Controversies in the Workup and Surgical Management of Parotid Neoplasms

The Effect of Using Perioperative Platelet-Rich Plasma on Wound Healing Rate and Prevention of Salivary Fistula Formation in Patients Undergoing Partial Parotidectomy

OBJECTIVES

This study aims to examine the effects of autologous platelet-rich plasma (PRP), which increases new connective tissue synthesis and revascularisation, on healing in parotid surgery wounds, prevention of salivary fistula formation, drain removal time and hospitalisation in the postoperative period.

MATERIALS AND METHODS

Fifty-four patients who had an operation on partial parotidectomy were randomised, and then two groups were created. PRP was obtained by centrifuging the blood taken from the patients in the study group at the end of the surgery. This obtained PRP was injected into the surgical site, and then the wound flap was closed by suturing. Patients were evaluated for parameters such as the development of salivary fistula, duration of drain removal, discharge time and all other complications during the postoperative 4 weeks.

RESULTS

Drain removal and discharge times of the PRP group cases were statistically shorter than those in the control group. The rate of development of a salivary fistula was remarkably high in the control group, but it was not statistically significant. A statistically significant correlation was found between the location of the compared tumour, the volume of material removed and the incidence of all complications.

CONCLUSIONS

PRP reduced the duration of drain removal and discharge times for those who had an operation on partial parotidectomy. Thus, the decreased discharge time provides both reduced health costs and reduced risk of developing nosocomial infections. Although it was not statistically significant, a significant difference was observed in the rates of salivary fistula development.

Preoperative CT-based intra- and peri-tumoral radiomic models for differentiating benign and malignant tumors of the parotid gland: a two-center study

OBJECTIVE

To investigate the ability of intra- and peritumoral radiomics based on three-phase computed tomography (CT) to distinguish between malignant and benign parotid tumors.

METHODS

We conducted a retrospective analysis of data from 374 patients with parotid gland tumors, all confirmed by histopathology. A total of 321 patients from Center 1 (January 2014 to January 2023) were randomly divided into the training set and internal testing set at a ratio of 7:3, whereas 53 patients from Center 2 (January 2020 to June 2022) constituted the external testing set. CT images of both the tumor and surrounding areas (2 mm and 5 mm areas surrounding the tumor) were reviewed, and their radiomic features were extracted for the construction of different radiomic models. In addition, a combined clinical-radiomic model was developed using multivariate logistic regression analysis. The model's predictive performance was evaluated using decision curve analysis (DCA) and receiver operating characteristic (ROC) curves.

RESULTS

Among the models evaluated, Tumor + External2 model demonstrated superior predictive performance. The areas under the curve (AUCs) of this model were 0.986 in the training set, 0.827 in the internal test set, and 0.749 in the external test set. For the clinical model, independent predictive factors included symptoms, boundaries, and lymph node swelling. The combined clinical-radiomic model achieved AUCs of 0.981, 0.842, and 0.749 in the three cohorts, outperforming both the Tumor model and the clinical model individually.

CONCLUSION

The CT-based radiomic models incorporating intratumoral and peritumoral radiomic features can effectively distinguish malignant from benign parotid tumors, and the predictive accuracy is further improved by incorporating clinically independent predictors.

Deep learning-assisted diagnosis of benign and malignant parotid gland tumors based on automatic segmentation of ultrasound images: a multicenter retrospective study

Objectives

To construct deep learning-assisted diagnosis models based on automatic segmentation of ultrasound images to facilitate radiologists in differentiating benign and malignant parotid tumors.

Methods

A total of 582 patients histopathologically diagnosed with PGTs were retrospectively recruited from 4 centers, and their data were collected for analysis. The radiomics features of six deep learning models (ResNet18, Inception_v3 etc) were analyzed based on the ultrasound images that were obtained under the best automatic segmentation model (Deeplabv3, UNet++, and UNet). The performance of three physicians was compared when the optimal model was used and not. The Net Reclassification Index (NRI) and Integrated Discrimination Improvement (IDI) were utilized to evaluate the clinical benefit of the optimal model.

