Abstract

Orthodontic treatment requires calculating the distance of specific points, or landmarks, of each tooth in a 3-dimensional (3D) arch model data. Orthodontic experts use an application to identify each tooth and point out the specific points in each tooth. Therefore, the dentition condition of the patient can be determined. This study proposed a new method to identify each tooth using deep learning combined with weighted mesh points. The deep learning method is used for the teeth segmentation process. The weighted mesh points method is used for determining the landmarks of each tooth automatically. The weighted mesh points method exploits the labelled mesh to calculate the suitable point to be a landmark. Deep learning is used to segment each tooth to set the type of tooth. Then, the weighted mesh of each tooth is calculated to set the landmarks. The algorithm successfully recognizes the specific points for each tooth with 2.225 in Root Mean Squared Error (RMSE).

Original languageEnglish
Title of host publication5th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages336-341
Number of pages6
ISBN (Electronic)9781665456456
DOIs
Publication statusPublished - 2023
Event5th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2023 - Virtual, Online, Indonesia
Duration: 20 Feb 202323 Feb 2023

Publication series

Name5th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2023

Conference

Conference5th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2023
Country/TerritoryIndonesia
CityVirtual, Online
Period20/02/2323/02/23

Keywords

  • Automation
  • Deep learning
  • Tooth Landmark
  • Weighted

Fingerprint

Dive into the research topics of 'Automatic 3D Digital Dental Landmark Based on Point Transformation Weight'. Together they form a unique fingerprint.

Cite this