Texture-Based Analysis of 100 MR Examinations of Head and Neck Tumors - Is It Possible to Discriminate Between Benign and Malignant Masses in a Multicenter Trial?

External validation of an MR-based radiomic model predictive of locoregional control in oropharyngeal cancer

OBJECTIVES

To externally validate a pre-treatment MR-based radiomics model predictive of locoregional control in oropharyngeal squamous cell carcinoma (OPSCC) and to assess the impact of differences between datasets on the predictive performance.

METHODS

Radiomic features, as defined in our previously published radiomics model, were extracted from the primary tumor volumes of 157 OPSCC patients in a different institute. The developed radiomics model was validated using this cohort. Additionally, parameters influencing performance, such as patient subgroups, MRI acquisition, and post-processing steps on prediction performance will be investigated. For this analysis, matched subgroups (based on human papillomavirus (HPV) status of the tumor, T-stage, and tumor subsite) and a subgroup with only patients with 4-mm slice thickness were studied. Also the influence of harmonization techniques (ComBat harmonization, quantile normalization) and the impact of feature stability across observers and centers were studied. Model performances were assessed by area under the curve (AUC), sensitivity, and specificity.

RESULTS

Performance of the published model (AUC/sensitivity/specificity: 0.74/0.75/0.60) drops when applied on the validation cohort (AUC/sensitivity/specificity: 0.64/0.68/0.60). The performance of the full validation cohort improves slightly when the model is validated using a patient group with comparable HPV status of the tumor (AUC/sensitivity/specificity: 0.68/0.74/0.60), using patients acquired with a slice thickness of 4 mm (AUC/sensitivity/specificity: 0.67/0.73/0.57), or when quantile harmonization was performed (AUC/sensitivity/specificity: 0.66/0.69/0.60).

CONCLUSION

The previously published model shows its generalizability and can be applied on data acquired from different vendors and protocols. Harmonization techniques and subgroup definition influence performance of predictive radiomics models.

KEY POINTS

• Radiomics, a noninvasive quantitative image analysis technique, can support the radiologist by enhancing diagnostic accuracy and/or treatment decision-making. • A previously published model shows its generalizability and could be applied on data acquired from different vendors and protocols.

Largest diameter delineations can substitute 3D tumor volume delineations for radiomics prediction of human papillomavirus status on MRI's of oropharyngeal cancer

PURPOSE

Laborious and time-consuming tumor segmentations are one of the factors that impede adoption of radiomics in the clinical routine. This study investigates model performance using alternative tumor delineation strategies in models predictive of human papillomavirus (HPV) in oropharyngeal squamous cell carcinoma (OPSCC).

METHODS

Of 153 OPSCC patients, HPV status was determined using p16/p53 immunohistochemistry. MR-based radiomic features were extracted within 3D delineations by an inexperienced observer, experienced radiologist or radiation oncologist, and within a 2D delineation of the largest axial tumor diameter and 3D spheres within the tumor. First, logistic regression prediction models were constructed and tested separately for each of these six delineation strategies. Secondly, the model trained on experienced delineations was tested using these delineation strategies. The latter methodology was repeated with the omission of shape features. Model performance was evaluated using area under the curve (AUC), sensitivity and specificity.

RESULTS

Models constructed and tested using single-slice delineations (AUC/Sensitivity/Specificity: 0.84/0.75/0.84) perform better compared to 3D experienced observer delineations (AUC/Sensitivity/Specificity: 0.76/0.76/0.71), where models based on 4 mm sphere delineations (AUC/Sensitivity/Specificity: 0.77/0.59/0.71) show similar performance. Similar performance was found when experienced and largest diameter delineations (AUC/Sens/Spec: 0.76/0.75/0.65 vs 0.76/0.69/0.69) was used to test the model constructed using experienced delineations without shape features.

CONCLUSION

Alternative delineations can substitute labor and time intensive full tumor delineations in a model that predicts HPV status in OPSCC. These faster delineations may improve adoption of radiomics in the clinical setting. Future research should evaluate whether these alternative delineations are valid in other radiomics models.

