Look-alike humans identified by facial recognition algorithms show genetic similarities

The human face is one of the most visible features of our unique identity as individuals. Interestingly, monozygotic twins share almost identical facial traits and the same DNA sequence but could exhibit differences in other biometrical parameters. The expansion of the world wide web and the possibility to exchange pictures of humans across the planet has increased the number of people identified online as virtual twins or doubles that are not family related. Herein, we have characterized in detail a set of "look-alike" humans, defined by facial recognition algorithms, for their multiomics landscape. We report that these individuals share similar genotypes and differ in their DNA methylation and microbiome landscape. These results not only provide insights about the genetics that determine our face but also might have implications for the establishment of other human anthropometric properties and even personality characteristics.

Case Report: The success of face analysis technology in extremely rare genetic diseases in Korea: Tatton–Brown–Rahman syndrome and Say–Barber –Biesecker–Young–Simpson variant of ohdo syndrome

Tatton–Brown–Rahman syndrome (TBRS) and Say–Barber–Biesecker– Young–Simpson variant of Ohdo syndrome (SBBYSS) are extremely rare genetic disorders with less than 100 reported cases. Patients with these disorders exhibit a characteristic facial dysmorphism: TBRS is characterized by a round face, a straight and thick eyebrow, and prominent maxillary incisors, whereas SBBYSS is characterized by mask-like facies, blepharophimosis, and ptosis. The usefulness of Face2Gene as a tool for the identification of dysmorphology syndromes is discussed, because, in these patients, it suggested TBRS and SBBYSS within the top five candidate disorders. Face2Gene is useful for the diagnosis of extremely rare diseases in Korean patients, suggesting the possibility of expanding its clinical applications.

Ten-year follow-up of Nicolaides-Baraitser syndrome with a de novo mutation and analysis of 58 gene loci of SMARCA2-associated NCBRS

As a clinical subtype of SWI/SNF‐related intellectual disability syndromes, Nicolaides–Baraitser syndrome (NCBRS, OMIM601358) has a unique genotype–phenotype. Due to the scarcity of the number of cases reported and the limitations of diagnosis methods, so far only more than 80 cases have been reported worldwide. In this article, a new patient with a de novo mutation was followed up for 10 years; it includes the epilepsy treatment process, the characteristics of NBCRS with seizures, typical faces, sparse hair, prominent interphalangeal joints, and intellectual disability, and we also summarized the genotype–phenotype of the 80 reported cases for comparison. Due to insufficient studies and lack of attention paid to the syndrome, it is believed that the actual number of cases should be far more than the reported number. The syndrome is phased and progressive. The genotype–phenotype correlation of the disease is related to the location of the gene locus, especially closely related to the SNF2 ATPase domain.

Ophthalmologic and facial abnormalities of Nicolaides-Baraitser syndrome

BACKGROUND

Nicolaides-Baraitser syndrome (NCBRS), first described in 1993, is a rare autosomal dominant disease caused by pathogenic variants in the SMARCA2 gene on chromosome 9p24.3. NCBRS typically presents with dysmorphic facial features, seizures, intellectual disability, and developmental delays. Abnormal findings of the eye and ocular adnexa associated with NCBRS have not been systematically evaluated and summarized in literature. This report presents the case of a 4-year-old male with NCBRS along with a systematic review of literature of the abnormal ophthalmologic and facial features of NCBRS cases.

METHODS

A systematic review of literature of published cases of molecularly confirmed NCBRS was performed and the frequencies of eye, ocular adnexa, and facial abnormalities were calculated.

RESULTS

Our patient's abnormal eye features include myopia, down slanting palpebral fissures, sagging inferior periorbital skin, hypertelorism, and long eyelashes. From the systemic review of literature, the most common abnormal eye and ocular adnexa features include prominent/long eyelashes, thick eyebrows, sagging periorbital skin, down slanting palpebral fissures, and ptosis. The most common facial dysmorphic features include thick/everted lower lip, coarse facial features, wide/large mouth, and thin upper lip. Dental abnormalities are also commonly reported.

CONCLUSIONS

NCBRS frequently presents with well-defined ophthalmic and facial abnormalities. Prompt ophthalmologic evaluation following NCBRS diagnosis may be recommended to screen for several eye disorders. Surgical correction of ptosis may be indicated for NCBRS patients. This report may help further delineate the phenotype of this condition, which may allow for more rapid identification of those affected and provide incentive for additional studies.

