Machine learning-based MRI radiomics for assessing the level of tumor infiltrating lymphocytes in oral tongue squamous cell carcinoma: a pilot study.

BACKGROUND: To investigate the value of machine learning (ML)-based magnetic resonance imaging (MRI) radiomics in assessing tumor-infiltrating lymphocyte (TIL) levels in patients with oral tongue squamous cell carcinoma (OTSCC). METHODS: The study included 68 patients with pathologically diagnosed OTSCC (30 with high TILs and 38 with low TILs) who underwent pretreatment MRI. Based on the regions of interest encompassing the entire tumor, a total of 750 radiomics features were extracted from T2-weighted (T2WI) and contrast-enhanced T1-weighted (ceT1WI) imaging. To reduce dimensionality, reproducibility analysis by two radiologists and collinearity analysis were performed. The top six features were selected from each sequence alone, as well as their combination, using the minimum-redundancy maximum-relevance algorithm. Random forest, logistic regression, and support vector machine models were used to predict TIL levels in OTSCC, and 10-fold cross-validation was employed to assess the performance of the classifiers. RESULTS: Based on the features selected from each sequence alone, the ceT1WI models outperformed the T2WI models, with a maximum area under the curve (AUC) of 0.820 versus 0.754. When combining the two sequences, the optimal features consisted of one T2WI and five ceT1WI features, all of which exhibited significant differences between patients with low and high TILs (all P < 0.05). The logistic regression model constructed using these features demonstrated the best predictive performance, with an AUC of 0.846 and an accuracy of 80.9%. CONCLUSIONS: ML-based T2WI and ceT1WI radiomics can serve as valuable tools for determining the level of TILs in patients with OTSCC.

Machine learning based on magnetic resonance imaging and clinical parameters helps predict mesenchymal-epithelial transition factor expression in oral tongue squamous cell carcinoma: a pilot study.

OBJECTIVES: This study aimed to develop machine learning models to predict phosphorylated mesenchymal-epithelial transition factor (p-MET) expression in oral tongue squamous cell carcinoma (OTSCC) using magnetic resonance imaging (MRI)-derived texture features and clinical features. METHODS: Thirty-four patients with OTSCC were retrospectively collected. Texture features were derived from preoperative MR images, including T2WI, apparent diffusion coefficient mapping, and contrast-enhanced (ce)-T1WI. Dimension reduction was performed consecutively with reproducibility analysis and an information gain algorithm. Five machine learning methods-AdaBoost, logistic regression (LR), naïve Bayes (NB), random forest (RF), and support vector machine (SVM)-were adopted to create models predicting p-MET expression. Their performance was assessed with fivefold cross-validation. RESULTS: In total, 22 and 12 cases showed low and high p-MET expression, respectively. After dimension reduction, 3 texture features (ADC-Minimum, ce-T1WI-Imc2, and ce-T1WI-DependenceVariance) and 2 clinical features (depth of invasion [DOI] and T-stage) were selected with good reproducibility and best correlation with p-MET expression levels. The RF model yielded the best overall performance, correctly classifying p-MET expression status in 87.5% of OTSCCs with an area under the receiver operating characteristic curve of 0.875. CONCLUSION: Differences in p-MET expression in OTSCCs can be noninvasively reflected in MRI-based texture features and clinical parameters. Machine learning can potentially predict biomarker expression levels, such as MET, in patients with OTSCC.

MRI-based radiomics nomogram for distinguishing solitary fibrous tumor from schwannoma in the orbit: a two-center study.