A Deep Learning Model for Preoperative Differentiation of Glioblastoma, Brain Metastasis and Primary Central Nervous System Lymphoma: A Pilot Study

Background

Neuroimaging differentiation of glioblastoma, primary central nervous system lymphoma (PCNSL) and solitary brain metastasis (BM) remains challenging in specific cases showing similar appearances or atypical features. Overall, advanced MRI protocols have high diagnostic reliability, but their limited worldwide availability, coupled with the overlapping of specific neuroimaging features among tumor subgroups, represent significant drawbacks and entail disparities in the planning and management of these oncological patients.

Objective

To evaluate the classification performance metrics of a deep learning algorithm trained on T1-weighted gadolinium-enhanced (T1Gd) MRI scans of glioblastomas, atypical PCNSLs and BMs.

Materials and Methods

We enrolled 121 patients (glioblastoma: n=47; PCNSL: n=37; BM: n=37) who had undergone preoperative T1Gd-MRI and histopathological confirmation. Each lesion was segmented, and all ROIs were exported in a DICOM dataset. The patient cohort was then split in a training and hold-out test sets following a 70/30 ratio. A Resnet101 model, a deep neural network (DNN), was trained on the training set and validated on the hold-out test set to differentiate glioblastomas, PCNSLs and BMs on T1Gd-MRI scans.

Results

The DNN achieved optimal classification performance in distinguishing PCNSLs (AUC: 0.98; 95%CI: 0.95 - 1.00) and glioblastomas (AUC: 0.90; 95%CI: 0.81 - 0.97) and moderate ability in differentiating BMs (AUC: 0.81; 95%CI: 0.70 - 0.95). This performance may allow clinicians to correctly identify patients eligible for lesion biopsy or surgical resection.

Conclusion

We trained and internally validated a deep learning model able to reliably differentiate ambiguous cases of PCNSLs, glioblastoma and BMs by means of T1Gd-MRI. The proposed predictive model may provide a low-cost, easily-accessible and high-speed decision-making support for eligibility to diagnostic brain biopsy or maximal tumor resection in atypical cases.

The Role of Pretreatment 18F-FDG PET/CT for Early Prediction of Neoadjuvant Chemotherapy Response in Patients with Locoregionally Advanced Nasopharyngeal Carcinoma

Introduction

To evaluate the role of maximal standardized uptake values (SUVmax) and total lesion glycolysis (TLG) from serial ¹⁸F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) for early prediction of neoadjuvant chemotherapy (NAC) response in locoregionally advanced nasopharyngeal carcinoma (LANPC).

Methods

A total of 121 LANPC patients who completed pretreatment ¹⁸F-FDG PET/CT between June 2017 and July 2020 were retrospectively included. The median age of all the participants was 50 years old (range: 19–74 years), with 94 (77.7%) males and 27 (22.3%) females. The SUVmax from the primary tumor site (SUVmax-PT) and the total lesion glycolysis from the primary tumor site (TLG-PT) were recorded. Tumor response was calculated according to the Response Evaluation Criteria in Solid Tumor (RECIST) 1.1 Criteria at two-week post-secondary NAC cycle. Patients who achieved an objectively partial or full reaction after two cycles of NAC were defined as ‘responders’, and patients who obtained stability or progression were classified as ‘non-responders’.

Results

After two cycles of NAC, 96 patients were categorized as “responders” and 25 patients as “non-responders”. The optimal thresholds of the SUVmax-PT were 11.8 and 38.5 for the TLG-PT. Non-responders were significantly associated with high SUVmax-PT (HR, 3.49; 95% CI, 1.17–10.36; p = 0.024) and TLG-PT (HR, 4.45; 95% CI, 1.44–13.78; p = 0.010) in multivariate analysis. Recursive partitioning analysis (RPA) categorized patients into three prognostic groups based on SUVmax-PT and TLG-PT: high-response group, intermediate-response group, and low-response group, with corresponding favorable response rates of 94%, 80%, and 55%, respectively. Moreover, a nomogram was created based on metabolic parameters that precisely projected an individual’s response of NAC (C-index, 0.787; 95% CI, 0.533–1.000).

