OPG-based dental age estimation using a data-technical exploration of deep learning techniques.

Dental age estimation, a cornerstone in forensic age assessment, has been extensively tried and tested, yet manual methods are impeded by tedium and interobserver variability. Automated approaches using deep transfer learning encounter challenges like data scarcity, suboptimal training, and fine-tuning complexities, necessitating robust training methods. This study explores the impact of convolutional neural network hyperparameters, model complexity, training batch size, and sample quantity on age estimation. EfficientNet-B4, DenseNet-201, and MobileNet V3 models underwent cross-validation on a dataset of 3896 orthopantomograms (OPGs) with batch sizes escalating from 10 to 160 in a doubling progression, as well as random subsets of this training dataset. Results demonstrate the EfficientNet-B4 model, trained on the complete dataset with a batch size of 160, as the top performer with a mean absolute error of 0.562 years on the test set, notably surpassing the MAE of 1.01 at a batch size of 10. Increasing batch size consistently improved performance for EfficientNet-B4 and DenseNet-201, whereas MobileNet V3 performance peaked at batch size 40. Similar trends emerged in training with reduced sample sizes, though they were outperformed by the complete models. This underscores the critical role of hyperparameter optimization in adopting deep learning for age estimation from complete OPGs. The findings not only highlight the nuanced interplay of hyperparameters and performance but also underscore the potential for accurate age estimation models through optimization. This study contributes to advancing the application of deep learning in forensic age estimation, emphasizing the significance of tailored training methodologies for optimal outcomes.

Joint multi-ancestry and admixed GWAS reveals the complex genetics behind human cranial vault shape.

The cranial vault in humans is highly variable, clinically relevant, and heritable, yet its genetic architecture remains poorly understood. Here, we conduct a joint multi-ancestry and admixed multivariate genome-wide association study on 3D cranial vault shape extracted from magnetic resonance images of 6772 children from the ABCD study cohort yielding 30 genome-wide significant loci. Follow-up analyses indicate that these loci overlap with genomic risk loci for sagittal craniosynostosis, show elevated activity cranial neural crest cells, are enriched for processes related to skeletal development, and are shared with the face and brain. We present supporting evidence of regional localization for several of the identified genes based on expression patterns in the cranial vault bones of E15.5 mice. Overall, our study provides a comprehensive overview of the genetics underlying normal-range cranial vault shape and its relevance for understanding modern human craniofacial diversity and the etiology of congenital malformations.

Towards Improved Identification of Vertebral Fractures in Routine Computed Tomography (CT) Scans: Development and External Validation of a Machine Learning Algorithm.

Vertebral fractures (VFs) are the hallmark of osteoporosis, being one of the most frequent types of fragility fracture and an early sign of the disease. They are associated with significant morbidity and mortality. VFs are incidentally found in one out of five imaging studies, however, more than half of the VFs are not identified nor reported in patient computed tomography (CT) scans. Our study aimed to develop a machine learning algorithm to identify VFs in abdominal/chest CT scans and evaluate its performance. We acquired two independent data sets of routine abdominal/chest CT scans of patients aged 50 years or older: a training set of 1011 scans from a non-interventional, prospective proof-of-concept study at the Universitair Ziekenhuis (UZ) Brussel and a validation set of 2000 subjects from an observational cohort study at the Hospital of Holbaek. Both data sets were externally reevaluated to identify reference standard VF readings using the Genant semiquantitative (SQ) grading. Four independent models have been trained in a cross-validation experiment using the training set and an ensemble of four models has been applied to the external validation set. The validation set contained 15.3% scans with one or more VF (SQ2-3), whereas 663 of 24,930 evaluable vertebrae (2.7%) were fractured (SQ2-3) as per reference standard readings. Comparison of the ensemble model with the reference standard readings in identifying subjects with one or more moderate or severe VF resulted in an area under the receiver operating characteristic curve (AUROC) of 0.88 (95% confidence interval [CI], 0.85-0.90), accuracy of 0.92 (95% CI, 0.91-0.93), kappa of 0.72 (95% CI, 0.67-0.76), sensitivity of 0.81 (95% CI, 0.76-0.85), and specificity of 0.95 (95% CI, 0.93-0.96). We demonstrated that a machine learning algorithm trained for VF detection achieved strong performance on an external validation set. It has the potential to support healthcare professionals with the early identification of VFs and prevention of future fragility fractures. © 2023 UCB S.A. and The Authors. Journal of Bone and Mineral Research published by Wiley Periodicals LLC on behalf of American Society for Bone and Mineral Research (ASBMR).

