Research of orthodontic soft tissue profile prediction based on conditional generative adversarial networks

被引：0

作者：

Gong, Beiwen ^{[1
]}

Chang, Qiao ^{[1
]}

Shi, Tianlei ^{[3
]}

Wang, Shaofeng ^{[1
]}

Wang, Yajie ^{[2
,3
]}

Zuo, Feifei ^{[3
]}

Xie, Xianju ^{[1
]}

Bai, Yuxing ^{[1
]}

机构：

[1] Capital Med Univ, Sch Stomatol, Dept Orthodont, Beijing 100070, Peoples R China

[2] Tsinghua Univ, Dept Engn Phys, Beijing 100084, Peoples R China

[3] LargeV Instrument Corp Ltd, Beijing 100192, Peoples R China

来源：

JOURNAL OF DENTISTRY | 2025年 / 154卷

关键词：

Accuracy; Orthodontic treatment; Artificial intelligence; Machine learning; Conditional generative adversarial network; ACCURACY;

D O I：

10.1016/j.jdent.2025.105570

中图分类号：

R78 [口腔科学];

学科分类号：

1003 ;

摘要：

Objective: This study constructed a new conditional generative adversarial network (CGAN) model to predict changes in lateral appearance following orthodontic treatment. Methods: Lateral cephalometric radiographs of adult patients were obtained before (T1) and after (T2) orthodontic treatment. The expanded dataset was divided into training, validation, and test sets by random sampling in a ratio of 8:1:1. The existing networks-Pix2Pix, Cycle-GAN, and CGAN-were trained to generate posttreatment outcomes. A new deep learning model, soft-P-CGAN, was proposed and incorporated a conditional vector input module, U-Net-based generator module, and PatchGAN-based discriminator module. Soft loss was designed to enhance generating soft tissue contours; a multiscale feature pyramid refined image quality. Predicted and actual post-treatment radiographs were superimposed and compared based on soft-tissue landmarks using mean radial error (MRE) and successful detection rate (SDR) within 2.0, 2.5, 3.0, and 4.0 mm. Any parameters of PT2 and T2 outcomes were compared using paired t-tests or Wilcoxon tests. Results: Soft-P-CGAN showed superior performance using quantitative image quality assessment. The average MRE was 1.08 +/- 0.75 mm with SDRs of 2.0, 2.5, 3.0, and 4.0 mm at 88.8 %, 95.1 %, 97.8 %, and 100 %, respectively. Soft tissue point A was the most accurate landmark, whereas predictions in the mandibular region were relatively inaccurate. None of the cephalometric predictions differed significantly from the actual results (P > 0.05). Conclusions: Soft-P-CGAN could predict post-treatment lateral appearance changes by learning the relationship between soft and hard tissue changes in lateral cephalograms. Most predictions were clinically acceptable, aiding clinicians in setting orthodontic treatment goals. Clinical Significance: This study explored and validated the use of image generation networks for predicting orthodontic lateral profiles and proposed new methods for enhancing their accuracy and interpretability.

引用

页数：11

共 34 条

[1]

Peck H., Peck S., A concept of facial esthetics, Angle Orthod., 40, 4, pp. 284-318, (1970)

[2]

Bishara S.E., Cummins D.M., Jakobsen J.R., The morphologic basis for the extraction decision in class II, division 1 malocclusions: a comparative study, Am. J. Orthod. Dentofacial Orthop., 107, 2, pp. 129-135, (1995)

[3]

Caplan M.J., Shivapuja P.K., The effect of premolar extractions on the soft-tissue profile in adult African American females, Angle Orthod., 67, 2, pp. 129-136, (1997)

[4]

Ricketts R.M., Planning treatment on the basis of the facial pattern and an estimate of its growth, Angle Orthod., 27, 1, pp. 14-37, (1957)

[5]

Shirvani A., Sadeghian S., Abbasi S., Prediction of lip response to orthodontic treatment using a multivariable regression model, Dent. Res. J. (Isfahan), 13, 1, pp. 38-45, (2016)

[6]

Denis K.L., Speidel T.M., Comparison of three methods of profile change prediction in the adult orthodontic patient, Am. J. Orthod., 92, 5, pp. 396-402, (1987)

[7]

Van Hemelen G., Van Genechten M., Renier L., Desmedt M., Verbruggen E., Nadjmi N., Three-dimensional virtual planning in orthognathic surgery enhances the accuracy of soft tissue prediction, J. Craniomaxillofac. Surg., 43, 6, pp. 918-925, (2015)

[8]

Holdaway R.A., A soft⁃tissue cephalometric analysis and its use in orthodontic treatment planning. PartII, Am. J. Orthod., 85, 4, pp. 279-293, (1984)

[9]

Chen S., Lou H., Guo L., Rong Q., Liu Y., Xu T.M., 3-D finite element modelling of facial soft tissue and preliminary application in orthodontics, Comput. Methods Biomech. Biomed. Engin., 15, 3, pp. 255-261, (2012)

[10]

Zhu J., Yang Y., Wong H.M., Development and accuracy of artificial intelligence-generated prediction of facial changes in orthodontic treatment: a scoping review, J. Zhejiang Univ. Sci. B, pp. 1-11, (2023)

← 1 2 3 4 →