Conclusion

Pretreatment ¹⁸F-FDG PET/CT to measure SUVmax-PT and TLG-PT could be a useful non-invasive method for early indication of NAC efficacy. The nomogram based on PET/CT parameters may potentially provide direction for treatment decisions based on NAC levels.

Radiomics feature stability of open-source software evaluated on apparent diffusion coefficient maps in head and neck cancer

Radiomics is a promising technique for discovering image based biomarkers of therapy response in cancer. Reproducibility of radiomics features is a known issue that is addressed by the image biomarker standardisation initiative (IBSI), but it remains challenging to interpret previously published radiomics signatures. This study investigates the reproducibility of radiomics features calculated with two widely used radiomics software packages (IBEX, MaZda) in comparison to an IBSI compliant software package (PyRadiomics). Intensity histogram, shape and textural features were extracted from 334 diffusion weighted magnetic resonance images of 59 head and neck cancer (HNC) patients from the PREDICT-HN observational radiotherapy study. Based on name and linear correlation, PyRadiomics shares 83 features with IBEX and 49 features with MaZda, a sub-set of well correlated features are considered reproducible (IBEX: 15 features, MaZda: 18 features). We explore the impact of including non-reproducible radiomics features in a HNC radiotherapy response model. It is possible to classify equivalent patient groups using radiomic features from either software, but only when restricting the model to reliable features using a correlation threshold method. This is relevant for clinical biomarker validation trials as it provides a framework to assess the reproducibility of reported radiomic signatures from existing trials.

Diagnostic Utility of Radiomics in Thyroid and Head and Neck Cancers

Radiomics is an emerging field in radiology that utilizes advanced statistical data characterizing algorithms to evaluate medical imaging and objectively quantify characteristics of a given disease. Due to morphologic heterogeneity and genetic variation intrinsic to neoplasms, radiomics have the potential to provide a unique insight into the underlying tumor and tumor microenvironment. Radiomics has been gaining popularity due to potential applications in disease quantification, predictive modeling, treatment planning, and response assessment - paving way for the advancement of personalized medicine. However, producing a reliable radiomic model requires careful evaluation and construction to be translated into clinical practices that have varying software and/or medical equipment. We aim to review the diagnostic utility of radiomics in otorhinolaryngology, including both cancers of the head and neck as well as the thyroid.

MRI-Based radiomics nomogram for differentiation of benign and malignant lesions of the parotid gland

OBJECTIVES

Preoperative differentiation between benign parotid gland tumors (BPGT) and malignant parotid gland tumors (MPGT) is important for treatment decisions. The purpose of this study was to develop and validate an MRI-based radiomics nomogram for the preoperative differentiation of BPGT from MPGT.

METHODS

A total of 115 patients (80 in training set and 35 in external validation set) with BPGT (n = 60) or MPGT (n = 55) were enrolled. Radiomics features were extracted from T1-weighted and fat-saturated T2-weighted images. A radiomics signature model and a radiomics score (Rad-score) were constructed and calculated. A clinical-factors model was built based on demographics and MRI findings. A radiomics nomogram model combining the Rad-score and independent clinical factors was constructed using multivariate logistic regression analysis. The diagnostic performance of the three models was evaluated and validated using ROC curves on the training and validation datasets.

RESULTS

Seventeen features from MR images were used to build the radiomics signature. The radiomics nomogram incorporating the clinical factors and radiomics signature had an AUC value of 0.952 in the training set and 0.938 in the validation set. Decision curve analysis showed that the nomogram outperformed the clinical-factors model in terms of clinical usefulness.

CONCLUSIONS

The above-described radiomics nomogram performed well for differentiating BPGT from MPGT, and may help in the clinical decision-making process.

KEY POINTS

• Differential diagnosis between BPGT and MPGT is rather difficult by conventional imaging modalities. • A radiomics nomogram integrated with the radiomics signature, clinical data, and MRI features facilitates differentiation of BPGT from MPGT with improved diagnostic efficacy.

A CT-based radiomics nomogram for differentiation of lympho-associated benign and malignant lesions of the parotid gland

OBJECTIVES

Preoperative differentiation between benign lymphoepithelial lesion (BLEL) and mucosa-associated lymphoid tissue lymphoma (MALToma) in the parotid gland is important for treatment decisions. The purpose of this study was to develop and validate a CT-based radiomics nomogram combining radiomics signature and clinical factors for the preoperative differentiation of BLEL from MALToma in the parotid gland.

