We've updated our Privacy Policy to make it clearer how we use your personal data. We use cookies to provide you with a better experience. You can read our Cookie Policy here.


Detecting Genetic Syndromes With Facial Analysis

Detecting Genetic Syndromes With Facial Analysis content piece image
Credit: Springer Nature Switzerland AG 2019
Listen with
Register for free to listen to this article
Thank you. Listen to this article using the player above.

Want to listen to this article for FREE?

Complete the form below to unlock access to ALL audio articles.

Read time: 1 minute

Every year, more than one million children are born with a genetic disease. Although approximately half of the genetic syndromes present facial dysmorphology, abnormal facial features are often subtle at birth and their identification by pediatricians can be difficult. Delays and errors in the diagnosis have a significant impact on mortality and morbidity associated with genetic syndromes.

For example, the average precision in detecting one of the most studied genetic syndromes, Down syndrome, by a pediatrician, is as low as 64% in the United States. Thus, the methods for the early detection of genetic syndromes become very important.

Today, children's facial analysis from photographs is a technique that allows early identification of genetic syndromes. However, the images may present some problems of calibration and lighting. Although 3D photography overcomes some of these problems, 3D scanners for the quantification of craniofacial dysmorphology in children are expensive and are not usually available to all health centers. A recent study presents a new method of optimization of face analysis that allows reconstructing the face in 3D from 2D photographs.

Araceli Morales, Gemma Piella and Federico Sukno, members of the SIMBIOsys research group and the Cognitive Media Technologies of the Department of Information Technology and Communications ( DTIC ) of the UPF, together with researchers from the University of Washington (USA) are the authors of an article describing a new method of optimization in order to make facial reconstructions in 3D of the shape of the child's face from 2D non-calibrated photographs using a new statistical model.

The new method estimates the position of the camera using a statistical model and a set of 2D facial data. Secondly, the method calculates the position of the camera and the parameters of the statistical model minimizing the distance between the estimated projection of the face in 3D on the image plan of each camera and the geometry of the 2D face observed.

"Through the reconstructed 3D faces , we automatically extract a set of geometric and 3D-looking descriptors and use them to form a classifier to identify facial dysmorphology associated with genetic syndromes ," explains Morales, co-author of the article.

The face reconstruction method in 3D photographs has been evaluated in 54 children (age range 0 to 3 years) with the authors explaining "Our classifier has detected genetic syndromes on 3D faces reconstructed from 2D photos with a Sensitivity of 100% and a specificity of 92.11%."


Tu et al. (2019) Three-Dimensional Face Reconstruction from Uncalibrated Photographs: Application to Early Detection of Genetic Syndromes. CLIP 2019, UNSURE 2019. DOI: https://doi.org/10.1007/978-3-030-32689-0_19

This article has been republished from the following materials. Note: material may have been edited for length and content. For further information, please contact the cited source.