Results

The Deeplabv3 model performed optimally in terms of automatic segmentation. The ResNet18 deep learning model had the best prediction performance, with an area under the receiver-operating characteristic curve of 0.808 (0.694-0.923), 0.809 (0.712-0.906), and 0.812 (0.680-0.944) in the internal test set and external test sets 1 and 2, respectively. Meanwhile, the optimal model-assisted clinical and overall benefits were markedly enhanced for two out of three radiologists (in internal validation set, NRI: 0.259 and 0.213 [p = 0.002 and 0.017], IDI: 0.284 and 0.201 [p = 0.005 and 0.043], respectively; in external test set 1, NRI: 0.183 and 0.161 [p = 0.019 and 0.008], IDI: 0.205 and 0.184 [p = 0.031 and 0.045], respectively; in external test set 2, NRI: 0.297 and 0.297 [p = 0.038 and 0.047], IDI: 0.332 and 0.294 [p = 0.031 and 0.041], respectively).

Conclusions

The deep learning model constructed for automatic segmentation of ultrasound images can improve the diagnostic performance of radiologists for PGTs.

Differentiation of benign and malignant parotid gland tumors based on the fusion of radiomics and deep learning features on ultrasound images

Objective

The pathological classification and imaging manifestation of parotid gland tumors are complex, while accurate preoperative identification plays a crucial role in clinical management and prognosis assessment. This study aims to construct and compare the performance of clinical models, traditional radiomics models, deep learning (DL) models, and deep learning radiomics (DLR) models based on ultrasound (US) images in differentiating between benign parotid gland tumors (BPGTs) and malignant parotid gland tumors (MPGTs).

Methods

Retrospective analysis was conducted on 526 patients with confirmed PGTs after surgery, who were randomly divided into a training set and a testing set in the ratio of 7:3. Traditional radiomics and three DL models (DenseNet121, VGG19, ResNet50) were employed to extract handcrafted radiomics (HCR) features and DL features followed by feature fusion. Seven machine learning classifiers including logistic regression (LR), support vector machine (SVM), RandomForest, ExtraTrees, XGBoost, LightGBM and multi-layer perceptron (MLP) were combined to construct predictive models. The most optimal model was integrated with clinical and US features to develop a nomogram. Receiver operating characteristic (ROC) curve was employed for assessing performance of various models while the clinical utility was assessed by decision curve analysis (DCA).

Results

The DLR model based on ExtraTrees demonstrated superior performance with AUC values of 0.943 (95% CI: 0.918-0.969) and 0.916 (95% CI: 0.861-0.971) for the training and testing set, respectively. The combined model DLR nomogram (DLRN) further enhanced the performance, resulting in AUC values of 0.960 (95% CI: 0.940- 0.979) and 0.934 (95% CI: 0.876-0.991) for the training and testing sets, respectively. DCA analysis indicated that DLRN provided greater clinical benefits compared to other models.

Conclusion

DLRN based on US images shows exceptional performance in distinguishing BPGTs and MPGTs, providing more reliable information for personalized diagnosis and treatment plans in clinical practice.

Deep learning-assisted diagnosis of benign and malignant parotid tumors based on ultrasound: a retrospective study

BACKGROUND

To develop a deep learning(DL) model utilizing ultrasound images, and evaluate its efficacy in distinguishing between benign and malignant parotid tumors (PTs), as well as its practicality in assisting clinicians with accurate diagnosis.

METHODS

A total of 2211 ultrasound images of 980 pathologically confirmed PTs (Training set: n = 721; Validation set: n = 82; Internal-test set: n = 89; External-test set: n = 88) from 907 patients were retrospectively included in this study. The optimal model was selected and the diagnostic performance evaluation is conducted by utilizing the area under curve (AUC) of the receiver-operating characteristic(ROC) based on five different DL networks constructed at varying depths. Furthermore, a comparison of different seniority radiologists was made in the presence of the optimal auxiliary diagnosis model. Additionally, the diagnostic confusion matrix of the optimal model was calculated, and an analysis and summary of misjudged cases' characteristics were conducted.

