Comparing 2D and 3D representations for face-based genetic syndrome diagnosis

Abstract

Human genetic syndromes are often challenging to diagnose clinically. Facial phenotype is a key diagnostic indicator for hundreds of genetic syndromes and computer-assisted facial phenotyping is a promising approach to assist diagnosis. Most previous approaches to automated face-based syndrome diagnosis have analyzed different datasets of either 2D images or surface mesh-based 3D facial representations, making direct comparisons of performance challenging. In this work, we developed a set of subject-matched 2D and 3D facial representations, which we then analyzed with the aim of comparing the performance of 2D and 3D image-based approaches to computer-assisted syndrome diagnosis. This work represents the most comprehensive subject-matched analyses to date on this topic. In our analyses of 1907 subject faces representing 43 different genetic syndromes, 3D surface-based syndrome classification models significantly outperformed 2D image-based models trained and evaluated on the same subject faces. These results suggest that the clinical adoption of 3D facial scanning technology and continued collection of syndromic 3D facial scan data may substantially improve face-based syndrome diagnosis.

Fig. 1. Frontal renderings of the same example subject surface scan captured using different distances between the camera and the subject face.

Field of view was adjusted to capture the full face in each rendering. Even when subjects are imaged from a frontal orientation, camera distance influences the appearance of 2D facial photographs that may affect diagnostic models.

Fig. 2. Subject demographic histogram.

The age and sex distribution of the facial data used in this study. Young subjects (aged 5-20 years) were generally more numerous than older subjects.

Fig. 3

The three image-like facial representations used in this study from an example subject.