Face classi cation of patients with intellectual disability
Keywords
Loading...
Authors
Issue Date
2020-08-01
Language
en
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Diagnosing a genetic syndrome can be di cult as extracted genetic data is not always
decisive. To reach a diagnosis, doctors can compare the facial characteristics of a patient
with previously diagnosed patients. This process is subjective and therefore doctors would
bene t from an objective model to compare these faces. This research aims to compare
the performance of several models for the task of syndrome vs. control face classi cation.
Five di erent models have been used for syndrome vs. control classi cation, including one
ensemble model. Three models use either a face representation based on a neural network, a
3D landmark representation or a morphometric representation based on these 3D landmarks.
The last model is a Hybrid model which is based on previous research done at the Radboudumc
and this model also has the best performance for most of the 12 syndromes included in this
project. Future research can focus on reducing the computation time of the Hybrid model
and making its predictions more explainable.
Description
Citation
Faculty
Faculteit der Sociale Wetenschappen