Genodermatoses associated with melanocytic nevi

Though melanocytic nevi are ubiquitous in the general population, they can also be key cutaneous manifestations of genetic syndromes. We describe genodermatoses associated with melanocytic nevi and discuss their clinical characteristics, cutaneous manifestations, underlying genetics, and, if applicable, guidelines for when genetic testing should be performed. We categorized these genodermatoses based on their association with congenital nevi, acquired nevi, or nevi whose first appearance is unknown. In many cases, the distinctive morphology or distribution of melanocytic nevi can be an important clue that an underlying genetic syndrome is present, allowing both the patient as well as family members to be screened for the more serious complications of their genetic disorder and receive education on potential preventative measures. As we continue to advance our understanding of how various genotypes give rise to the wide spectrum of phenotypes observed in these genodermatoses, we shall be able to better stratify risk and tailor our screening methods to clinically manage the heterogeneous manifestations of genodermatoses among these patients.

A deep learning-based diagnostic tool for identifying various diseases via facial images

With the current health crisis caused by the COVID-19 pandemic, patients have become more anxious about infection, so they prefer not to have direct contact with doctors or clinicians. Lately, medical scientists have confirmed that several diseases exhibit corresponding specific features on the face the face. Recent studies have indicated that computer-aided facial diagnosis can be a promising tool for the automatic diagnosis and screening of diseases from facial images. However, few of these studies used deep learning (DL) techniques. Most of them focused on detecting a single disease, using handcrafted feature extraction methods and conventional machine learning techniques based on individual classifiers trained on small and private datasets using images taken from a controlled environment. This study proposes a novel computer-aided facial diagnosis system called FaceDisNet that uses a new public dataset based on images taken from an unconstrained environment and could be employed for forthcoming comparisons. It detects single and multiple diseases. FaceDisNet is constructed by integrating several spatial deep features from convolutional neural networks of various architectures. It does not depend only on spatial features but also extracts spatial-spectral features. FaceDisNet searches for the fused spatial-spectral feature set that has the greatest impact on the classification. It employs two feature selection techniques to reduce the large dimension of features resulting from feature fusion. Finally, it builds an ensemble classifier based on stacking to perform classification. The performance of FaceDisNet verifies its ability to diagnose single and multiple diseases. FaceDisNet achieved a maximum accuracy of 98.57% and 98% after the ensemble classification and feature selection steps for binary and multiclass classification categories. These results prove that FaceDisNet is a reliable tool and could be employed to avoid the difficulties and complications of manual diagnosis. Also, it can help physicians achieve accurate diagnoses without the need for physical contact with the patients.

CACNA1A Mutations Causing Early Onset Ataxia: Profiling Clinical, Dysmorphic and Structural-Functional Findings

The CACNA1A gene encodes the pore-forming α_1A subunit of the voltage-gated Ca_V2.1 Ca²⁺ channel, essential in neurotransmission, especially in Purkinje cells. Mutations in CACNA1A result in great clinical heterogeneity with progressive symptoms, paroxysmal events or both. During infancy, clinical and neuroimaging findings may be unspecific, and no dysmorphic features have been reported. We present the clinical, radiological and evolutionary features of three patients with congenital ataxia, one of them carrying a new variant. We report the structural localization of variants and their expected functional consequences. There was an improvement in cerebellar syndrome over time despite a cerebellar atrophy progression, inconsistent response to acetazolamide and positive response to methylphenidate. The patients shared distinctive facial gestalt: oval face, prominent forehead, hypertelorism, downslanting palpebral fissures and narrow nasal bridge. The two α_1A affected residues are fully conserved throughout evolution and among the whole human Ca_V channel family. They contribute to the channel pore and the voltage sensor segment. According to structural data analysis and available functional characterization, they are expected to exert gain- (F1394L) and loss-of-function (R1664Q/R1669Q) effect, respectively. Among the CACNA1A-related phenotypes, our results suggest that non-progressive congenital ataxia is associated with developmental delay and dysmorphic features, constituting a recognizable syndromic neurodevelopmental disorder.

