This service exclusively searches for literature that cites resources. Please be aware that the total number of searchable documents is limited to those containing RRIDs and does not include all open-access literature.
Voice changes may be the earliest signs in laryngeal cancer. We investigated whether automated voice signal analysis can be used to distinguish patients with laryngeal cancer from healthy subjects. We extracted features using the software package for speech analysis in phonetics (PRAAT) and calculated the Mel-frequency cepstral coefficients (MFCCs) from voice samples of a vowel sound of /a:/. The proposed method was tested with six algorithms: support vector machine (SVM), extreme gradient boosting (XGBoost), light gradient boosted machine (LGBM), artificial neural network (ANN), one-dimensional convolutional neural network (1D-CNN) and two-dimensional convolutional neural network (2D-CNN). Their performances were evaluated in terms of accuracy, sensitivity, and specificity. The result was compared with human performance. A total of four volunteers, two of whom were trained laryngologists, rated the same files. The 1D-CNN showed the highest accuracy of 85% and sensitivity and sensitivity and specificity levels of 78% and 93%. The two laryngologists achieved accuracy of 69.9% but sensitivity levels of 44%. Automated analysis of voice signals could differentiate subjects with laryngeal cancer from those of healthy subjects with higher diagnostic properties than those performed by the four volunteers.
The objective of this study was to evaluate the clinical outcome of patients with acinic cell carcinomas of the parotid gland after elective neck dissection (END). A retrospective chart review was performed including 66 patients with acinic cell carcinoma of the parotid gland. Clinical parameters were retrieved and statistically analyzed regarding disease-free survival (DFS) and disease-specific survival (DSS). An END was done in 27 (40.9%) patients, and occult metastases were detected in 4 (14.8%) patients of whom three were low-grade carcinoma. Positive neck nodes were associated with significantly worse DSS (p = 0.05). Intermediate and high-grade carcinoma (HR 8.62; 95% confidence interval (CI): 1.69-44.01; p = 0.010), perineural invasion (HR 19.6; 95%CI: 0.01-0.37; p = 0.003) and lymphovascular invasion (HR 10.2; 95%CI: 0.02-0.59; p = 0.011) were worse prognostic factors for DFS. An END should be considered in patients with acinic cell carcinoma of the parotid gland due to (i) a notable rate of occult neck metastases in low-grade tumors and (ii) the worse DSS of patients with positive neck nodes.
Welcome to the FDI Lab - SciCrunch.org Resources search. From here you can search through a compilation of resources used by FDI Lab - SciCrunch.org and see how data is organized within our community.
You are currently on the Community Resources tab looking through categories and sources that FDI Lab - SciCrunch.org has compiled. You can navigate through those categories from here or change to a different tab to execute your search through. Each tab gives a different perspective on data.
If you have an account on FDI Lab - SciCrunch.org then you can log in from here to get additional features in FDI Lab - SciCrunch.org such as Collections, Saved Searches, and managing Resources.
Here is the search term that is being executed, you can type in anything you want to search for. Some tips to help searching:
You can save any searches you perform for quick access to later from here.
We recognized your search term and included synonyms and inferred terms along side your term to help get the data you are looking for.
If you are logged into FDI Lab - SciCrunch.org you can add data records to your collections to create custom spreadsheets across multiple sources of data.
Here are the facets that you can filter your papers by.
From here we'll present any options for the literature, such as exporting your current results.
If you have any further questions please check out our FAQs Page to ask questions and see our tutorials. Click this button to view this tutorial again.
Year:
Count: