Parotid gland tumors: comparison of conventional and diffusion-weighted MRI findings with histopathological results

Diagnostic performance of MRI-based radiomics models using machine learning approaches for the triple classification of parotid tumors

Rationale and objectives

Preoperative differentiation of malignant tumors (MT), pleomorphic adenomas (PA), and other benign tumors of the parotid gland is critical to clinical strategy, this study aimed to develop and validate a T2-weighted image (T2WI) based radiomics model through machine learning approaches for the triple classification of parotid gland tumors.

Materials and methods

We retrospectively enrolled 147 patients from January 2010 to July 2022. T2WIs were used to extract radiomics features. Max-Relevance and Min-Redundancy (mRMR) and Extreme Gradient Boosting (XGBoost) algorithms were used to select features. Using a 5-fold cross-validation strategy, radiomics models were constructed using a Support Vector Machine (SVM), Logistic Regression (LR), and k-Nearest Neighbor (KNN) for the triple classification of parotid tumors. The three models were evaluated and compared using the receiver operator characteristic (ROC) curve, sensitivity, specificity, and accuracy.

Results

A total of 1057 radiomics features were extracted, and 8 features were selected to developed the radiomics model, including First-order Median, First-order Skewness, First-order Minimum, Original_shape_Flatness, Glcm Inverse Variance, Glcm Inverse Variance, Glszm Low Gray Level Zone Emphasis, and Glszm Small Area Low Gray Level Emphasis. The mean area under the curves (AUCs) for the radiomics models in training and validation sets through LR, SVM and KNN were 0.85 and 0.80, 0.85 and 0.80 and 0.83 and 0.79, respectively.

Conclusion

The T2WI-based radiomics models through LR, SVM and KNN demonstrated good performance in the triple classification of parotid tumors.

MiR-26a and miR-191 are upregulated while PLAG1 and HIF2 are downregulated in pleomorphic adenomas of the salivary glands compared to Warthin tumors

BACKGROUND

Salivary gland tumors (SGTs) are a heterogenous group of pathologies, which still represents a challenge regarding differential diagnosis and therapy. Although histological findings govern SGTs management, detection of molecular alterations is emerging as an effective additional tool. The aim of this study was to analyze the relative expression levels of three micro RNAs (miR-26a, miR-26b, and miR-191), and three pro-oncogenic molecular markers (PLAG1, MTDH, and HIF2) in SGTs and normal salivary gland (NSG) tissues and evaluate them as potential differential diagnosis markers.

METHODS

This cross-sectional study included 58 patients with SGTs (23 pleomorphic adenomas, 27 Warthin tumors, and 8 malignant SGTs) and 10 controls (normal salivary gland tissues). Relative gene expression levels of all investigated molecules were determined by reverse transcriptase-real-time polymerase chain reaction.

RESULTS

All three micro RNAs exhibited highest expression levels in benign SGTs, whereas miR-26a And miR-191 were significantly more expressed in PAs compared to WTs (p = 0.045 and p = 0.029, respectively). PLAG1 And HIF2 were both overexpressed in WTs compared to PAs (p = 0.048 and p = 0.053, respectively). Bioinformatic analysis suggested that all investigated micro RNAs function as negative regulators of MTDH.

CONCLUSION

The results of this study suggest that all three micro RNAs have a considerable negative impact on MTDH oncogene expression in malignant tumors, while the differences between levels of miR-26a, miR-191, PLAG1, and HIF2 in PA and WT represent possible differential diagnosis markers.

Parotid Gland Segmentation Using Purely Transformer-Based U-Shaped Network and Multimodal MRI

Parotid gland tumors account for approximately 2% to 10% of head and neck tumors. Segmentation of parotid glands and tumors on magnetic resonance images is essential in accurately diagnosing and selecting appropriate surgical plans. However, segmentation of parotid glands is particularly challenging due to their variable shape and low contrast with surrounding structures. Recently, deep learning has developed rapidly, and Transformer-based networks have performed well on many computer vision tasks. However, Transformer-based networks have yet to be well used in parotid gland segmentation tasks. We collected a multi-center multimodal parotid gland MRI dataset and implemented parotid gland segmentation using a purely Transformer-based U-shaped segmentation network. We used both absolute and relative positional encoding to improve parotid gland segmentation and achieved multimodal information fusion without increasing the network computation. In addition, our novel training approach reduces the clinician's labeling workload by nearly half. Our method achieved good segmentation of both parotid glands and tumors. On the test set, our model achieved a Dice-Similarity Coefficient of 86.99%, Pixel Accuracy of 99.19%, Mean Intersection over Union of 81.79%, and Hausdorff Distance of 3.87. The purely Transformer-based U-shaped segmentation network we used outperforms other convolutional neural networks. In addition, our method can effectively fuse the information from multi-center multimodal MRI dataset, thus improving the parotid gland segmentation.