A statistical shape model for estimating missing soft tissues of the face in a black South African population.

PURPOSE: Facial disfigurement may affect the quality of life of many patients. Facial prostheses are often used as an adjuvant to surgical intervention and may sometimes be the only viable treatment option. Traditional methods for designing soft-tissue facial prostheses are time-consuming and subjective, while existing digital techniques are based on mirroring of contralateral features of the patient, or the use of existing feature templates/models that may not be readily available. We aim to support the objective and semi-automated design of facial prostheses with primary application to midline or bilateral defect restoration where no contralateral features are present. Specifically, we developed and validated a statistical shape model (SSM) for estimating the shape of missing facial soft tissue segments, from any intact parts of the face. MATERIALS AND METHODS: An SSM of 3D facial variations was built from meshes extracted from computed tomography and cone beam computed tomography images of a black South African sample (n = 235) without facial disfigurement. Various types of facial defects were simulated, and the missing parts were estimated automatically by a weighted fit of each mesh to the SSM. The estimated regions were compared to the original regions using color maps and root-mean-square (RMS) distances. RESULTS: Root mean square errors (RMSE) for defect estimations of one orbit, partial nose, cheek, and lip were all below 1.71 mm. Errors for the full nose, bi-orbital defects, as well as small and large composite defects were between 2.10 and 2.58 mm. Statistically significant associations of age and type of defect with RMSE were observed, but not with sex or imaging modality. CONCLUSION: This method can support the objective and semi-automated design of facial prostheses, specifically for defects in the midline, crossing the midline or bilateral defects, by facilitating time-consuming and skill-dependent aspects of prosthesis design.

Deep learning-based dental implant recognition using synthetic X-ray images.

A novel algorithm for generating artificial training samples from triangulated three-dimensional (3D) surface models within the context of dental implant recognition is proposed. The proposed algorithm is based on the calculation of two-dimensional (2D) projections (from a number of different angles) of 3D volumetric representations of computer-aided design (CAD) surface models. A fully convolutional network (FCN) is subsequently trained on the artificially generated X-ray images for the purpose of automatically identifying the connection type associated with a specific dental implant in an actual X-ray image. Semi-automated and fully automated systems are proposed for segmenting questioned dental implants from the background in actual X-ray images. Within the context of the semi-automated system, suitable regions of interest (ROIs), which contain the dental implants, are manually specified. However, as part of the fully automated system, suitable ROIs are automatically detected. It is demonstrated that a segmentation/detection accuracy of 94.0% and a classification/recognition accuracy of 71.7% are attainable within the context of the proposed fully automated system. Since the proposed systems utilise an ensemble of techniques that has not been employed for the purpose of dental implant classification/recognition on any previous occasion, the above-mentioned results are very encouraging.

Bloodstain impact pattern Area of Origin estimation using least-squares angles: A HemoVision validation study.

Bloodstain impact pattern Area of Origin (AO) estimation is an important but time-consuming process in criminal investigations. HemoVision is a software package that automates and accelerates this process. To date, however, no study has been published that evaluates HemoVision's accuracy. Moreover, HemoVision relies on an automated variant of the tangent method to estimate a pattern's AO, even though the use of front-view projections has been shown to provide biased AO estimates. Therefore, the goal of this paper is twofold. First, a novel AO estimation method is proposed, whereby AO estimation is formulated as a least-squares optimisation problem that operates in three dimensions directly, eliminating the need for front view projections. Second, ten impact patterns with known AO coordinates at both 50 cm and 100 cm with respect to the target wall are created and used to compare the proposed approach's accuracy and robustness to the manual tangent method, HemoSpat, and HemoVision's automated tangent method. Results show that for impacts at 100 cm or less to the target wall, the proposed approach achieves the lowest average error of 17.29 cm with the least uncertainty, and that it performs significantly better than the manual tangent and automated tangent methods at a 5% significance level. Moreover, it is shown to achieve errors of less than 30 cm at these distances with just nine stains, whereas the automated tangent method requires a minimum of 16 stains to achieve the same average error.

Cross-Modal Distillation to Improve MRI-Based Brain Tumor Segmentation With Missing MRI Sequences.

