Pictorial review: MR imaging of parotid tumours

An anatomy-aware framework for automatic segmentation of parotid tumor from multimodal MRI

Magnetic Resonance Imaging (MRI) plays an important role in diagnosing the parotid tumor, where accurate segmentation of tumors is highly desired for determining appropriate treatment plans and avoiding unnecessary surgery. However, the task remains nontrivial and challenging due to ambiguous boundaries and various sizes of the tumor, as well as the presence of a large number of anatomical structures around the parotid gland that are similar to the tumor. To overcome these problems, we propose a novel anatomy-aware framework for automatic segmentation of parotid tumors from multimodal MRI. First, a Transformer-based multimodal fusion network PT-Net is proposed in this paper. The encoder of PT-Net extracts and fuses contextual information from three modalities of MRI from coarse to fine, to obtain cross-modality and multi-scale tumor information. The decoder stacks the feature maps of different modalities and calibrates the multimodal information using the channel attention mechanism. Second, considering that the segmentation model is prone to be disturbed by similar anatomical structures and make wrong predictions, we design anatomy-aware loss. By calculating the distance between the activation regions of the prediction segmentation and the ground truth, our loss function forces the model to distinguish similar anatomical structures with the tumor and make correct predictions. Extensive experiments with MRI scans of the parotid tumor showed that our PT-Net achieved higher segmentation accuracy than existing networks. The anatomy-aware loss outperformed state-of-the-art loss functions for parotid tumor segmentation. Our framework can potentially improve the quality of preoperative diagnosis and surgery planning of parotid tumors.

Tratamiento quirúrgico de la patología tumoral de la glándula parótida. Estudio descriptivo de 263 parotidectomías

Introducción y objetivo: Los tumores salivales representan el 3-10% de los tumores de cabeza y cuello, siendo el 75-80% de origen parotídeo y en su mayoría benignos. La parotidectomía es una técnica quirúrgica que consiste en la exéresis de la glándula parótida. Existen diversos tipos; parotidectomía superficial (PS), parotidectomía superficial parcial (PSP) y parotidectomía total (PT). En esta última, al no respetarse el nervio facial (NF), las complicaciones son más frecuentes. Nuestro objetivo es analizar el resultado (tasa de recidiva y complicaciones) de la parotidectomía como técnica quirúrgica empleada en el manejo de la patología parotídea, así como evaluar qué prueba complementaria es la más eficaz en el diagnostico prequirúrgico de la patología parotídea tumoral. Material y método: Se realiza un estudio retrospectivo incluyendo 263 pacientes tratados mediante PS o PT entre enero de 2004 y diciembre de 2020 en el Hospital Universitario de Fuenlabrada. Se registraron datos demográficos, tiempo de evolución de la lesión, pruebas complementarias, protocolo quirúrgico y complicaciones postoperatorias. Se analiza principalmente la correlación positiva entre las pruebas realizadas prequirúrgicas (PAAF, ecografía, TC y RMN), con el diagnóstico definitivo anatomopatológico obtenido tras examinar la pieza quirúrgica. También se describe la tasa de paresia y parálisis facial y otras complicaciones habidas. Resultados: Se incluyeron 263 pacientes tratados mediante parotidectomía. El tiempo de evolución medio de las lesiones parotídeas fue de 15 meses (DE 19.88). La sensibilidad de la PAAF en nuestro estudio fue de 68.7%. Se realizó ecografía en un 44.10% de los pacientes, TC en un 77.94% y RMN en un 15.20%, mostrando una sensibilidad de 18.05%, 31.21% y 45%, respectivamente. La cirugía más frecuente fue la PS (43.3%, 114/263), seguida por la PSP (41.1%, 108/263) y, por último, la menos habitual fue la PT (15.58%, 41/263). Los tumores benignos fueron más frecuentes (84.79%, 223/263), siendo el adenoma pleomorfo el más frecuente, 45.73% (102/223). Dentro del grupo de tumores malignos (15.20%, 40/263), el más habitual fue el carcinoma mucoepidermoide (17.5%, 7/40) y las metástasis (17.5%, 7/40). La paresia facial, según la escala de House-Brackmann, fue leve (grado I y II) y transitoria en la mayoría de los casos, apareciendo en un 31.55%. Tras un periodo medio de seguimiento de 6 años no se han encontrado recidivas post parotidectomía por ningún tipo tumoral en nuestro estudio. Conclusión: En nuestra muestra, los tumores benignos representaron la gran mayoría de la patología parotídea. Dentro de este grupo, el adenoma pleomorfo fue el más frecuente. La PAAF fue la prueba complementaria con mejor correlación con el diagnostico anatomopatológico definitivo, seguida por la RMN. La paresia facial leve (grados I y II) y transitoria fue la complicación postquirúrgica mas habitual.