Automatic Facial Recognition of Williams-Beuren Syndrome Based on Deep Convolutional Neural Networks

Background: Williams-Beuren syndrome (WBS) is a rare genetic syndrome with a characteristic "elfin" facial gestalt. The "elfin" facial characteristics include a broad forehead, periorbital puffiness, flat nasal bridge, short upturned nose, wide mouth, thick lips, and pointed chin. Recently, deep convolutional neural networks (CNNs) have been successfully applied to facial recognition for diagnosing genetic syndromes. However, there is little research on WBS facial recognition using deep CNNs. Objective: The purpose of this study was to construct an automatic facial recognition model for WBS diagnosis based on deep CNNs. Methods: The study enrolled 104 WBS children, 91 cases with other genetic syndromes, and 145 healthy children. The photo dataset used only one frontal facial photo from each participant. Five face recognition frameworks for WBS were constructed by adopting the VGG-16, VGG-19, ResNet-18, ResNet-34, and MobileNet-V2 architectures, respectively. ImageNet transfer learning was used to avoid over-fitting. The classification performance of the facial recognition models was assessed by five-fold cross validation, and comparison with human experts was performed. Results: The five face recognition frameworks for WBS were constructed. The VGG-19 model achieved the best performance. The accuracy, precision, recall, F1 score, and area under curve (AUC) of the VGG-19 model were 92.7 ± 1.3%, 94.0 ± 5.6%, 81.7 ± 3.6%, 87.2 ± 2.0%, and 89.6 ± 1.3%, respectively. The highest accuracy, precision, recall, F1 score, and AUC of human experts were 82.1, 65.9, 85.6, 74.5, and 83.0%, respectively. The AUCs of each human expert were inferior to the AUCs of the VGG-16 (88.6 ± 3.5%), VGG-19 (89.6 ± 1.3%), ResNet-18 (83.6 ± 8.2%), and ResNet-34 (86.3 ± 4.9%) models. Conclusions: This study highlighted the possibility of using deep CNNs for diagnosing WBS in clinical practice. The facial recognition framework based on VGG-19 could play a prominent role in WBS diagnosis. Transfer learning technology can help to construct facial recognition models of genetic syndromes with small-scale datasets.

Expanding the phenotype of X-linked SSR4-CDG: Connective tissue implications

Signal sequence receptor protein 4 (SSR4) is a subunit of the translocon-associated protein complex, which participates in the translocation of proteins across the endoplasmic reticulum membrane, enhancing the efficiency of N-linked glycosylation. Pathogenic variants in SSR4 cause a congenital disorder of glycosylation: SSR4-congenital disorders of glycosylation (CDG). We describe three SSR4-CDG boys and review the previously reported. All subjects presented with hypotonia, failure to thrive, developmental delay, and dysmorphic traits and showed a type 1 serum sialotransferrin profile, facilitating the diagnosis. Genetic confirmation of this X-linked CDG revealed one de novo hemizygous deletion, one maternally inherited deletion, and one de novo nonsense mutation of SSR4. The present subjects highlight the similarities with a connective tissue disorder (redundant skin, joint laxity, blue sclerae, and vascular tortuosity). The connective tissue problems are relevant, and require preventive rehabilitation measures. As an X-linked disorder, genetic counseling is essential.

De novo SMARCA2 variants clustered outside the helicase domain cause a new recognizable syndrome with intellectual disability and blepharophimosis distinct from Nicolaides-Baraitser syndrome

PURPOSE

Nontruncating variants in SMARCA2, encoding a catalytic subunit of SWI/SNF chromatin remodeling complex, cause Nicolaides-Baraitser syndrome (NCBRS), a condition with intellectual disability and multiple congenital anomalies. Other disorders due to SMARCA2 are unknown.

METHODS

By next-generation sequencing, we identified candidate variants in SMARCA2 in 20 individuals from 18 families with a syndromic neurodevelopmental disorder not consistent with NCBRS. To stratify variant interpretation, we functionally analyzed SMARCA2 variants in yeasts and performed transcriptomic and genome methylation analyses on blood leukocytes.

RESULTS

Of 20 individuals, 14 showed a recognizable phenotype with recurrent features including epicanthal folds, blepharophimosis, and downturned nasal tip along with variable degree of intellectual disability (or blepharophimosis intellectual disability syndrome [BIS]). In contrast to most NCBRS variants, all SMARCA2 variants associated with BIS are localized outside the helicase domains. Yeast phenotype assays differentiated NCBRS from non-NCBRS SMARCA2 variants. Transcriptomic and DNA methylation signatures differentiated NCBRS from BIS and those with nonspecific phenotype. In the remaining six individuals with nonspecific dysmorphic features, clinical and molecular data did not permit variant reclassification.

CONCLUSION

We identified a novel recognizable syndrome named BIS associated with clustered de novo SMARCA2 variants outside the helicase domains, phenotypically and molecularly distinct from NCBRS.

