The value of fine needle aspiration cytology in the clinical management of rare salivary gland tumors

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.

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.

[Indications for fine-needle aspiration and core needle biopsy for diagnosis of salivary gland tumors]

BACKGROUND

Salivary gland malignancies are rare neoplasms of the head and neck area. Preoperative clinical and imaging assessment of salivary gland masses is challenging. However, preoperative identification of malignancy is crucial for further treatment and for the course of the disease.

OBJECTIVE

This article presents the advantages and disadvantages of fine-needle aspiration cytology (FNAC) and core needle biopsy (CNB). Additionally, the sensitivity and specificity of both methods for predicting malignancy were analyzed. Furthermore, it is discussed which procedure is suitable for the diagnostic work-up of salivary gland tumors.

MATERIALS AND METHODS

This current article summarizes important and recent studies in the field of the diagnostic work-up for salivary gland lesions, with discussion of original articles, metanalyses, and systematic reviews concerning FNAC and CNB.

RESULTS

The sensitivity and specificity of the predictive ability of FNAC for malignancy is described at between 70.0-80.0% and 87.5-97.9%. The pooled sensitivity and specificity for CNB were 92.0-98.0% and 95.0-100.0%, respectively. Tumor cell seeding or facial nerve palsy are very rare complications of both procedures.

CONCLUSION

If malignancy is suspected based on clinical examination or imaging, FNAC or CNB should be performed. FNAC is easy to perform; however, an onsite cytologist is necessary. CNB has a higher sensitivity for routine diagnosis of malignancy; tumor typing and grading is facilitated by preserving the histological architecture. In conclusion, CNB is the procedure of choice in the diagnostic work-up for suspected malignant salivary gland tumors.

A Rare Case of Nodular Lymphocyte Predominance Hodgkin's Lymphoma of the Parotid Gland: Diagnostic Pitfall in Fine Needle Aspiration Cytology

Primary malignant lymphoma of the salivary glands is a very rare entity, and primary parotid Hodgkin's Lymphoma (HL) is even rarer. It is rare in the initial evaluation to suspect a parotid tumor. Thus, it is important to keep lymphomatous involvement in mind when facing parotid masses in differential diagnosis. This study presented a case of a 56-year-old male with a 5-month history of left cheek enlargement. Fine Needle Aspiration (FNA) biopsy was performed with no suspicion for lymphoma. Parotidectomy was also done and nodular lymphocyte predominance HL within the parotid gland was confirmed by immunohistochemical study. The Nodular Lymphocyte Predominance Hodgkin's Lymphoma has been defined as a specific histopathological subtype of HL. The initial diagnostic approach is usually carried out through FNA, obtaining high sensitivity and specificity, which allows establishing an adjusted for co-correct diagnosis.

Radiomics and deep learning approach to the differential diagnosis of parotid gland tumors

PURPOSE OF REVIEW

Advances in computer technology and growing expectations from computer-aided systems have led to the evolution of artificial intelligence into subsets, such as deep learning and radiomics, and the use of these systems is revolutionizing modern radiological diagnosis. In this review, artificial intelligence applications developed with radiomics and deep learning methods in the differential diagnosis of parotid gland tumors (PGTs) will be overviewed.

RECENT FINDINGS

The development of artificial intelligence models has opened new scenarios owing to the possibility of assessing features of medical images that usually are not evaluated by physicians. Radiomics and deep learning models come to the forefront in computer-aided diagnosis of medical images, even though their applications in the differential diagnosis of PGTs have been limited because of the scarcity of data sets related to these rare neoplasms. Nevertheless, recent studies have shown that artificial intelligence tools can classify common PGTs with reasonable accuracy.

SUMMARY

All studies aimed at the differential diagnosis of benign vs. malignant PGTs or the identification of the commonest PGT subtypes were identified, and five studies were found that focused on deep learning-based differential diagnosis of PGTs. Data sets were created in three of these studies with MRI and in two with computed tomography (CT). Additional seven studies were related to radiomics. Of these, four were on MRI-based radiomics, two on CT-based radiomics, and one compared MRI and CT-based radiomics in the same patients.

Deep Learning for Differentiating Benign From Malignant Parotid Lesions on MR Images

Purpose/Objectives(s)

Salivary gland tumors are a rare, histologically heterogeneous group of tumors. The distinction between malignant and benign tumors of the parotid gland is clinically important. This study aims to develop and evaluate a deep-learning network for diagnosing parotid gland tumors via the deep learning of MR images.