Magnetic resonance imaging of parotid gland tumors: a pictorial essay

Imaging of parotid gland tumors is challenging due to the wide variety of differential diagnoses. Malignant parotid tumors can have very similar features to benign ones, such as slow growth and displacement instead of infiltration of neighboring structures. Malignant and benign tumors may therefore not be clinically distinguishable. Correct characterization of parotid tumors (i.e., benign or malignant) determines preoperative treatment planning and is important in optimizing the individualized surgical plan. Magnetic resonance imaging (MRI) is the imaging modality of choice for evaluation of suspected parotid gland lesions and differentiation between benign and malignant lesions. Certain conventional MRI features can suggest whether a mass is more likely to be a benign or low-grade malignancy or a high-grade malignancy and adding diffusion-weighted imaging or advanced MRI techniques like perfusion can aid in this distinction. Morphological features seen on MRI, such as low signal on T2-w, infiltrative changes or ill-defined margins, change over time and diffusion restriction can point to the malignant nature of the lesion. MRI is useful for detection and localization of the lesion(s), and associated findings like perineural spread of tumor, lymph node involvement and infiltrative changes of the surrounding tissues. In this pictorial essay, we present selected images of a variety of benign and malignant parotid tumors and emphasize the MRI features that may be useful in their characterization.

Machine learning-based radiomics for histological classification of parotid tumors using morphological MRI: a comparative study

OBJECTIVES

To evaluate the effectiveness of machine learning models based on morphological magnetic resonance imaging (MRI) radiomics in the classification of parotid tumors.

METHODS

In total, 298 patients with parotid tumors were randomly assigned to a training and test set at a ratio of 7:3. Radiomics features were extracted from the morphological MRI images and screened using the Select K Best and LASSO algorithm. Three-step machine learning models with XGBoost, SVM, and DT algorithms were developed to classify the parotid neoplasms into four subtypes. The ROC curve was used to measure the performance in each step. Diagnostic confusion matrices of these models were calculated for the test cohort and compared with those of the radiologists.

RESULTS

Six, twelve, and eight optimal features were selected in each step of the three-step process, respectively. XGBoost produced the highest area under the curve (AUC) for all three steps in the training cohort (0.857, 0.882, and 0.908, respectively), and for the first step in the test cohort (0.826), but produced slightly lower AUCs than SVM in the latter two steps in the test cohort (0.817 vs. 0.833, and 0.789 vs. 0.821, respectively). The total accuracies of XGBoost and SVM in the confusion matrices (70.8% and 59.6%) outperformed those of DT and the radiologist (46.1% and 49.2%).

CONCLUSION

This study demonstrated that machine learning models based on morphological MRI radiomics might be an assistive tool for parotid tumor classification, especially for preliminary screening in absence of more advanced scanning sequences, such as DWI.

KEY POINTS

• Machine learning algorithms combined with morphological MRI radiomics could be useful in the preliminary classification of parotid tumors. • XGBoost algorithm performed better than SVM and DT in subtype differentiation of parotid tumors, while DT seemed to have a poor validation performance. • Using morphological MRI only, the XGBoost and SVM algorithms outperformed radiologists in the four-type classification task for parotid tumors, thus making these models a useful assistant diagnostic tool in clinical practice.

