Time-series X-ray image prediction of dental skeleton treatment progress via neural networks.
Authors
Affiliations (5)
Affiliations (5)
- Department of Mechanical Engineering, Yonsei University, Seoul, 03722, Republic of Korea.
- Department of Orthodontics, Institute of Craniofacial Deformity, College of Dentistry, Yonsei University, Seoul, 03722, Republic of Korea.
- Department of Mechanical Engineering, Yonsei University, Seoul, 03722, Republic of Korea; Center for Precision Medicine Platform Based on Smart Hemo-Dynamic Index (SHDI), Seoul, 03722, Republic of Korea.
- Department of Orthodontics, Institute of Craniofacial Deformity, College of Dentistry, Yonsei University, Seoul, 03722, Republic of Korea. Electronic address: [email protected].
- Department of Mechanical Engineering, Yonsei University, Seoul, 03722, Republic of Korea; Center for Precision Medicine Platform Based on Smart Hemo-Dynamic Index (SHDI), Seoul, 03722, Republic of Korea. Electronic address: [email protected].
Abstract
Accurate prediction of skeletal changes during orthodontic treatment in growing patients remains challenging due to significant individual variability in craniofacial growth and treatment responses. Conventional methods, such as support vector regression and multilayer perceptrons, require multiple sequential radiographs to achieve acceptable accuracy. However, they are limited by increased radiation exposure, susceptibility to landmark identification errors, and the lack of visually interpretable predictions. To overcome these limitations, this study explored advanced generative approaches, including denoising diffusion probabilistic models (DDPMs), latent diffusion models (LDMs), and ControlNet, to predict future cephalometric radiographs using minimal input data. We evaluated three diffusion-based models-a DDPM utilizing three sequential cephalometric images (3-input DDPM), a single-image DDPM (1-input DDPM), and a single-image LDM-and a vision-based generative model, ControlNet, conditioned on patient-specific attributes such as age, sex, and orthodontic treatment type. Quantitative evaluations demonstrated that the 3-input DDPM achieved the highest numerical accuracy, whereas the single-image LDM delivered comparable predictive performance with significantly reduced clinical requirements. ControlNet also exhibited competitive accuracy, highlighting its potential effectiveness in clinical scenarios. These findings indicate that the single-image LDM and ControlNet offer practical solutions for personalized orthodontic treatment planning, reducing patient visits and radiation exposure while maintaining robust predictive accuracy.