OBJECTIVES: To investigate the value of magnetic resonance imaging (MRI) radiomics for distinguishing solitary fibrous tumor (SFT) from schwannoma in the orbit. MATERIALS AND METHODS: A total of 140 patients from two institutions were retrospectively included. All patients from institution 1 were randomized into a training cohort (n = 69) and a validation cohort (n = 35), and patients from institution 2 were used as an external testing cohort (n = 36). One hundred and six features were extracted from T2-weighted imaging (T2WI) and contrast-enhanced T1-weighted imaging (CET1WI). A radiomics model was built for each sequence using least absolute shrinkage and selection operator logistic regression, and radiomics scores were calculated. A combined model was constructed and displayed as a radiomics nomogram. Two radiologists jointly assessed tumor category based on MRI findings. The performances of the radiomics models and visual assessment were compared via area under the curve (AUC). RESULTS: The performances of the radiomics nomogram combining T2WI and CET1WI radiomics scores were superior to those of the pooled readers in the training (AUC 0.986 vs. 0.807, p < 0.001), validation (AUC 0.989 vs. 0.788, p = 0.009), and the testing (AUC 0.903 vs. 0.792, p = 0.093), although significant difference was not found in the testing cohort. Decision curve analysis demonstrated that the radiomics nomogram had better clinical utility than visual assessment. CONCLUSION: MRI radiomics nomogram can be used for distinguishing between orbital SFT and schwannoma, which may help tumor management by clinicians. CLINICAL RELEVANCE STATEMENT: It is of great importance and challenging for distinguishing solitary fibrous tumor from schwannoma in the orbit. In the present study, an MRI-based radiomics nomogram were developed and independently validated, which could help the discrimination of the two entities. KEY POINTS: • It is challenging to differentiate solitary fibrous tumor from schwannoma in the orbit due to similar clinical and image features. • A radiomics nomogram based on T2-weighted imaging and contrast-enhanced T1-weighted imaging has advantages over radiologists. • Radiomics can provide a non-invasive diagnostic tool for differentiating between the two entities.

An MRI-based radiomics nomogram for detecting cervical esophagus invasion in hypopharyngeal squamous cell carcinoma.

BACKGROUND: Accurate detection of cervical esophagus invasion (CEI) in HPSCC is challenging but crucial. We aimed to investigate the value of magnetic resonance imaging (MRI)-based radiomics for detecting CEI in patients with HPSCC. METHODS: This retrospective study included 151 HPSCC patients with or without CEI, which were randomly assigned into a training (n = 101) or validation (n = 50) cohort. A total of 750 radiomics features were extracted from T2-weighted imaging (T2WI) and contrast-enhanced T1-weighted imaging (ceT1WI), respectively. A radiomics signature was constructed using the least absolute shrinkage and selection operator method. Multivariable logistic regression analyses were adopted to establish a clinical model and a radiomics nomogram. Two experienced radiologists evaluated the CEI status based on morphological findings. Areas under the curve (AUCs) of the models and readers were compared using the DeLong method. The performance of the nomogram was also assessed by its calibration and clinical usefulness. RESULTS: The radiomics signature, consisting of five T2WI and six ceT1WI radiomics features, was significantly associated with CEI in both cohorts (all p < 0.001). The radiomics nomogram combining the radiomics signature and clinical T stage achieved significantly higher predictive value than the clinical model and pooled readers in the training (AUC 0.923 vs. 0.723 and 0.621, all p < 0.001) and validation (AUC 0.888 vs. 0.754 and 0.647, all p < 0.05) cohorts. The radiomics nomogram showed favorable calibration in both cohorts and provided better net benefit than the clinical model. CONCLUSIONS: The MRI-based radiomics nomogram is a promising method for detecting CEI in HPSCC.

Development and validation of apparent diffusion coefficient histogram-based nomogram for predicting malignant transformation of sinonasal inverted papilloma.

OBJECTIVES: To develop and validate a nomogram based on whole-tumour histograms of apparent diffusion coefficient (ADC) maps for predicting malignant transformation (MT) in sinonasal inverted papilloma (IP). METHODS: This retrospective study included 209 sinonasal IPs with and without MT, which were assigned into a primary cohort (n = 140) and a validation cohort (n = 69). Eight ADC histogram features were extracted from the whole-tumour region of interest. Morphological MRI features and ADC histogram parameters were compared between the two groups (with and without MT). Stepwise logistic regression was used to identify independent predictors and to construct models. The predictive performances of variables and models were assessed using the area under the curve (AUC). The optimal model was presented as a nomogram, and its calibration was assessed. RESULTS: Four morphological features and seven ADC histogram parameters showed significant differences between the two groups in both cohorts (all p < 0.05). Maximum diameter, loss of convoluted cerebriform pattern, ADC10th and ADCSkewness were identified as independent predictors to construct the nomogram. The nomogram showed significantly better performance than the morphological model in both the primary (AUC, 0.96 vs 0.88; p = 0.006) and validation (AUC, 0.96 vs 0.88; p = 0.015) cohorts. The nomogram showed good calibration in both cohorts. Decision curve analysis demonstrated that the nomogram is clinically useful. CONCLUSIONS: The developed nomogram, which incorporates morphological MRI features and ADC histogram parameters, can be conveniently used to facilitate the pre-operative prediction of MT in IPs.