Different MRI-based radiomics models for differentiating misdiagnosed or ambiguous pleomorphic adenoma and Warthin tumor of the parotid gland: a multicenter study

Purpose

To evaluate the effectiveness of MRI-based radiomics models in distinguishing between Warthin tumors (WT) and misdiagnosed or ambiguous pleomorphic adenoma (PA).

Methods

Data of patients with PA and WT from two centers were collected. MR images were used to extract radiomic features. The optimal radiomics model was found by running nine machine learning algorithms after feature reduction and selection. To create a clinical model, univariate logistic regression (LR) analysis and multivariate LR were used. The independent clinical predictors and radiomics were combined to create a nomogram. Two integrated models were constructed by the ensemble and stacking algorithms respectively based on the clinical model and the optimal radiomics model. The models' performance was evaluated using the area under the curve (AUC).

Results

There were 149 patients included in all. Gender, age, and smoking of patients were independent clinical predictors. With the greatest average AUC (0.896) and accuracy (0.839) in validation groups, the LR model was the optimal radiomics model. In the average validation group, the radiomics model based on LR did not have a higher AUC (0.795) than the clinical model (AUC = 0.909). The nomogram (AUC = 0.953) outperformed the radiomics model in terms of discrimination performance. The nomogram in the average validation group had a highest AUC than the stacking model (0.914) or ensemble model (0.798).

Conclusion

Misdiagnosed or ambiguous PA and WT can be non-invasively distinguished using MRI-based radiomics models. The nomogram exhibited excellent and stable diagnostic performance. In daily work, it is necessary to combine with clinical parameters for distinguishing between PA and WT.

Discriminating atypical parotid carcinoma and pleomorphic adenoma utilizing extracellular volume fraction and arterial enhancement fraction derived from contrast-enhanced CT imaging: A multicenter study

OBJECTIVES

To investigate the added value of extracellular volume fraction (ECV) and arterial enhancement fraction (AEF) derived from enhanced CT to conventional image and clinical features for differentiating between pleomorphic adenoma (PA) and atypical parotid adenocarcinoma (PCA) pre-operation.

METHODS

From January 2010 to October 2023, a total of 187 cases of parotid tumors were recruited, and divided into training cohort (102 PAs and 51 PCAs) and testing cohort (24 PAs and 10 atypical PCAs). Clinical and CT image features of tumor were assessed. Both enhanced CT-derived ECV and AEF were calculated. Univariate analysis identified variables with statistically significant differences between the two subgroups in the training cohort. Multivariate logistic regression analysis with the forward variable selection method was used to build four models (clinical model, clinical model+ECV, clinical model+AEF, and combined model). Diagnostic performances were evaluated using receiver operating characteristic (ROC) curve analyses. Delong's test compared model differences, and calibration curve and decision curve analysis (DCA) assessed calibration and clinical application.

RESULTS

Age and boundary were chosen to build clinical model, and to construct its ROC curve. Amalgamating the clinical model, ECV, and AEF to establish a combined model demonstrated superior diagnostic effectiveness compared to the clinical model in both the training and test cohorts (AUC = 0.888, 0.867). There was a significant statistical difference between the combined model and the clinical model in the training cohort (p = 0.0145).

CONCLUSIONS

ECV and AEF are helpful in differentiating PA and atypical PCA, and integrating clinical and CT image features can further improve the diagnostic performance.

Characterization of parotid gland tumors using diffusion-relaxation correlation spectrum imaging: a preliminary study

AIM

To assess the performance of diffusion-relaxation correlation spectrum imaging (DR-CSI) in the characterization of parotid gland tumors.

MATERIALS AND METHODS

Twenty-five pleomorphic adenomas (PA) patients, 9 Warthin's tumors (WT) patients and 7 malignant tumors (MT) patients were prospectively recruited. DR-CSI (7 b-values combined with 5 TEs, totally 35 diffusion-weighted images) was scanned for pre-treatment assessment. Diffusion (D)-T2 signal spectrum summating all voxels were built for each patient, characterized by D-axis with range 0∼5 × 10-3 mm2/s, and T2-axis with range 0∼300ms. With boundaries of 0.5 and 2.5 × 10-3 mm2/s for D, all spectra were divided into three compartments labeled A (low D), B (mediate D) and C (high D). Volume fractions acquired from each compartment (VA, VB, VC) were compared among PA, WT and MT. Diagnostic performance was assessed using receiver operating characteristic analysis and area under the curve (AUC).

