TY - JOUR
T1 - Applying machine learning to assess the morphology of sculpted teeth
AU - Fan, Fang Yu
AU - Lin, Wei Chun
AU - Huang, Huei Yu
AU - Shen, Yung Kang
AU - Chang, Yung Chun
AU - Li, Heng Yu
AU - Ruslin, Muhammad
AU - Lee, Sheng Yang
N1 - Publisher Copyright:
© 2023 Association for Dental Sciences of the Republic of China
PY - 2024/1
Y1 - 2024/1
N2 - Background/purpose: Producing tooth crowns through dental technology is a basic function of dentistry. The morphology of tooth crowns is the most important parameter for evaluating its acceptability. The procedures were divided into four steps: tooth collection, scanning skills, use of mathematical methods and software, and machine learning calculation. Materials and methods: Dental plaster rods were prepared. The effective data collected were to classify 121 teeth (15th tooth position), 342 teeth (16th tooth position), 69 teeth (21st tooth position), and 89 teeth (43rd tooth position), for a total of 621 teeth. The procedures are divided into four steps: tooth collection, scanning skills, use of mathematical methods and software, and machine learning calculation. Results: The area under the curve (AUC) value was 0, 0.5, and 0.72 in this study. The precision rate and recall rate of micro-averaging/macro-averaging were 0.75/0.73 and 0.75/0.72. If we took a newly carved tooth picture into the program, the current effectiveness of machine learning was about 70%–75% to evaluate the quality of tooth morphology. Through the calculation and analysis of the two different concepts of micro-average/macro-average and AUC, similar values could be obtained. Conclusion: This study established a set of procedures that can judge the quality of hand-carved plaster sticks and teeth, and the accuracy rate is about 70%–75%. It is expected that this process can be used to assist dental technicians in judging the pros and cons of hand-carved plaster sticks and teeth, so as to help dental technicians to learn the tooth morphology more effectively.
AB - Background/purpose: Producing tooth crowns through dental technology is a basic function of dentistry. The morphology of tooth crowns is the most important parameter for evaluating its acceptability. The procedures were divided into four steps: tooth collection, scanning skills, use of mathematical methods and software, and machine learning calculation. Materials and methods: Dental plaster rods were prepared. The effective data collected were to classify 121 teeth (15th tooth position), 342 teeth (16th tooth position), 69 teeth (21st tooth position), and 89 teeth (43rd tooth position), for a total of 621 teeth. The procedures are divided into four steps: tooth collection, scanning skills, use of mathematical methods and software, and machine learning calculation. Results: The area under the curve (AUC) value was 0, 0.5, and 0.72 in this study. The precision rate and recall rate of micro-averaging/macro-averaging were 0.75/0.73 and 0.75/0.72. If we took a newly carved tooth picture into the program, the current effectiveness of machine learning was about 70%–75% to evaluate the quality of tooth morphology. Through the calculation and analysis of the two different concepts of micro-average/macro-average and AUC, similar values could be obtained. Conclusion: This study established a set of procedures that can judge the quality of hand-carved plaster sticks and teeth, and the accuracy rate is about 70%–75%. It is expected that this process can be used to assist dental technicians in judging the pros and cons of hand-carved plaster sticks and teeth, so as to help dental technicians to learn the tooth morphology more effectively.
KW - Artificial intelligence
KW - Digital dental technology
KW - Machine learning
KW - Restoration
KW - Tooth morphology
UR - http://www.scopus.com/inward/record.url?scp=85173380706&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85173380706&partnerID=8YFLogxK
U2 - 10.1016/j.jds.2023.09.023
DO - 10.1016/j.jds.2023.09.023
M3 - Article
AN - SCOPUS:85173380706
SN - 1991-7902
VL - 19
SP - 542
EP - 549
JO - Journal of Dental Sciences
JF - Journal of Dental Sciences
IS - 1
ER -