METHODS

A total of 101 patients with BLEL (n = 46) or MALToma (n = 55) were divided into a training set (n = 70) and validation set (n = 31). Radiomics features were extracted from non-contrast CT images, a radiomics signature was constructed, and a radiomics score (Rad-score) was calculated. Demographics and CT findings were assessed to build a clinical factor model. A radiomics nomogram combining the Rad-score and independent clinical factors was constructed using multivariate logistic regression analysis. The performance levels of the nomogram, radiomics signature, and clinical model were evaluated and validated on the training and validation datasets, and then compared among the three models.

RESULTS

Seven features were used to build the radiomics signature. The radiomics nomogram incorporating the clinical factors and radiomics signature showed favorable predictive value for differentiating parotid BLEL from MALToma, with AUCs of 0.983 and 0.950 for the training set and validation set, respectively. Decision curve analysis showed that the nomogram outperformed the clinical factor model in terms of clinical usefulness.

CONCLUSIONS

The CT-based radiomics nomogram incorporating the Rad-score and clinical factors showed favorable predictive efficacy for differentiating BLEL from MALToma in the parotid gland, and may help in the clinical decision-making process.

KEY POINTS

• Differential diagnosis between BLEL and MALToma in parotid gland is rather difficult by conventional imaging modalities. • A radiomics nomogram integrated with the radiomics signature, demographics, and CT findings facilitates differentiation of BLEL from MALToma with improved diagnostic efficacy.

Clinical variables and magnetic resonance imaging-based radiomics predict human papillomavirus status of oropharyngeal cancer

BACKGROUND

Human papillomavirus (HPV)-positive oropharyngeal squamous cell carcinoma (OPSCC) have better prognosis and treatment response compared to HPV-negative OPSCC. This study aims to noninvasively predict HPV status of OPSCC using clinical and/or radiological variables.

METHODS

Seventy-seven magnetic resonance radiomic features were extracted from T1-weighted postcontrast images of the primary tumor of 153 patients. Logistic regression models were created to predict HPV status, determined with immunohistochemistry, based on clinical variables, radiomic features, and its combination. Model performance was evaluated using area under the curve (AUC).

RESULTS

Model performance showed AUCs of 0.794, 0.764, and 0.871 for the clinical, radiomic, and combined models, respectively. Smoking, higher T-classification (T3 and T4), larger, less round, and heterogeneous tumors were associated with HPV-negative tumors.

CONCLUSION

Models based on clinical variables and/or radiomic tumor features can predict HPV status in OPSCC patients with good performance and can be considered when HPV testing is not available.

Texture analysis of T2-weighted MRI predicts SDH mutation in paraganglioma

PURPOSE

Texture analysis can quantify sophisticated imaging characteristics. We hypothesized that 2D textures computed with T2-weighted and post-contrast T1-weighted MRI can predict succinate dehydrogenase (SDH) mutation status in head and neck paragangliomas.

METHODS

Our retrospective study included 21 patients (1 to 4 tumors/patient) with 24 pathologically proven paragangliomas in the head and neck. Fourteen lesions (58%) were SDH mutation-positive. All patients underwent T2-weighted and post-contrast T1-weighted MRI sequences. Three 2D texture features of dependence non-uniformity normalized (DNN), small dependence high gray level emphasis (SDHGLE), and small dependence low gray level emphasis (SDLGLE) were calculated. Computed textures between SDH mutants and non-mutants were compared using Mann-Whitney U test. Area under the receiver operating characteristic (AUROC) curve was used to quantify the predictive power of each texture.

RESULTS

Only T2-based SDLGLE was statistically significant (p = 0.048), and AUROC was 0.71. Diagnostic accuracy was 70.8%.

CONCLUSION

2D texture parameter of T2-based SDLGLE predicts SDH mutation in head and neck paragangliomas. This noninvasive technique can potentially facilitate further genetic workup.

