3D Geometric Tooth Alignment Planning via Deep Reinforcement Learning

2026-07-16

AI Summary

This work proposes a deep reinforcement learning–based approach for automatically generating safe and efficient three-dimensional tooth alignment paths from initial malocclusion to target dental arches. Orthodontic treatment planning is formulated as a Markov decision process, wherein a novel Transformer architecture models spatial interactions among teeth, and a dynamic action masking mechanism emulates the stepwise clinical logic of tooth movement. A two-stage curriculum learning strategy is further introduced to enhance training stability. Evaluated on a dataset comprising 10,000 clinical treatment plans, the method significantly outperforms existing baselines in both path safety and geometric efficiency, demonstrating robustness and scalability for automated orthodontic planning.

Abstract

3D geometric tooth alignment planning, which determines sequential trajectories from initial malocclusion to the final target alignment, is a cornerstone of modern digital orthodontics. This paper presents a novel deep reinforcement learning (DRL) framework to automate the generation of these alignment paths. We formulate the planning process as a Markov Decision Process (MDP) to capture its sequential decision-making nature, focusing on optimizing geometric trajectories while integrating essential spatial constraints, such as inter-dental collision avoidance and path efficiency. The proposed method leverages the Deep Deterministic Policy Gradient (DDPG) algorithm, enhanced by three key innovations: (1) a Transformer-based agent to model complex spatial interactions between teeth and manage high-dimensional state-action spaces; (2) a dynamic masking scheme that restricts movement to a sparse subset of teeth per step, better reflecting the clinical logic of sequential alignment; and (3) a two-stage curriculum learning strategy that gradually increases task difficulty to ensure training stability and efficient path discovery. We evaluate our approach on a dataset of 10K expert-designed treatment plans based on clinical data. Experimental results demonstrate that our method outperforms existing baselines in terms of path safety and geometric efficiency, providing a robust and automated solution for 3D geometric orthodontic alignment planning.

Problem

• 3D geometric tooth alignment
• orthodontic planning
• sequential trajectory generation
• malocclusion correction
• digital orthodontics

Innovation

• Deep Reinforcement Learning
• Transformer-based Agent
• Dynamic Masking
• Curriculum Learning
• 3D Tooth Alignment