RESULTS

Each subtype of parotid tumors had their specific D-T2 spectrum. PA showed significantly lower VA (8.85 ± 4.77% vs 20.68 ± 10.85%), higher VB (63.40 ± 8.18% vs 43.05 ± 7.16%), and lower VC (27.75 ± 8.51% vs 36.27 ± 11.09) than WT (all p<0.05). VB showed optimal diagnostic performance (AUC 0.969, sensitivity 92.00%, specificity 100.00%). MT showed significantly higher VA (21.23 ± 12.36%), lower VB (37.09 ± 6.43%), and higher VC (41.68 ± 13.72%) than PA (all p<0.05). Similarly, VB showed optimal diagnostic performance (AUC 0.994, sensitivity 96.00%, specificity 100.00%). No significant difference of VA, VB and VC was found between WT and MT.

CONCLUSIONS

DR-CSI might be a promising and non-invasive way for characterizing parotid gland tumors.

Differentiation of salivary gland tumours using diffusion-weighted image-based virtual MR elastography: a pilot study

OBJECTIVES

Differentiation among benign salivary gland tumours, Warthin tumours (WTs), and malignant salivary gland tumours is crucial to treatment planning and predicting patient prognosis. However, differentiation of those tumours using imaging findings remains difficult. This study evaluated the usefulness of elasticity determined from diffusion-weighted image (DWI)-based virtual MR elastography (MRE) compared with conventional magnetic resonance imaging (MRI) findings in differentiating the tumours.

METHODS

This study included 17 benign salivary gland tumours, 6 WTs, and 11 malignant salivary gland tumours scanned on neck MRI. The long and short diameters, T1 and T2 signal intensities, tumour margins, apparent diffusion coefficient (ADC) values, and elasticity from DWI-based virtual MRE of the tumours were evaluated. The interobserver agreement in measuring tumour elasticity and the receiver operating characteristic (ROC) curves were also assessed.

RESULTS

The long and short diameters and the T1 and T2 signal intensities showed no significant difference among the 3 tumour groups. Tumour margins and the mean ADC values showed significant differences among some tumour groups. The elasticity from virtual MRE showed significant differences among all 3 tumour groups and the interobserver agreement was excellent. The area under the ROC curves of the elasticity were higher than those of tumour margins and mean ADC values.

CONCLUSION

Elasticity values based on DWI-based virtual MRE of benign salivary gland tumours, WTs, and malignant salivary gland tumours were significantly different. The elasticity of WTs was the highest and that of benign tumours was the lowest. The elasticity from DWI-based virtual MRE may aid in the differential diagnosis of salivary gland tumours.

Construction and Application of a Nomogram for Predicting Benign and Malignant Parotid Tumors

OBJECTIVE

A prediction model of benign and malignant differentiation was established by magnetic resonance signs of parotid gland tumors to provide an important basis for the preoperative diagnosis and treatment of parotid gland tumor patients.

METHODS

The data from 138 patients (modeling group) who were diagnosed based on a pathologic evaluation in the Department of Stomatology of Jilin University from June 2019 to August 2021 were retrospectively analyzed. The independent factors influencing benign and malignant differentiation of parotid tumors were selected by logistic regression analysis, and a mathematical prediction model for benign and malignant tumors was established. The data from 35 patients (validation group) who were diagnosed based on pathologic evaluation from September 2021 to February 2022 were collected for verification.

RESULTS

Univariate and multivariate logistic regression analysis showed that tumor morphology, tumor boundary, tumor signal, and tumor apparent diffusion coefficient (ADC) were independent risk factors for predicting benign and malignant parotid gland tumors ( P < 0.05). Based on multivariate logistic regression analysis of the modeling group, a mathematical prediction model was established as follows: Y = the ex/(1 + ex) and X = 0.385 + (1.416 × tumor morphology) + (1.473 × tumor border) + (1.306 × tumor signal) + (2.312 × tumor ADC value). The results showed that the area under the receiver operating characteristic curve of the model was 0.832 (95% confidence interval, 0.75-0.91), the sensitivity was 82.6%, and the specificity was 70.65%. The validity of the model was verified using validation group data, for which the sensitivity was 85.71%, the specificity was 96.4%, and the correct rate was 94.3%. The results showed that the area under receiver operating characteristic curve was 0.936 (95% confidence interval, 0.83-0.98).

