A Quasiconformal-Based Geometric Model for Craniofacial Analysis and Its Application

• Published in: Axioms 2023-04, Vol.12 (4), p.393
• Main Authors: Wong, Ming-Hei, Li, Meixi, Tam, King-Man, Yuen, Hoi-Man, Au, Chun-Ting, Chan, Kate Ching-Ching, Li, Albert Martin, Lui, Lok-Ming
• Format: Article
• Language: English
• Subjects: 3D facial model reconstruction; Accuracy; Airway management; Angles (geometry); Artificial intelligence; Bones; Classification; Computation; Curvature; Geometry; image analysis; Image reconstruction; machine learning; Methods; Model accuracy; Morphometrics (Biology); obstructive sleep apnoea; Optimization; Physiological aspects; preliminary disease diagnosis; quasiconformal geometry; Respiration; Skull; Sleep disorders; Three dimensional models
• ISSN: 2075-1680; 2075-1680
• DOI: 10.3390/axioms12040393

We address the problem of craniofacial morphometric analysis using geometric models, which has important clinical applications for the diagnosis of syndromes associated with craniofacial dysmorphologies. In this work, a novel geometric model is proposed to analyze craniofacial structures based on local curvature information and Teichmüller mappings. A key feature of the proposed model is that its pipeline starts with few two-dimensional images of the human face captured at different angles, from which the three-dimensional craniofacial structure can be reconstructed. The 3D surface reconstruction from 2D images is based on a modified 3D morphable model (3DMM) framework. Geometric quantities around important feature landmarks according to different clinical applications can then be computed on each three-dimensional craniofacial structure. Together with the Teichmüller mapping, the landmark-based Teichmüller curvature distances (LTCDs) for every classes can be computed, which are further used for three-class classification. A composite score model is used and the parameter optimization is carried out to further improve the classification accuracy. Our proposed model is applied to study the craniofacial structures of children with and without the obstructive sleep apnoea (OSA). Sixty subjects, with accessible multi-angle photography and polysomnography (PSG) data, are divided into three classes based on the severity of OSA. Using our proposed model, our proposed model achieves a high 90% accuracy, which outperforms other existing models. This demonstrates the effectiveness of our proposed geometric model for craniofacial analysis.