Uses of Different Machine Learning Algorithms for Diagnosis of Dental Caries

Author:

Talpur Sarena1ORCID,Azim Fahad2ORCID,Rashid Munaf3ORCID,Syed Sidra Abid1ORCID,Talpur Baby Alisha4ORCID,Khan Saad Jawaid1ORCID

Affiliation:

1. Department of Biomedical Engineering, Ziauddin University, Karachi, Pakistan

2. Department of Electrical Engineering, Ziauddin University, Karachi, Pakistan

3. Department of Software Engineering, Ziauddin University, Karachi, Pakistan

4. Liaquat University of Medical and Health Sciences, Jamshoro, Pakistan

Abstract

Background. Dental caries is one of the major oral health problems and is increasing rapidly among people of every age (children, men, and women). Deep learning, a field of Artificial Intelligence (AI), is a growing field nowadays and is commonly used in dentistry. AI is a reliable platform to make dental care better, smoother, and time-saving for professionals. AI helps the dentistry professionals to fulfil demands of patients and to ensure quality treatment and better oral health care. AI can also help in predicting failures of clinical cases and gives reliable solutions. In this way, it helps in reducing morbidity ratio and increasing quality treatment of dental problem in population. Objectives. The main objective of this study is to conduct a systematic review of studies concerning the association between dental caries and machine learning. The objective of this study is to design according to the PICO criteria. Materials and Methods. A systematic search for randomized trials was conducted under the guidelines of PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses). In this study, e-search was conducted from four databases including PubMed, IEEE Xplore, Science Direct, and Google Scholar, and it involved studies from year 2008 to 2022. Result. This study fetched a total of 133 articles, from which twelve are selected for this systematic review. We analyzed different types of machine learning algorithms from which deep learning is widely used with dental caries images dataset. Neural Network Backpropagation algorithm, one of the deep learning algorithms, gives a maximum accuracy of 99%. Conclusion. In this systematic review, we concluded how deep learning has been applied to the images of teeth to diagnose the detection of dental caries with its three types (proximal, occlusal, and root caries). Considering our findings, further well-designed studies are needed to demonstrate the diagnosis of further types of dental caries that are based on progression (chronic, acute, and arrested), which tells us about the severity of caries, virginity of lesion, and extent of caries. Apart from dental caries, AI in the future will emerge as supreme technology to detect other diseases of oral region combinedly and comprehensively because AI will easily analyze big datasets that contain multiple records.

Publisher

Hindawi Limited

Subject

Health Informatics,Biomedical Engineering,Surgery,Biotechnology

Reference31 articles.

Cited by 11 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Current Progress and Challenges of Using Artificial Intelligence in Clinical Dentistry—A Narrative Review;Journal of Clinical Medicine;2023-11-28

2. Artificial Intelligence Quality Standards in Healthcare: A Rapid Umbrella Review (Preprint);2023-11-19

3. Deep learning architectures in dental diagnostics: a systematic comparison of techniques for accurate prediction of dental disease through x-ray imaging;International Journal of Intelligent Computing and Cybernetics;2023-10-30

4. Classification of Dental Caries Level Using Conjugate Gradient Backpropagation Models;2023 International Seminar on Application for Technology of Information and Communication (iSemantic);2023-09-16

5. Detection of Mid Mesial Canal in Dental CBCT Images Using Combined YOLO and 2D U-Net Model;2023 International Conference on Network, Multimedia and Information Technology (NMITCON);2023-09-01

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3