3D analysis of facial morphology

被引:181
作者
Hammond, P
Hutton, TJ
Allanson, JE
Campbell, LE
Hennekam, RCM
Holden, S
Patton, MA
Shaw, A
Temple, IK
Trotter, M
Murphy, KC
Winter, RM
机构
[1] UCL, Eastman Dent Inst, London WC1X 8LD, England
[2] Univ Ottawa, Ottawa, ON K1N 6N5, Canada
[3] Childrens Hosp Eastern Ontario, Div Genet, Ottawa, ON K1H 8L1, Canada
[4] Kings Coll London, Inst Psychiat, London WC2R 2LS, England
[5] Univ Amsterdam, Emma Childrens Hosp, Dept Pediat, NL-1012 WX Amsterdam, Netherlands
[6] Univ Amsterdam, Emma Childrens Hosp, Dept Clin Genet, NL-1012 WX Amsterdam, Netherlands
[7] Univ Cambridge, Comp Lab, Cambridge CB2 3QG, England
[8] Univ London St Georges Hosp, Sch Med, Dept Med Genet, London SW17 0RE, England
[9] Southrampton Univ Hosp Trust, Wessex Clin Genet Serv, Southampton, Hants, England
[10] Catholic Univ Louvain, Wolfson Inst Biomed Res, London, England
[11] Royal Coll Surgeons Ireland, Dept Psychiat, Dublin 2, Ireland
[12] UCL, Inst Child Hlth, London, England
关键词
facial morphology; dense surface models; 3D analysis; dysmorphology; diagnosis; Noonan syndrome; velo-cardio-facial syndrome;
D O I
10.1002/ajmg.a.20665
中图分类号
Q3 [遗传学];
学科分类号
071007 ; 090102 ;
摘要
Dense surface models can be used to analyze 3D facial morphology by establishing a correspondence of thousands of points across each 3D face image. The models provide dramatic visualizations of 3D face-shape variation with potential for training physicians to recognize the key components of particular syndromes. We demonstrate their use to visualize and recognize shape differences in a collection of 3D face images that includes 280 controls (2 weeks to 56 years of age), 90 individuals with Noonan syndrome (NS) (7 months to 56 years), and 60 individuals with velo-cardio-facial syndrome (VCFS; 3 to 17 years of age). Ten-fold cross-validation testing of discrimination between the three groups was carried out on unseen test examples using five pattern recognition algorithms (nearest mean, C5.0 decision trees, neural networks, logistic regression, and support vector machines). For discriminating between individuals with NS and controls, the best average sensitivity and specificity levels were 92 and 93% for children, 83 and 94% for adults, and 88 and 94% for the children and adults combined. For individuals with VCFS and controls, the best results were 83 and 92%. In a comparison of individuals with NS and individuals with VCFS, a correct identification rate of 95% was achieved for both syndromes. This article contains supplementary material, which may be viewed at the American Journal of Medical Genetics website at http:Hwww-interscience. wiley.com/jpages/01148-7299/suppmat/index.html. (C) 2004 Wiley-Liss, Inc.
引用
收藏
页码:339 / 348
页数:10
相关论文
共 48 条
  • [1] Allanson JE, 1996, AM J MED GENET, V65, P13, DOI 10.1002/(SICI)1096-8628(19961002)65:1<13::AID-AJMG2>3.0.CO
  • [2] 2-Z
  • [3] Allanson JE, 1997, AM J MED GENET, V70, P1, DOI 10.1002/(SICI)1096-8628(19970502)70:1<1::AID-AJMG1>3.0.CO
  • [4] 2-3
  • [5] ANTHROPOMETRIC CRANIOFACIAL PATTERN PROFILES IN DOWN-SYNDROME
    ALLANSON, JE
    OHARA, P
    FARKAS, LG
    NAIR, RC
    [J]. AMERICAN JOURNAL OF MEDICAL GENETICS, 1993, 47 (05): : 748 - 752
  • [6] NOONAN SYNDROME - THE CHANGING PHENOTYPE
    ALLANSON, JE
    HALL, JG
    HUGHES, HE
    PREUS, M
    WITT, RD
    [J]. AMERICAN JOURNAL OF MEDICAL GENETICS, 1985, 21 (03): : 507 - 514
  • [7] Allanson JE, 1997, AM J MED GENET, V71, P414, DOI 10.1002/(SICI)1096-8628(19970905)71:4<414::AID-AJMG8>3.0.CO
  • [8] 2-T
  • [9] 3 DIMENSIONAL DIGITIZATION OF THE FACE AND SKULL
    ARRIDGE, S
    MOSS, JP
    LINNEY, AD
    JAMES, DR
    [J]. JOURNAL OF MAXILLOFACIAL SURGERY, 1985, 13 (03): : 136 - 143
  • [10] A case definition and photographic screening tool for the facial phenotype of fetal alcohol syndrome
    Astley, SJ
    Clarren, SK
    [J]. JOURNAL OF PEDIATRICS, 1996, 129 (01) : 33 - 41