CONCLUSIONS

Combined with tumor morphology, tumor ADC, tumor boundary, and tumor signal, the established prediction model provides an important reference for preoperative diagnosis of benign and malignant parotid gland tumors.

Deep Network-Based Comprehensive Parotid Gland Tumor Detection

RATIONALE AND OBJECTIVES

Salivary gland tumors constitute 2%-6% of all head and neck tumors and are most common in the parotid gland. Magnetic resonance (MR) imaging is the most sensitive imaging modality for diagnosis. Tumor type, localization, and relationship with surrounding structures are important factors for treatment. Therefore, parotid gland tumor segmentation is important. Specialists widely use manual segmentation in diagnosis and treatment. However, considering the development of artificial intelligence-based models today, it is seen that artificial intelligence-based automatic segmentation models can be used instead of manual segmentation, which is a time-consuming technique. Therefore, we segmented parotid gland tumor (PGT) using deep learning-based architectures in the paper.

MATERIALS AND METHODS

The dataset used in the study includes 102 T1-w, 102 contrast-enhanced T1-w (T1C-w), and 102 T2-w MR images. After cropping the raw and manually segmented images by experts, we obtained the masks of these images. After standardizing the image sizes, we split these images into approximately 80% training set and 20% test set. Hereabouts, we trained six models for these images using ResNet18 and Xception-based DeepLab v3+. We prepared a user-friendly Graphical User Interface application that includes each of these models.

RESULTS

From the results, the accuracy and weighted Intersection over Union values of the ResNet18-based DeepLab v3+ architecture trained for T1C-w, which is the most successful model in the study, are equal to 0.96153 and 0.92601, respectively. Regarding the results and the literature, it can be seen that the proposed system is competitive in terms of both using MR images and training the models independently for T1-w, T1C-w, and T2-w. Expressing that PGT is usually segmented manually in the literature, we predict that our study can contribute significantly to the literature.

CONCLUSION

In this study, we prepared and presented a software application that can be easily used by users for automatic PGT segmentation. In addition to predicting the reduction of costs and workload through the study, we developed models with meaningful performance metrics according to the literature.

Semiquantitative magnetic resonance imaging parameters for differentiating parotid pleomorphic adenoma from Warthin tumor

Background

Accurately distinguishing between pleomorphic adenoma (PA) and Warthin tumor (WT) is beneficial for their respective management. Preoperative magnetic resonance imaging (MRI) can provide valuable information due to its excellent soft tissue contrast. This study explored the value of semiquantitative contrast-enhanced MRI parameters in the differential diagnosis of PA and WT.

Methods

Data from 106 patients, 62 with PA and 44 with WT (confirmed by histopathology) were retrospectively and consecutively analyzed. The tumor-to-spinal cord contrast ratios (TSc-CR) based on the mean, maximum, and minimum signal intensity (T1-mean TSc-CR, T1-max TSc-CR, and T1-min TSc-CR, respectively) in the early and delayed phases were calculated on contrast-enhanced T1-weighted images as semiquantitative parameters, and then compared between PA and WT. Receiver operating characteristic (ROC) curve analysis and areas under the curve (AUCs) were used to determine the performance of these parameters in the differential diagnosis of PA from WT.

Results

Except T1-min TSc-CR in the early phase, all semiquantitative MRI parameters differed significantly between PA and WT (all P<0.05). T1-max TSc-CR showed higher sensitivity {70.45% [95% confidence interval (CI): 0.548-0.832]} and specificity [70.97% (95% CI: 0.581-0.818)] and had a higher AUC [0.707 (95% CI: 0.610-0.791)] in the early phase when using a cutoff value of 1.89. T1-max TSc-CR showed higher sensitivity [88.64% (95% CI: 0.754-0.962)], specificity [72.58% (95% CI: 0.598-0.831)], and AUC [0.854 (95% CI: 0.772-0.915)] in the delayed phase when using a cutoff value of 2.33. The sensitivity, specificity, and AUC were improved to 90.91% (95% CI: 0.783-0.975), 93.55% (95% CI: 0.843-0.982), and 0.960 (95% CI: 0.903-0.988), respectively, after combination of all semiquantitative parameters in the early and delayed phases. The two radiologists had excellent interobserver agreement on TSc-CRs [all interclass correlation coefficient (ICC) >0.75].

Conclusions

Semiquantitative parameters using TSc-CR are valuable in distinguishing PA from WT, and a combination of these parameters can improve the differential diagnostic efficiency.

Amide proton transfer-weighted magnetic resonance imaging for the differentiation of parotid gland tumors

Purpose

To assess the usefulness of amide proton transfer-weighted (APTw) imaging in the differentiation of parotid gland tumors.