Convolutional neural networks (CNNs) for brain tumor segmentation are generally developed using complete sets of magnetic resonance imaging (MRI) sequences for both training and inference. As such, these algorithms are not trained for realistic, clinical scenarios where parts of the MRI sequences which were used for training, are missing during inference. To increase clinical applicability, we proposed a cross-modal distillation approach to leverage the availability of multi-sequence MRI data for training and generate an enriched CNN model which uses only single-sequence MRI data for inference but outperforms a single-sequence CNN model. We assessed the performance of the proposed method for whole tumor and tumor core segmentation with multi-sequence MRI data available for training but only T1-weighted ([Formula: see text]) sequence data available for inference, using BraTS 2018, and in-house datasets. Results showed that cross-modal distillation significantly improved the Dice score for both whole tumor and tumor core segmentation when only [Formula: see text] sequence data were available for inference. For the evaluation using the in-house dataset, cross-modal distillation achieved an average Dice score of 79.04% and 69.39% for whole tumor and tumor core segmentation, respectively, while a single-sequence U-Net model using [Formula: see text] sequence data for both training and inference achieved an average Dice score of 73.60% and 62.62%, respectively. These findings confirmed cross-modal distillation as an effective method to increase the potential of single-sequence CNN models such that segmentation performance is less compromised by missing MRI sequences or having only one MRI sequence available for segmentation.

Automated landmarking for palatal shape analysis using geometric deep learning.

OBJECTIVES: To develop and evaluate a geometric deep-learning network to automatically place seven palatal landmarks on digitized maxillary dental casts. SETTINGS AND SAMPLE POPULATION: The sample comprised individuals with permanent dentition of various ethnicities. The network was trained from manual landmark annotations on 732 dental casts and evaluated on 104 dental casts. MATERIALS AND METHODS: A geometric deep-learning network was developed to hierarchically learn features from point-clouds representing the 3D surface of each cast. These features predict the locations of seven palatal landmarks. RESULTS: Repeat-measurement reliability was <0.3 mm for all landmarks on all casts. Accuracy is promising. The proportion of test subjects with errors less than 2 mm was between 0.93 and 0.68, depending on the landmark. Unusually shaped and large palates generate the highest errors. There was no evidence for a difference in mean palatal shape estimated from manual compared to the automatic landmarking. The automatic landmarking reduces sample variation around the mean and reduces measurements of palatal size. CONCLUSIONS: The automatic landmarking method shows excellent repeatability and promising accuracy, which can streamline patient assessment and research studies. However, landmark indications should be subject to visual quality control.

Three-dimensional image volumes from two-dimensional digitally reconstructed radiographs: A deep learning approach in lower limb CT scans.

PURPOSE: Three-dimensional (3D) reconstructions of the human anatomy have been available for surgery planning or diagnostic purposes for a few years now. The different image modalities usually rely on several consecutive two-dimensional (2D) acquisitions in order to reconstruct the 3D volume. Hence, such acquisitions are expensive, time-demanding and often expose the patient to an undesirable amount of radiation. For such reasons, along the most recent years, several studies have been proposed that extrapolate 3D anatomical features from merely 2D exams such as x rays for implant templating in total knee or hip arthroplasties. METHOD: The presented study shows an adaptation of a deep learning-based convolutional neural network to reconstruct 3D volumes from a mere 2D digitally reconstructed radiograph from one of the most extensive lower limb computed tomography datasets available. This novel approach is based on an encoder-decoder architecture with skip connections and a multidimensional Gaussian filter as data augmentation technique. RESULTS: The results achieved promising values when compared against the ground truth volumes, quantitatively yielding an average of 0.77 ± 0.05 structured similarity index. CONCLUSIONS: A novel deep learning-based approach to reconstruct 3D medical image volumes from a single x-ray image was shown in the present study. The network architecture was validated against the original scans presenting SSIM values of 0.77 ± 0.05 and 0.78 ± 0.06, respectively for the knee and the hip crop.

Theoretical analysis and experimental validation of volume bias of soft Dice optimized segmentation maps in the context of inherent uncertainty.

