Rapid automated landmarking for morphometric analysis of three‐dimensional facial scans

2017/01/12 by Mao Li, Li Mao, Joanne B. Cole +12 · 46 citations
Biochemistry, Genetics and Molecular Biology · Mathematics · #Artificial intelligence #Computer graphics (images) #Computer science #Computer vision #Gene expression and cancer classification #Genetic and phenotypic traits in livestock #Information retrieval #Morphological variations and asymmetry #Pattern recognition (psychology)

paper · pdf · doi:10.1111/joa.12576

published in Journal of Anatomy 230(4), 607-618 (Wiley)

openalex publication_date 2017/01/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01

Abstract

Automated phenotyping is essential for the creation of large, highly standardized datasets from anatomical imaging data. Such datasets can support large-scale studies of complex traits or clinical studies related to precision medicine or clinical trials. We have developed a method that generates three-dimensional landmark data that meet the requirements of standard geometric morphometric analyses. The method is robust and can be implemented without high-performance computing resources. We validated the method using both direct comparison to manual landmarking on the same individuals and also analyses of the variation patterns and outlier patterns in a large dataset of automated and manual landmark data. Direct comparison of manual and automated landmarks reveals that automated landmark data are less variable, but more highly integrated and reproducible. Automated data produce covariation structure that closely resembles that of manual landmarks. We further find that while our method does produce some landmarking errors, they tend to be readily detectable and can be fixed by adjusting parameters used in the registration and control-point steps. Data generated using the method described here have been successfully used to study the genomic architecture of facial shape in two different genome-wide association studies of facial shape.

Cited by

• Assessing the application of landmark-free morphometrics to macroevolutionary analyses
• ColourQuant: a high-throughput technique to extract and quantify colour phenotypes from plant images
• Body size and allometric variation in facial shape in children. [europepmc]
• Facial shape manifestations of growth faltering in Tanzanian children. [europepmc]
• The effect of automated landmark identification on morphometric analyses. [europepmc]
• MeshMonk: Open-source large-scale intensive 3D phenotyping. [europepmc]
• Quantification of Facial Traits. [europepmc]
• A Systematist's Guide to Estimating Bayesian Phylogenies From Morphological Data. [europepmc]
• Automated syndrome diagnosis by three-dimensional facial imaging. [europepmc]
• Fully Automatic Landmarking of Syndromic 3D Facial Surface Scans Using 2D Images. [europepmc]
• A Registration and Deep Learning Approach to Automated Landmark Detection for Geometric Morphometrics. [europepmc]
• A landmark-free morphometrics pipeline for high-resolution phenotyping: application to a mouse model of Down syndrome. [europepmc]
• Virtual Surgical Planning: Modeling from the Present to the Future. [europepmc]
• Decoding the Human Face: Progress and Challenges in Understanding the Genetics of Craniofacial Morphology. [europepmc]
• Automated morphological phenotyping using learned shape descriptors and functional maps: A novel approach to geometric morphometrics. [europepmc]
• Thirty years of geometric morphometrics: Achievements, challenges, and the ongoing quest for biological meaningfulness. [europepmc]
• Comparison Study of Extraction Accuracy of 3D Facial Anatomical Landmarks Based on Non-Rigid Registration of Face Template. [europepmc]
• Facial modeling and measurement based upon homologous topographical features. [europepmc]
• Assessing the application of landmark-free morphometrics to macroevolutionary analyses. [europepmc]

Related

• FaceDig: Automated tool for placing landmarks on facial portraits for geometric morphometrics users
• Automatic landmark annotation and dense correspondence registration for 3D human facial images
• Fully automated landmarking and facial segmentation on 3D photographs
• Gaussian Process Landmarking for Three-Dimensional Geometric Morphometrics
• PAL-Net: A Point-Wise CNN with Patch-Attention for 3D Facial Landmark Localization