RESULTS

The Resnet18 demonstrated superior diagnostic performance, with an AUC value of 0.947, accuracy of 88.5%, sensitivity of 78.2%, and specificity of 92.7% in internal-test set, and with an AUC value of 0.925, accuracy of 89.8%, sensitivity of 83.3%, and specificity of 90.6% in external-test set. The PTs were subjectively assessed twice by six radiologists, both with and without the assisted of the model. With the assisted of the model, both junior and senior radiologists demonstrated enhanced diagnostic performance. In the internal-test set, there was an increase in AUC values by 0.062 and 0.082 for junior radiologists respectively, while senior radiologists experienced an improvement of 0.066 and 0.106 in their respective AUC values.

CONCLUSIONS

The DL model based on ultrasound images demonstrates exceptional capability in distinguishing between benign and malignant PTs, thereby assisting radiologists of varying expertise levels to achieve heightened diagnostic performance, and serve as a noninvasive imaging adjunct diagnostic method for clinical purposes.

Algorithm for the reconstruction of the parotid region: a single institution experience

OBJECTIVE

This study aims to discuss the characteristics and treatment methods of malignant tumors in the parotid region, as well as the therapeutic effects of immediate free flap reconstruction of soft tissue for postoperative defects.

MATERIALS AND METHODS

A retrospective review was conducted on 11 cases of soft tissue flap reconstruction for postoperative defects following the resection of malignant tumors in the parotid region. Statistical analysis was performed based on clinical data.

RESULTS

Among the 11 cases of malignant tumors in the parotid region, there were 2 cases of secretory carcinoma (SC) of the salivary gland, 2 cases of squamous cell carcinoma (SCC), 2 cases of carcinosarcoma, 1 case of mucoepidermoid carcinoma (MEC), 1 case of epithelial-myoepithelial carcinoma (EMC), 1 case of salivary duct carcinoma (SDC), 1 case of basal cell carcinoma (BCC), and 1 case of osteosarcoma. Among these cases, 4 were initial diagnoses and 7 were recurrent tumors. The defect repairs involved: 8 cases with anterolateral thigh free flap (ALTF), 2 cases with pectoralis major muscle flaps, and 1 case with forearm flap. The size of the flaps ranged from approximately 1 cm × 3 cm to 7 cm × 15 cm. The recipient vessels included: 4 cases with the facial artery, 4 cases with the superior thyroid artery, and 1 case with the external carotid artery. The ratio of recipient vein anastomosis was: 57% for branches of the internal jugular vein, 29% for the facial vein, and 14% for the external jugular vein. Among the 8 cases that underwent neck lymph node dissection, one case showed lymph node metastasis on pathological examination. In the initial diagnosis cases, 2 cases received postoperative radiotherapy, and 1 case received 125I seed implantation therapeutic treatment after experiencing two recurrences. Postoperative follow-up revealed that 2 cases underwent reoperation due to local tumor recurrence, and there were 2 cases lost to follow-up. The survival outcomes after treatment included: one case of distant metastasis and one case of death from non-cancerous diseases.

CONCLUSION

Immediate soft tissue flap reconstruction is an important and valuable option to address postoperative defects in patients afflicted with malignant tumors in the parotid region.

Ability for fine needle aspiration and frozen section to predict extent of parotidectomy

INTRODUCTION

Several diagnostic modalities with various sensitivity and specificities can be used to evaluate a parotid mass. The aims of this project were to compare the diagnostic actionability, accuracy, and ability to accurately predict extent of surgery for FNA and frozen section during the evaluation of a parotid mass.

METHODS

A retrospective chart review of patients who underwent parotidectomy for a parotid mass from January 1, 2015 to January 30, 2022 was conducted. Actionability was defined as a pathology diagnosis or the histologic grade of a lesion, as this provided clear and useful information for the surgeon to act upon. Diagnostic accuracy was determined by comparing FNA and frozen section results to final pathology. Accuracy of extent of surgery was determined by comparing predicted extent of surgery from the FNA or frozen section result to the extent of surgery predicted by the final pathology.

