Extraparotid Warthin Tumors Imitating Metastasis of Oral Cancers

Introduction Extraparotid Warthin tumor (WT) is a very rare entity, especially when synchronous with oral cancer (OC). Objective The present study presents a case series of extraparotid WTs detected in the surgical specimen of patients treated for OC. Methods From 2007 to 2016, 336 patients were operated for OC in our institution. Neck dissection was performed in 306 patients. Results In the 306 patients operated for OC whose necks were dissected, unexpected WTs were observed in 4 surgical neck specimens. In 3 cases, extraparotid WTs were responsible for tumor, node, metastasis (TNM) overstaging before surgery. Conclusion Extraparotid WTs may be discovered during neck dissection in ∼ 1% of OC patients, and they may mimic neck metastasis, especially in positron-emission tomography/computed tomography (PET/CT) imaging.

Clinical, Pathological, and Genomic profiles of Salivary Warthin tumor-like Mucoepidermoid Carcinoma

Introduction/Objective Warthin tumor-like mucoepidermoid carcinoma(WTL- MEC) is one of the subvariant of mucoepidermoid carcinoma. It mimics the histological features of metaplastic Warthin tumors (mWTs). To investigate the clinicopathological, molecular features, and bio-behaviors of WTL-MEC, we retrospected a cohort of 29 WTL- MEC patients. Methods/Case Report The clinicopathological and microscopic data were collected. Dual-color FISH analysis was performed on paraffin-embedded sections of 29 WTL- MEC patients and 16 mWTs patients using a MAML2 break- apart probe. Whole-exome sequencing and whole transcription sequencing were performed on 3 WTL-MEC and 3 typical mucoepidermoid carcinomas (TMEC) patients. Genetic data were bioinformatically analyzed by software MuTect (v1.7), PINDEL (v0.2.5), SnpEff (v3.0), and etc. Results (if a Case Study enter NA) The cohort of WTL-MEC included 10 male and 19 female patients with a median age of 42.3 years (range, 8 to 68 years). Microscopically, the WTL-MEC lesion consisted of multi-cysts with variant shapes and sizes. The cystic spaces were lined by bi-layered and multilayered oncocytic cells. A transition zone between the bi-layered oncocytic epithelium to the multilayered oncocytic epithelium was observed in WTL-MEC. The cords of epidermoid cells and mucous cells could be found. The germinal center, extensive hyalinization, and mucus extravasation were observed. MAML2 rearrangement was identified in 29 (100%) WTL-MEC. No rearrangement was observed in mWTs by FISH. MET was the most commonly mutated gene in TMEC, and PRDM11 was the most commonly mutated gene in WTL-MEC. Twenty-nine patients were alive without recurrent at the end of the follow-up periods(5–128M). One Patient died due to the metastasis to the lung. Conclusion compared with mWTs, WTL- MEC usually presented in the young, non-smoking female. The histological feature of WTL-MEC depended mainly on the transition zone of the bi-layered oncocytic epithelium and the multilayered oncocytic epithelium. And MAML2 status can confirm the diagnosis. CRTC1-MAML2 and PRDM11 mutations appear to be the main driver event of WTL-MEC. Prognosis was usually favorable, but recurrence or metastasis may rarely occur.

Frequency of surgical complications and recurrence rate after extracapsular dissection of benign tumors of the parotid.

Objective: To determine surgical complications and recurrence rate in patients with benign lesions of the parotid undergoing extracapsular dissection. Study Design: Case Series. Setting: Department of Surgery, Rawalpindi Medical University, Rawalpindi. Period: January 2010 and December 2018. Material & Methods: The hospital records of all 50 patients who underwent extracapsular dissection with a diagnosis of either Pleomorphic adenoma or War thin tumor between reviewed retrospectively. Data regarding demographics, tumor, complications and recurrence was collected. Results: Out of 50 patients, 40 were males and 10 were females with age ranging from 26 to 52 years and mean age of 42 years. 44 of 50 parotid lumps were diagnosed as Pleomorphic adenoma and 6 were cases of Warthin tumor. The range of lesion size was 1.5 to 3 cm. 15 (30%) patients suffered from transient facial nerve weakness, whereas only 1 (2%) sustained a facial nerve injury which required repair. There was no case of Frey syndrome, sialocele and hematoma, however, salivary fistula was seen in 1 (2%) patient. Capsule rupture during surgery occurred in 15 (30%) patients and recurrence was seen in only 1 patient (2%). Conclusion: Extracapsular dissection has low recurrence rate, very few complications and is a safe and effective treatment for Pleomorphic adenoma and Warthin tumor.

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/MethodsTwo 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).ResultsThe 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.ConclusionThe 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.