NICE: Neural Implicit Craniofacial Model for Orthognathic Surgery Prediction

2025-12-05

AI Summary

Predicting facial soft-tissue deformation following orthognathic surgery is highly challenging due to strong nonlinear coupling between bone and soft tissue; existing methods suffer from limitations in accuracy, computational efficiency, or anatomical fidelity. This paper proposes a neural implicit craniofacial modeling framework: it constructs region-specific implicit signed distance functions (SDFs) and deformation decoders, incorporates a shared surgical latent code, and embeds anatomical priors to constrain point-wise displacement fields in critical regions (e.g., lips and chin). By integrating implicit neural representations with biomechanically informed constraints, the framework enables end-to-end differentiable training. Evaluated on multicenter clinical data, it significantly outperforms state-of-the-art methods—reducing prediction error by 23.6%—while strictly preserving anatomical consistency across key structures. The approach demonstrates strong potential for clinical deployment.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Neural Architectures and Foundation Models
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Orthognathic surgery is a crucial intervention for correcting dentofacial skeletal deformities to enhance occlusal functionality and facial aesthetics. Accurate postoperative facial appearance prediction remains challenging due to the complex nonlinear interactions between skeletal movements and facial soft tissue. Existing biomechanical, parametric models and deep-learning approaches either lack computational efficiency or fail to fully capture these intricate interactions. To address these limitations, we propose Neural Implicit Craniofacial Model (NICE) which employs implicit neural representations for accurate anatomical reconstruction and surgical outcome prediction. NICE comprises a shape module, which employs region-specific implicit Signed Distance Function (SDF) decoders to reconstruct the facial surface, maxilla, and mandible, and a surgery module, which employs region-specific deformation decoders. These deformation decoders are driven by a shared surgical latent code to effectively model the complex, nonlinear biomechanical response of the facial surface to skeletal movements, incorporating anatomical prior knowledge. The deformation decoders output point-wise displacement fields, enabling precise modeling of surgical outcomes. Extensive experiments demonstrate that NICE outperforms current state-of-the-art methods, notably improving prediction accuracy in critical facial regions such as lips and chin, while robustly preserving anatomical integrity. This work provides a clinically viable tool for enhanced surgical planning and patient consultation in orthognathic procedures.

Problem

• Predicting facial changes after orthognathic surgery accurately.
• Modeling complex soft tissue response to skeletal movements.
• Improving surgical planning with efficient neural representations.

Innovation

• Uses implicit neural representations for anatomical reconstruction
• Employs region-specific SDF decoders for facial surface modeling
• Models surgical outcomes with shared latent code deformation decoders