Materials/Methods

Two hundred thirty-three patients with parotid gland tumors were enrolled in this study. Histology results were available for all tumors. All patients underwent MRI scans, including T1-weighted, CE-T1-weighted and T2-weighted imaging series. The parotid glands and tumors were segmented on all three MR image series by a radiologist with 10 years of clinical experience. A total of 3791 parotid gland region images were cropped from the MR images. A label (pleomorphic adenoma and Warthin tumor, malignant tumor or free of tumor), which was based on histology results, was assigned to each image. To train the deep-learning model, these data were randomly divided into a training dataset (90%, comprising 3035 MR images from 212 patients: 714 pleomorphic adenoma images, 558 Warthin tumor images, 861 malignant tumor images, and 902 images free of tumor) and a validation dataset (10%, comprising 275 images from 21 patients: 57 pleomorphic adenoma images, 36 Warthin tumor images, 93 malignant tumor images, and 89 images free of tumor). A modified ResNet model was developed to classify these images. The input images were resized to 224x224 pixels, including four channels (T1-weighted tumor images only, T2-weighted tumor images only, CE-T1-weighted tumor images only and parotid gland images). Random image flipping and contrast adjustment were used for data enhancement. The model was trained for 1200 epochs with a learning rate of 1e-6, and the Adam optimizer was implemented. It took approximately 2 hours to complete the whole training procedure. The whole program was developed with PyTorch (version 1.2).

Results

The model accuracy with the training dataset was 92.94% (95% CI [0.91, 0.93]). The micro-AUC was 0.98. The experimental results showed that the accuracy of the final algorithm in the diagnosis and staging of parotid cancer was 82.18% (95% CI [0.77, 0.86]). The micro-AUC was 0.93.

Conclusion

The proposed model may be used to assist clinicians in the diagnosis of parotid tumors. However, future larger-scale multicenter studies are required for full validation.

Can Ultrasound in Combination with Virtual Touch Imaging Quantification Predict the Dignity of a Parotid Tumor?

Pre-operative evaluation of a parotid gland tumor is crucial in guiding treatment. This study evaluates the diagnostic performance of B-mode ultrasound in combination with Virtual Touch imaging quantification (VTIQ) in the assessment of parotid lesions. A prospective study of 268 patients with parotid lesions was conducted. Pre-operative ultrasound findings and VTIQ data were compared against histologic results. Ill-defined margins on ultrasound were associated with a significantly higher risk of malignancy (odds ratio [OR] = 1224.0, 95 % confidence interval [CI]: 151.8-9872.7). Faster mean shear waves on VTIQ (OR = 1.81, 95% CI: 1.47-2.23, per 1 m/s increase) and an area with shear wave velocity >6.0 m/s involving >70 % of the lesion (OR = 19.80, 95 % CI: 6.22-63.07) were associated with higher risk of malignancy. Addition of VTIQ to routine pre-operative B-mode ultrasound can provide supplemental information on the dignity of a parotid tumor, allowing for peri-operative procedural optimization.

Application value of shear wave elastography in salivary gland tumors

OBJECTIVE

The aims of this study were to retrospectively analyse the values of shear wave elastography (SWE) in differential diagnosis of salivary gland tumors (SGT).

METHODS

A total of 56 patients with salivary gland lump(s) were examined by SWE for measuring and comparing the differences in various Young's modules (malignant tumor (MT) and benign tumor (BT), parotid tumor (PA) and adenolymphomas (AL), etc.). All the cases were confirmed by surgery or fine needle aspiration pathology.

RESULTS

The 56 SGT cases included 10 cases MT, 27 cases of PA, 11 cases of AL, and 8 cases of other BT. There was no statistical significance in Young's modules between group BT and group MT (both P > 0.05); the differences between group PA and group AL were statistically significant (P < 0.05), and the corresponding ROC curve analysis found that the diagnostic value of the maximum Young's modulus was the highest with the best cut-off values and AUC as 32.4 KPa and 0.805. The sensitivity, specificity, and Yoden index of the diagnosis of PA and AL were 70.4%, 81.8%, and 0.522, respectively.

CONCLUSIONS

SWE can differentially diagnose PA and AL while not MT and BT in SGT.

Diagnostic value of preoperative fine needle aspiration cytology in parotid gland tumors

BACKGROUND

Salivary gland masses constitute a broad spectrum of lesions ranging from non-neoplastic to benign and malignant lesions. Parotid is the largest salivary gland and constitutes 75% to 80% of all salivary gland areas. 80% of parotid lesions are benign and 20% are malignant.

METHODS

Two-hundred and eight-six patients who underwent aspiration cytology in the pathology laboratory between January 1995 and January 2019, evaluated with a sufficient sample and diagnosed, and subsequently underwent surgical treatment were included in the study.

RESULTS

47.9% (137) of the patients were female and 52.1% (149) were male. The mean age was 58 years (range: 38-84 years). 13 (4.54%) of the cases were evaluated as non-diagnostic, 12 (4.1%) as atypia of undetermined significance, 196 (68.5%) as benign neoplasm, 43 (15%) as suspicious for malignancy, and 22 (7.86%) were evaluated as malignant. In the histopathological examination of the samples prepared from surgical specimens of 13 non-diagnostic cases, seven (53.8%) cases were reported as Warthin tumors, four (30.7%) as pleomorphic adenomas, and two (15.5%) were reported as lymph nodes with intraparotid localization.

