Deep Learning-Based Prediction of the 3D Postorthodontic Facial Changes

Abstract

With the increase of the adult orthodontic population, there is a need for an accurate and evidence-based prediction of the posttreatment face in 3 dimensions (3D). The objectives of this study are 1) to develop a 3D postorthodontic face prediction method based on a deep learning network using the patient-specific factors and orthodontic treatment conditions and 2) to validate the accuracy and clinical usability of the proposed method. Paired sets (n = 268) of pretreatment (T1) and posttreatment (T2) cone-beam computed tomography (CBCT) of adult patients were trained with a conditional generative adversarial network to generate 3D posttreatment facial data based on the patient's gender, age, and the changes of upper (Delta U1) and lower incisor position (Delta L1) as input. The accuracy was calculated with prediction error and mean absolute distances between real T2 (T2) and predicted T2 (PT2) near 6 perioral landmark regions, as well as percentage of prediction error less than 2 mm using test sets (n = 44). For qualitative evaluation, an online survey was conducted with experienced orthodontists as panels (n = 56). Overall, PT2 indicated similar 3D changes to the T2 face, with the most apparent changes simulated in the perioral regions. The mean prediction error was 1.2 +/- 1.01 mm with 80.8% accuracy. More than 50% of the experienced orthodontists were unable to distinguish between real and predicted images. In this study, we proposed a valid 3D postorthodontic face prediction method by applying a deep learning algorithm trained with CBCT data sets.