endoscopy or pre-treatment imaging. In these instances, advanced imaging modalities such as MRI or FDG PET-CT could provide alternative sources for patient stratification,^11,20 but are not always performed and are themselves limited in their ability to detect the primary tumor. In most institutions, contrast-enhanced CT remains the most common pre-treatment imaging modality performed.

Our study was limited by the retrospective nature of the analysis, small patient number and the absence of external validation. Multi-class training of texture features was also not possible, so analysis was limited to binary outcomes. Further validation of our models is planned with either a separate set of OPSCC patients meeting the same inclusion/exclusion criteria within our institution (internal validation) or from an external institution (external validation). For the latter option, differences in image acquisition secondary to technology- and protocoling-related differences will have to be taken into consideration.

Conclusions

In this study based on pre-treatment CT images of stage III-IV patients with OPSCC, we developed predictive models using texture features derived from primary tumor and/or metastatic lymphadenopathy. We showed that, while primary tumor data produced superior models, models derived from metastatic lymphadenopathy were only slightly inferior. In addition, the combination of radiomics features with knowledge of HPV-status in metastatic lymph nodes resulted in a superior model compared to radiomics features alone. These findings are of significance since the primary tumor may not be visible endoscopically or on medical imaging. Our findings suggest that radiomics using metastatic lymphadenopathy is a useful adjunctive approach to predicting treatment response. This is a preliminary study to show the potential of lymph node radiomic features as prognostic factor in treatment of OPSSC patients. These results need to be further investigated and validated in a larger, prospective multicentre cohort.

Supplemental Material

Supplemental Material - Risk Stratification for Oropharyngeal Squamous Cell Carcinoma Using Texture Analysis on CT – A Step Beyond HPV Status

Supplemental Material for Risk Stratification for Oropharyngeal Squamous Cell Carcinoma Using Texture Analysis on CT – A Step Beyond HPV Status by Yuh S. Chang, Jaykumar Raghavan Nair, Connor C. McDougall, Wu Qiu, Robyn Banerjee, Manish Joshi, and John T. Lysack in Canadian Association of Radiologists Journal

Characteristics	Number	Percentage
Sex
Male	70	87.5
Female	10	12.5
Ethnicity
White	77	96.3
Black	0	0
Hispanic	1	1.3
Asian	2	2.5
Smoking status
Current smoker	23	28.8
Former smoker	33	41.3
Never smoker	24	30
Tumor subsite in oropharynx
Base of tongue	36	43.8
Tonsil	44	55
p16/HPV status
Positive	68	85
Negative	12	15
Local control
Responder	53	66.3
Non-responder	27	33.8
Local recurrence	10	37% of non-responders
Distant metastases	16	59.3% of non-responders
Refractory to treatment	1	3.7% of non-responders

Type	Method	Number of Features
First-order statistics	Characterization of intensity distribution	34
Volume-based statistics	Characterizing the size & shape of the ROI	6
Texture features	Gray-level co-occurrence matrix	78
Gray-level run length matrix	66
Neighborhood gray-level difference matrix	10
Law textures	105
Local binary pattern	27