CONCLUSION

The diagnosis of Fine needle aspiration cytology (FNAC) in the parotid gland is difficult due to the rarity of malignant salivary gland neoplasms, the diversity of carcinoma types, and the similarity of cytologic findings of benign tumors and low-grade carcinomas. The diagnostic accuracy of preoperative FNAC is high for benign tumors and low for malignant tumors.

Mucosa-associated lymphoid tissue lymphoma of the accessory parotid gland presenting as a simple cheek mass: A case report

RATIONALE

Mucosa-associated lymphoid tissue (MALT) lymphoma, also known as extranodal marginal zone B-cell lymphoma, usually occurs in the gastric mucosa, lung, lacrimal glands, and salivary glands. MALT lymphoma arising from the accessory parotid gland is extremely rare and can therefore be easily confused with other types of soft tissue masses.

PATIENT CONCERNS

A 56-year-old woman presented with a 1-month history of a mass on the left cheek. The mass was hard and nontender. She had a history of thymectomy 26 years ago due to myasthenia gravis.

DIAGNOSIS

A soft tissue tumor measuring 2.5 × 0.8 cm was identified in the left accessory parotid gland on ultrasonography and enhanced computed tomography (CT). Additionally, CT revealed enlargement of both lacrimal glands and an enhancing mass in the right retropharyngeal space. Under suspicion of a malignant soft tissue tumor, ultrasonography-guided fine needle aspiration biopsy was performed, with findings suggestive of marginal zone B-cell lymphoma of the accessory parotid gland.

INTERVENTIONS

The patient was transferred to the department of hematology for immunochemotherapy.

OUTCOMES

The patient has received 6 cycles of rituximab with cyclophosphamide, vincristine, and prednisone chemotherapy. After 6-month follow-up, enhanced CT demonstrated complete remission. Now she is currently under periodic follow-up.

LESSONS

Physicians and surgeons should be aware that MALT lymphoma can occur in the accessory parotid gland. When this is suspected, careful history-taking, imaging workup, and biopsy are essential for accurate diagnosis and treatment.

Non-primary salivary malignancies: A 22-year retrospective study

PURPOSE

Most salivary gland malignancies are primary tumors, but in our medical center one of six is non-primary. The relative scarcity of such reports justifies studying them.

SUBJECTS & METHODS

We studied patients' demographic and clinical parameters, salivary tumors/metastasis, diagnosis and treatment, and survival rates.

RESULTS

Of all our salivary malignancy patients over the last 22 years, 15% (18/119) had non-primary malignant tumors, all located in the parotid glands. Of these, nine had skin cancer (SCC), 3 malignant solid tumors and 6 hematological systemic malignancies. Four had concomitant second malignancy. Mean age was 70.2 ± 13.8 years, 66.7% of the patients were males, 27.8% were smokers, none reported alcohol use. The most prevalent diagnostic tools used were CT (16 patients), FNA (13) and PET-CT (12). Eleven of 18 patients died from the disease despite receiving therapy: 6 SCC patients, 2 CLL patients and all 3 with solid tumors. All four lymphoma patients survived as did another three SCC patients.

CONCLUSIONS

Chemotherapy and radiotherapy for systemic disease prolonged life rather than surgery. Patients with poor prognosis non-primary salivary tumors should be treated conservatively; surgery should be for those without widespread metastases or systemic disease. Sometimes a palliative patient may benefit from tumor debulking.

The key radiologic and cytomorphologic features of oncocytic and oncocytoid lesions of the salivary gland

Oncocytic and oncocytoid lesions represent a distinct subset of salivary gland lesions. True oncocytic lesions of the salivary gland are entirely composed of oncocytes. These are characterized by the presence of abundant eosinophilic granules due to the presence of abundant cytoplasmic mitochondria. Oncocytic lesions of the salivary gland include oncocytosis, oncocytoma, and oncocytic carcinoma. In addition to the true oncocytic lesion, there exists another group of salivary gland lesions, which demonstrate cells with abundant and occasionally granular cytoplasm. These are often termed as "oncocytoid" lesions. The recently proposed Milan System for reporting salivary gland cytology clearly states that fine-needle aspiration specimens representing oncocytic/oncocytoid lesions of salivary gland cannot effectively distinguish between a nonneoplastic lesion, benign and malignant neoplasms. Therefore, most lesions lacking classic cytomorphologic features will be classified under the umbrella diagnostic term of "Salivary Gland Neoplasm of Uncertain Malignant Potential" (SUMP). In this review, we discuss and illustrate key clinicopathologic and radiologic features that can help the practicing cytopathologist narrow down the differential and provide the best management based diagnosis.