Myocardial Radiomics in Cardiac MRI

OBJECTIVE. The purpose of this article is to review the nascent field of radiomics in cardiac MRI. CONCLUSION. Cardiac MRI produces a large number of images in a fairly inefficient manner with sometimes limited clinical application. In the era of precision medicine, there is increasing need for imaging to account for a broader array of diseases in an efficient and objective manner. Radiomics, the extraction and analysis of quantitative imaging features from medical imaging, may offer potential solutions to this need.

MRI-derived radiomics: methodology and clinical applications in the field of pelvic oncology

Personalized medicine aims at offering optimized treatment options and improved survival for cancer patients based on individual variability. The success of precision medicine depends on robust biomarkers. Recently, the requirement for improved non-biologic biomarkers that reflect tumor biology has emerged and there has been a growing interest in the automatic extraction of quantitative features from medical images, denoted as radiomics. Radiomics as a methodological approach can be applied to any image and most studies have focused on PET, CT, ultrasound, and MRI. Here, we aim to present an overview of the radiomics workflow as well as the major challenges with special emphasis on the use of multiparametric MRI datasets. We then reviewed recent studies on radiomics in the field of pelvic oncology including prostate, cervical, and colorectal cancer.

The Transition from Metal-Based to Metal-Free Contrast Agents for T1 Magnetic Resonance Imaging Enhancement

Magnetic resonance imaging (MRI) has received significant attention as the noninvasive diagnostic technique for complex diseases. Image-guided therapeutic strategy for diseases such as cancer has also been at the front line of biomedical research, thanks to the innovative MRI, enhanced by the prior delivery of contrast agents (CAs) into patients' bodies through injection. These CAs have contributed a great deal to the clinical utility of MRI but have been based on metal-containing compounds such as gadolinium, manganese, and iron oxide. Some of these CAs have led to cytotoxicities such as the incurable Nephrogenic Systemic Fibrosis (NSF), resulting in their removal from the market. On the other hand, CAs based on organic nitroxide radicals, by virtue of their structural composition, are metal free and without the aforementioned drawbacks. They also have improved biocompatibility, ease of functionalization, and long blood circulation times, and have been proven to offer tissue contrast enhancement with longitudinal relaxivities comparable with those for the metal-containing CAs. Thus, this Review highlights the recent progress in metal-based CAs and their shortcomings. In addition, the remarkable goals achieved by the organic nitroxide radical CAs in the enhancement of MR images have also been discussed extensively. The focal point of this Review is to emphasize or demonstrate the crucial need for transition into the use of organic nitroxide radicals-metal-free CAs-as against the metal-containing CAs, with the aim of achieving safer application of MRI for early disease diagnosis and image-guided therapy.

Radiomics based likelihood functions for cancer diagnosis

Radiomic features based classifiers and neural networks have shown promising results in tumor classification. The classification performance can be further improved greatly by exploring and incorporating the discriminative features towards cancer into mathematical models. In this research work, we have developed two radiomics driven likelihood models in Computed Tomography(CT) images to classify lung, colon, head and neck cancer. Initially, two diagnostic radiomic signatures were derived by extracting 105 3-D features from 200 lung nodules and by selecting the features with higher average scores from several supervised as well as unsupervised feature ranking algorithms. The signatures obtained from both the ranking approaches were integrated into two mathematical likelihood functions for tumor classification. Validation of the likelihood functions was performed on 265 public data sets of lung, colon, head and neck cancer with high classification rate. The achieved results show robustness of the models and suggest that diagnostic mathematical functions using general tumor phenotype can be successfully developed for cancer diagnosis.