Materials and methods

Patients with parotid gland tumors who underwent APTw imaging were retrospectively enrolled and divided into groups according to pathology. Two radiologists evaluated the APTw image quality independently, and APTw images with quality score ≥3 were enrolled. The maximum and average values of APTw imaging for tumor lesions (APTmax and APTmean) were measured. The differences in APTmax and APTmean were compared between malignant tumors (MTs) and benign tumors (BTs), as well as between MTs and pleomorphic adenomas (PAs) and between MTs and Warthin tumors (WTs). Independent-samples t-test, Kruskal-Wallis H test, and receiver operating characteristic (ROC) curve analyses were used for statistical analysis.

Results

Seventy-three patients were included for image quality evaluation. In this study, 32/73 and 29/73 parotid tumors were scored as 4 and 3, respectively. After excluding lesions with quality score ≤2 (12/73), the APTmean and APTmax of MTs were 4.15% ± 1.33% and 7.43% ± 1.61%, higher than those of BTs 2.74% ± 1.04% and 5.25% ± 1.54%, respectively (p < 0.05). The areas under the ROC curve (AUCs) of the APTmean and APTmax for differentiation between MTs and BTs were 0.819 and 0.821, respectively. MTs indicated significantly higher APTmean and APTmax values than those of PAs (p < 0.05) and WTs (p < 0.05). The AUCs of the APTmean and APTmax for differentiation between MTs and PAs were 0.830 and 0.815 and between MTs and WTs were 0.847 and 0.920, respectively.

Conclusion

Most APTw images for parotid tumors had acceptable image quality for APTw value evaluation. Both APTmax and APTmean can be used to differentiate MTs from BTs and to differentiate MTs from subtype parotid gland tumors.

A preliminary diagnostic accuracy study of quantitative MRI biomarkers for differentiating parotid tumor types

Background

Differentiating among the different types of parotid tumors on imaging is useful for guiding clinical disposition, which ultimately may lead to surgical management. The goal of this study was to determine whether quantitative T2 signal characteristics and morphologic features on magnetic resonance imaging (MRI) can serve as predictive biomarkers for distinguishing between tumor types.

Methods

A retrospective review of T2-weighted MRIs in patients with pathology-proven parotid tumors was performed. Quantitative T2 maps and surface regularity measurements of the tumors were obtained via semi-automated regions of interest (ROI). Linear Discriminant Analysis was used to populate the receiver operating characteristics (ROCs) curves for these variables. A P value of <0.05 was considered to be significant.

Results

A total of 35 tumors (21 benign and 14 malignant neoplasms) were included in this analysis. For differentiating the benign versus malignant classes of parotid tumors, T2 signal and surface regularity combined yielded an area under the curve of 0.62 (P value: 0.2) through the ROC analysis. However, for the pleomorphic adenomas versus other types of parotid tumors, using both T2 signal and surface regularity yielded an area under the curve of 0.81 (P value: 0.007) through the ROC analysis.

Conclusions

T2 signal and surface regularity combined can significantly differentiate pleomorphic adenomas from other types of parotid tumors and can potentially be used as a predictive imaging biomarker.

Value of pre-/post-contrast-enhanced T1 mapping and readout segmentation of long variable echo-train diffusion-weighted imaging in differentiating parotid gland tumors

PURPOSE

This study aimed to explore the value of pre-/post-contrast-enhanced T1 mapping and readout segmentation of long variable echo-train diffusion-weighted imaging (RESOLVE-DWI) for the differential diagnosis of parotid gland tumors.

METHODS

A total of 128 patients with histopathologically confirmed parotid gland tumors [86 benign tumors (BTs) and 42 malignant tumors (MTs)] were retrospectively recruited. BTs were further divided into pleomorphic adenomas (PAs, n = 57) and Warthin's tumors (WTs, n = 15). MRI examinations were performed before and after contrast injection to measure the longitudinal relaxation time (T1) value (T1p and T1e, respectively) and the apparent diffusion coefficient (ADC) value of the parotid gland tumors. The reduction in T1 (T1d) values and the percentage of T1 reduction (T1d%) were calculated.