The clinical interest is often to measure the volume of a structure, which is typically derived from a segmentation. In order to evaluate and compare segmentation methods, the similarity between a segmentation and a predefined ground truth is measured using popular discrete metrics, such as the Dice score. Recent segmentation methods use a differentiable surrogate metric, such as soft Dice, as part of the loss function during the learning phase. In this work, we first briefly describe how to derive volume estimates from a segmentation that is, potentially, inherently uncertain or ambiguous. This is followed by a theoretical analysis and an experimental validation linking the inherent uncertainty to common loss functions for training CNNs, namely cross-entropy and soft Dice. We find that, even though soft Dice optimization leads to an improved performance with respect to the Dice score and other measures, it may introduce a volume bias for tasks with high inherent uncertainty. These findings indicate some of the method's clinical limitations and suggest doing a closer ad-hoc volume analysis with an optional re-calibration step.

Optimization for Medical Image Segmentation: Theory and Practice When Evaluating With Dice Score or Jaccard Index.

In many medical imaging and classical computer vision tasks, the Dice score and Jaccard index are used to evaluate the segmentation performance. Despite the existence and great empirical success of metric-sensitive losses, i.e. relaxations of these metrics such as soft Dice, soft Jaccard and Lovász-Softmax, many researchers still use per-pixel losses, such as (weighted) cross-entropy to train CNNs for segmentation. Therefore, the target metric is in many cases not directly optimized. We investigate from a theoretical perspective, the relation within the group of metric-sensitive loss functions and question the existence of an optimal weighting scheme for weighted cross-entropy to optimize the Dice score and Jaccard index at test time. We find that the Dice score and Jaccard index approximate each other relatively and absolutely, but we find no such approximation for a weighted Hamming similarity. For the Tversky loss, the approximation gets monotonically worse when deviating from the trivial weight setting where soft Tversky equals soft Dice. We verify these results empirically in an extensive validation on six medical segmentation tasks and can confirm that metric-sensitive losses are superior to cross-entropy based loss functions in case of evaluation with Dice Score or Jaccard Index. This further holds in a multi-class setting, and across different object sizes and foreground/background ratios. These results encourage a wider adoption of metric-sensitive loss functions for medical segmentation tasks where the performance measure of interest is the Dice score or Jaccard index.

Towards fully automated third molar development staging in panoramic radiographs.

Staging third molar development is commonly used for age assessment in sub-adults. Current staging techniques are, at most, semi-automated and rely on manual interactions prone to operator variability. The aim of this study was to fully automate the staging process by employing the full potential of deep learning, using convolutional neural networks (CNNs) in every step of the procedure. The dataset used to train the CNNs consisted of 400 panoramic radiographs (OPGs), with 20 OPGs per developmental stage per sex, staged in consensus between three observers. The concepts of transfer learning, using pre-trained CNNs, and data augmentation were used to mitigate the issues when dealing with a limited dataset. In this work, a three-step procedure was proposed and the results were validated using fivefold cross-validation. First, a CNN localized the geometrical center of the lower left third molar, around which a square region of interest (ROI) was extracted. Second, another CNN segmented the third molar within the ROI. Third, a final CNN used both the ROI and the segmentation to classify the third molar into its developmental stage. The geometrical center of the third molar was found with an average Euclidean distance of 63 pixels. Third molars were segmented with an average Dice score of 93%. Finally, the developmental stages were classified with an accuracy of 54%, a mean absolute error of 0.69 stages, and a linear weighted Cohen's kappa coefficient of 0.79. The entire automated workflow on average took 2.72 s to compute, which is substantially faster than manual staging starting from the OPG. Taking into account the limited dataset size, this pilot study shows that the proposed fully automated approach shows promising results compared with manual staging.

Effect of Lower Third Molar Segmentations on Automated Tooth Development Staging using a Convolutional Neural Network.

Staging third molar development is commonly used for age estimation in subadults. Automated developmental stage allocation to the mandibular left third molar in panoramic radiographs has been examined in a pilot study. This method used an AlexNet Deep Convolutional Neural Network (CNN) approach to stage lower left third molars, which had been selected by manually drawn bounding boxes around them. This method (bounding box AlexNet = BA) still contained parts of surrounding structures which may have affected the automated stage allocation performance. We hypothesize that segmenting only the third molar could further improve the automated stage allocation performance. Therefore, the current study aimed to determine and validate the effect of lower third molar segmentations on automated tooth development staging. Retrospectively, 400 panoramic radiographs were collected, processed and segmented in three ways: bounding box (BB), rough (RS), and full (FS) tooth segmentation. A DenseNet201 CNN was used for automated stage allocation. Automated staging results were compared with reference stages - allocated by human observers - overall and per stage. FS rendered the best results with a stage allocation accuracy of 0.61, a mean absolute difference of 0.53 stages and a Cohen's linear κ of 0.84. Misallocated stages were mostly neighboring stages, and DenseNet201 rendered better results than AlexNet by increasing the percentage of correctly allocated stages by 3% (BA compared to BB). FS increased the percentage of correctly allocated stages by 7% compared to BB. In conclusion, full tooth segmentation and a DenseNet CNN optimize automated dental stage allocation for age estimation.