Repeatability of texture features derived from magnetic resonance and computed tomography imaging and use in predictive models for non-small cell lung cancer outcome

PURPOSE

To evaluate the repeatability of MRI and CT derived texture features and to investigate the feasibility of use in predictive single and multi-modality models for radiotherapy of non-small cell lung cancer. Methods: Fifty-nine texture features were extracted from unfiltered and wavelet filtered images. Repeatability of test-retest features from helical 4D CT scans, true fast MRI with steady state precession (TRUFISP), and volumetric interpolation breath-hold examination (VIBE) was determined by the concordance correlation coefficient (CCC). A workflow was developed to predict overall survival at 12, 18, and 24 months and tumour response at end of treatment for tumour features, and normal muscle tissue features as a control. Texture features were reduced to repeatable and stable features before clustering. Cluster representative feature selection was performed by univariate or medoid analysis before model selection. P-values were corrected for false discovery rate. Results: Repeatable (CCC ≥ 0.9) features were found for both tumour and normal muscle tissue: CT: 54.4% for tumour and 78.5% for normal tissue, TRUFISP: 64.4% for tumour and 67.8% for normal tissue, and VIBE: 52.6% for tumour and 72.9% for normal muscle tissue. Muscle tissue control analysis found 7 significant models with 6 of 7 models utilizing the univariate representative feature selection technique. Tumour analysis revealed 12 significant models for overall survival and none for tumour response at end of treatment. The accuracy of significant single modality was about the same for MR and CT. Multi-modality tumour models had comparable performance to single modality models. Conclusion: MR derived texture features may add value to predictive models and should be investigated in a larger cohort. Control analysis demonstrated that the medoid representative feature selection method may result in more robust models. .

The utility of MRI histogram and texture analysis for the prediction of histological diagnosis in head and neck malignancies

BACKGROUND

To assess the utility of histogram and texture analysis of magnetic resonance (MR) fat-suppressed T2-weighted imaging (Fs-T2WI) for the prediction of histological diagnosis of head and neck squamous cell carcinoma (SCC) and malignant lymphoma (ML).

METHODS

The cases of 57 patients with SCC (45 well/moderately and 12 poorly differentiated SCC) and 10 patients with ML were retrospectively analyzed. Quantitative parameters with histogram features (relative mean signal, coefficient of variation, kurtosis and skewness) and gray-level co-occurrence matrix (GLCM) features (contrast, correlation, energy and homogeneity) were calculated using Fs-T2WI data with a manual tumor region of interest (ROI).

RESULTS

The following significantly different values were obtained for the total SCC versus ML groups: relative mean signal (3.65 ± 0.86 vs. 2.61 ± 0.49), contrast (72.9 ± 16.2 vs. 49.3 ± 8.7) and homogeneity (2.22 ± 0.25 × 10^- 1 vs. 2.53 ± 0.12 × 10^- 1). In the comparison of the SCC histological grades, the relative mean signal and contrast were significantly lower in the poorly differentiated SCC (2.89 ± 0.63, 56.2 ± 12.9) compared to the well/moderately SCC (3.85 ± 0.81, 77.5 ± 13.9). The homogeneity in poorly differentiated SCC (2.56 ± 0.15 × 10^- 1) was higher than that of the well/moderately SCC (2.1 ± 0.18 × 10^- 1).

CONCLUSIONS

Parameters obtained by histogram and texture analysis of Fs-T2WI may be useful for noninvasive prediction of histological type and grade in head and neck malignancy.

Quantitative Radiomics: Impact of Pulse Sequence Parameter Selection on MRI-Based Textural Features of the Brain

Objectives

Radiomic features extracted from diverse MRI modalities have been investigated regarding their predictive and/or prognostic value in a variety of cancers. With the aid of a 3D realistic digital MRI phantom of the brain, the aim of this study was to examine the impact of pulse sequence parameter selection on MRI-based textural parameters of the brain.

Methods

MR images of the employed digital phantom were realized with SimuBloch, a simulation package made for fast generation of image sequences based on the Bloch equations. Pulse sequences being investigated consisted of spin echo (SE), gradient echo (GRE), spoiled gradient echo (SP-GRE), inversion recovery spin echo (IR-SE), and inversion recovery gradient echo (IR-GRE). Twenty-nine radiomic textural features related, respectively, to gray-level intensity histograms (GLIH), cooccurrence matrices (GLCOM), zone size matrices (GLZSM), and neighborhood difference matrices (GLNDM) were evaluated for the obtained MR realizations, and differences were identified.