A c-MET-Targeted Topical Fluorescent Probe cMBP-ICG Improves Oral Squamous Cell Carcinoma Detection in Humans.

INTRODUCTION: The postoperative survival of oral squamous cell carcinoma (SCC) relies on precise detection and complete resection of original tumors. The mucosal extension of the tumor is evaluated visually during surgery, but small and flat foci are difficult to detect. Real-time fluorescence imaging may improve detection of tumor margins. MATERIALS AND METHODS: In the current study, a peptide-based near-infrared (NIR) fluorescence dye, c-MET-binding peptide-indocyanine green (cMBP-ICG), which specifically targets tumor via c-MET binding, was synthetized. A prospective pilot clinical trial then was conducted with oral SCC patients and intraoperatively to assess the feasibility of cMBP-ICG used to detect tumors margins. Fluorescence was histologically correlated to determine sensitivity and specificity. RESULTS: The immunohistochemistry (IHC) results demonstrated increased c-Met expression in oral SCC compared with normal mucosa. Tumor-to-background ratios ranged from 2.71 ± 0.7 to 3.11 ± 1.2 in different concentration groups. From 10 patients with oral SCC, 60 specimens were collected from tumor margins. The sensitivity and specificity of discriminative value derived from cMBP-ICG application in humans were respectively 100% and 75%. CONCLUSIONS: Topical application of cMBP-ICG is feasible and safe for optimizing intraoperative visualization and tumor margin detection in oral SCC patients, which could clinically increase the probability of complete resections and improve oncologic outcomes.

Histogram analysis of diffusion-weighted imaging and dynamic contrast-enhanced MRI for predicting occult lymph node metastasis in early-stage oral tongue squamous cell carcinoma.

OBJECTIVES: To investigate the feasibility of whole-tumor histogram analysis of diffusion-weighted imaging (DWI) and dynamic contrast-enhanced (DCE) MRI for predicting occult lymph node metastasis (LNM) in early-stage oral tongue squamous cell cancer (OTSCC). MATERIALS AND METHODS: This retrospective study included 55 early-stage OTSCC (cT1-2N0M0) patients; 34 with pathological LNM and 21 without. Eight whole-tumor histogram features were extracted from quantitative apparent diffusion coefficient (ADC) maps and two semi-quantitative DCE parametric maps (wash-in and wash-out). The clinicopathological factors and histogram features were compared between the two groups. Stepwise logistic regression was used to identify independent predictors. Receiver operating characteristic curves were generated to assess the performances of significant variables and a combined model for predicting occult LNM. RESULTS: MRI-determined depth of invasion and ADCentropy was significantly higher in the LNM group, with respective areas under the curve (AUCs) of 0.67 and 0.69, and accuracies of 0.73 and 0.73. ADC10th. ADCuniformity and wash-inskewness were significantly lower in the LNM group, with respective AUCs of 0.68, 0.71, and 0.69, and accuracies of 0.65, 0.71, and 0.64. Histogram features from wash-out maps were not significantly associated with cervical node status. In the logistic regression analysis, ADC10th, ADCuniformity, and wash-inskewness were independent predictors. The combined model yielded the best predictive performance, with an AUC of 0.87 and an accuracy of 0.82. CONCLUSIONS: Whole-tumor histogram analysis of ADC and wash-in maps is a feasible tool for preoperative evaluation of cervical node status in early-stage OTSCC. KEY POINTS: • Histogram analysis of parametric maps from DWI and DCE-MRI may assist the prediction of occult LNM in early-stage OTSCC. • ADC10th, ADCuniformity, and wash-inskewness were independent predictors. • The combined model exhibited good predictive performance, with an accuracy of 0.82.

Histogram analysis of dynamic contrast-enhanced magnetic resonance imaging in the differential diagnosis of parotid tumors.

