Automated syndrome diagnosis by three-dimensional facial imaging

Abstract

Purpose Deep phenotyping is an emerging trend in precision medicine for genetic disease. The shape of the face is affected in 30–40% of known genetic syndromes. Here, we determine whether syndromes can be diagnosed from 3D images of human faces. Methods We analyzed variation in three-dimensional (3D) facial images of 7057 subjects: 3327 with 396 different syndromes, 727 of their relatives, and 3003 unrelated, unaffected subjects. We developed and tested machine learning and parametric approaches to automated syndrome diagnosis using 3D facial images. Results Unrelated, unaffected subjects were correctly classified with 96% accuracy. Considering both syndromic and unrelated, unaffected subjects together, balanced accuracy was 73% and mean sensitivity 49%. Excluding unrelated, unaffected subjects substantially improved both balanced accuracy (78.1%) and sensitivity (56.9%) of syndrome diagnosis. The best predictors of classification accuracy were phenotypic severity and facial distinctiveness of syndromes. Surprisingly, unaffected relatives of syndromic subjects were frequently classified as syndromic, often to the syndrome of their affected relative. Conclusion Deep phenotyping by quantitative 3D facial imaging has considerable potential to facilitate syndrome diagnosis. Furthermore, 3D facial imaging of “unaffected” relatives may identify unrecognized cases or may reveal novel examples of semidominant inheritance.

FaceBase 3: analytical tools and FAIR resources for craniofacial and dental research

“…The team developed and tested various parametric and machine-learning approaches to automated syndrome diagnosis (Bannister et al, 2017(Bannister et al, , 2020, and applied these methods to compare their utility to automated diagnosis of syndromes with craniofacial dysmorphology. The best results came from the machine-learning approach, achieving balanced accuracy of 78.1% and sensitivity of 56.9% for syndrome diagnosis (Hallgrimsson et al, 2020). These studies demonstrated that facial deep phenotyping by quantitative facial 3D imaging has strong potential to be useful in clinical diagnosis.…”

A Method for the Automatic Normalization and 3D Facial Mesh Extraction from Head Magnetic Resonance Imaging

“…This method simplifies the use of HMR for 3D facial shape analysis that enables clinical diagnostic applications for many syndromes with associated facial dysmorphologies [3].…”

“…The proposed method was developed and evaluated using 185 HMR obtained at the Hospital Sant Joan de Déu in a 1.5T GE Sigma scanner. High-resolution structural 3D T1 MRI were obtained with the following acquisition parameters: matrix size 512×512; 180 contiguous axial slices; voxel resolution 0.47×0.47×1 mm 3 ; echo (TE), repetition (TR) and inversion (TI) times, (TE/TR/TI)=3.93ms/ 2000ms/ 710ms, respectively; flip angle 15. The stacked sets of images were loaded to the 3D analysis software for scientific data Amira (http://www.fei.com/software/amira-3d-for-life-sciences/) to manually reconstruct the 3D surfaces of the anatomy of the participants.…”

“…In this context, 3D facial shape analysis constitutes a promising and noninvasive support to traditional diagnostic methods [3]. Often, this analysis is based on the detection of facial landmarks at distinctive facial features (eyes, nose, mouth) and the computation of facial biomarkers based on statistical shape analysis tools such as geometric morphometrics [8].…”

Wnt Signaling Drives Correlated Changes in Facial Morphology and Brain Shape

“…Quantitative approaches, such as our approach here, have shown that craniofacial morphology is highly integrated. This applies to the constellations of features that characterize craniofacial anomalies and facial shape effects of major mutations but also to standing variation within naturally occurring populations (Hallgrímsson et al, 2009(Hallgrímsson et al, , 2020Martinez-Abadias et al, 2012;Cole et al, 2017). This is important because these patterns of covariation reveal underlying regularities in the relationship between developmental mechanisms and phenotypic variation.…”