Cross-sectional imaging and cytologic investigations in the preoperative diagnosis of parotid gland tumors - An updated literature review

An accurate preoperative diagnosis of parotid tumors is essential for the selection and planning of surgical treatment. Various modern cross-sectional imaging and cytologic investigations can support the differential diagnosis of parotid tumors. The aim of this study was to achieve a comprehensive and updated review of modern imaging and cytologic investigations used in parotid tumor diagnosis, based on the latest literature data. This literature review could serve as a guide for clinicians in selecting different types of investigations for the preoperative differential diagnosis of parotid tumors. Magnetic resonance imaging (MRI) with its dynamic and advanced sequences is the first-line imaging investigation used in differentiating parotid tumors. Computed tomography (CT) and positron emission tomography (PET)-CT provide limited indications in differentiating parotid tumors. Fine needle aspiration biopsy and core needle biopsy can contribute with satisfactory results to the cytological diagnosis of parotid tumors. Dynamic MRI with its dynamic contrast-enhanced and diffusion-weighted sequences provides the best accuracy for the preoperative differential diagnosis of parotid tumors. CT allows the best evaluation of bone invasion, being useful when MRI cannot be performed, and PET-CT has value in the follow-up of cancer patients. The dual cytological and imaging approach is the safest method for an accurate differential diagnosis of parotid tumors.

Differentiation of pleomorphic adenoma and Warthin's tumor of the parotid gland: ultrasonographic features

BACKGROUND

Parotid tumor is an uncommon neoplasm. Only a few studies describing the sonographic features of pleomorphic adenomas and Warthin's tumors have been published, and most of those reports are based on a relatively small number of cases.

PURPOSE

To define the sonographic characteristics of pleomorphic adenoma and Warthin's tumor in the parotid gland.

MATERIAL AND METHODS

We retrospectively evaluated the sonographic features of 77 pleomorphic adenomas in 70 patients and 93 Warthin's tumors in 61 patients. The features included tumor size, shape, border, echogenicity, and homogeneity, the presence of a cystic area, acoustic enhancement, and the grade and distribution of vascularization.

RESULTS

Lobulated lesions were observed in 49 pleomorphic adenomas and 36 Warthin's tumors. The lobulated shape was observed more frequently in pleomorphic adenomas than in Warthin's tumors (P = 0.005). Cystic areas within lesions were detected in 16 (16/77, 20.8%) pleomorphic adenomas and 42 (42/93, 45.2%) Warthin's tumors (P = 0.001). Of the pleomorphic adenomas, 77.9% had grade 0 or grade 1 vascularity, while 73.1% of Warthin's tumors had grade 2 or grade 3 vascularity (P = 0.000). Flow was peripheral in 53.2% of pleomorphic adenomas. The frequencies of central perfusion and mixed perfusion in Warthin's tumors were equal (47.3% vs. 47.3%, respectively). The differences in the vessel distribution between these two diseases was significant (P = 0.000).

CONCLUSION

Ultrasound imaging characteristics, including multiple occurrences, shape, intrinsic cystic change, and the grade and distribution of tumor vessels, can be used to differentiate pleomorphic adenomas from Warthin's tumors.

Les tumeurs des glandes salivaires

Tumors of salivary glands arise mainly from the parotid gland. Magnetic Resonance Imaging (MRI) is mandatory not only to localize precisely the tumor within the gland but also to differentiate between benign and malignant neoplasms, in competition with cytology in fine-needle aspiration biopsy. Tumors without risk of transformation, such as adenolymphoma, are not systematically operated on. Indications of roentgenotherapy and irradiation volumes depend on histologic type, localisation and size of the tumor.