Results

It was found that radiomic features vary considerably among images generated by the five different T1-weighted pulse sequences, and the deviations from those measured on the T1 map vary among features, from a few percent to over 100%. Radiomic features extracted from T1-weighted spin-echo images with TR varying from 360 ms to 620 ms and TE = 3.4 ms showed coefficients of variation (CV) up to 45%, while up to 70%, for T2-weighted spin-echo images with TE varying over the range 60-120 ms and TR = 6400 ms.

Conclusion

Variability of radiologic textural appearance on MR realizations with respect to the choice of pulse sequence and imaging parameters is feature-dependent and can be substantial. It calls for caution in employing MRI-derived radiomic features especially when pooling imaging data from multiple institutions with intention of correlating with clinical endpoints.

Evaluation of radiomic texture feature error due to MRI acquisition and reconstruction: A simulation study utilizing ground truth

The purpose of this study was to examine the dependence of image texture features on MR acquisition parameters and reconstruction using a digital MR imaging phantom. MR signal was simulated in a parallel imaging radiofrequency coil setting as well as a single element volume coil setting, with varying levels of acquisition noise, three acceleration factors, and four image reconstruction algorithms. Twenty-six texture features were measured on the simulated images, ground truth images, and clinical brain images. Subtle algorithm-dependent errors were observed on reconstructed phantom images, even in the absence of added noise. Sources of image error include Gibbs ringing at image edge gradients (tissue interfaces) and well-known artifacts due to high acceleration; two of the iterative reconstruction algorithms studied were able to mitigate these image errors. The difference of the texture features from ground truth, and their variance over reconstruction algorithm and parallel imaging acceleration factor, were compared to the clinical "effect size", i.e., the feature difference between high- and low-grade tumors on T1- and T2-weighted brain MR images of twenty glioma patients. The measured feature error (difference from ground truth) was small for some features, but substantial for others. The feature variance due to reconstruction algorithm and acceleration factor were generally smaller than the clinical effect size. Certain texture features may be preserved by MR imaging, but adequate precautions need to be taken regarding their validity and reliability. We present a general simulation framework for assessing the robustness and accuracy of radiomic textural features under various MR acquisition/reconstruction scenarios.

Exploring Applications of Radiomics in Magnetic Resonance Imaging of Head and Neck Cancer: A Systematic Review

Background

Radiomics has been widely investigated for non-invasive acquisition of quantitative textural information from anatomic structures. While the vast majority of radiomic analysis is performed on images obtained from computed tomography, magnetic resonance imaging (MRI)-based radiomics has generated increased attention. In head and neck cancer (HNC), however, attempts to perform consistent investigations are sparse, and it is unclear whether the resulting textural features can be reproduced. To address this unmet need, we systematically reviewed the quality of existing MRI radiomics research in HNC.

Methods

Literature search was conducted in accordance with guidelines established by Preferred Reporting Items for Systematic Reviews and Meta-Analyses. Electronic databases were examined from January 1990 through November 2017 for common radiomic keywords. Eligible completed studies were then scored using a standardized checklist that we developed from Enhancing the Quality and Transparency of Health Research guidelines for reporting machine-learning predictive model specifications and results in biomedical research, defined by Luo et al. (1). Descriptive statistics of checklist scores were populated, and a subgroup analysis of methodology items alone was conducted in comparison to overall scores.

Results

Sixteen completed studies and four ongoing trials were selected for inclusion. Of the completed studies, the nasopharynx was the most common site of study (37.5%). MRI modalities varied with only four of the completed studies (25%) extracting radiomic features from a single sequence. Study sample sizes ranged between 13 and 118 patients (median of 40), and final radiomic signatures ranged from 2 to 279 features. Analyzed endpoints included either segmentation or histopathological classification parameters (44%) or prognostic and predictive biomarkers (56%). Liu et al. (2) addressed the highest number of our checklist items (total score: 48), and a subgroup analysis of methodology checklist items alone did not demonstrate any difference in scoring trends between studies [Spearman’s ρ = 0.94 (p < 0.0001)].

Conclusion

Although MRI radiomic applications demonstrate predictive potential in analyzing diverse HNC outcomes, methodological variances preclude accurate and collective interpretation of data.

