Automated diagnosis of fetal alcohol syndrome using 3D facial image analysis

  1. S Fang,
  2. J McLaughlin,
  3. J Fang,
  4. J Huang,
  5. I Autti-Rämö,
  6. Å Fagerlund,
  7. SW Jacobson,
  8. LK Robinson,
  9. HE Hoyme,
  10. SN Mattson,
  11. E Riley,
  12. F Zhou,
  13. R Ward,
  14. ES Moore,
  15. T Foroud,
  16. Collaborative Initiative on Fetal Alcohol Spectrum Disorders†

Article first published online: 11 JUL 2008

DOI: 10.1111/j.1601-6343.2008.00425.x

Issue

Orthodontics & Craniofacial Research

Orthodontics & Craniofacial Research

Volume 11, Issue 3, pages 162–171, August 2008

Additional Information

How to Cite

Fang, S., McLaughlin, J., Fang, J., Huang, J., Autti-Rämö, I., Fagerlund, Å., Jacobson, S., Robinson, L., Hoyme, H., Mattson, S., Riley, E., Zhou, F., Ward, R., Moore, E., Foroud, T. and Collaborative Initiative on Fetal Alcohol Spectrum Disorders (2008), Automated diagnosis of fetal alcohol syndrome using 3D facial image analysis. Orthodontics & Craniofacial Research, 11: 162–171. doi: 10.1111/j.1601-6343.2008.00425.x

Author Information

  1. Shiaofen Fang, Jason McLaughlin, Jiandong Fang, Jeffrey Huang, Department of Computer Science, Purdue University, Indianapolis, IN, USA Ilona Autti-Rämö, Department of Child Neurology, HUCH Hospital for Children and Adolescents, Helsinki, Finland and Finnish Office for Health Technology Assessment / STAKES Åse Fagerlund, Folkhälsan Research Center, Helsinki, Finland and Department of Psychology, Åbo Akademi University, Turku, Finland Sandra W. Jacobson, Department of Psychiatry and Behavioral Neurosciences, Wayne State University School of Medicine, Detroit, MI, USA Luther K. Robinson, State University of New York at Buffalo School of Medicine and Biomedical Sciences, Buffalo, NY, USA H. Eugene Hoyme, Stanford University School of Medicine, Stanford, CA, USA Sarah N. Mattson, Edward Riley, Department of Psychology, San Diego State University, San Diego, CA, USA Feng Zhou, Tatiana Foroud, Indiana University School of Medicine, Indianapolis, IN, USA Richard Ward, Elizabeth S. Moore, Indiana University School of Liberal Arts, Indianapolis, IN, USA Elizabeth S. Moore, St. Vincent Women’s Hospital, Indianapolis, IN, USA

  1. †

    The Collaborative Initiative on Fetal Alcohol Spectrum Disorders (CIFASD) (PI: E. Riley, San Diego State University) includes eight different centers where data collection and analysis take place. The four sites and associated investigators who contributed data for the current project were: Folkhälsan Research Center-Helsinki (I. Autti-Rämö, Å. Fagerlund, M. Korkman), Cape Town (S.W. Jacobson), State University of New York at Buffalo School of Medicine and Biomedical Sciences (L.K. Robinson), and San Diego State University (S.N. Mattson).

*Shiaofen Fang, PhD 723 W. Michigan St., SL 280 Indianapolis, IN 46202, USA E-mail: sfang@cs.iupui.edu

  • †

    The Collaborative Initiative on Fetal Alcohol Spectrum Disorders (CIFASD) (PI: E. Riley, San Diego State University) includes eight different centers where data collection and analysis take place. The four sites and associated investigators who contributed data for the current project were: Folkhälsan Research Center-Helsinki (I. Autti-Rämö, Å. Fagerlund, M. Korkman), Cape Town (S.W. Jacobson), State University of New York at Buffalo School of Medicine and Biomedical Sciences (L.K. Robinson), and San Diego State University (S.N. Mattson).

Publication History

  1. Issue published online: 11 JUL 2008
  2. Article first published online: 11 JUL 2008
  3. Dates: Accepted 1 April 2008

SEARCH

SEARCH BY CITATION

ARTICLE TOOLS

View Full Article (HTML) Get PDF (157K)

Keywords:

  • fetal alcohol syndrome;
  • geometric feature extraction;
  • image analysis;
  • machine learning;
  • pattern classification

Structured Abstract

Authors –  Fang S, McLaughlin J, Fang J, Huang J, Autti-Rämö I, Fagerlund Å, Jacobson SW, Robinson LK, Hoyme HE, Mattson SN, Riley E, Zhou F, Ward R, Moore ES, Foroud T, and the Collaborative Initiative on Fetal Alcohol Spectrum Disorders.

Objectives –  Use three-dimensional (3D) facial laser scanned images from children with fetal alcohol syndrome (FAS) and controls to develop an automated diagnosis technique that can reliably and accurately identify individuals prenatally exposed to alcohol.

Methods –  A detailed dysmorphology evaluation, history of prenatal alcohol exposure, and 3D facial laser scans were obtained from 149 individuals (86 FAS; 63 Control) recruited from two study sites (Cape Town, South Africa and Helsinki, Finland). Computer graphics, machine learning, and pattern recognition techniques were used to automatically identify a set of facial features that best discriminated individuals with FAS from controls in each sample.

Results –  An automated feature detection and analysis technique was developed and applied to the two study populations. A unique set of facial regions and features were identified for each population that accurately discriminated FAS and control faces without any human intervention.

Conclusion –  Our results demonstrate that computer algorithms can be used to automatically detect facial features that can discriminate FAS and control faces.

View Full Article (HTML) Get PDF (157K)