Objective: In this study, we exploited a VGG-16 deep convolutional neural network (DCNN) model to differentiate papillary thyroid carcinoma (PTC) from benign thyroid nodules using cytological images.Methods: A pathology-proven dataset was built from 279 cytological images of thyroid nodules. The images were cropped into fragmented images and divided into a training dataset and a test dataset. VGG-16 and Inception-v3 DCNNs were trained and tested to make differential diagnoses. The characteristics of tumor cell nucleus were quantified as contours, perimeter, area and mean of pixel intensity and compared using independent Student's t-tests.Results: In the test group, the accuracy rates of the VGG-16 model and Inception-v3 on fragmented images were 97.66% and 92.75%, respectively, and the accuracy rates of VGG-16 and Inception-v3 in patients were 95% and 87.5%, respectively. The contours, perimeter, area and mean of pixel intensity of PTC in fragmented images were more than the benign nodules, which were 61.01±17.10 vs 47.00±24.08, p=0.000, 134.99±21.42 vs 62.40±29.15, p=0.000, 1770.89±627.22 vs 1157.27±722.23, p=0.013, 165.84±26.33 vs 132.94±28.73, p=0.000), respectively.Conclusion: In summary, after training with a large dataset, the DCNN VGG-16 model showed great potential in facilitating PTC diagnosis from cytological images. The contours, perimeter, area and mean of pixel intensity of PTC in fragmented images were more than the benign nodules.

The mammalian peptide hormone stanniocalcin 2 (STC2) plays an oncogenic role in many human cancers. However, the exact function of STC2 in human head and neck squamous cell carcinoma (HNSCC) is unclear. We aimed to examine the function and clinical significance of STC2 in HNSCC. Using in vitro and in vivo assays, we show that overexpression of STC2 suppressed cell apoptosis, promoted cell proliferation, migration, invasion, and cell cycle arrest at the G1/S transition. By contrast, silencing of STC2 inhibited these activities. We further show that STC2 upregulated the phosphorylation of AKT and enhanced HNSCC metastasis via Snail-mediated increase of vimentin and decrease of E-cadherin. These responses were blocked by silencing of STC2/Snail expression or inhibition of pAKT activity. Furthermore, clinical data indicate that high STC2 expression was associated with high levels of pAKT and Snail in tumor samples from HNSCC patients with regional lymph node metastasis (P < 0.01). Thus, we conclude that STC2 controls HNSCC metastasis via the PI3K/AKT/Snail signaling axis and that targeted therapy against STC2 may be a novel strategy to effectively treat patients with metastatic HNSCC.

To identify genetic markers for laryngeal squamous cell carcinoma (LSCC), we conducted a genome-wide association study (GWAS) on 993 individuals with LSCC (cases) and 1,995 cancer-free controls from Chinese populations. The most promising variants (association P < 1 × 10(-5)) were then replicated in 3 independent sets including 2,398 cases and 2,804 controls, among which we identified 3 new susceptibility loci at 11q12 (rs174549), 6p21 (rs2857595) and 12q24 (rs10492336). The minor alleles of each of these loci showed protective effects, with odds ratios (95% confidence intervals) of 0.73 (0.68-0.78; P = 1.00 × 10(-20)), 0.78 (0.72-0.84; P = 2.43 × 10(-15)) and 0.71 (0.65-0.77; P = 4.48 × 10(-14)), respectively. None of these variants showed an interaction with smoking or drinking. This is the first GWAS to our knowledge solely on LSCC, and the findings might advance understanding of the etiology of LSCC.

Background: To explore whether deep convolutional neural networks (DCNNs) have the potential to improve diagnostic efficiency and increase the level of interobserver agreement in the classification of thyroid nodules in histopathological slides.Methods: A total of 11,715 fragmented images from 806 patients' original histological images were divided into a training dataset and a test dataset. Inception-ResNet-v2 and VGG-19 were trained using the training dataset and tested using the test dataset to determine the diagnostic efficiencies of different histologic types of thyroid nodules, including normal tissue, adenoma, nodular goiter, papillary thyroid carcinoma (PTC), follicular thyroid carcinoma (FTC), medullary thyroid carcinoma (MTC) and anaplastic thyroid carcinoma (ATC). Misdiagnoses were further analyzed.Results: The total 11,715 fragmented images were divided into a training dataset and a test dataset for each pathology type at a ratio of 5:1. Using the test set, VGG-19 yielded a better average diagnostic accuracy than did Inception-ResNet-v2 (97.34% vs. 94.42%, respectively). The VGG-19 model applied to 7 pathology types showed a fragmentation accuracy of 88.33% for normal tissue, 98.57% for ATC, 98.89% for FTC, 100% for MTC, 97.77% for PTC, 100% for nodular goiter and 92.44% for adenoma. It achieved excellent diagnostic efficiencies for all the malignant types. Normal tissue and adenoma were the most challenging histological types to classify. Conclusions:The DCNN models, especially VGG-19, achieved satisfactory accuracies on the task of differentiating thyroid tumors by histopathology. Analysis of the misdiagnosed cases revealed that normal tissue and adenoma were the most challenging histological types for the DCNN to differentiate, while all the malignant classifications achieved excellent diagnostic efficiencies. The results indicate that DCNN models may have potential for facilitating histopathologic thyroid disease diagnosis.

In the carotid space, schwannomas of the vagus nerve are usually located below the hyoid bone, whereas schwannomas of the sympathetic nerve more commonly arise from the suprahyoid compartment. Accurate preoperative diagnosis and the intracapsular enucleation surgical approach decreased the incidence of postoperative morbidity. © 2016 Wiley Periodicals, Head Neck 39: 42-47, 2017.