Facial recognition from DNA using face-to-DNA classifiers.

Facial recognition from DNA refers to the identification or verification of unidentified biological material against facial images with known identity. One approach to establish the identity of unidentified biological material is to predict the face from DNA, and subsequently to match against facial images. However, DNA phenotyping of the human face remains challenging. Here, another proof of concept to biometric authentication is established by using multiple face-to-DNA classifiers, each classifying given faces by a DNA-encoded aspect (sex, genomic background, individual genetic loci), or by a DNA-inferred aspect (BMI, age). Face-to-DNA classifiers on distinct DNA aspects are fused into one matching score for any given face against DNA. In a globally diverse, and subsequently in a homogeneous cohort, we demonstrate preliminary, but substantial true (83%, 80%) over false (17%, 20%) matching in verification mode. Consequences of future efforts include forensic applications, necessitating careful consideration of ethical and legal implications for privacy in genomic databases.

Cascaded statistical shape model based segmentation of the full lower limb in CT.

Image segmentation has become an important tool in orthopedic and biomechanical research. However, it greatly remains a time-consuming and laborious task. In this manuscript, we propose a fully automatic model-based segmentation pipeline for the full lower limb in computed tomography (CT) images. The method relies on prior shape model fitting, followed by a gradient-defined free from deformation. The technique allows for the generation of anatomically corresponding surface meshes, which can subsequently be applied in anatomical and mechanical simulation studies. Starting from an initial, small (n ≤ 10) sample of manual segmentations, the model is continuously updated and refined with newly segmented training samples. Validation of the segmentation pipeline was performed by comparing the automatic segmentations against corresponding manual segmentations. Convergence of the segmentation pipeline was obtained in 250 cases and failed in three samples. The average distance error ranged from 0.53 to 0.76 mm and maximal error ranged from 2.0 to 7.8 mm for the 7 different osteological structures that were investigated. The accuracy of the shape model-based segmentation gradually increased as the number of training shapes in the updated population also increased. When optimized with the free form deformation, however, average segmentation accuracy rapidly plateaued from already as little as 20 training samples on. The maximum segmentation error plateaued from 100 training samples on.

Genome-wide mapping of global-to-local genetic effects on human facial shape.

Genome-wide association scans of complex multipartite traits like the human face typically use preselected phenotypic measures. Here we report a data-driven approach to phenotyping facial shape at multiple levels of organization, allowing for an open-ended description of facial variation while preserving statistical power. In a sample of 2,329 persons of European ancestry, we identified 38 loci, 15 of which replicated in an independent European sample (n = 1,719). Four loci were completely new. For the others, additional support (n = 9) or pleiotropic effects (n = 2) were found in the literature, but the results reported here were further refined. All 15 replicated loci highlighted distinctive patterns of global-to-local genetic effects on facial shape and showed enrichment for active chromatin elements in human cranial neural crest cells, suggesting an early developmental origin of the facial variation captured. These results have implications for studies of facial genetics and other complex morphological traits.

HemoVision: An automated and virtual approach to bloodstain pattern analysis.

Bloodstain pattern analysis (BPA) is a subspecialty of forensic sciences, dealing with the analysis and interpretation of bloodstain patterns in crime scenes. The aim of BPA is uncovering new information about the actions that took place in a crime scene, potentially leading to a confirmation or refutation of a suspect's statement. A typical goal of BPA is to estimate the flight paths for a set of stains, followed by a directional analysis in order to estimate the area of origin for the stains. The traditional approach, referred to as stringing, consists of attaching a piece of string to each stain, and letting the string represent an approximation of the stain's flight path. Even though stringing has been used extensively, many (practical) downsides exist. We propose an automated and virtual approach, employing fiducial markers and digital images. By automatically reconstructing a single coordinate frame from several images, limited user input is required. Synthetic crime scenes were created and analysed in order to evaluate the approach. Results demonstrate the correct operation and practical advantages, suggesting that the proposed approach may become a valuable asset for practically analysing bloodstain spatter patterns. Accompanying software called HemoVision is currently provided as a demonstrator and will be further developed for practical use in forensic investigations.