Group	Top-Ranked Features
Primary tumor (OP)	1. Standard deviation of Laws LLS 2. Standard deviation of Laws LLW 3. Absolute mean of Laws LLS 4. Absolute mean of Laws LLW 5. Standard deviation of Laws LLR 6. Mean of Laws EER 7. Mean of Laws EES 8. Absolute mean of Laws LES 9. Mean of Laws EWW 10. Absolute mean of Laws LLE 11. Standard deviation of Laws LLE 12. Homogeneity of GLCM with level number 60 at sagittal orientation 13. Mean of Laws LEW 14. The second moment of GLDM at axial orientation 15. Entropy of GLDM at axial orientation
Lymph node (LN)	1. Proportion of 3 × 3 × 3 kernel LBP with a value of 5 to the total distribution of LBP values 2. Standard deviation of information measure of correlation1 of GLCM at sagittal orientation 3. Proportion of 5 × 5 × 5 kernel LBP with a value of 8 to the total distribution of LBP values 4. Mean of information measure of correlation1 of GLCM at axial orientation 5. Proportion of 5 × 5 × 5 kernel LBP with a value of 10 to the total distribution of LBP values 6. Proportion of 5 × 5 × 5 kernel LBP with a value of 4 to the total distribution of LBP values 7. Mean of 5 × 5 × 5 kernel LBP 8. Mean of information measure of correlation2 of GLCM at axial orientation 9. Run length of non-uniformity of GLRL at level of 120 at coronal orientation 10. Proportion of 5 × 5 × 5 kernel LBP with a value of 11 to the total distribution of LBP values 11. Proportion of 3 × 3 × 3 kernel LBP with a value of 4 to the total distribution of LBP values 12. Mean of information measure of correlation2 of GLCM at axial orientation 13. GLCM_axial_NL60_inf1h_m 14. Coarseness of NGTDM at level of600 15. Coarseness of NGTDM at level of 60
P16	1. Mean of LAWS LES 2. Mean of LAWS LEE 3. Proportion of pixel numbers with 25 – 50 HU to the total number of ROI pixels 4. Proportion of pixel numbers with 0 -25 HU to the total number of ROI pixels 5. Mean of LAWS SSW 6. Mean of GLDM in sagittal orientation 7. Standard deviation of LAWS EEE 8. Angular second moment of GLDM at sagittal orientation 9. Standard deviation of LAWS EES 10. Standard deviation of HU distribution for ROI 11. Standard deviation of GFB blurred at .16 mm 12. Standard deviation of GFB blurred at .32 mm 13. Standard deviation of GFB blurred at .64 mm 14. Standard deviation of LAWS EEW 15. Mean of LAWS SWW
OP + P16 positive	1. Mean of LAWS EEW 2. Mean of LAWS EER 3. Standard deviation of LAWS LLS 4. Mean of LAWS EWW 5. Standard deviation of LAWS LLR 6. Standard deviation of information measure of correlation2 of GLCM at axial orientation 7. Standard deviation of LAWS LLW 8. Absolute mean of LAWS LLS 9. Absolute mean of LAWS LLW 10. Run length of non-uniformity of GLRL at level of 30 at coronal orientation 11. Standard deviation of sum of entropy of GLCM at sagittal orientation 12. Absolute mean of LAWS LLR 13. Proportion of pixel numbers with 75 - 100 HU to the total number of ROI pixels 14. Proportion of LBP length of 2 with kernel size of 3 15. Angular second moment of GLDM at axial orientation
LN + P16 positive	1. Proportion of 5 × 5 × 5 kernel LBP with a value of 10 to the total distribution of LBP values 2. Proportion of 5 × 5 × 5 kernel LBP with a value of 11 to the total distribution of LBP values 3. Proportion of 5 × 5 × 5 kernel LBP with a value of 8 to the total distribution of LBP values 4. Standard deviation of maximum proportion of GLCM at axial orientation 5. Proportion of 3 × 3 × 3 kernel LBP with a value of 4 to the total distribution of LBP values 6. Mean of information measure of correlation1 of GLCM at axial orientation 7. Standard deviation of information measure of correlation1 of GLCM at sagittal orientation 8. Run length of non-uniformity of GLRL at level of 120 at coronal orientation 9. Proportion of 3 × 3 × 3 kernel LBP with a value of 5 to the total distribution of LBP values 10. Proportion of 5 × 5 × 5 kernel LBP with a value of 8 to the total distribution of LBP values 11. Coarseness of NGTDM at level of 600 12. Coarseness of NGTDM at level of 60 13. Run length of non-uniformity of GLRL at level of 120 at sagittal orientation 14. Mean of information measure of correlation2 of GLCM at axial orientation 15. Short run of high gray level emphasis of GLRL at level of 120 at sagittal orientation

Footnotes

Abbreviations

Declaration of Conflicting Interests

The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Funding

The author(s) received no financial support for the research, authorship, and/or publication of this article.

ORCID iD

John T. Lysack

Supplemental Material

Supplemental material for this article is available online

References

Chung

Bagheri

D'Souza

. Epidemiology of oral human papillomavirus infection. Oral Oncol. 2014;50:364-369.

Lydiatt

Ridge

Shah

, et al. Oropharynx (p16-) and Hypopharynx. In: Amin

Edge

Greene

, et al, eds. AJCC Cancer Staging Manual. 8th ed. New York: Springer; 2017:123.

O’Sullivan

Lydiatt

Haughey

, et al. HPV-Mediated (p16+) Oropharyngeal Cancer. In: Amin

Edge

Greene

Byrd

Brookland

, eds. AJCC Cancer Staging Manual. 8th ed. New York: Springer; 2017:113.

Chera

Amdur

. Current status and future directions of treatment deintensification in human papilloma virus-associated oropharyngeal squamous cell carcinoma. Semin Radiat Oncol. 2018;28:27-34.

Cheraghlou

Otremba

, et al. Treatment deintensification in human papillomavirus-positive oropharynx cancer: Outcomes from the National Cancer Data Base. Cancer. 2018;124:717-726.

Kelly

Husain

Burtness

. Treatment de-intensification strategies for head and neck cancer. Eur J Cancer. 2016;68:125-133.

