Table 1.

Overview of study characteristics, divided by topic.

Article	Number of Patients	Subsite	Imaging	Analyzed Endpoint	Statistical Findings	Conclusion
Segmentation
C. Parmar et al. Robust Radiomics Feature Quantification Using Semiautomatic Volumetric Segmentation [15]	20	Lung NSCLC	CT	Segmentation	56 3D radiomic features, quantifying phenotypic differences based on tumor intensity, shape and texture	Radiomic features extracted from 3D slicer segmentations had significantly higher reproducibility, were more robust and overlapping with the feature ranges extracted from manual contouring.
Kuhl, C.K.; Truhn, D. The Long Route to Standardized Radiomics: Unraveling the Knot from the End [16]	51	Soft-tissue sarcoma	CT, MRI and PET	Segmentation	169 preselected features	167 features demonstrated good to excellent reproducibility and 71 were reproducible after a comprehensive inter- and intra-CT image acquisition analysis.
Gitto, S. et al. Effects of Interobserver Variability on 2D and 3D CT- and MRI-Based Texture Feature Reproducibility of Cartilaginous Bone Tumors [17]	30	Bone tumors	CT and MRI	Segmentation	783 and 1132 features were extracted	The features extracted were reproducible. 3D and 2D MRI-based texture analyses provided similar rates of stable features.
Huan Yu et al. Coregistered FDG PET/CT-Based Textural Characterization of Head and Neck Cancer for Radiation Treatment Planning [18]	40	Head and neck cancer and lung cancer	F-FDG PET and CT	Segmentation	Texture features	Gray-tone difference matrices (NGTDM) (PET coarseness, PET contrast and CT coarseness) provided good discrimination performance.
Yu, H. et al. Automated Radiation Targeting in Head-and-Neck Cancer Using Region-Based Texture Analysis of PET and CT Images [19]	10	Head and neck cancer	F-FDG PET and CT	Segmentation	Co-registered multimodality pattern analysis segmentation system (COMPASS)	Tumor delineation was similar to those of the radiation oncologists.
Characterization
Buch, K. et al. Using Texture Analysis to Determine Human Papillomavirus Status of Oropharyngeal Squamous Cell Carcinomas on CT [20]	40	Oropharyngeal carcinoma	CT	Characterization	A t-test evaluated differences in 42 texture features between HPV-positive and -negative carcinoma	There are statistically significant differences in some texture features between human-papillomavirus-positive and human-papillomavirus-negative oropharyngeal tumors.
Fujita, A et al. Difference Between HPV-Positive and HPV-Negative Non-Oropharyngeal Head and Neck Cancer [21]	46	Oral cavity, larynx and hypopharynx cancer	CT	Characterization	Texture analysis program extracted 42 texture features	16 texture parameters showed significant differences in relation to HPV status.
Vallieres, M. et al. FDG-PET Image-Derived Features Can Determine HPV Status in Head-and-Neck Cancer [22]	67	Hypopharynx	FDG-PET	Characterization	Six texture features, two SUV measures and three shape features were extracted, and logistic regression and support vector machine were performed	It is possible to predict HPV status and treatment failure in HNSCC using a combination of FDG-PET texture and morphological features.
Payabvash, S. et al. Differentiation of lymphomatous, metastatic, and non-malignant lymphadenopathy in the neck with quantitative diffusion-weighted imaging: Systematic review and meta-analysis [23]	Review (27 studies and 1165 patients)	Neck lymph nodes	MRI (Diffusion Weighted Imaging, DWI)	Characterization	Random-effects models, pooled diagnostic odds ratio (DOR), summary receiver operating characteristics (sROC), area under the curve (AUC) were determined	Quantitative valuation of ADC can help with differentiation of cervical lymph nodes. Lower ADC values are linked to malignancy and HPV positive status.
Payabvash, S. et al. Quantitative diffusion magnetic resonance imaging for prediction of human papillomavirus status in head and neck squamous-cell carcinoma: A systematic review and meta-analysis [24]	Review (5 studies and 264 patients)	HNSCC	MRI (DWI)	Characterization	Meta-analysis	HPV-positive HNSCC primary lesions have lower ADC.
Marzi, S.et al. Multifactorial Model Based on DWI-Radiomics to Determine HPV Status in Oropharyngeal Squamous Cell Carcinoma [25]	144	Oropharyngeal carcinoma	MRI (DWI)	Characterization	Different families of machine-learning (ML) algorithms and five-fold cross-validation	DWI-based radiomics can help in differentiating HPV-positive from HPV-negative patients.
Suh, C.H. et al. Oropharyngeal squamous cell carcinoma: Radiomic machine-learning classifiers from multiparametric MR images for determination of HPV infection status [26]	60	Oropharyngeal carcinoma	MRI	Characterization	1618 quantitative features extraction, features selection, three machine-learning classifiers (logistic regression, random forest and XG boost)	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.