OBJECTIVE: Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) histograms were used to investigate whether their parameters can distinguish between benign and malignant parotid gland tumors and further differentiate tumor subgroups. MATERIALS AND METHODS: A total of 117 patients (32 malignant and 85 benign) who had undergone DCE-MRI for pretreatment evaluation were retrospectively included. Histogram parameters including mean, median, entropy, skewness, kurtosis and 10th, 90th percentiles were calculated from time to peak (TTP) (s), wash in rate (WIR) (l/s), wash out rate (WOR) (l/s), and maximum relative enhancement (MRE) (%) mono-exponential models. The Mann-Whitney U test was used to compare the differences between the benign and malignant groups. The diagnostic value of each significant parameter was determined on Receiver operating characteristic (ROC) analysis. Multivariate stepwise logistic regression analysis was used to identify the independent predictors of the different tumor groups. RESULTS: For both the benign and malignant groups and the comparisons among the subgroups, the parameters of TTP and MRE showed better performance among the various parameters. WOR can be used as an indicator to distinguish Warthin's tumors from other tumors. Warthin's tumors showed significantly lower values on 10th MRE and significantly higher values on skewness TTP and 10th WOR, and the combination of 10th MRE, skewness TTP and 10th WOR showed optimal diagnostic performance (AUC, 0.971) and provided 93.12% sensitivity and 96.70% specificity. After Warthin's tumors were removed from among the benign tumors, malignant parotid tumors showed significantly lower values on the 10th TTP (AUC, 0.847; sensitivity 90.62%; specificity 69.09%; P < 0.05) and higher values on skewness MRE (AUC, 0.777; sensitivity 71.87%; specificity 76.36%; P < 0.05). CONCLUSION: DCE-MRI histogram parameters, especially TTP and MRE parameters, show promise as effective indicators for identifying and classifying parotid tumors. Entropy TTP and kurtosis MRE were found to be independent differentiating variables for malignant parotid gland tumors. The 10th WOR can be used as an indicator to distinguish Warthin's tumors from other tumors.

Determination of Cervical Lymph Nodes Metastasis and Extra Nodal Extension Status by Quantitative Assessment of Border Irregularity and Apparent Diffusion Coefficient in Patients With Tongue Squamous Cell Carcinoma.

OBJECTIVE: The objective of this study was to determine the diagnostic value of quantitative border irregularity assessment and apparent diffusion coefficient (ADC) in patients with squamous cell carcinoma of the tongue (SCCT). METHODS: Cervical lymph nodes (n = 192) from 63 patients with SCCT were examined preoperatively by magnetic resonance imaging, including routine head and neck sequences, dynamic contrast-enhanced magnetic resonance imaging, diffusion-weighted imaging, ADC, surface regularity (SR), and visually assessed variables, and evaluated pathologically after surgery. RESULTS: Necrosis, lymphatic hilum, unclear margin, higher SR, long to short axis ratio, and ADC were associated with metastasis in cervical lymph nodes (M-cLNs) and extranodal extension (ENE), and thickened nodal rim with ENE alone. Apparent diffusion coefficient, SR, unclear margin, and visible necrosis were strongly associated with M-cLN, whereas SR, unclear margin, and visible necrosis were associated with ENE status on logistic regression analysis. CONCLUSIONS: Quantitative SR and ADC data greatly improved diagnosis of M-cLNs and ENE, relative to visible variables alone in patients with SCCT.

Machine learning-based MRI texture analysis to predict occult lymph node metastasis in early-stage oral tongue squamous cell carcinoma.