Windon

D'Souza

Fakhry

. Treatment preferences in human papillomavirus- associated oropharyngeal cancer. Future Oncol. 2018;14:2521-2530.

Gorphe

Classe

Ammari

, et al. Patterns of disease events and causes of death in patients with HPV-positive versus HPV-negative oropharyngeal carcinoma. Radiother Oncol. 2022;168:40-45.

Gillies

Kinahan

Hricak

. Radiomics: Images are more than pictures, they are data. Radiology. 2016;278:563-577.

10.

Lambin

Leijenaar

RTH

Deist

, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol. 2017;14:749-762.

11.

Cheng

Fang

YHD

Lee

, et al. Zone-size nonuniformity of 18F-FDG PET regional textural features predicts survival in patients with oropharyngeal cancer. Eur J Nucl Med Mol Imag. 2015;42:419-428.

12.

Buch

FujitA

Qureshi

Sakai

. Using texture analysis to determine human papillomavirus status of oropharyngeal squamous cell carcinomas on CT. AJNR Am J Neuroradiol. 2015;36:1343-1348.

13.

Dang

Lysack

, et al. MRI texture analysis predicts p53 status in head and neck squamous cell carcinoma. AJNR Am J Neuroradiol. 2015;36:166-170.

14.

Jansen

JFA

Parra

Shukla-Dave

. Evaluation of head and neck tumors with functional MR imaging. Magn Reson Imag Clin N Am. 2016;24:123-133.

15.

Blanchard

Rosellini

, et al. Predictive and prognostic value of CT based radiomics signature in locally advanced head and neck cancers patients treated with concurrent chemoradiotherapy or bioradiotherapy and its added value to Human Papillomavirus status. Oral Oncol. 2017;71:150-155.

16.

Park

Kim

Choi

, et al. Application of dynamic contrast-enhanced mri parameters for differentiating squamous cell carcinoma and malignant lymphoma of the oropharynx. AJR Am J Roentgenol. 2016;206:401-407.

17.

Vallieres

Kay-Rivest

Perrin

, et al. Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer. Sci Rep. 2017;7:10117.

18.

Wong

Kanwar

Mohamed

Fuller

. Radiomics in head and neck cancer: From exploration to application. Transl Cancer Res. 2016;5:371-382.

19.

Chawla

Kim

Dougherty

, et al. Pretreatment diffusion-weighted and dynamic contrast-enhanced MRI for prediction of local treatment response in squamous cell carcinomas of the head and neck. AJR Am J Roentgenol. 2013;200:35-43.

20.

Chawla

Loevner

Kim

, et al. Dynamic contrast-enhanced MRI-derived intracellular water lifetime (tau i ): A prognostic marker for patients with head and neck squamous cell carcinomas. AJNR Am J Neuroradiol. 2018;39:138-144.

21.

Group MDACCHaNQIW . Investigation of radiomic signatures for local recurrence using primary tumor texture analysis in oropharyngeal head and neck cancer patients. Sci Rep. 2018;8:1524.

22.

Meyer

Ronald

Vernuccio

, et al. Reproducibility of CT radiomic features within the same patient: influence of radiation dose and CT reconstruction settings. Radiology. 2019;293:583-591. [Epub ahead of print]. doi:10.1148/radiol.2019190928

23.

Rosset

Spadola

Ratib

. OsiriX: an open-source software for navigating in multidimensional DICOM images. J Digit Imag. 2004;17:205-216.

24.

Qiu

Kuang

Nair

, et al. Radiomics-based intracranial thrombus features on CT and CTA predict recanalization with intravenous alteplase in patients with acute ischemic stroke. AJNR Am J Neuroradiol. 2019;40:39-44.

25.

Bogowicz

Tanadini-Lang

Guckenberger

Riesterer

. Combined CT radiomics of primary tumor and metastatic lymph nodes improves prediction of loco-regional control in head and neck cancer. Sci Rep. 2019;9:15198.

26.

Laws

. Texture Identification. Proc. SPIE 1980. doi:10.1117/12.959169

27.

Topi

Timo

Matti

, et al. Robust texture classification by subsets of local binary patterns. Proceedings 15th International Conference on Pattern Recognition ICPR-2000 2000;935-938.

28.

Wang

. Texture classification using texture spectrum. Pattern Recognition 1990;23:905-910.

29.

Galloway

. Texture analysis using gray level run lengths. Computer Graphics and Image Processing 1975;4:172-179.

30.

Soh

Tsatsoulis

. Texture analysis of SAR sea ice imagery using gray level co-occurence matrices. IEEE Trans Geosci Remote Sens 1999;37:780-795. doi:10.1109/36.752194

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.14 MB