A Self-Supervised Deep Framework for Reference Bony Shape Estimation in Orthognathic Surgical Planning

Patient-specific reference model estimation for orthognathic surgical planning

PURPOSE

Accurate estimation of reference bony shape models is fundamental for orthognathic surgical planning. Existing methods to derive this model are of two types: one determines the reference model by estimating the deformation field to correct the patient's deformed jaw, often introducing distortions in the predicted reference model; The other derives the reference model using a linear combination of their landmarks/vertices but overlooks the intricate nonlinear relationship between the subjects, compromising the model's precision and quality.

METHODS

We have created a self-supervised learning framework to estimate the reference model. The core of this framework is a deep query network, which estimates the similarity scores between the patient's midface and those of the normal subjects in a high-dimensional space. Subsequently, it aggregates high-dimensional features of these subjects and projects these features back to 3D structures, ultimately achieving a patient-specific reference model.

RESULTS

Our approach was trained using a dataset of 51 normal subjects and tested on 30 patient subjects to estimate their reference models. Performance assessment against the actual post-operative bone revealed a mean Chamfer distance error of 2.25 mm and an average surface distance error of 2.30 mm across the patient subjects.

CONCLUSION

Our proposed method emphasizes the correlation between the patients and the normal subjects in a high-dimensional space, facilitating the generation of the patient-specific reference model. Both qualitative and quantitative results demonstrate its superiority over current state-of-the-art methods in reference model estimation.

A Proof of Concept: Optimized Jawbone-Reduction Model for Mandibular Fracture Surgery

Previous research on computer-assisted jawbone reduction for mandibular fracture surgery has only focused on the relationship between fractured sections disregarding proper dental occlusion with the maxilla. To overcome malocclusion caused by overlooking dental articulation, this study aims to provide a model for jawbone reduction based on dental occlusion. After dental landmarks and fracture sectional features are extracted, the maxilla and two mandible segments are aligned first using the extracted dental landmarks. A swarm-based optimization is subsequently performed by simultaneously observing the fracture section fitting and the dental occlusion condition. The proposed method was evaluated using jawbone data of 12 subjects with simulated and real mandibular fractures. Results showed that the optimized model achieved both accurate jawbone reduction and desired dental occlusion, which may not be possible by existing methods.