First active hydrothermal vents on an ultraslow-spreading center: Southwest Email alerting services articles cite this article to receive free e-mail alerts when new www.gsapubs.org/cgi/alerts click Subscribe to subscribe to Geology www.gsapubs.org/subscriptions/ click Permission request to contact GSA http://www.geosociety.org/pubs/copyrt.htm#gsa click official positions of the Society. citizenship, gender, religion, or political viewpoint. Opinions presented in this publication do not reflect presentation of diverse opinions and positions by scientists worldwide, regardless of their race, includes a reference to the article's full citation. GSA provides this and other forums for the the abstracts only of their articles on their own or their organization's Web site providing the posting to further education and science. This file may not be posted to any Web site, but authors may post works and to make unlimited copies of items in GSA's journals for noncommercial use in classrooms requests to GSA, to use a single figure, a single table, and/or a brief paragraph of text in subsequent their employment. Individual scientists are hereby granted permission, without fees or further

Characterization of parotid tumors is important for treatment planning and prognosis, and parotid tumor discrimination has recently been developed at the molecular level. The aim of the present study was to establish a machine learning (ML) predictive model based on multiparametric traditional multislice CT (MSCT) radiomic and clinical data analysis to improve the accuracy of differentiation among pleomorphic adenoma (PA), Warthin tumor (WT) and parotid carcinoma (PCa). A total of 345 patients (200 with WT, 91 with PA and 54 with PCa) with pathologically confirmed parotid tumors were retrospectively enrolled from five independent institutions between January 2010 and May 2019. A total of 273 patients recruited from institutions 1, 2 and 3 were randomly assigned to the training model; the independent validation set consisted of 72 patients treated at institutions 1, 4 and 5. Data were investigated using a linear discriminant analysis-based ML classifier. Feature selection and dimension reduction were conducted using reproducibility testing and a wrapper method. The diagnostic accuracy of the predictive model was compared with histopathological findings as reference results. This classifier achieved a satisfactory performance for the discrimination of PA, WT and PCa, with a total accuracy of 82.1% in the training cohort and 80.5% in the validation cohort. In conclusion, ML-based multiparametric traditional MSCT radiomics can improve the accuracy of differentiation among PA, WT and PCa. The findings of the present study should be validated by multicenter prospective studies using completely independent external data.

No abstract