Download PDF
Methods Inf Med 2001; 40(05): 365-372
DOI: 10.1055/s-0038-1634194
Original Article
Schattauer GmbH

Classifying Vertical Facial Deformity using Supervised and Unsupervised Learning

P. Hammond
1   Eastman Dental Institute for Oral Health Care Sciences, University College London, UK
,
T. J. Hutton
1   Eastman Dental Institute for Oral Health Care Sciences, University College London, UK
,
Z. L. Nelson-Moon
1   Eastman Dental Institute for Oral Health Care Sciences, University College London, UK
,
N. P. Hunt
1   Eastman Dental Institute for Oral Health Care Sciences, University College London, UK
,
A. J. A. Madgwick
1   Eastman Dental Institute for Oral Health Care Sciences, University College London, UK
› Author Affiliations
Further Information

Publication History

Publication Date:
08 February 2018 (online)

    Permissions and Reprints

Summary

Objectives: To evaluate the potential for machine learning techniques to identify objective criteria for classifying vertical facial deformity.

Methods: 19 parameters were determined from 131 lateral skull radiographs. Classifications were induced from raw data with simple visualisation, C5.0 and Kohonen feature maps; and using a Point Distribution Model (PDM) of shape templates comprising points taken from digitised radiographs.

Results: The induced decision trees enable a direct comparison of clinicians’ idiosyncrasies in classification. Unsupervised algorithms induce models that are potentially more objective, but their blackbox nature makes them unsuitable for clinical application. The PDM methodology gives dramatic visualisations of two modes separating horizontal and vertical facial growth. Kohonen feature maps favour one clinician and PDM the other. Clinical response suggests that while Clinician 1 places greater weight on 5 of 6 parameters, Clinician 2 relies on more parameters that capture facial shape.

Conclusions: While machine learning and statistical analyses classify subjects for vertical facial height, they have limited application in their present form. The supervised learning algorithm C5.0 is effective for generating rules for individual clinicians but its inherent bias invalidates its use for objective classification of facial form for research purposes. On the other hand, promising results from unsupervised strategies (especially the PDM) suggest a potential use for objective classification and further identification and analysis of ambiguous cases. At present, such methodologies may be unsuitable for clinical application because of the invisibility of their underlying processes. Further study is required with additional patient data and a wider group of clinicians.

Keywords

Maxillofacial Abnormalities - Artificial Intelligence
 

  • References

  • 1 Schendel SA, Eisenfeld J, Bell WH, Epker BN, Mishelevich DJ. The Long Face Syndrome: vertical maxillary excess. Am J Orthod 1976; 70: 398-408.
    CrossrefPubMedGoogle Scholar
  • 2 Bjork A. Prediction of mandibular growth rotation. Am J Orthod 1969; 55: 585-99.
    CrossrefPubMedGoogle Scholar
  • 3 Opdebeeck H, Bell WH. The short face syndrome. Am J Orthod 1978; 73: 499-511.
    CrossrefPubMedGoogle Scholar
  • 4 Bhatia SN, Leighton BC. A manual of facial growth. A computer analysis of longitudinal cephalometric growth data. Oxford: Oxford University Press; 1993
    Google Scholar
  • 5 Tarassenko L. A guide to neural computing applications. London: Arnold; 1998
    Google Scholar
  • 6 Cootes JF, Taylor CJ, Cooper DH, Graham J. Active shape models – their training and application. Comput Vis Image Underst 1995; 61 (Suppl. 01) 38-59.
    CrossrefPubMedGoogle Scholar
  • 7 Altman D. Practical statistics for medical research. London: Chapman & Hall; 1991
    Google Scholar
  • 8 Quinlan JR. C4.5: Programs for machine learning. San Mateo, CA: Morgan Kaufman; 1993
    Google Scholar
  • 9 Goodall C. Procrustes methods in the statistical analysis of shape. J R Stat Soc 1991; B 53 (Suppl. 02) 285-339.
    PubMedGoogle Scholar