OBJECTIVES: To develop and compare several machine learning models to predict occult cervical lymph node (LN) metastasis in early-stage oral tongue squamous cell cancer (OTSCC) from preoperative MRI texture features. MATERIALS AND METHODS: We retrospectively enrolled 116 patients with early-stage OTSCC (cT1-2N0) who had been surgically treated by tumor excision and elective neck dissection (END). For each patient, we extracted 86 texture features from T2-weighted imaging (T2WI) and contrast-enhanced T1-weighted imaging (ceT1WI), respectively. Dimension reduction was performed in three consecutive steps: reproducibility analysis, collinearity analysis, and information gain algorithm. Models were created using six machine learning methods, including logistic regression (LR), random forest (RF), naïve Bayes (NB), support vector machine (SVM), AdaBoost, and neural network (NN). Their performance was assessed using tenfold cross-validation. RESULTS: Occult LN metastasis was pathologically detected in 42.2% (49/116) of the patients. No significant association was identified between node status and patients' gender, age, or clinical T stage. Dimension reduction steps selected 6 texture features. The NB model gave the best overall performance, which correctly classified the nodal status in 74.1% (86/116) of the carcinomas, with an AUC of 0.802. CONCLUSION: Machine learning-based MRI texture analysis offers a feasible tool for preoperative prediction of occult cervical node metastasis in early-stage OTSCC. KEY POINTS: • A machine learning-based MRI texture analysis approach was adopted to predict occult cervical node metastasis in early-stage OTSCC with no evidence of node involvement on conventional images. • Six texture features from T2WI and ceT1WI of preoperative MRI were selected to construct the predictive model. • After comparing six machine learning methods, naïve Bayes (NB) achieved the best performance by correctly identifying the node status in 74.1% of the patients, using tenfold cross-validation.

Radiomics of apparent diffusion coefficient maps to predict histologic grade in squamous cell carcinoma of the oral tongue and floor of mouth: a preliminary study.

BACKGROUND: Histologic grade assessment plays an important part in the clinical decision making and prognostic evaluation of squamous cell carcinoma (SCC) of the oral tongue and floor of mouth (FOM). PURPOSE: To assess the value of apparent diffusion coefficient (ADC)-based radiomics in discriminating between low- and high-grade SCC of the oral tongue and FOM. MATERIAL AND METHODS: We included data from 88 patients (training cohort: n = 59; testing cohort: n = 29) who underwent diffusion-weighted imaging with a 3.0-T magnetic resonance imaging scanner before treatment. A total of 526 radiomics features were extracted from ADC maps to construct a radiomics signature with least absolute shrinkage and selection operator logistic regression. Receiver operating characteristic curves and areas under the curve (AUCs) were used to evaluate the performance of radiomic signature. RESULTS: Five features were selected to construct the radiomics signature for predicting histologic grade. The ADC-based radiomics signature performed well for discriminating between low- and high-grade tumors, with AUCs of 0.83 in both cohorts. Based on the cut-off value of the training cohort, the radiomics signature achieved accuracies of 0.78 and 0.79, sensitivities of 0.65 and 0.71, and specificities of 0.85 and 0.82 in the training and testing cohorts, respectively. CONCLUSION: ADC-based radiomics can be a useful and promising non-invasive method for predicting histologic grade of SCC of the oral tongue and FOM.

Multiparametric Magnetic Resonance Imaging Features That Predict Treatment Response to Endovascular Sclerotherapy in Craniofacial Venous Malformations.

PURPOSE: Craniofacial venous malformations (VMs) cause severe psychological and physiological burden to patients, and treatment is meaningful only when the benefits of treatment outweigh the risks. Therefore, it is very important to predict the treatment response before treatment. This study was performed to explore the value of multiparametric magnetic resonance imaging for predicting treatment response to endovascular sclerotherapy in VMs. MATERIALS AND METHODS: We designed and implemented a case-control study and enrolled a sample from patients with VM treated by endovascular sclerotherapy at our hospital from January 2014 to January 2018. The primary predictor variables were pretreatment volume (prevolume), lesion classification, phleboliths, initial slope of increase (ISI), gender, age, and sclerosants. The primary outcome variable was treatment response (positive response or negative response). Descriptive, univariate and multivariate binary logistic regressions, and Firth's penalized maximum likelihood estimate were computed to measure the association between predictor variables and treatment response. The level of statistical significance was set at a P value less than or equal to .05. RESULTS: The sample was composed of 42 patients with a median age of 17.50 years, and 33.3% were males. There were 27 and 15 patients in the positive and negative response groups, respectively. There were significant differences between the 2 groups for ISI (adjusted odds ratio [OR], 2.184; P = .0268; 95% confidence interval [95% CI], 1.094 to 4.360), lesion classification (adjusted OR, 9.072; P = .0226; 95% CI, 1.363 to 60.400), and prevolume (adjusted OR, 1.020; P = .0268; 95% CI, 1.002 to 1.038). The cutoff point for prevolume and ISI was 40.42 cm3 and 2.61. CONCLUSIONS: Multiparametric magnetic resonance imaging could provide an approach for predicting treatment response in craniofacial VMs. When the prevolume was greater than 40.42 cm3, ISI was greater than 2.61, and the classification was infiltrating type, the response to sclerotherapy was negative.