RESULTS

A total of 626 patients were included in this study. FNA was obtained in 396 (63%) patients, while all neoplasms were evaluated by frozen section analysis. FNA diagnosis was actionable in 318 (80%), while frozen section diagnosis was actionable in 616 (98%) patients. Exactly 294 (92.5%) FNA diagnoses were accurate compared with 600 (98%) frozen section diagnoses. The FNA diagnosis predicted appropriate extent of surgery in 294 (74%) while the frozen section diagnosis predicted appropriate extent of surgery in 600 (96%). Among the 396 patients with FNA, frozen section was significantly more likely to accurately predict appropriate extent of surgery compared with FNA (p < 0.001).

CONCLUSION

Frozen section is more likely to yield actionable and accurate results compared with FNA. Additionally, frozen section is better than FNA in predicting the appropriate extent of surgery.

Deep learning-assisted diagnosis of benign and malignant parotid tumors based on contrast-enhanced CT: a multicenter study

OBJECTIVES

To develop deep learning-assisted diagnosis models based on CT images to facilitate radiologists in differentiating benign and malignant parotid tumors.

METHODS

Data from 573 patients with histopathologically confirmed parotid tumors from center 1 (training set: n = 269; internal-testing set: n = 116) and center 2 (external-testing set: n = 188) were retrospectively collected. Six deep learning models (MobileNet V3, ShuffleNet V2, Inception V3, DenseNet 121, ResNet 50, and VGG 19) based on arterial-phase CT images, and a baseline support vector machine (SVM) model integrating clinical-radiological features with handcrafted radiomics signatures were constructed. The performance of senior and junior radiologists with and without optimal model assistance was compared. The net reclassification index (NRI) and integrated discrimination improvement (IDI) were calculated to evaluate the clinical benefit of using the optimal model.

RESULTS

MobileNet V3 had the best predictive performance, with sensitivity increases of 0.111 and 0.207 (p < 0.05) in the internal- and external-testing sets, respectively, relative to the SVM model. Clinical benefit and overall efficiency of junior radiologist were significantly improved with model assistance; for the internal- and external-testing sets, respectively, the AUCs improved by 0.128 and 0.102 (p < 0.05), the sensitivity improved by 0.194 and 0.120 (p < 0.05), the NRIs were 0.257 and 0.205 (p < 0.001), and the IDIs were 0.316 and 0.252 (p < 0.001).

CONCLUSIONS

The developed deep learning models can assist radiologists in achieving higher diagnostic performance and hopefully provide more valuable information for clinical decision-making in patients with parotid tumors.

KEY POINTS

• The developed deep learning models outperformed the traditional SVM model in predicting benign and malignant parotid tumors. • Junior radiologist can obtain greater clinical benefits with assistance from the optimal deep learning model. • The clinical decision-making process can be accelerated in patients with parotid tumors using the established deep learning model.

Basal cell adenoma of parotid gland: two case reports and literature review

Most of salivary tumors are benign in nature and are typically diagnosed and classified based on their histopathological presentation. Basal cell adenoma of the salivary glands is a rare, benign disease accounting for 1% to 3% of salivary gland tumors. Despite its low incidence, basal cell adenoma is the third most common benign tumor of the salivary gland after pleomorphic adenoma and Warthin's tumor. It usually appears as a firm and slow-growing mass. Due to the prognosis, differential diagnosis with basal cell adenocarcinoma, adenoid cystic carcinoma and basaloid squamous cell carcinoma is required. In this report, we present two cases; a 62-year-old woman who presented with an asymptomatic, and slow-growing mass and a 64-year-old woman with a static-sized mass in the parotid gland. In both cases, the mass was completely excised, postoperative pathology reports confirmed the diagnosis of basal cell adenoma. We also review the literature and discuss this rare entity.