RESULTS

The T1d and ADC values of the BTs were considerably higher than those of the MTs (all P <.05). The area under the curve (AUC) of the T1d and ADC values for differentiating between BTs and MTs of the parotid was 0.618 and 0.804, respectively (all P <.05). The AUC of the T1p, T1d, T1d%, and ADC values for differentiating between PAs and WTs was 0.926, 0.945, 0.925, and 0.996, respectively (all P >.05). The ADC and T1d% + ADC values performed better in differentiating between PAs and MTs than the T1p, T1d, and T1d% (AUC values: 0.902, 0.909, 0.660, 0.726, and 0.736, respectively). The T1p, T1d, T1d%, and T1d% + T1p values all had high diagnosis efficacy in differentiating WTs from MTs (AUC values: 0.865, 0.890, 0.852, and 0.897, respectively, all P >.05).

CONCLUSION

T1 mapping and RESOLVE-DWI can be used to differentiate parotid gland tumors quantitatively and can be complementary to each other.

The Value of Multiparametric Magnetic Resonance Imaging in the Preoperative Differential Diagnosis of Parotid Gland Tumors

BACKGROUND

The aim of the present study was to determine the value of multiparametric MRI in the preoperative differential diagnosis of parotid tumors, which is essential for therapeutic strategy selection.

METHODS

A three-year prospective study was conducted with 65 patients. Each patient was investigated preoperatively with multiparametric MRI and surgical excision of the tumor was performed. The preoperative imaging diagnosis was compared with the histopathological report. Several MRI parameters were analyzed, including T1 and T2 weighted image (WI), apparent diffusion coefficient (ADC), time to peak (TTP), and the time intensity curve (TIC).

RESULTS

In the differential diagnosis of benign from malignant tumors, T2WI and ADC showed statistically significant differences. Multiparametric MRI had a sensitivity, specificity, and accuracy of 81.8%, 88.6% and 92.3%, respectively. All of the studied parameters (T1, T2, TIC, TTP, ADC) were significantly different in the comparison between pleomorphic adenomas and Warthin tumors. With reference to the scope of this study, the conjunction of multiparametric and conventional MRI demonstrated a sensitivity, specificity, and accuracy of 94.1%, 100%, and 97.8%, respectively.

CONCLUSIONS

Morphological analysis using conventional MRI combined with diffusion-weighted imaging (DW) and dynamic contrast-enhanced (DCE) multiparametric MRI improved the preoperative differential diagnosis of parotid gland tumors.

Advantages of contrast-enhanced CT combined with DCE-MRI in identifying malignant parotid tumor

OBJECTIVE

To study the value of single and combined application of contrast-enhanced computerized tomography (CT) and dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) in diagnosing parotid tumors.

METHODS

In this retrospective study, 82 patients with parotid gland mass who received contrast-enhanced CT and DCE-MRI detection in The First People's Hospital of Huzhou from March 2018 to March 2022 were selected as study subjects. The nature of the parotid tumor was pathologically examined following the surgery. According to the pathological diagnosis results, these patients were divided into a benign group (n=59) and a malignant group (n=23). All patients underwent contrast-enhanced CT and DCE-MRI examinations. The diagnostic accuracy rates of contrast-enhanced CT, DCE-MRI and the joint application were compared. The CT or MRI images of benign and malignant parotid tumors were compared. The correlation of parotid cancer with the imaging features was analyzed. Diagnostic efficiency of contrast-enhanced CT, DCE-MRI and joint application for parotid cancer was assessed by receiver operating characteristic curve.

RESULTS

In terms of diagnostic accuracy, there was a significant difference between contrast-enhanced CT combined with DCE-MRI and contrast-enhanced CT alone (95.12% vs. 81.71%, P<0.001), and between the joint application and DCE-MRI alone (95.12% vs. 86.58%, P=0.004). Results of contrast-enhanced CT revealed statistical differences in tumor boundary, tumor size, calcification and cystic degeneration between benign and malignant tumors (P<0.05), but no obvious difference in lymph node enlargement between the two groups. MRI results showed that there were differences in the DCE-MRI time-signal intensity curve and ADC value between benign and malignant tumors (P<0.05). Correlation analysis results showed that the malignant tumor was negatively correlated with tumor boundary, calcification, cystic degeneration and ADC values, and it was positively correlated with DCE-MRI time-signal intensity curve and tumor size (P<0.05). Analysis of diagnostic efficacy showed that contrast-enhanced CT combined with DCE-MRI were significantly better than contrast-enhanced CT alone in terms of sensitivity and specificity (P<0.05). Moreover, the sensitivity of the joint application was also higher than that of MRI alone, while no obvious difference was found for specificity between joint application and MRI alone. The areas under the curve of contrast-enhanced CT combined with DCE-MRI in diagnosing malignant parotid tumor was remarkably greater than that of CT or MRI alone (P<0.05).