Machine Learning-Based MRI Texture Analysis to Predict the Histologic Grade of Oral Squamous Cell Carcinoma.

OBJECTIVE. This study aimed to explore the performance of machine learning (ML)-based MRI texture analysis in discriminating between well-differentiated (WD) oral squamous cell carcinoma (OSCC) and moderately or poorly differentiated OSCC. MATERIALS AND METHODS. The study enrolled 80 patients with pathologically confirmed OSCC (18 WD OSCCs and 62 moderately or poorly differentiated OSCCs) who underwent pretreatment MRI. ROIs were manually delineated to cover the entire tumor to the greatest possible extent on T2-weighted imaging and contrast-enhanced T1-weighted imaging, and 1118 texture features were extracted. Dimension reduction was performed using reproducibility analysis by two radiologists, collinearity analysis, and feature selection with a minimum-redundancy maximum-relevance algorithm. Models were created using random forest (RF), artificial neural network, and logistic regression (LR) alone and with a synthetic minority oversampling technique (SMOTE). Classifier performance was assessed using 10-fold cross-validation. RESULTS. Dimension reduction steps yielded eight texture features, including four features from each sequence. None of the clinical variables was selected. Among the eight texture features, five and seven texture features showed significant differences between the two groups in the actual data and balanced data, respectively (p < 0.05). All classifiers with SMOTE achieved better performances than those alone. The RF classifier with SMOTE achieved the best performance with an area under the ROC curve of 0.936 and accuracy of 86.3%. CONCLUSION. ML-based MRI texture analysis provides a promising noninvasive approach for predicting the histologic grade of OSCC.

Machine learning-based CT texture analysis to predict HPV status in oropharyngeal squamous cell carcinoma: comparison of 2D and 3D segmentation.

OBJECTIVE: To compare the CT texture feature reproducibility of 2D and 3D segmentations and their machine learning (ML)-based classifications for predicting human papilloma virus (HPV) status in oropharyngeal squamous cell carcinoma (OPSCC). MATERIALS AND METHODS: Data about 47 patients with pathological OPSCC (15 HPV positive and 32 HPV negative) were collected from a public database. Using 2D and 3D manual segmentations, 1032 texture features were extracted from contrast-enhanced CT images. Intraclass correlation coefficients (ICCs) were calculated to evaluate intraobserver and interobserver reproducibility. Collinearity analysis and a wrapper-based subset search algorithm were used for feature selection. Models were created using k-nearest neighbors (k-NN), logistic regression (LR), and random forest (RF) alone and with a synthetic minority oversampling technique (SMOTE). Classifier performance was assessed using 10-fold cross-validation. RESULTS: Compared with 2D segmentation (468 of 1032, 45.3%), 3D segmentation (576 of 1032, 55.8%) yielded more texture features with reliable reproducibility (good to excellent in both intraobserver and interobserver analyses) (p < 0.001). RF and k-NN classifiers failed to achieve better classification performance using 3D features than using 2D features either alone or with SMOTE. The best models for 2D and 3D segmentations were both created using RF, which alone achieved areas under the curve (AUCs) of 0.880 and 0.847, respectively, and with SMOTE, AUCs of 0.953 and 0.920, respectively, were achieved. CONCLUSIONS: Three-dimensional segmentation had better CT texture feature reproducibility, but 2D segmentation showed better performance. Considering the cost, 2D segmentation is more recommended for ML-based classification of HPV status of OPSCC. KEY POINTS: • Three-dimensional segmentation had better CT texture feature reproducibility than 2D segmentation. • Despite yielding more features with reliable reproducibility, 3D segmentation failed to provide better classification performance as compared to 2D for predicting HPV status of oropharyngeal squamous cell carcinoma. • The best models for 2D and 3D segmentations were both created using random forest classifier.

Machine learning-based multiparametric MRI radiomics for predicting the aggressiveness of papillary thyroid carcinoma.