Diagnosis and Management of Parotid Gland Cancer with Focus on the Role of Preoperative Fine-Needle Aspiration Cytology: A 10-Year-Long Retrospective Study with 5-Year Follow-Up

Introduction

Salivary gland cancers represent a rare heterogeneous group of neoplasms with complex clinicopathological characteristics and distinct biological behaviour. The appropriate diagnosis and management of parotid gland cancer are challenging and should be based on the clinical, imaging, cytological, and histological features. The present study analysed the use of preoperative fine-needle aspiration cytology (FNAC) and intraoperative frozen section (FS) to guide the appropriate surgical and postoperative treatment of parotid gland cancers.

Materials and Methods

We selected 48 patients with primary malignancy of the parotid gland surgically treated between 1 January 2008 and 30 June 2017 at the Maxillo-Facial Surgery Division, University Hospital of Parma, Italy. The patients had postoperative histological diagnosis of malignant parotid cancer and were followed up for longer than 5 years.

Results

The 48 patients included in this study had a mean age of 56.7 years. The most frequent type of parotid gland cancer was carcinoma ex pleomorphic adenoma (22.9%), followed by mucoepidermoid carcinoma (16.7%) and acinic cell carcinoma (14.6%). All 48 patients underwent preoperative FNAC: 29 (60.4%) and 19 (39.6%) were suggestive of malignant and benign lesions, respectively. In 31 patients, intraoperative FS was performed.

Discussion

Compared to previous studies, the present study showed significantly lower diagnostic sensitivity of FNAC for parotid gland cancers. The preoperative diagnostic accuracy for suspected malignant cases may be improved by repeat analysis of the cytological specimen by experts, preoperative core needle biopsy, and/or intraoperative FS analysis of the suspected mass.

CT-based radiomics with various classifiers for histological differentiation of parotid gland tumors

Objective

This study assessed whether radiomics features could stratify parotid gland tumours accurately based on only noncontrast CT images and validated the best classifier of different radiomics models.

Methods

In this single-centre study, we retrospectively recruited 249 patients with a diagnosis of pleomorphic adenoma (PA), Warthin tumour (WT), basal cell adenoma (BCA) or malignant parotid gland tumours (MPGTs) from June 2020 to August 2022. Each patient was randomly classified into training and testing cohorts at a ratio of 7:3, and then, pairwise comparisons in different parotid tumour groups were performed. CT images were transferred to 3D-Slicer software and the region of interest was manually drawn for feature extraction. Feature selection methods were performed using the intraclass correlation coefficient, t test and least absolute shrinkage and selection operator. Five common classifiers, namely, random forest (RF), support vector machine (SVM), logistic regression (LR), K-nearest neighbours (KNN) and general Bayesian network (Gnb), were selected to build different radiomics models. The receiver operating characteristic curve, area under the curve (AUC), accuracy, sensitivity, specificity and F-1 score were used to assess the prediction performances of these models. The calibration of the model was calculated by the Hosmer–Lemeshow test. DeLong’s test was utilized for comparing the AUCs.

Results

The radiomics model based on the RF, SVM, Gnb, LR, LR and RF classifiers obtained the highest AUC in differentiating PA from MPGTs, WT from MPGTs, BCA from MPGTs, PA from WT, PA from BCA, and WT from BCA, respectively. Accordingly, the AUC and the accuracy of the model for each classifier were 0.834 and 0.71, 0.893 and 0.79, 0.844 and 0.79, 0.902 and 0.88, 0.602 and 0.68, and 0.861 and 0.94, respectively.

Conclusion

Our study demonstrated that noncontrast CT-based radiomics could stratify refined pathological types of parotid tumours well but could not sufficiently differentiate PA from BCA. Different classifiers had the best diagnostic performance for different parotid tumours. Our study findings add to the current knowledge on the differential diagnosis of parotid tumours.

Comparative analysis of benign and malignant parotid gland tumors: A retrospective study of 992 patients

OBJECTIVE

We analyzed and compared the clinical characteristics of benign and malignant parotid gland tumors.