CONCLUSION

Contrast-enhanced CT combined with DCE-MRI can significantly improve the diagnostic accuracy, sensitivity and specificity for malignant parotid tumor, and the joint application was able to point out the direction of targeted surgical treatment plans.

Contrast-Enhanced Ultrasound in the Differentiation between the Most Common Benign Parotid Gland Tumors: A Systematic Review and Meta-Analysis

Recently, contrast-enhanced ultrasound (CEUS) has become a promising tool in distinguishing benign from malignant parotid gland tumors. However, its usefulness in differentiating various benign parotid tumors has not been determined so far. This study aimed to systematically review the literature to determine the utility of CEUS in the preoperative differentiation between pleomorphic adenomas (PAs) and Warthin's tumors (WTs) of the parotid gland. PubMed, Embase, and Cochrane were searched for English-language articles published until 21 July 2022. Fifteen studies were included. On CEUS examination, a significantly greater percentage of PAs displayed heterogeneous enhancement texture compared to WTs. Contrarily, the enhanced lesion size, the enhancement margin, and the presence of the enhancement rim did not differ significantly between the entities. Significantly longer normalized mean transit time (nMTT) and time to peak (TTP) were observed in PAs. Contrarily, the mean values of area under the curve (AUC) and time from peak to one half (TPH) were significantly higher for WTs. Due to the considerable overlap among the qualitative CEUS characteristics of PAs and WTs, the reproducible, investigator-independent quantitative CEUS measurements have a greater potential to distinguish PAs from WTs, which might influence the selection of an appropriate management strategy.

Apparent Diffusion Coefficient (ADC) Histogram Analysis in Parotid Gland Tumors: Evaluating a Novel Approach for Differentiation between Benign and Malignant Parotid Lesions Based on Full Histogram Distributions

The aim of this study was to assess the diagnostic value of ADC distribution curves for differentiation between benign and malignant parotid gland tumors and to compare with mean ADC values. 73 patients with parotid gland tumors underwent head-and-neck MRI on a 1.5 Tesla scanner prior to surgery and histograms of ADC values were extracted. Histopathological results served as a reference standard for further analysis. ADC histograms were evaluated by comparing their similarity to a reference distribution using Chi2-test-statistics. The assumed reference distribution for benign and malignant parotid gland lesions was calculated after pooling the entire ADC data. In addition, mean ADC values were determined. For both methods, we calculated and compared the sensitivity and specificity between benign and malignant parotid gland tumors and three subgroups (pleomorphic adenoma, Warthin tumor, and malignant lesions), respectively. Moreover, we performed cross-validation (CV) techniques to estimate the predictive performance between ADC distributions and mean values. Histopathological results revealed 30 pleomorphic adenomas, 22 Warthin tumors, and 21 malignant tumors. ADC histogram distribution yielded a better specificity for detection of benign parotid gland lesions (ADChistogram: 75.0% vs. ADCmean: 71.2%), but mean ADC values provided a higher sensitivity (ADCmean: 71.4% vs. ADChistogram: 61.9%). The discrepancies are most pronounced in the differentiation between malignant and Warthin tumors (sensitivity ADCmean: 76.2% vs. ADChistogram: 61.9%; specificity ADChistogram: 81.8% vs. ADCmean: 68.2%). Using CV techniques, ADC distribution revealed consistently better accuracy to differentiate benign from malignant lesions (“leave-one-out CV” accuracy ADChistogram: 71.2% vs. ADCmean: 67.1%). ADC histogram analysis using full distribution curves is a promising new approach for differentiation between primary benign and malignant parotid gland tumors, especially with respect to the advantage in predictive performance based on CV techniques.

Differentiation of Benign From Malignant Parotid Gland Tumors Using Conventional MRI Based on Radiomics Nomogram

Objectives

We aimed to develop and validate radiomic nomograms to allow preoperative differentiation between benign- and malignant parotid gland tumors (BPGT and MPGT, respectively), as well as between pleomorphic adenomas (PAs) and Warthin tumors (WTs).

Materials and Methods

This retrospective study enrolled 183 parotid gland tumors (68 PAs, 62 WTs, and 53 MPGTs) and divided them into training (n = 128) and testing (n = 55) cohorts. In total, 2553 radiomics features were extracted from fat-saturated T2-weighted images, apparent diffusion coefficient maps, and contrast-enhanced T1-weighted images to construct single-, double-, and multi-sequence combined radiomics models, respectively. The radiomics score (Rad-score) was calculated using the best radiomics model and clinical features to develop the radiomics nomogram. The receiver operating characteristic curve and area under the curve (AUC) were used to assess these models, and their performances were compared using DeLong’s test. Calibration curves and decision curve analysis were used to assess the clinical usefulness of these models.