Preoperative diagnostic values of fine-needle cytology and MRI in parotid gland tumors

The aim of this retrospective study was to assess and compare the diagnostic value of fine-needle cytology and MRI for the prediction of malignancy in parotid tumors. During an 11-year period, 148 patients underwent preoperative fine-needle aspiration cytology in our institution. Eighty-seven patients underwent a preoperative MRI study, and 54 had both MRI and cytology. The study compares results of cytology and MRI with histological reports. The sensitivity, specificity and accuracy for detecting malignant lesions were 87, 94 and 93% respectively for MRI, 81, 95 and 92% respectively for cytology and 100, 88 and 91% respectively for both studies combined. Fine-needle cytology provided better information than MRI concerning precise histological diagnoses. Conversely, the proportion of non-diagnostic smears reached 10%. Fine-needle cytology and MRI are simple, well-tolerated diagnostic means with an impact on the management of salivary gland tumors. The associated anatomic information obtained by MRI imaging makes it the test of first choice in an optimal medical environment.

Radiological imaging in primary parotid malignancy

In a retrospective analysis of the preoperative imaging of patients presenting with primary malignant parotid disease, all relevant images were collected and reviewed by two experienced head and neck radiologists, blinded to the diagnosis. Forty-two patients (25 male, 17 female), median age 67.5 years (range 15-86), were included in the study of which 32 had undergone CT scanning, nine MR and three ultrasound. Forty tumours (93%) were correctly diagnosed as malignant when compared with histology. The two false negatives arose in a patient who had received an ultrasound scan only and in a patient with lymphoma, whose CT scan was reported as a pleomorphic adenoma. Neither had undergone prior radiotherapy. A poorly defined tumour boundary was the most consistent observation for both MR and CT images for the malignant tumours examined. Local infiltration was correctly correlated with pathological findings in eight of the nine MR scans, however, CT proved less reliable, correct in 14 of 24 cases (p=0.01). No correlation was identified between any of the imaging features examined and the final histological diagnosis. A poorly defined tumour boundary with evidence of local invasion was the best indicator of malignancy and was reported more frequently from MR scans than from CT. Imaging alone, however, proved unreliable in the prediction of final histological diagnosis or grade of tumour.

High resolution ultrasound assessment of the parotid gland

A variety of neoplastic and non-neoplastic conditions may present with parotid swelling. It is rarely possible to predict the nature of a swelling on clinical grounds alone and accurate imaging is necessary for further assessment. The parotid glands are superficial structures and are readily amenable to high resolution ultrasound examination. Ultrasound is able to: differentiate possible benign from malignant neoplasms; demonstrate whether a palpable lesion arises within the parotid gland, or is periparotid in location; and identify those entities that may not need surgical intervention. In this article the sonographic features of a range of parotid pathologies are reviewed and examples illustrated and the role of ultrasound in parotid assessment is discussed.

The role of imaging in the evaluation of parotid disease

In this review the imaging features of a range of parotid lesions are presented and the roles of ultrasound (US), computed tomography (CT) and magnetic resonance imaging (MRI) in the assessment of parotid disease are discussed.

Prediction of the position of the intraparotid portion of the facial nerve on MRI and CT

Despite developments in imaging technology, visualisation of the intraparotid portion of the facial nerve is not possible. Three separate radiological techniques have been described to predict the position of the facial nerve: Conn's arc; a plane extending posteriorly from the outer surface of the mandibular ramus; and soft-tissue structures, including the posterior belly of the digastric muscle, the retromandibular vein and the lateral border of the masseter muscle. We investigated the reliability of these techniques in predicting the relationship of tumours to the facial nerve. Cross-sectional imaging of the parotid glands was performed prior to the removal of a parotid mass in 26 patients. Twenty patients underwent MRI, and six had CT scans. We removed 14 malignant neoplasms, nine benign lesions and three non-neoplastic lesions. The relationship of the tumour to the facial nerve was assessed radiologically by each of the three techniques, and compared with the findings at surgery. In 18 patients the tumour involved the parotid gland deep to the facial nerve. The above techniques predicted the position of the facial nerve in 69%, 58% and 46% of cases, respectively. When planning parotid surgery, it is important that the surgeon understands the advantages and limitations of the radiological assessment of the position of parotid tumours in relation to the facial nerve.