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

S. Fang, J. McLaughlin, J. Fang, J. Huang, I. Autti-Rämö, Å Fagerlund, S. W. Jacobson, L. K. Robinson, H. E. Hoyme, S. N. Mattson, E. Riley, Feng Zhou, R. Ward, E. S. Moore, Tatiana Foroud

Research output: Contribution to journalArticle

25 Citations (Scopus)

Abstract

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.

Original languageEnglish
Pages (from-to)162-171
Number of pages10
JournalOrthodontics and Craniofacial Research
Volume11
Issue number3
DOIs
StatePublished - Aug 2008
Externally publishedYes

Fingerprint

Fetal Alcohol Spectrum Disorders
Lasers
Alcohols
Computer Graphics
Finland
South Africa
Population

Keywords

  • Fetal alcohol syndrome
  • Geometric feature extraction
  • Image analysis
  • Machine learning
  • Pattern classification

ASJC Scopus subject areas

  • Orthodontics
  • Oral Surgery
  • Otorhinolaryngology
  • Surgery
  • Medicine(all)

Cite this

Automated diagnosis of fetal alcohol syndrome using 3D facial image analysis. / Fang, S.; McLaughlin, J.; Fang, J.; Huang, J.; Autti-Rämö, I.; Fagerlund, Å; Jacobson, S. W.; Robinson, L. K.; Hoyme, H. E.; Mattson, S. N.; Riley, E.; Zhou, Feng; Ward, R.; Moore, E. S.; Foroud, Tatiana.

In: Orthodontics and Craniofacial Research, Vol. 11, No. 3, 08.2008, p. 162-171.

Research output: Contribution to journalArticle

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 2008, 'Automated diagnosis of fetal alcohol syndrome using 3D facial image analysis', Orthodontics and Craniofacial Research, vol. 11, no. 3, pp. 162-171. https://doi.org/10.1111/j.1601-6343.2008.00425.x
Fang, S. ; McLaughlin, J. ; Fang, J. ; Huang, J. ; Autti-Rämö, I. ; Fagerlund, Å ; Jacobson, S. W. ; Robinson, L. K. ; Hoyme, H. E. ; Mattson, S. N. ; Riley, E. ; Zhou, Feng ; Ward, R. ; Moore, E. S. ; Foroud, Tatiana. / Automated diagnosis of fetal alcohol syndrome using 3D facial image analysis. In: Orthodontics and Craniofacial Research. 2008 ; Vol. 11, No. 3. pp. 162-171.
@article{e3c25b032f9f4073b76a75c1e6dbe522,
title = "Automated diagnosis of fetal alcohol syndrome using 3D facial image analysis",
abstract = "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.",
keywords = "Fetal alcohol syndrome, Geometric feature extraction, Image analysis, Machine learning, Pattern classification",
author = "S. Fang and J. McLaughlin and J. Fang and J. Huang and I. Autti-R{\"a}m{\"o} and {\AA} Fagerlund and Jacobson, {S. W.} and Robinson, {L. K.} and Hoyme, {H. E.} and Mattson, {S. N.} and E. Riley and Feng Zhou and R. Ward and Moore, {E. S.} and Tatiana Foroud",
year = "2008",
month = "8",
doi = "10.1111/j.1601-6343.2008.00425.x",
language = "English",
volume = "11",
pages = "162--171",
journal = "Orthodontics and Craniofacial Research",
issn = "1601-6335",
publisher = "Wiley-Blackwell",
number = "3",

}

TY - JOUR

T1 - Automated diagnosis of fetal alcohol syndrome using 3D facial image analysis

AU - Fang, S.

AU - McLaughlin, J.

AU - Fang, J.

AU - Huang, J.

AU - Autti-Rämö, I.

AU - Fagerlund, Å

AU - Jacobson, S. W.

AU - Robinson, L. K.

AU - Hoyme, H. E.

AU - Mattson, S. N.

AU - Riley, E.

AU - Zhou, Feng

AU - Ward, R.

AU - Moore, E. S.

AU - Foroud, Tatiana

PY - 2008/8

Y1 - 2008/8

N2 - 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.

AB - 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.

KW - Fetal alcohol syndrome

KW - Geometric feature extraction

KW - Image analysis

KW - Machine learning

KW - Pattern classification

UR - http://www.scopus.com/inward/record.url?scp=54049144743&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=54049144743&partnerID=8YFLogxK

U2 - 10.1111/j.1601-6343.2008.00425.x

DO - 10.1111/j.1601-6343.2008.00425.x

M3 - Article

VL - 11

SP - 162

EP - 171

JO - Orthodontics and Craniofacial Research

JF - Orthodontics and Craniofacial Research

SN - 1601-6335

IS - 3

ER -