PATIENTS AND METHODS

A total of 992 patients who underwent surgical treatment for parotid gland tumors from January 2010 to December 2020 were included in this study. This study population was subdivided into benign (n = 812, 81.9 %) and malignant parotid gland tumors (n = 180, 18.1 %).

RESULTS

Pleomorphic adenoma is the most common benign tumor and mucoepidermoid carcinoma is the most common malignant tumor. The patients with malignant parotid gland tumors were older than the patients with benign lesions. The duration of symptoms was longer in patients with benign parotid gland tumors compared to those with malignant lesions. The size of the malignant tumors was larger than that of the benign lesions. Preoperative fine-needle aspiration cytology had a diagnostic sensitivity of 50.3 %, diagnostic specificity of 98.7 %, a positive predictive value of 89.5 %, a negative predictive value of 89.9 %, and accuracy of 89.9 % for diagnosing malignant parotid gland tumors. For benign parotid gland tumors, superficial parotidectomy was most frequently performed, and for malignant parotid gland tumors, total parotidectomy was most frequently performed. Facial palsy was observed in 19.4 % of the patients with malignant parotid gland tumors compared to 5.4 % of those with benign tumors.

CONCLUSION

The clinical features of benign and malignant parotid gland tumors showed differences in age, symptoms, duration of symptoms, size and site of the parotid tumors, surgical procedures, and postoperative facial nerve palsy.

A Deep Learning Model for Classification of Parotid Neoplasms Based on Multimodal Magnetic Resonance Image Sequences

OBJECTIVE

To design a deep learning model based on multimodal magnetic resonance image (MRI) sequences for automatic parotid neoplasm classification, and to improve the diagnostic decision-making in clinical settings.

METHODS

First, multimodal MRI sequences were collected from 266 patients with parotid neoplasms, and an artificial intelligence (AI)-based deep learning model was designed from scratch, combining the image classification network of Resnet and the Transformer network of Natural language processing. Second, the effectiveness of the deep learning model was improved through the multi-modality fusion of MRI sequences, and the fusion strategy of various MRI sequences was optimized. In addition, we compared the effectiveness of the model in the parotid neoplasm classification with experienced radiologists.

RESULTS

The deep learning model delivered reliable outcomes in differentiating benign and malignant parotid neoplasms. The model, which was trained by the fusion of T2-weighted, postcontrast T1-weighted, and diffusion-weighted imaging (b = 1000 s/mm² ), produced the best result, with an accuracy score of 0.85, an area under the receiver operator characteristic (ROC) curve of 0.96, a sensitivity score of 0.90, and a specificity score of 0.84. In addition, the multi-modal paradigm exhibited reliable outcomes in diagnosing the pleomorphic adenoma and the Warthin tumor, but not in the identification of the basal cell adenoma.

CONCLUSION

An accurate and efficient AI based classification model was produced to classify parotid neoplasms, resulting from the fusion of multimodal MRI sequences. The effectiveness certainly outperformed the model with single MRI images or single MRI sequences as input, and potentially, experienced radiologists.

LEVEL OF EVIDENCE

3 Laryngoscope, 133:327-335, 2023.

Endoscope-Assisted Resection of Benign Parotid Tumors via Concealed Post-Auricular Sulcus Incision

OBJECTIVES

To investigate the feasibility, safety, and effectiveness of endoscopic-assisted resection of benign parotid tumors via concealed post-auricular sulcus incision.

METHODS

Between October 2019 and March 2021, eligible patients with diagnosed benign parotid tumors were prospectively included and randomly assigned to two groups: the endoscope-assisted post-auricular sulcus incision group (endoscope group) and the conventional Blair "S" incision group (conventional group).