Results

The multi-sequence combined radiomics model exhibited better differentiation performance (BPGT vs. MPGT, AUC=0.863; PA vs. MPGT, AUC=0.929; WT vs. MPGT, AUC=0.825; PA vs. WT, AUC=0.927) than the single- and double sequence radiomics models. The nomogram based on the multi-sequence combined radiomics model and clinical features attained an improved classification performance (BPGT vs. MPGT, AUC=0.907; PA vs. MPGT, AUC=0.961; WT vs. MPGT, AUC=0.879; PA vs. WT, AUC=0.967).

Conclusions

Radiomics nomogram yielded excellent diagnostic performance in differentiating BPGT from MPGT, PA from MPGT, and PA from WT.

The Diagnostic Value of Ultrasound-Based Deep Learning in Differentiating Parotid Gland Tumors

Objectives. Evidence suggests that about 80% of all salivary gland tumors involve the parotid glands, with approximately 20% of parotid gland tumors (PGTs) being malignant. Discriminating benign and malignant parotid gland lesions preoperatively is vital for selecting the appropriate treatment strategy. This study explored the diagnostic performance of deep learning system for discriminating benign and malignant PGTs in ultrasonography images and compared it with radiologists. Methods. A total of 251 consecutive patients with surgical resection and proven parotid gland malignant or benign tumors who underwent preoperative ultrasound examinations were enrolled in this study between January 2014 and November 2020. Next, we compared the diagnostic accuracy of deep learning methods (ViT-B\16, EfficientNetB3, DenseNet121, and ResNet50) and radiologists in parotid gland tumor. In addition, the area under the curve (AUC), specificity, sensitivity, positive predictive value, and negative predictive value were calculated. Results. Among the 251 patients, 176/251 were the training set, whereas 75/251 were the validation set. Results showed that 74/251 patients had malignant tumor. Deep learning models achieved good performance in differentiating benign from malignant tumors, with the diagnostic accuracy and AUCs of ViT-B\16, EfficientNetB3, DenseNet121, and ResNet50 model being 81% and 0.81, 80% and 0.82, 77% and 0.81, and 79% and 0.80, respectively. On the other hand, the diagnostic accuracy and AUCs of radiologists were 77%-81% and 0.68-0.75, respectively. It was evident that the diagnostic accuracy of deep learning methods was higher than that of inexperienced radiologists, but there was no significant difference between deep learning methods and experienced radiologists. Conclusions. This study shows that the deep learning system can be used for diagnosing parotid tumors. The findings also suggest that the deep learning system may improve the diagnosis performance of inexperienced radiologists.

Differentiation of Benign and Malignant Parotid Gland Tumors with MRI and Diffusion Weighted Imaging

Objective

This study investigated the effectivity of Magnetic Resonance Imaging (MRI) findings and Apparent Diffusion Coefficient (ADC) value in evaluating parotid gland tumors (PGTs), and aimed to reduce the biopsy procedure before surgery.

Methods

This retrospective study included 54 PGTs of 42 patients' (24 female, 18 male, mean age; 51.4±15.9). All of the patients had an MRI, and histopathologic diagnosis. The signal intensity [T1 and T2 Weighted (W), T1W after intravenous contrast agent injection] and mean ADC values of the PGTs were measured. Also contrast enhancement pattern (homogenous, heterogeneous, peripheral or none), margin features (well or ill-defined), sizes, location (superficial lobe/deeplobe/both), perineural spread, presence of lymphadenopathy, and extension to adjacent structures were noted.

Results

The distribution of PGTs was; 21 pleomorphic adenomas, 18 Warthin tumors, 2 lymph nodes, 2 mucoepidermoid carcinomas, 5 adenoid cystic carcinoma, 1 basal cell carcinoma,2 metastases and 2 lymphomas; (13 malignant and 41 benign lesions). Morphologic parameters; ill-defined margin, perineural spread, lymphadenopathy, and extension to adjacent structures were found to be significantly associated with malign lesions (p<0.01). There was a significant difference between ADC values of malignant and benign PGTs (p<0.05). Also ADC values and T2 signal intensity was significantly lower in Warthin tumors rather than pleomorphic adenomas (p<0.05).

Conclusions

Mean ADC values when considered with morphological features may be accessible methods to distinguish benign and malignant PGTs, also ADC values and T2 signal intensity may be useful for differentiating pleomorphic adenomas from Warthin tumors, thereby reducing the number of biopsies and thus complications.