文章基本信息

标题：An overview of deep learning in the field of dentistry
本地全文：下载
作者：Hwang, Jae-Joon ; Jung, Yun-Hoa ; Cho, Bong-Hae 等
期刊名称：Imaging Science in Dentistry
印刷版ISSN：2233-7822
出版年度：2019
卷号：49
期号：1
页码：1-7
DOI：10.5624/isd.2019.49.1.1
出版社：Korean Academy of Oral and Maxillofacial Radiology
摘要：This paper examines periodontal disease as well as other oral health indicators of the Jomon population in order to understand variations in their lifestyle and their response to dietary diversity. The oral conditions of three Jomon populations in Late Jomon period are evaluated using two periodontal indicators, namely the distance measured between the cement–enamel junction to the alveolar crest (CEJ-AC distance), and the degree of inflammation of the alveolar septum. The incidence of affected individuals with moderate to severe periodontal disease ranges from 31.8% to 38.6% based on the evaluation of the CEJ-AC distance, and from 38.4% to 66.0 % based on the interdental septum morphology, respectively. Comparisons of the inter-site difference (which includes that between coastal and inland populations) and sex differences were conducted with a combined dataset of the periodontal and oral health indicators (caries, antemortem tooth loss, wear, and chipping). The results indicated that inter-site and inter-sex differences are smaller in the cases with periodontal disease than in those with caries and antemortem tooth loss. In particular, almost no difference was found in the periodontal conditions between the coastal and inland sites. Although previous studies have indicated the effect of occlusal wear on the CEJ-AC distance, the results of the multivariate analysis show that the inflammation of the interdental septum is more relevant than the occlusal wear. In addition, the sex difference was significant compared to the inter-site difference, and each sex difference within a site showed a common trend. Detected inter-site and sex differences are discussed and assumed to be associated with bioarchaeological background.
关键词：Artificial intelligence; Deep Learning; Dentistry; Radiology