Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Computer-based recognition of dysmorphic faces.

Hartmut S Loos1, Dagmar Wieczorek, Rolf P Würtz

  • 1Institut für Neuroinformatik, Ruhr-Universität Bochum, Germany.

European Journal of Human Genetics : EJHG
|August 2, 2003
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

EpiATLAS - a reference for human epigenomic research.

bioRxiv : the preprint server for biology·2026
Same author

[GPs' assessment of the reform of the psychotherapy guideline].

Gesundheitswesen (Bundesverband der Arzte des Offentlichen Gesundheitsdienstes (Germany))·2026
Same author

[TSS in the care of people with mental illness - results of a survey of psychotherapists].

Psychiatrische Praxis·2026
Same author

Motivations and experiences of high-risk men in risk-adapted prostate cancer early detection: A qualitative study.

Patient education and counseling·2026
Same author

Systematic analysis of snRNA genes reveals frequent RNU2-2 variants in dominant and recessive developmental and epileptic encephalopathies.

Nature genetics·2026
Same author

The Cooperative Network Architecture: Learning Structured Networks as Representation of Sensory Patterns.

Neural computation·2026
Same journal

Parental and public views on genomic newborn screening: a systematic review.

European journal of human genetics : EJHG·2026
Same journal

Correction: follow-up, cancer risk and mortality in Peutz-Jeghers syndrome: data from the PRED-IdF network.

European journal of human genetics : EJHG·2026
Same journal

Characterisation of the SMN1/2 locus using a highly specific variant caller on whole-genome sequence data from 500,000 individuals.

European journal of human genetics : EJHG·2026
Same journal

When truncation is not loss of function: neo-tail architecture as a determinant of pathogenicity in NMD-escaping frameshift variants.

European journal of human genetics : EJHG·2026
Same journal

CMIP as a novel candidate gene for neurodevelopmental and neuropsychiatric disorders.

European journal of human genetics : EJHG·2026
Same journal

Parent and professional experiences of a clinical trial of prenatal and postnatal stem cell therapy for severe osteogenesis imperfecta.

European journal of human genetics : EJHG·2026
See all related articles

Computers can identify distinct facial patterns in genetic syndromes like mucopolysaccharidosis type III and fragile X syndrome. This technology achieved higher accuracy than clinical geneticists in recognizing these craniofacial malformations.

Area of Science:

  • Medical genetics
  • Computer vision
  • Biometrics

Background:

  • Genetic syndromes frequently manifest with craniofacial malformations, posing diagnostic challenges.
  • Recognizing specific facial patterns associated with genetic disorders is crucial for accurate diagnosis.

Purpose of the Study:

  • To investigate the capability of a computer system to recognize disease-specific facial patterns in patients with various genetic syndromes.
  • To compare the computer's recognition accuracy with that of clinical geneticists.

Main Methods:

  • Utilized Gabor wavelet transformation for preprocessing 55 patient photographs from five genetic syndromes.
  • Extracted feature vectors at 32 facial nodes for pattern analysis.
  • Classified patients based on facial feature vector comparisons.

Related Experiment Videos

Main Results:

  • The computer system correctly classified 76% of patients (42/55).
  • In 7% of cases (4/55), the computer's top two diagnostic scores were equally plausible.
  • Clinical geneticists achieved a 62% recognition rate with the same photographs.

Conclusions:

  • Specific genetic syndromes exhibit recognizable, mathematically definable facial patterns.
  • Computer-assisted facial pattern recognition shows potential as a diagnostic tool for genetic disorders.
  • This approach may offer higher accuracy than human expert recognition in certain cases.