Disruptive Technologies for Learning and Further Investigation of the Potential Toxicity Produced by Titanium in the Human Body during the COVID-19 Pandemic Period

Titanium is considered to be a biocompatible material and is used to a great extent in the pharmaceutical and oral implantology fields. While initially, specialists considered that its use does not cause adverse effects on the human body, as time has gone by, it has become clear that its use can lead to the development of certain diseases. The objective of this study was to identify the way in which digital technologies have the capacity to facilitate information regarding the potential long-term harm caused by titanium device toxicity during the COVID-19 pandemic. In this study, a regression model was developed to identify how a series of independent variables have the ability to influence the dependent variable (respondents' perceptions of how new web technologies have the ability to help future physicians to facilitate information absorption with regard to potential titanium toxicity). The results illustrated that new technologies have the potential to support both the learning process on this topic and the innovation activity by discovering new solutions that will gradually lead to the reduction of the side effects of titanium used in the pharmaceutical and oral implantology fields.

A smart home dental care system: integration of deep learning, image sensors, and mobile controller

In this study, a home dental care system consisting of an oral image acquisition device and deep learning models for maxillary and mandibular teeth images is proposed. The presented method not only classifies tooth diseases, but also determines whether a professional dental treatment (NPDT) is required. Additionally, a specially designed oral image acquisition device was developed to perform image acquisition of maxillary and mandibular teeth. Two evaluation metrics, namely, tooth disease and NPDT classifications, were examined using 610 compounded and 5251 tooth images annotated by an experienced dentist with a Doctor of Dental Surgery and another dentist with a Doctor of Dental Medicine. In the tooth disease and NPDT classifications, the proposed system showed accuracies greater than 96% and 89%, respectively. Based on these results, we believe that the proposed system will allow users to effectively manage their dental health by detecting tooth diseases by providing information on the need for dental treatment.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s12652-021-03366-8.