Efficiency of Computer-Aided Facial Phenotyping (DeepGestalt) in Individuals With and Without a Genetic Syndrome: Diagnostic Accuracy Study

Background

Collectively, an estimated 5% of the population have a genetic disease. Many of them feature characteristics that can be detected by facial phenotyping. Face2Gene CLINIC is an online app for facial phenotyping of patients with genetic syndromes. DeepGestalt, the neural network driving Face2Gene, automatically prioritizes syndrome suggestions based on ordinary patient photographs, potentially improving the diagnostic process. Hitherto, studies on DeepGestalt’s quality highlighted its sensitivity in syndromic patients. However, determining the accuracy of a diagnostic methodology also requires testing of negative controls.

Objective

The aim of this study was to evaluate DeepGestalt's accuracy with photos of individuals with and without a genetic syndrome. Moreover, we aimed to propose a machine learning–based framework for the automated differentiation of DeepGestalt’s output on such images.

Methods

Frontal facial images of individuals with a diagnosis of a genetic syndrome (established clinically or molecularly) from a convenience sample were reanalyzed. Each photo was matched by age, sex, and ethnicity to a picture featuring an individual without a genetic syndrome. Absence of a facial gestalt suggestive of a genetic syndrome was determined by physicians working in medical genetics. Photos were selected from online reports or were taken by us for the purpose of this study. Facial phenotype was analyzed by DeepGestalt version 19.1.7, accessed via Face2Gene CLINIC. Furthermore, we designed linear support vector machines (SVMs) using Python 3.7 to automatically differentiate between the 2 classes of photographs based on DeepGestalt's result lists.

Results

We included photos of 323 patients diagnosed with 17 different genetic syndromes and matched those with an equal number of facial images without a genetic syndrome, analyzing a total of 646 pictures. We confirm DeepGestalt’s high sensitivity (top 10 sensitivity: 295/323, 91%). DeepGestalt’s syndrome suggestions in individuals without a craniofacially dysmorphic syndrome followed a nonrandom distribution. A total of 17 syndromes appeared in the top 30 suggestions of more than 50% of nondysmorphic images. DeepGestalt’s top scores differed between the syndromic and control images (area under the receiver operating characteristic [AUROC] curve 0.72, 95% CI 0.68-0.76; P<.001). A linear SVM running on DeepGestalt’s result vectors showed stronger differences (AUROC 0.89, 95% CI 0.87-0.92; P<.001).

Conclusions

DeepGestalt fairly separates images of individuals with and without a genetic syndrome. This separation can be significantly improved by SVMs running on top of DeepGestalt, thus supporting the diagnostic process of patients with a genetic syndrome. Our findings facilitate the critical interpretation of DeepGestalt’s results and may help enhance it and similar computer-aided facial phenotyping tools.

Shared facial phenotype of patients with mucolipidosis type IV: A clinical observation reaffirmed by next generation phenotyping

BACKGROUND

Mucolipidosis type IV (ML-IV) is a rare autosomal-recessive lysosomal storage disease, caused by mutations in MCOLN1. ML-IV manifests with developmental delay, esotropia and corneal clouding. While the clinical phenotype is well-described, the diagnosis of ML-IV is often challenging and elusive.

OBJECTIVE

Our experience with ML-IV patients brought to the clinical observation that they share common and identifiable facial features, not yet described in the literature to date. Here, we utilized a computerized facial analysis tool to establish this association.

METHODS

Using the DeepGestalt algorithm, 50 two-dimensional facial images of ten ML-IV patients were analyzed, and compared to unaffected controls (n = 98) and to individuals affected with other genetic disorders (n = 99). Results were expressed in terms of the area-under-the-curve (AUC) of the receiver-operating-characteristic curve (ROC).

RESULTS

When compared to unaffected cases and to cases diagnosed with syndromes other than ML-IV, the ML-IV cohort showed an AUC of 0.822 (p value < 0.01) and an AUC of 0.885 (p value < 0.001), respectively.

CONCLUSIONS

We describe recognizable facial features typical in patients with ML-IV. Reaffirmed by the DeepGestalt technology, the described common facial phenotype adds to the tools currently available for clinicians and may thus assist in reaching an earlier diagnosis of this rare and underdiagnosed disorder.

Coffin-Siris Syndrome-1: Report of five cases from Asian populations with truncating mutations in the ARID1B gene

BACKGROUND

Pathogenic variants of the ARID1B gene are recognized as the most common cause of Coffin-Siris syndrome (CSS) and also one of the most common causes for intellectual disability (ID). Reported ARID1B variants in association with CSS are mostly from patients of European ancestry.

