A Quasiconformal-Based Geometric Model for Craniofacial Analysis and Its Application
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 lo...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Axioms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1680/12/4/393 |
| _version_ | 1797606460338733056 |
|---|---|
| author | Ming-Hei Wong Meixi Li King-Man Tam Hoi-Man Yuen Chun-Ting Au Kate Ching-Ching Chan Albert Martin Li Lok-Ming Lui |
| author_facet | Ming-Hei Wong Meixi Li King-Man Tam Hoi-Man Yuen Chun-Ting Au Kate Ching-Ching Chan Albert Martin Li Lok-Ming Lui |
| author_sort | Ming-Hei Wong |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-11T05:15:30Z |
| format | Article |
| id | doaj.art-e935e655eb134199a72e1fd8cdd67fc3 |
| institution | Directory Open Access Journal |
| issn | 2075-1680 |
| language | English |
| last_indexed | 2024-03-11T05:15:30Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Axioms |
| spelling | doaj.art-e935e655eb134199a72e1fd8cdd67fc32023-11-17T18:19:44ZengMDPI AGAxioms2075-16802023-04-0112439310.3390/axioms12040393A Quasiconformal-Based Geometric Model for Craniofacial Analysis and Its ApplicationMing-Hei Wong0Meixi Li1King-Man Tam2Hoi-Man Yuen3Chun-Ting Au4Kate Ching-Ching Chan5Albert Martin Li6Lok-Ming Lui7Department of Mathematics, The Chinese University of Hong Kong, Hong Kong, ChinaDepartment of Mathematics, The Chinese University of Hong Kong, Hong Kong, ChinaDepartment of Mathematics, The Chinese University of Hong Kong, Hong Kong, ChinaDepartment of Paediatrics, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong, ChinaDepartment of Paediatrics, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong, ChinaDepartment of Paediatrics, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong, ChinaDepartment of Paediatrics, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong, ChinaDepartment of Mathematics, The Chinese University of Hong Kong, Hong Kong, ChinaWe 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.https://www.mdpi.com/2075-1680/12/4/393obstructive sleep apnoeaquasiconformal geometrymachine learningpreliminary disease diagnosisimage analysis3D facial model reconstruction |
| spellingShingle | Ming-Hei Wong Meixi Li King-Man Tam Hoi-Man Yuen Chun-Ting Au Kate Ching-Ching Chan Albert Martin Li Lok-Ming Lui A Quasiconformal-Based Geometric Model for Craniofacial Analysis and Its Application Axioms obstructive sleep apnoea quasiconformal geometry machine learning preliminary disease diagnosis image analysis 3D facial model reconstruction |
| title | A Quasiconformal-Based Geometric Model for Craniofacial Analysis and Its Application |
| title_full | A Quasiconformal-Based Geometric Model for Craniofacial Analysis and Its Application |
| title_fullStr | A Quasiconformal-Based Geometric Model for Craniofacial Analysis and Its Application |
| title_full_unstemmed | A Quasiconformal-Based Geometric Model for Craniofacial Analysis and Its Application |
| title_short | A Quasiconformal-Based Geometric Model for Craniofacial Analysis and Its Application |
| title_sort | quasiconformal based geometric model for craniofacial analysis and its application |
| topic | obstructive sleep apnoea quasiconformal geometry machine learning preliminary disease diagnosis image analysis 3D facial model reconstruction |
| url | https://www.mdpi.com/2075-1680/12/4/393 |
| work_keys_str_mv | AT mingheiwong aquasiconformalbasedgeometricmodelforcraniofacialanalysisanditsapplication AT meixili aquasiconformalbasedgeometricmodelforcraniofacialanalysisanditsapplication AT kingmantam aquasiconformalbasedgeometricmodelforcraniofacialanalysisanditsapplication AT hoimanyuen aquasiconformalbasedgeometricmodelforcraniofacialanalysisanditsapplication AT chuntingau aquasiconformalbasedgeometricmodelforcraniofacialanalysisanditsapplication AT katechingchingchan aquasiconformalbasedgeometricmodelforcraniofacialanalysisanditsapplication AT albertmartinli aquasiconformalbasedgeometricmodelforcraniofacialanalysisanditsapplication AT lokminglui aquasiconformalbasedgeometricmodelforcraniofacialanalysisanditsapplication AT mingheiwong quasiconformalbasedgeometricmodelforcraniofacialanalysisanditsapplication AT meixili quasiconformalbasedgeometricmodelforcraniofacialanalysisanditsapplication AT kingmantam quasiconformalbasedgeometricmodelforcraniofacialanalysisanditsapplication AT hoimanyuen quasiconformalbasedgeometricmodelforcraniofacialanalysisanditsapplication AT chuntingau quasiconformalbasedgeometricmodelforcraniofacialanalysisanditsapplication AT katechingchingchan quasiconformalbasedgeometricmodelforcraniofacialanalysisanditsapplication AT albertmartinli quasiconformalbasedgeometricmodelforcraniofacialanalysisanditsapplication AT lokminglui quasiconformalbasedgeometricmodelforcraniofacialanalysisanditsapplication |