Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

OrthoAI v2: From Single-Agent Segmentation to Dual-Agent Treatment Planning for Clear Aligners

Lansiaux Edouard, Leman Margaux

Abstract

We present OrthoAI v2, the second iteration of our open-source pipeline for AI-assisted orthodontic treatment planning with clear aligners, substantially extending the single-agent framework previously introduced. The first version established a proof-of-concept based on Dynamic Graph Convolutional Neural Networks (\dgcnn{}) for tooth segmentation but was limited to per-tooth centroid extraction, lacked landmark-level precision, and produced a scalar quality score without staging simulation. \vtwo{} addresses all three limitations through three principal contributions: (i)~a second agent adopting the Conditioned Heatmap Regression Methodology (\charm{})~\cite{rodriguez2025charm} for direct, segmentation-free dental landmark detection, fused with Agent~1 via a confidence-weighted orchestrator in three modes (parallel, sequential, single-agent); (ii)~a composite six-category biomechanical scoring model (biomechanics $\times$ 0.30 + staging $\times$ 0.20 + attachments $\times$ 0.15 + IPR $\times$ 0.10 + occlusion $\times$ 0.10 + predictability $\times$ 0.15) replacing the binary pass/fail check of v1; (iii)~a multi-frame treatment simulator generating $F = A \times r$ temporally coherent 6-DoF tooth trajectories via SLERP interpolation and evidence-based staging rules, enabling ClinCheck 4D visualisation. On a synthetic benchmark of 200 crowding scenarios, the parallel ensemble of OrthoAI v2 reaches a planning quality score of $92.8 \pm 4.1$ vs.\ $76.4 \pm 8.3$ for OrthoAI v1, a $+21\%$ relative gain, while maintaining full CPU deployability ($4.2 \pm 0.8$~s).

OrthoAI v2: From Single-Agent Segmentation to Dual-Agent Treatment Planning for Clear Aligners

Abstract

We present OrthoAI v2, the second iteration of our open-source pipeline for AI-assisted orthodontic treatment planning with clear aligners, substantially extending the single-agent framework previously introduced. The first version established a proof-of-concept based on Dynamic Graph Convolutional Neural Networks (\dgcnn{}) for tooth segmentation but was limited to per-tooth centroid extraction, lacked landmark-level precision, and produced a scalar quality score without staging simulation. \vtwo{} addresses all three limitations through three principal contributions: (i)~a second agent adopting the Conditioned Heatmap Regression Methodology (\charm{})~\cite{rodriguez2025charm} for direct, segmentation-free dental landmark detection, fused with Agent~1 via a confidence-weighted orchestrator in three modes (parallel, sequential, single-agent); (ii)~a composite six-category biomechanical scoring model (biomechanics 0.30 + staging 0.20 + attachments 0.15 + IPR 0.10 + occlusion 0.10 + predictability 0.15) replacing the binary pass/fail check of v1; (iii)~a multi-frame treatment simulator generating temporally coherent 6-DoF tooth trajectories via SLERP interpolation and evidence-based staging rules, enabling ClinCheck 4D visualisation. On a synthetic benchmark of 200 crowding scenarios, the parallel ensemble of OrthoAI v2 reaches a planning quality score of vs.\ for OrthoAI v1, a relative gain, while maintaining full CPU deployability (~s).
Paper Structure (31 sections, 10 equations, 2 figures, 4 tables)

This paper contains 31 sections, 10 equations, 2 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Motivating Prior Work: OrthoAI v1
  3. Contributions of OrthoAI v2
  4. Related Work
  5. Tooth Segmentation on 3D Dental Models
  6. Dental Landmark Detection
  7. AI for Orthodontic Treatment Planning
  8. OrthoAI v2 Architecture
  9. Agent 1: DGCNN Segmentation Agent (inherited from v1)
  10. Agent 2: CHaRM Landmark Detection Agent (new in v2)
  11. Orchestrator (new in v2)
  12. Composite Biomechanical Scoring Engine
  13. From Scalar to Composite: The v1 Limitation
  14. Six-Category Scoring Model
  15. Invisalign Biomechanical Principles
  16. ...and 16 more sections

Figures (2)

  • Figure 1: Architecture comparison: OrthoAI v1 (left column) vs. OrthoAI v2 (full right pipeline). Grey components are inherited; blue components (new in v2) are the orchestrator, composite scorer, and frame generator.
  • Figure 2: Representative treatment frames for a Class I crowding case (28 aligners, 84 frames). OrthoAI v1 produced only the "Frame $F$" snapshot; OrthoAI v2 generates the full trajectory.