MR-based radiomics signature in differentiating ocular adnexal lymphoma from idiopathic orbital inflammation

OBJECTIVES

To assess the value of the MR-based radiomics signature in differentiating ocular adnexal lymphoma (OAL) and idiopathic orbital inflammation (IOI).

METHODS

One hundred fifty-seven patients with pathology-proven OAL (84 patients) and IOI (73 patients) were divided into primary and validation cohorts. Eight hundred six radiomics features were extracted from morphological MR images. The least absolute shrinkage and selection operator (LASSO) procedure and linear combination were used to select features and build radiomics signature for discriminating OAL from IOI. Discriminating performance was assessed by the area under the receiver-operating characteristic curve (AUC). The predictive results were compared with the assessment of radiologists by chi-square test.

RESULTS

Five radiomics features were included in the radiomics signature, which differentiated OAL from IOI with an AUC of 0.74 and 0.73 in the primary and validation cohorts respectively. There was a significant difference between the classification results of the radiomics signature and those of a radiology resident (p < 0.05), although there was no significant difference between the results of the radiomics signature and those of a more experienced radiologist (p > 0.05).

CONCLUSIONS

Radiomics features have the potential to differentiate OAL from IOI.

KEY POINTS

• Clinical and imaging findings of OAL and IOI often overlap, which makes diagnosis difficult. • Radiomics features can potentially differentiate OAL from IOI non invasively. • The radiomics signature discriminates OAL from IOI at the same level as an experienced radiologist.

MRI-Based Texture Analysis to Differentiate Sinonasal Squamous Cell Carcinoma from Inverted Papilloma

BACKGROUND AND PURPOSE

Because sinonasal inverted papilloma can harbor squamous cell carcinoma, differentiating these tumors is relevant. The objectives of this study were to determine whether MR imaging-based texture analysis can accurately classify cases of noncoexistent squamous cell carcinoma and inverted papilloma and to compare this classification performance with neuroradiologists' review.

MATERIALS AND METHODS

Adult patients who had inverted papilloma or squamous cell carcinoma resected were eligible (coexistent inverted papilloma and squamous cell carcinoma were excluded). Inclusion required tumor size of >1.5 cm and preoperative MR imaging with axial T1, axial T2, and axial T1 postcontrast sequences. Five well-established texture analysis algorithms were applied to an ROI from the largest tumor cross-section. For a training dataset, machine-learning algorithms were used to identify the most accurate model, and performance was also evaluated in a validation dataset. On the basis of 3 separate blinded reviews of the ROI, isolated tumor, and entire images, 2 neuroradiologists predicted tumor type in consensus.

RESULTS

The inverted papilloma (n = 24) and squamous cell carcinoma (n = 22) cohorts were matched for age and sex, while squamous cell carcinoma tumor volume was larger (P = .001). The best classification model achieved similar accuracies for training (17 squamous cell carcinomas, 16 inverted papillomas) and validation (7 squamous cell carcinomas, 6 inverted papillomas) datasets of 90.9% and 84.6%, respectively (P = .537). For the combined training and validation cohorts, the machine-learning accuracy (89.1%) was better than that of the neuroradiologists' ROI review (56.5%, P = .0004) but not significantly different from the neuroradiologists' review of the tumors (73.9%, P = .060) or entire images (87.0%, P = .748).

CONCLUSIONS

MR imaging-based texture analysis has the potential to differentiate squamous cell carcinoma from inverted papilloma and may, in the future, provide incremental information to the neuroradiologist.

Radiomics in head and neck cancer: from exploration to application

In the context of clinical oncology, a fundamental goal of radiomics is the extraction of large amounts of quantitative features whose subsequent analysis can be used for decision support towards personalized and actionable cancer care. Head and neck cancers present a unique set of diagnostic and therapeutic challenges by nature of its complex anatomy and heterogeneity. Radiomics holds the potential to address these barriers, but only if as a collective field we direct future effort towards investigating specific oncologic function and oncologic outcomes, with external validation and collaborative multi-institutional efforts to begin standardizing and refining radiomic signatures. Here we present an overview of radiomic texture analysis methods as well as the software infrastructure, review the developments of radiomics in head and neck cancer applications, discuss unmet challenges, and propose key recommendations for moving the field forward.