PURPOSE: To investigate the predictive capability of machine learning-based multiparametric magnetic resonance (MR) imaging radiomics for evaluating the aggressiveness of papillary thyroid carcinoma (PTC) preoperatively. METHODS: This prospective study enrolled consecutive patients who underwent neck MR scans and subsequent thyroidectomy during the study interval. The diagnosis and aggressiveness of PTC were determined by pathological evaluation of thyroidectomy specimens. Thyroid nodules were segmented manually on the MR images, and radiomic features were then extracted. Predictive machine learning modelling was used to evaluate the prediction of PTC aggressiveness. Area under the receiver operating characteristic curve (AUC) values for the model performance were obtained for radiomic features, clinical characteristics, and combinations of radiomic features and clinical characteristics. RESULTS: The study cohort included 120 patients with pathology-confirmed PTC (training cohort: n = 96; testing cohort: n = 24). A total of 1393 features were extracted from T2-weighted, apparent diffusion coefficient (ADC) and contrast-enhanced T1-weighted MR images for each patient. The combination of Least Absolute Shrinkage and Selection Operator for radiomic feature selection and Gradient Boosting Classifier for classifying PTC aggressiveness achieving the AUC of 0.92. In contrast, clinical characteristics alone poorly predicted PTC aggressiveness, with an AUC of 0.56. CONCLUSIONS: Our study showed that machine learning-based multiparametric MR imaging radiomics could accurately distinguish aggressive from non-aggressive PTC preoperatively. This approach may be helpful for informing treatment strategies and prognosis of patients with aggressive PTC.

A comparative analysis of diffusion-weighted imaging and ultrasound in thyroid nodules.

BACKGROUND: Diffusion-weighted imaging (DWI) and ultrasound are commonly used methods to examine thyroid nodules, but their comparative value is rarely studied. We evaluated the utility of DWI and ultrasound in differentiating benign and malignant thyroid nodules. METHODS: A total of 100 patients with 137 nodules who underwent both DWI and ultrasound before operation were enrolled. The T1 and T2 signal intensity ratio (SIR) of each thyroid nodule was calculated by measuring the mean signal intensity divided by that of paraspinal muscle. The apparent diffusion coefficient (ADC) value and the SIR of benign and malignant thyroid nodules were analyzed by two-sample independent t tests. The sensitivity, specificity, and accuracy of DWI and ultrasound were compared with chi-square tests. RESULTS: There was no significant difference in the SIR between benign and malignant thyroid nodules. The ADC value was significantly different. At the threshold value was 1.12 × 10- 3 mm2/s, the maximum area under the curve was 0.944. The sensitivity, specificity, and accuracy were 84.9, 92.2, and 87.6% respectively. The corresponding values of ultrasound diagnosis were 90.1, 80.4, and 86.9%. CONCLUSIONS: Ultrasound has high sensitivity in differentiating benign and malignant thyroid nodules, and the ADC value has high specificity, but there is no statistical difference in sensitivity or specificity between the two modalities. DWI and ultrasound each have their own advantages in differentiating benign and malignant thyroid nodules.

MRI-based radiomic signature as predictive marker for patients with head and neck squamous cell carcinoma.

PURPOSE: To develop magnetic resonance imaging (MRI)-based radiomic signature and nomogram for preoperatively predicting prognosis in head and neck squamous cell carcinoma (HNSCC) patients. METHOD: This retrospective study consisted of a training cohort (n = 85) and a validation cohort (n = 85) of patients with HNSCC. LASSO Cox regression model was used to select the most useful prognostic features with their coefficients, upon which a radiomic signature was generated. The receiver operator characteristics (ROC) analysis and association of the radiomic signature with overall survival (OS) of patients was assessed in both cohorts. A nomogram incorporating the radiomic signature and independent clinical predictors was then constructed. The incremental prognostic value of the radiomic signature was evaluated. RESULTS: The radiomic signature, consisted of 7 selected features from MR images, was significantly associated with OS of patients with HNSCC (P < 0.0001 for training cohort, P = 0.0013 for validation cohort). The radiomic signature and TNM stage were proved to be independently associated with OS of HNSCC patients, which therefore were incorporated to generate the radiomic nomogram. In the training cohort, the nomogram showed a better prognostic capability than TNM stage only (P =  0.005), which was confirmed in the validation cohort (P =  0.01). Furthermore, the calibration curves of the nomogram demonstrated good agreement with actual observation. CONCLUSIONS: MRI-based radiomic signature is an independent prognostic factor for HNSCC patients. Nomogram based on radiomic signature and TNM stage shows promising in non-invasively and preoperatively predicting prognosis of HNSCC patient in clinical practice.

