Please use this identifier to cite or link to this item: https://dspace.uzhnu.edu.ua/jspui/handle/lib/62396
Title: Artificial intelligence in endodontics: relevant trends and practical perspectives
Authors: Myroslav Goncharuk-Khomyn
Igor Noenko
Alessandro Leite Cavalcanti
Özkan Adigüzel
Artem Dubnov
Keywords: artificial intelligence, endodontics, review, image processing, computer-assisted
Issue Date: 5-Mar-2023
Publisher: Ukrainian Dental Journal
Citation: Goncharuk-Khomyn, M., Noenko, I., Leite Cavalcanti, A., Adigüzel, Özkan, & Dubnov, A. (2023). Artificial intelligence in endodontics: relevant trends and practical perspectives. Ukrainian Dental Journal, 2(1), 96–101. https://doi.org/10.56569/UDJ.2.1.2023.96-101
Series/Report no.: Vol. 2 No. 1 (2023): Ukrainian Dental Journal;
Abstract: Abstract Background. Overall pool of studies regarding artificial intelligence (AI) implementation in dentistry is increasing every year, while possibilities for using AI methods within everyday endodontic practice is still quite confined and not always enough affirmed. Objective. To systematize and depict principal data regarding use of virtual artificial intelligence for various endodontic-related clinical purposes. Materials and Methods. Targeted literature search was provided within National Center for Biotechnology Information databases using pre-specified Mesh-terms algorithm. The following information was extracted from each publication during content analysis: diagnostic and treatment planning aspects of endodontic practice for which AI methods could be applied; accuracy levels registered for AI models used for different endodontic-related purposes; limitations of using AI within endodontic practice. Results. AI features could be used in endodontic practice for the following reasons: analysis of root canal morphology, identification of root fractures, verification of periapical lesions, estimation of root canal working length, root canal treatment planning, prediction of pain development during post-treatment period, predication of endodontic interventions success. The most prevalently used artificial intelligence methods for different endodontic diagnostic and treatment planning objectives were the following: convolutional neural network, artificial neurons network, case-based reasoning, deep learning, machine learning, neuro-fuzzy inference system, probabilistic neural network. Conclusion. Main advantage of using AI models in endodontic practice associated with improvement of diagnostic accuracy within reduced amount of time needed for X-ray images and clinical data analysis. AI application for apical foramen detection and working length determination demonstrates the highest level of accuracy compared to AI performance for other clinically related objectives in endodontics.
Type: Text
Publication type: Стаття
URI: https://dspace.uzhnu.edu.ua/jspui/handle/lib/62396
Appears in Collections:Наукові публікації кафедри терапевтичної стоматології

Files in This Item:
File Description SizeFormat 
UDJ_2_96-101-Goncharuk.pdf215.1 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.