FIGURE 1 - uploaded by Veronika Moslerová
Content may be subject to copyright.
Color-coded maps and shell distance significance maps describing facial shape differences between syndrome patients and control individuals. (a) Color-coded maps showing the relative anterior/posterior positions of average syndrome and control facial shapes. Red denotes particular area of individual syndrome faces that were located in front of control faces after superimposition and blue indicates the opposite condition. (b) Shell distance significance maps
Source publication
Three‐dimensional (3D) virtual facial models facilitate genotype–phenotype correlations and diagnostics in clinical dysmorphology. Within cross‐sectional analysis of both genders we evaluated facial features in representative cohorts of Czech patients with Williams–Beuren‐(WBS; 12 cases), Noonan‐(NS; 14), and 22q11.2 deletion syndromes (22q11.2DS;...
Context in source publication
Context 1
... detailed overview of facial shape deviations associated with individ- ual syndromes is provided by color-coded maps superimposing aver- age faces obtained for each syndrome onto the average control face (Figure 1). The average faces for each syndrome were constructed using all available face scans of patients included in the study. ...
Similar publications
Background
Williams Beuren Syndrome is a multisystemic disorder manifested by congenital heart defects associated with dysmorphic features, intellectual delay, and a particular behavioural profile due to a microdeletion in 7q11.2.
Methods
To establish a genotype-phenotype correlation; we carried out a molecular cytogenetic analysis on 31 Tunisian...
Citations
... It originated in the late 1980s and early 1990s, focusing on changes in the shape of objects, and through corresponding theories and methods and different objects identified, these analyses have identified fixed patterns or groups of organisms which is of vital significance. Correspondingly, this approach has been widely applied in entomology, anthropology, various fields of medicine, etc. (Adams et al., 2013;Bookstein et al., 1999;Caplovičová et al., 2018;Chen et al., 2013;Gillet et al., 2020;Humphries et al., 2015;Martin, 2003;Mitteroecker & Gunz, 2009;Park et al., 2013;Xing et al., 2010;Yan & Hua, 2010). ...
China’s Xinjiang Uyghur Autonomous Region has long been a vital link between Europe and eastern Asia. Xinjiang’s geographical location and natural environment have led to unique dietary habits and traditions among both the region’s modern inhabitants as well as their ancient forebears. Here, we report on the analysis of human dental residue samples unearthed from the Jiayi Cemetery, a 10th to 2nd century BCE mortuary complex located in the Turpan Basin, Xinjiang, generating ancient starch granules produced by vegetal foodstuffs. Morphological analysis of starch granules and comparative data indicate that crops of Triticeae tribe and subfamily Panicoideae comprised a large portion of the diet, while common legumes, nuts, root and tuber were also present, although in relatively smaller proportions. The discovery of these plant starch granules in archaeological context provides direct evidence of the Jiayi population’s vegetal diet and sheds light on agricultural practices during this period. With supporting evidence drawn from zooarchaeological, archaeobotanical, and paleo‐isotopic studies of Bronze Age sites in Xinjiang, we conclude that the people interred in the Jiayi Cemetery practiced cereal crop cultivation and animal husbandry in the Late Bronze and Early Iron Ages. The species of cereal crops represented suggest meaningful economic communication between Central and West Asia.
Background:
Congenital Central Hypoventilation Syndrome (CCHS) has devastating consequences if not diagnosed promptly. Despite identification of the disease-defining gene PHOX2B and a facial phenotype, CCHS remains underdiagnosed. This study aimed to incorporate automated techniques on facial photos to screen for CCHS in a diverse pediatric cohort to improve early case identification and assess a facial phenotype-PHOX2B genotype relationship.
Methods:
Facial photos of children and young adults with CCHS were control-matched by age, sex, race/ethnicity. After validating landmarks, principal component analysis (PCA) was applied with logistic regression (LR) for feature attribution and machine learning models for subject classification and assessment by PHOX2B pathovariant.
Results:
Gradient-based feature attribution confirmed a subtle facial phenotype and models were successful in classifying CCHS: neural network performed best (median sensitivity 90% (IQR 84%, 95%)) on 179 clinical photos (versus LR and XGBoost, both 85% (IQR 75-76%, 90%)). Outcomes were comparable stratified by PHOX2B genotype and with the addition of publicly available CCHS photos (n = 104) using PCA and LR (sensitivity 83-89% (IQR 67-76%, 92-100%).
Conclusions:
Utilizing facial features, findings suggest an automated, accessible classifier may be used to screen for CCHS in children with the phenotype and support providers to seek PHOX2B testing to improve the diagnostics.
Impact:
Facial landmarking and principal component analysis on a diverse pediatric and young adult cohort with PHOX2B pathovariants delineated a distinct, subtle CCHS facial phenotype. Automated, low-cost machine learning models can detect a CCHS facial phenotype with a high sensitivity in screening to ultimately refer for disease-defining PHOX2B testing, potentially addressing gaps in disease underdiagnosis and allow for critical, timely intervention.
The human genome codes for more than 22,000 genes, many of which have been implicated in human diseases. These genetic diseases are often associated with dysmorphic facial features. Dysmorphic features occur due to premature closure of cranial sutures resulting in changes in skull shape and facial characteristics. Assessment of dysmorphic features is a crucial component of genetic consultations. This requires a great deal of clinical experience and expertise and tends to be subjective. Artificial intelligence-based analysis can come in handy for quick and accurate identification of dysmorphic features. This review explores the role played by artificial intelligence in identifying dysmorphic facies and diagnosing various genetic diseases in children.
