JOURNAL ARTICLE

Reliability and time-based efficiency of artificial intelligence-based automatic digital model analysis system.

  • Published In: European Journal of Orthodontics, 2023, v. 45, n. 6. P. 712 1 of 3

  • Database: Dentistry & Oral Sciences Source 2 of 3

  • Authored By: Yu, Jae-Hun; Kim, Ji-Hoi; Liu, Jing; Mangal, Utkarsh; Ahn, Hee-Kap; Cha, Jung-Yul 3 of 3

Abstract

This article focuses on comparing the reliability, reproducibility, and time efficiency of automatic digital (AD) versus manual digital (MD) orthodontic model analyses using intraoral scan models. The study found that the AD method, which employs deep graph convolutional neural networks for automatic tooth segmentation and rule-based measurements, demonstrated higher reproducibility and significantly reduced analysis time (0.56 minutes vs. 8.62 minutes) compared to the MD method. However, significant differences in measurement values—particularly tooth size and arch perimeter—were observed between the two methods, indicating they are not interchangeable. The authors recommend using AD analysis as a rapid, computer-aided diagnostic tool to assist orthodontic decision-making rather than as a full replacement for manual analysis.

Additional Information

  • Source:European Journal of Orthodontics. 2023/12, Vol. 45, Issue 6, p712
  • Document Type:Article
  • Subject Area:Mathematics
  • Publication Date:2023
  • ISSN:0141-5387
  • DOI:10.1093/ejo/cjad032
  • Accession Number:173959408
  • Copyright Statement:Copyright of European Journal of Orthodontics is the property of Oxford University Press / USA and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Looking to go deeper into this topic? Look for more articles on EBSCOhost.