Evaluating the Precision of Automatic Segmentation of Teeth, Gingiva and Facial Landmarks for 2D Digital Smile Design Using Real-Time Instance Segmentation Network
Digital smile design (DSD) technology, which takes pictures of patients’ faces together with anterior dentition and uses them for prosthesis design, has been recently introduced. However, the limitation of DSD is that it evaluates a patient with only one photograph taken in a still state, and the pa...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-02-01
|
Series: | Journal of Clinical Medicine |
Subjects: | |
Online Access: | https://www.mdpi.com/2077-0383/11/3/852 |
_version_ | 1797486862895415296 |
---|---|
author | Seulgi Lee Jong-Eun Kim |
author_facet | Seulgi Lee Jong-Eun Kim |
author_sort | Seulgi Lee |
collection | DOAJ |
description | Digital smile design (DSD) technology, which takes pictures of patients’ faces together with anterior dentition and uses them for prosthesis design, has been recently introduced. However, the limitation of DSD is that it evaluates a patient with only one photograph taken in a still state, and the patient’s profile cannot be observed from various viewpoints. Therefore, this study aims to segment the patient’s anterior teeth, gingiva and facial landmarks using YOLACT++. We trained YOLACT++ on the annotated data of the teeth, lips and gingiva from the Flickr-Faces-HQ (FFHQ) data. We evaluated that the model trained by 2D candid facial images for the detection and segmentation of smile characteristics. The results show the possibility of an automated smile characteristic identification system for the automatic and accurate quantitative assessment of a patient’s smile. |
first_indexed | 2024-03-09T23:39:20Z |
format | Article |
id | doaj.art-cc8447d8ddab467bac401807205fd86d |
institution | Directory Open Access Journal |
issn | 2077-0383 |
language | English |
last_indexed | 2024-03-09T23:39:20Z |
publishDate | 2022-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Journal of Clinical Medicine |
spelling | doaj.art-cc8447d8ddab467bac401807205fd86d2023-11-23T16:55:02ZengMDPI AGJournal of Clinical Medicine2077-03832022-02-0111385210.3390/jcm11030852Evaluating the Precision of Automatic Segmentation of Teeth, Gingiva and Facial Landmarks for 2D Digital Smile Design Using Real-Time Instance Segmentation NetworkSeulgi Lee0Jong-Eun Kim1Department of Mechanical Engineering, Yonsei University, Yonsei-ro 50, Seodaemun-gu, Seoul 03722, KoreaDepartment of Prosthodontics, Yonsei University College of Dentistry, Yonsei-ro 50-1, Seodaemun-gu, Seoul 03772, KoreaDigital smile design (DSD) technology, which takes pictures of patients’ faces together with anterior dentition and uses them for prosthesis design, has been recently introduced. However, the limitation of DSD is that it evaluates a patient with only one photograph taken in a still state, and the patient’s profile cannot be observed from various viewpoints. Therefore, this study aims to segment the patient’s anterior teeth, gingiva and facial landmarks using YOLACT++. We trained YOLACT++ on the annotated data of the teeth, lips and gingiva from the Flickr-Faces-HQ (FFHQ) data. We evaluated that the model trained by 2D candid facial images for the detection and segmentation of smile characteristics. The results show the possibility of an automated smile characteristic identification system for the automatic and accurate quantitative assessment of a patient’s smile.https://www.mdpi.com/2077-0383/11/3/852deep learningdigital smile designdigital dentistryYOLACT++detectionsegmentation |
spellingShingle | Seulgi Lee Jong-Eun Kim Evaluating the Precision of Automatic Segmentation of Teeth, Gingiva and Facial Landmarks for 2D Digital Smile Design Using Real-Time Instance Segmentation Network Journal of Clinical Medicine deep learning digital smile design digital dentistry YOLACT++ detection segmentation |
title | Evaluating the Precision of Automatic Segmentation of Teeth, Gingiva and Facial Landmarks for 2D Digital Smile Design Using Real-Time Instance Segmentation Network |
title_full | Evaluating the Precision of Automatic Segmentation of Teeth, Gingiva and Facial Landmarks for 2D Digital Smile Design Using Real-Time Instance Segmentation Network |
title_fullStr | Evaluating the Precision of Automatic Segmentation of Teeth, Gingiva and Facial Landmarks for 2D Digital Smile Design Using Real-Time Instance Segmentation Network |
title_full_unstemmed | Evaluating the Precision of Automatic Segmentation of Teeth, Gingiva and Facial Landmarks for 2D Digital Smile Design Using Real-Time Instance Segmentation Network |
title_short | Evaluating the Precision of Automatic Segmentation of Teeth, Gingiva and Facial Landmarks for 2D Digital Smile Design Using Real-Time Instance Segmentation Network |
title_sort | evaluating the precision of automatic segmentation of teeth gingiva and facial landmarks for 2d digital smile design using real time instance segmentation network |
topic | deep learning digital smile design digital dentistry YOLACT++ detection segmentation |
url | https://www.mdpi.com/2077-0383/11/3/852 |
work_keys_str_mv | AT seulgilee evaluatingtheprecisionofautomaticsegmentationofteethgingivaandfaciallandmarksfor2ddigitalsmiledesignusingrealtimeinstancesegmentationnetwork AT jongeunkim evaluatingtheprecisionofautomaticsegmentationofteethgingivaandfaciallandmarksfor2ddigitalsmiledesignusingrealtimeinstancesegmentationnetwork |