Sohn, B. et al. Machine Learning Based Radiomic HPV Phenotyping of Oropharyngeal SCC: A Feasibility Study Using MRI [27]	62	Oropharyngeal carcinoma	MRI	Characterization	170 radiomic features	Six radiomic features with strong association with HPV status of SCC were selected using least absolute shrinkage and selection operator (LASSO).
Aerts, H.J.W.L. et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach [28]	1019	Lung or head-and-neck cancer	CT	Characterization	440 features	Some radiomic features had prognostic power associated with underlying gene expression patterns.
Zwirner, K. et al. Radiogenomics in head and neck cancer: Correlation of radiomic heterogeneity and somatic mutations in TP53, FAT1 and KMT2D [29]	20	HNSCC	CT	Characterization	Radiomic features and genetic analysis	Somatic mutations in FAT1 and smaller primary tumor volumes were associated with reduced radiomic intra-tumor heterogeneity.
Huang, C. et al. Development and validation of radiomic signatures of head and neck squamous cell carcinoma molecular features and subtypes [30]	113	HNSCC	CT	Characterization	540 features, logistic regression, AUC	Quantitative image features can distinguish several molecular phenotypes.
Zhu, Y. et al. Imaging-Genomic Study of Head and Neck Squamous Cell Carcinoma: Associations Between Radiomic Phenotypes and Genomic Mechanisms via Integration of The Cancer Genome Atlas and The Cancer Imaging Archive [31]	126	HNSCC	CT	Characterization	Linear regression and gene set enrichment analysis	Associations between genomic features and radiomic features
Chen, R.-Y. et al.; Associations of Tumor PD-1 Ligands, Immunohistochemical Studies, and Textural Features in 18F-FDG PET in Squamous Cell Carcinoma of the Head and Neck [32]	53	HNSCC	18F-FDG PET	Characterization	Associations of tumor PD-1 ligands, immunohistochemical studies and textural features	PD-L1 expressions were positively correlated with Ki-67 c-Met and p16.
Brown, A.M. et al.; Multi-institutional validation of a novel textural analysis tool for preoperative stratification of suspected thyroid tumors on diffusion-weighted MRI [33]		Thyroid tumors	MRI (DWI)	Characterization	21 textural features	Textural analysis (TA) could characterize thyroid nodules using diffusion-weighted MRI (DW-MRI).
Jansen, J.F. Texture analysis on parametric maps derived from dynamic contrast-enhanced magnetic resonance imaging in head and neck cancer [34]	19	HNSCC	Dynamic contrast enhanced (DCE)-MRI	Characterization	Image texture analysis was employed on maps of Ktrans and ve, generating two texture measures	Chemoradiation treatment in HNSCC significantly reduced the heterogeneity of tumors.
Kim, S. et al. Prediction of Response to Chemoradiation Therapy in Squamous Cell Carcinomas of the Head and Neck Using Dynamic Contrast-Enhanced MR Imaging [35]	33	HNSCC	DCE-MRI	Characterization	The data were analyzed by using SSM for estimation of Ktrans, ve and τi	Pretreatment DCE-MR imaging can potentially be used for prediction of response to chemoradiation therapy.
Shukla-Dave et al. Dynamic Contrast-Enhanced Magnetic Resonance Imaging as a Predictor of Outcome in Head-and-Neck Squamous Cell Carcinoma Patients with Nodal Metastases [36]	64	HNSCC	DCE-MRI	Characterization	DCE-MRI data were analyzed using the Tofts model	Important role of pretreatment DCE-MRI parameter K{sup trans} as a predictor of outcome
Dang, M. et al.; MRI Texture Analysis Predicts p53 Status in Head and Neck Squamous Cell Carcinoma [37]	16	HNSCC	MRI	Characterization	Texture analysis	MR imaging texture analysis predicted p53 status.
Staging
Wang, F. et al. Radiomic Nomogram Improves Preoperative T Category Accuracy in Locally Advanced Laryngeal Carcinoma [38]	211	Laryngeal carcinoma	CT	Staging	1390 radiomic features extracted and analyzed	Eight features were found associated with preoperative T category.
Ren, J. et al.; Magnetic resonance imaging based radiomics signature for the preoperative discrimination of stage I-II and III-IV head and neck squamous cell carcinoma [39]	127	HNSCC	MRI	Staging	Radiomics signatures were constructed with least absolute shrinkage and selection operator (LASSO) logistic regression and analyzed	Radiomics signature based on MRI could discriminate stage I–II from stage III–IV HNSCC.
Romeo, V. et al. Prediction of Tumor Grade and Nodal Status in Oropharyngeal and Oral Cavity Squamous-cell Carcinoma Using a Radiomic Approach [40]	40	Oropharyngeal oral cavity carcinoma	CT	Staging	TA features	Tumor grade (TG) and nodal status (NS) could be predicted.
Wang, H. et al.; Machine learning-based multiparametric MRI radiomics for predicting the aggressiveness of papillary thyroid carcinoma [41]	120	Papillary thyroid carcinoma	MRI	Staging	1393 features	Aggressive and non-aggressive PTC could be distinguished preoperatively through machine-learning-based multiparametric MR imaging radiomics.