• DocumentCode
    2397062
  • Title

    Automatic analysis of local nasal features in 22q11.2DS affected individuals

  • Author

    Wu, Jia ; Wilamowska, Katarzyna ; Shapiro, Linda ; Heike, Carrie

  • Author_Institution
    Dept. of Comput. Sci. & Eng., Univ. of Washington, Seattle, WA, USA
  • fYear
    2009
  • fDate
    3-6 Sept. 2009
  • Firstpage
    3597
  • Lastpage
    3600
  • Abstract
    The 22q11.2 deletion syndrome is a common genetic condition with an estimated prevalence between 1:2000 and 1:6000 live births in the US. The syndrome is manifested in multiple different craniofacial features. The nasal area is known to play a role in assessing the extent of dysmorphology of an individual patient. In this paper, we present a method for detecting and assessing the severity of a common nasal feature: the bulbous nasal tip. Our method locates the nose and computes four descriptors, each of which leads to a severity score. Experiments with the four severity scores and a combinations of the best two show that using all five scores gives the best prediction of bulbous nasal tip. Furthermore, the bulbous nasal tip measures outperformed the median of human experts and attains similar results to our own prior work on global descriptors for prediction of 22q11.2DS.
  • Keywords
    face recognition; feature extraction; genetics; medical disorders; medical image processing; 22q11.2 deletion syndrome; automatic analysis; bulbous nasal tip; craniofacial features; dysmorphology; genetic condition; nasal features; Adolescent; Adult; Algorithms; Automation; Child; Child, Preschool; Chromosome Deletion; Chromosomes, Human, Pair 22; Female; Humans; Imaging, Three-Dimensional; Infant; Male; Mutation; Nasal Cartilages; Nose; Pattern Recognition, Automated;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE
  • Conference_Location
    Minneapolis, MN
  • ISSN
    1557-170X
  • Print_ISBN
    978-1-4244-3296-7
  • Electronic_ISBN
    1557-170X
  • Type

    conf

  • DOI
    10.1109/IEMBS.2009.5333755
  • Filename
    5333755