Magnetic Resonance Imaging Characteristics of Papillary Thyroid Carcinoma for the Prediction of Cervical Central Compartment Lymph Node Metastasis.

OBJECTIVE: Cervical lymph node metastasis (LNM) is associated with local recurrence and distant metastasis in papillary thyroid carcinoma (PTC). This study was to assess magnetic resonance imaging (MRI) characteristics for predicting cervical LNM in PTC. MATERIALS AND METHODS: A total of 119 patients with 154 PTC examined by MRI were assessed. According to inclusion and exclusion criteria, 78 subjects (78 tumors) were included in the final analysis. Conventional MRI findings and apparent diffusion coefficient were recorded. Descriptive statistics for LNM, sensitivity, specificity, and accuracy of various features were obtained. Multivariate logistic regression was performed for identifying independent variables for predicting LNM. Receiver operating characteristic curves were used to assess the diagnostic performance of the independent variables and model. RESULTS: There were 31 node-positive and 47 node-negative PTCs in this study. Node-positive patients significantly differed from the node-negative group in age (P = 0.039), long/short diameter of lymph nodes (both P < 0.001), lymph nodes cystic change (P = 0.005), tumor size (P < 0.001), poorly defined tumor margin in contrast-enhanced imaging (P < 0.001), and thyroid contour protrusion sign (P < 0.001). Satisfactory interobserver agreement was obtained between the 2 examiners (Cohen κ of 0.871 and 0.872). Thyroid contour protrusion sign and poorly defined tumor margin were identified as independent predictive factors of LNM in PTC (both P < 0.05), with area under the curves of 0.813 and 0.851, and accuracies of 0.810 and 0.838. When the independent factors were combined, the diagnostic performance was improved with an area under the curve of 0.944 and an accuracy of 0.884. CONCLUSIONS: Thyroid contour protrusion sign and poorly defined tumor margin in contrast-enhanced imaging could be 2 important predicted findings for cervical LNM in PTC.

Magnetic resonance imaging based radiomics signature for the preoperative discrimination of stage I-II and III-IV head and neck squamous cell carcinoma.

PURPOSE: This study aimed to investigate the predictive ability of magnetic resonance imaging (MRI) based radiomics signature for the preoperative staging in HNSCC. METHODS: This study involved127 consecutive patients (training cohort: n = 85; testing cohort, n = 42) with stage I-IV HNSCC. A total of 970 radiomics features were extracted from T2-weighted (T2W) (n = 485) and contrast-enhanced T1-weighted (ceT1W) (n = 485) MRI for each case. Radiomics signatures were constructed with least absolute shrinkage and selection operator (LASSO) logistic regression. Associations between radiomics signatures and HNSCC staging were explored. Areas under the receiver operating characteristic curve (AUC) and classification performance of radiomics signatures were determined and compared with those of the visual assessment. RESULTS: Ten features from T2W images, six from ceT1W images, and six from combined T2W and ceT1W images were selected by LASSO logistic regression. The three radiomics signatures of stage III-IV HNSCC were significantly higher than that for stage I-II in both cohorts (all P < 0.05). The radiomics signatures from ceT1W and combined images performed well in the discrimination of stage I-II and III-IV HNSCC, with AUCs of 0.828 and 0.850 in the training cohort, and AUCs of 0.853 and 0.849 in the testing cohort. Based on the cut-off value of the training cohort, the radiomics signature from combined images achieved best classification performance in both cohorts, with accuracies of 0.788 and 0.857, sensitivities of 0.836 and 0.885, and specificities of 0.700 and 0.813. Significant differences in accuracy and sensitivity were found between the radiomics signature from combined images and the visual assessment of the radiologists in the training cohort. CONCLUSION: Radiomics signature based on MRI could discriminate stage I-II from stage III-IV HNSCC, which may serve as a complementary tool for preoperative staging.