RESULTS

A total of 45 patients were finally included, including 24 subjects in the endoscope group and 21 subjects in the conventional group. No obvious differences were observed in basic information between these two groups of patients. The surgical incision length in endoscope group patients was 4.0 ± 0.4 cm, which was significantly shorter than that in conventional group patients, 10.3 ± 1.6 cm (p < 0.001). The total intraoperative blood loss, the first post-operative day drainage volume, the total post-operative drainage volume, and the total drainage days were all significantly lower in endoscope group patients than in conventional group patients (all p < 0.05). Among 3 months follow-ups, no local recurrence or residual tumor were found in both groups of patients, and there were none of them had permanent facial paralysis or parotid fistula. The self-evaluated appearance satisfaction VAS scores of endoscope group patients were all 0, which was significantly lower than that of conventional group patients, 4.7 ± 1.6 (p < 0.001).

CONCLUSION

Compared with the conventional Blair "S" incision surgery, the endoscope-assisted resection of the benign parotid tumors via concealed post-auricular sulcus incision was safe and effective and showed advantages of faster recovery and better self-assessments of appearance satisfaction.

LEVEL OF EVIDENCE

2 Laryngoscope, 133:133-138, 2023.

Point-of-care ultrasound scan as the primary modality for evaluating parotid tumors

Objectives

This study aimed to explore ultrasonography as a single imaging modality for the initial assessment of parotid lesions compared to computed tomography (CT) and magnetic resonance imaging (MRI).

Methods

A retrospective cross-sectional study was performed on 264 parotid gland lesions evaluated in a dedicated point-of-care ultrasound (POCUS) clinic with concurrent fine needle biopsy (FNB). Two hundred and nine of these lesions also underwent CT or MRI imaging. Histopathology results, when available, were recorded and compared to imaging impressions.

Results

Surgeon-performed POCUS classified parotid masses accurately when compared to final histopathology (90/96, 94%). Using predefined criteria, POCUS determined the nature of parotid lesions more definitively than the descriptive CT or MRI radiology reports (p <.001). Sub-analysis showed that ultrasonography was able to distinguish between benign pathologies with high degree of accuracy (Warthin tumor-82%, pleomorphic adenoma-64%).

Conclusions

POCUS can accurately distinguish between benign and malignant parotid lesions. POCUS may suffice as the only imaging study for benign lesions, obviating the need for additional cross-sectional imaging. This can be combined with fine needle or core biopsy in the same visit, resulting in expedient diagnosis, low cost, and lack of radiation exposure.

Level of Evidence

2b, individual cross-sectional cohort study.

Multiphasic CT-Based Radiomics Analysis for the Differentiation of Benign and Malignant Parotid Tumors

Objective

This study aims to investigate the value of machine learning models based on clinical-radiological features and multiphasic CT radiomics features in the differentiation of benign parotid tumors (BPTs) and malignant parotid tumors (MPTs).

Methods

This retrospective study included 312 patients (205 cases of BPTs and 107 cases of MPTs) who underwent multiphasic enhanced CT examinations, which were randomly divided into training (N = 218) and test (N = 94) sets. The radiomics features were extracted from the plain, arterial, and venous phases. The synthetic minority oversampling technique was used to balance minority class samples in the training set. Feature selection methods were done using the least absolute shrinkage and selection operator (LASSO), mutual information (MI), and recursive feature extraction (RFE). Two machine learning classifiers, support vector machine (SVM), and logistic regression (LR), were then combined in pairs with three feature selection methods to build different radiomics models. Meanwhile, the prediction performances of different radiomics models based on single phase (plain, arterial, and venous phase) and multiphase (three-phase combination) were compared to determine which model construction method and phase were more discriminative. In addition, clinical models based on clinical-radiological features and combined models integrating radiomics features and clinical-radiological features were established. The prediction performances of the different models were evaluated by the area under the receiver operating characteristic (ROC) curve (AUC) and the drawing of calibration curves.

Results

Among the 24 established radiomics models composed of four different phases, three feature selection methods, and two machine learning classifiers, the LASSO-SVM model based on a three-phase combination had the optimal prediction performance with AUC (0.936 [95% CI = 0.866, 0.976]), sensitivity (0.78), specificity (0.90), and accuracy (0.86) in the test set, and its prediction performance was significantly better than with the clinical model based on LR (AUC = 0.781, p = 0.012). In the test set, the combined model based on LR had a lower AUC than the optimal radiomics model (AUC = 0.933 vs. 0.936), but no statistically significant difference (p = 0.888).

