Skip to Main Content
 

Global Search Box

 
 
 

ETD Abstract Container

Abstract Header

Assessment of malalignment factors related to the Invisalign treatment time using artificial intelligence

Lee, Sanghee
http://orcid.org/0000-0003-3597-4094
http://rave.ohiolink.edu/etdc/view?acc_num=osu1647437347808257

Abstract Details

2022, Master of Science, Ohio State University, Dentistry.
Introduction: There have been questions about the efficiency of aligner treatment. Previous studies do not support the efficiency of the clear aligner treatment, nor is what type of tooth movement significantly extends treatment time clearly reported. Deep learning technology allows assessing large quantities of categorized tooth movements in a 3-dimensional manner possible to evaluate the efficiency. Objectives: The aim of this study is to identify predictors regarding type and severity of the malocclusion affect total Invisalign treatment duration based on intraoral digital scan utilizing Artificial Intelligence (AI). We hypothesize that the type of tooth movement and the degree of malalignment can determine total Invisalign treatment time. Methods: The subject of this retrospective clinical cohort are the 116 patients treated with Invisalign appliance at the Ohio State University, graduate orthodontic clinic. The initial and final 3D digital models were collected. A deep learning method were used for automatic tooth segmentation and landmark identification. The six degrees of freedom (DOF), representing types of malalignment of each tooth, were measured. Linear regression was performed to find the contributing factor associated with treatment time. In addition, the PAR score and a composite score combining 6 DOFs were separately correlated to the treatment time. Results: Among 6 DOF, the absolute maximum tipping (p-value=0.0066) and torque (p-value=0.0303) are positively associated with the total number of trays, indicating that a degree increase in maximum absolute tipping and torque movement implies that the number of trays required increases by 3.05 and 1.73, respectively. The total number of trays and the composite score, combining 6 DOF, showed a higher correlation (correlation coefficient=0.8, p-value < 0.001) than an individual tooth movement. In addition, the correlation coefficient showed that each movement is not highly correlated. Pre-treatment upper and lower anterior segment PAR score is positively associated with the treatment time (p-value <0.001). There is evidence that the number of trays may differ between males and females (p-value=0.0015). Also, patients’ age was not significantly related to the total number of trays (p-value= 0.1685). Conclusions: Certain types of tooth movement, such as tipping and torque, showed a positive correlation with the total aligner treatment time. A combined degree of freedom seems to be a better predictor (64% of predictability) for total treatment time than individual malalignment factors in aligner treatment. Upper and lower anterior malalignment factors have a significant effect on the total treatment duration. Males tend to have extended treatment duration than females, while their tooth movements were not significantly different. AI allows massive calculation of DOF with high accuracy.
Ching-Chang Ko (Advisor)
Toru Deguchi (Committee Member)
Ai Ni (Committee Member)
Tai-Hsien Wu (Committee Member)
61 p.
Dentistry
Invisalign, Aligner, Artificial intelligence, Deep learning

Recommended Citations

Citations

  • Lee, S. (2022). Assessment of malalignment factors related to the Invisalign treatment time using artificial intelligence [Master's thesis, Ohio State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=osu1647437347808257

    APA Style (7th edition)

  • Lee, Sanghee. Assessment of malalignment factors related to the Invisalign treatment time using artificial intelligence . 2022. Ohio State University, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=osu1647437347808257.

    MLA Style (8th edition)

  • Lee, Sanghee. "Assessment of malalignment factors related to the Invisalign treatment time using artificial intelligence ." Master's thesis, Ohio State University, 2022. http://rave.ohiolink.edu/etdc/view?acc_num=osu1647437347808257

    Chicago Manual of Style (17th edition)

osu1647437347808257
119
© , all rights reserved.
This open access ETD is published by The Ohio State University and OhioLINK.