An investigation of matching symmetry in the human pinnae with possible implications for 3D ear recognition and sound localization.

The human external ears, or pinnae, have an intriguing shape and, like most parts of the human external body, bilateral symmetry is observed between left and right. It is a well-known part of our auditory sensory system and mediates the spatial localization of incoming sounds in 3D from monaural cues due to its shape-specific filtering as well as binaural cues due to the paired bilateral locations of the left and right ears. Another less broadly appreciated aspect of the human pinna shape is its uniqueness from one individual to another, which is on the level of what is seen in fingerprints and facial features. This makes pinnae very useful in human identification, which is of great interest in biometrics and forensics. Anatomically, the type of symmetry observed is known as matching symmetry, with structures present as separate mirror copies on both sides of the body, and in this work we report the first such investigation of the human pinna in 3D. Within the framework of geometric morphometrics, we started by partitioning ear shape, represented in a spatially dense way, into patterns of symmetry and asymmetry, following a two-factor anova design. Matching symmetry was measured in all substructures of the pinna anatomy. However, substructures that 'stick out' such as the helix, tragus, and lobule also contained a fair degree of asymmetry. In contrast, substructures such as the conchae, antitragus, and antihelix expressed relatively stronger degrees of symmetric variation in relation to their levels of asymmetry. Insights gained from this study were injected into an accompanying identification setup exploiting matching symmetry where improved performance is demonstrated. Finally, possible implications of the results in the context of ear recognition as well as sound localization are discussed.

3-dimensional analysis of regenerative endodontic treatment outcome.

INTRODUCTION: A growing body of evidence supports the regeneration potential of dental tissues after regenerative endodontic treatment (RET). Nevertheless, a standard method for the evaluation of RET outcome is lacking. The aim of this study was to develop a standardized quantitative method for RET outcome analysis based on cone-beam computed tomographic (CBCT) volumetric measurements. METHODS: Five human teeth embedded in mandibular bone samples were scanned using both an Accuitomo 170 CBCT machine (Morita, Kyoto, Japan) and a SkyScan 1174 micro-computed tomographic (µCT) system (SkyScan, Antwerp, Belgium). For subsequent clinical application, clinical data and low-dose CBCT scans (preoperatively and follow-up) from 5 immature permanent teeth treated with RET were retrieved. In vitro and clinical 3-dimensional image data sets were imported into a dedicated software tool. Two segmentation steps were applied to extract the teeth of interest from the surrounding tissue (livewire) and to separate tooth hard tissue and root canal space (level set methods). In vitro and clinical volumetric measurements were assessed separately for differences using Wilcoxon matched pairs test. Pearson correlation analysis and Bland-Altman plots were used to evaluate the relation and agreement between the segmented CBCT and µCT volumes. RESULTS: The results showed no statistical differences and strong agreement between CBCT and µCT volumetric measurements. Volumetric comparison of the root hard tissue showed significant hard tissue formation. (The mean volume of newly formed hard tissue was 27.9 [±10.5] mm(3) [P < .05]). CONCLUSIONS: Analysis of 3-dimensional data for teeth treated with RET offers valuable insights into the treatment outcome and patterns of hard tissue formation.

Modeling 3D facial shape from DNA.

Human facial diversity is substantial, complex, and largely scientifically unexplained. We used spatially dense quasi-landmarks to measure face shape in population samples with mixed West African and European ancestry from three locations (United States, Brazil, and Cape Verde). Using bootstrapped response-based imputation modeling (BRIM), we uncover the relationships between facial variation and the effects of sex, genomic ancestry, and a subset of craniofacial candidate genes. The facial effects of these variables are summarized as response-based imputed predictor (RIP) variables, which are validated using self-reported sex, genomic ancestry, and observer-based facial ratings (femininity and proportional ancestry) and judgments (sex and population group). By jointly modeling sex, genomic ancestry, and genotype, the independent effects of particular alleles on facial features can be uncovered. Results on a set of 20 genes showing significant effects on facial features provide support for this approach as a novel means to identify genes affecting normal-range facial features and for approximating the appearance of a face from genetic markers.