Conclusion

Multiphasic CT-based radiomics analysis showed a machine learning model based on clinical-radiological features and radiomics features has the potential to provide a valuable tool for discriminating benign from malignant parotid tumors.

CT-based radiomics analysis of different machine learning models for differentiating benign and malignant parotid tumors

OBJECTIVES

This study aimed to explore and validate the value of different radiomics models for differentiating benign and malignant parotid tumors preoperatively.

METHODS

This study enrolled 388 patients with pathologically confirmed parotid tumors (training cohort: n = 272; test cohort: n = 116). Radiomics features were extracted from CT images of the non-enhanced, arterial, and venous phases. After dimensionality reduction and selection, radiomics models were constructed by logistic regression (LR), support vector machine (SVM), and random forest (RF). The best radiomic model was selected by using ROC curve analysis. Univariate and multivariable logistic regression was applied to analyze clinical-radiological characteristics and identify variables for developing a clinical model. A combined model was constructed by incorporating radiomics and clinical features. Model performances were assessed by ROC curve analysis, and decision curve analysis (DCA) was used to estimate the models' clinical values.

RESULTS

In total, 2874 radiomic features were extracted from CT images. Ten radiomics features were deemed valuable by dimensionality reduction and selection. Among radiomics models, the SVM model showed greater predictive efficiency and robustness, with AUCs of 0.844 in the training cohort; and 0.840 in the test cohort. Ultimate clinical features constructed a clinical model. The discriminatory capability of the combined model was the best (AUC, training cohort: 0.904; test cohort: 0.854). Combined model DCA revealed optimal clinical efficacy.

CONCLUSIONS

The combined model incorporating radiomics and clinical features exhibited excellent ability to distinguish benign and malignant parotid tumors, which may provide a noninvasive and efficient method for clinical decision making.

KEY POINTS

The current study is the first to compare the value of different radiomics models (LR, SVM, and RF) for preoperative differentiation of benign and malignant parotid tumors. A CT-based combined model, integrating clinical-radiological and radiomics features, is conducive to distinguishing benign and malignant parotid tumors, thereby improving diagnostic performance and aiding treatment.

Is there a Role for Frozen Section Evaluation of Parotid Masses After Preoperative Cytology or Biopsy Diagnosis?

Fine-needle aspiration (FNA) biopsy reliably diagnoses parotid gland lesions preoperatively, whereas intraoperative frozen section (FS) has the additional benefit of assessing surgical margins and refining diagnoses; however, the role of FS in the setting of prior FNA diagnosis is not well established. Our aim was to determine whether FS should still be performed after a prior FNA/ CNB diagnosis. Parotid gland resections from January 2009 to January 2020 were identified; however, only patients who had both FNA and FS constituted our study population. For the purpose of statistical analysis, FNA diagnoses were classified into non-diagnostic (ND), non-neoplastic (NN), benign neoplasm (BN), indeterminate, and malignant. FS diagnoses were classified into benign, indeterminate, or malignant. Resections were dichotomized into benign and malignant and regarded as the gold standard to subsequently calculate diagnostic accuracy of FNA and FS. A total of 167 parotid gland resections were identified, but only 76 patients (45.5%) had both FNA and FS. In 35 cases deemed as benign preoperatively, three (8.6%) were reclassified as malignant on FS. Out of 18 lesions reported as malignant on FNA, four (22.2%) were interpreted as benign on FS, with three of these benign lesions confirmed on permanent slides. In addition, in patients with both FNA and FS, compared to FNA, FS was able to provide a definitive diagnosis in all five ND cases and in 61.1% (11/18) of indeterminate tumors. Intraoperative assessment provided a relative increase of 33.3% in specificity and 38.5% in positive predictive value when compared to preoperative FNA. The addition of FS to FNA was helpful to further refine the diagnoses of parotid gland lesions, which may provide better guidance for surgical intervention.