METHODS

We performed next-generation sequencing to identify pathogenic variants in patients with congenital disorders from the Genetics clinics. The identified variants were validated by Sanger sequencing. Parental samples were tested by Sanger sequencing to determine inheritance status.

RESULTS

Truncating variants in ARID1B were identified in five unrelated Asian patients (one Malay, two Chinese and two Indian) with features of CSS. One was a nonsense mutation which had been documented in three other reports while the other four were novel variants, including two nonsense substitutions and two small deletions resulting in premature termination of translation. Similar to previous reports, all patients have developmental and speech delay, with additional presentations such as ectodermal/facial abnormalities commonly observed in CSS patients.

CONCLUSIONS

Our results unveil ARID1B variants in association with CSS in multiple Southeast Asian ethnic groups, and confirm that variants associated with this disorder tend to be of the truncating type. This finding may provide additional insight into the function of the protein and the disease mechanism.

Clinical versus automated assessments of morphological variants in twins with and without neurodevelopmental disorders

Physical examinations are recommended as part of a comprehensive evaluation for individuals with neurodevelopmental disorders (NDDs), such as autism spectrum disorder (ASD) and attention-deficit/hyperactivity disorder. These examinations should include assessment for morphological variants. Previous studies have shown an increase in morphological variants in individuals with NDDs, particularly ASD, and that these variants may be present in greater amounts in individuals with genetic alterations. Unfortunately, assessment for morphological variants can be subjective and time-consuming, and require a high degree of clinical expertise. Therefore, objective, automated methods of morphological assessment are desirable. This study compared the use of Face2Gene, an automated tool to explore facial morphological variants, to clinical consensus assessment, using a cohort of N = 290 twins enriched for NDDs (n = 135 with NDD diagnoses). Agreement between automated and clinical assessments were satisfactory to complete (78.3-100%). In our twin sample, individuals with NDDs did not have greater numbers of facial morphological variants when compared to those with typical development, nor when controlling for shared genetic and environmental factors within twin pairs. Common facial morphological variants in those with and without NDDs were similar and included thick upper lip vermilion, abnormality of the nasal tip, long face, and upslanted palpebral fissure. We conclude that although facial morphological variants can be assessed reliably in NDDs with automated tools like Face2Gene, clinical utility is limited when just exploring the facial region. Therefore, currently, automated assessments may best complement, rather than replace, in-person clinical assessments.

Dysmorphology in a Genomic Era

Dysmorphology is the practice of defining the morphologic phenotype of syndromic disorders. Genomic sequencing has advanced our understanding of human variation and molecular dysmorphology has evolved in response to the science of relating embryologic developmental implications of abnormal gene signaling pathways to the resultant phenotypic presentation. Machine learning has enabled the application of deep convoluted neural networks to recognize the comparative likeness of these phenotypes relative to the causal genotype or disrupted gene pathway.

Striking phenotypic overlap between Nicolaides-Baraitser and Coffin-Siris syndromes in monozygotic twins with ARID1B intragenic deletion

The chromatin remodeling AT-Rich interaction domain containing 1B protein (ARID1B) also known as BAF-associated factor, 250-KD, B (BAF250B) codified by the ARID1B gene (MIM#614556), is a small subunit of the mammalian SWI/SNF or BAF complex, an ATP-dependent protein machinery which is able to activate or repress gene transcription, allowing protein access to histones through DNA relaxed conformation. ARID1B gene mutations have been associated with two hereditary syndromic conditions, namely Coffin-Siris (CSS, MIM#135900) and Nicolaides-Baraitser syndromes (NCBRS, MIM#601358), characterized by neurodevelopment delay, craniofacial dysmorphisms and skeletal anomalies. Furthermore, intellectual impairment and central nervous system (CNS) alterations, comprising abnormal corpus callosum, have been associated with mutations in this gene. Moreover, ARID1B anomalies resulted to be involved in neoplastic events and Hirschprung disease. Here we report on two monozygotic male twins, displaying clinical appearance strikingly resembling NCBRS and CSS phenotype, who resulted carriers of a novel 6q25.3 microdeletion, encompassing only part of the ARID1B gene. The deleted segment was not inherited from the only parent tested and afflicted the first exons of the gene, coding for protein disordered region. We also provide, for the first time, a review of previously published ARID1B mutated patients with NCBRS and CSS phenotype and a computer-assisted dysmorphology analysis of NCBRS and ARID1B related CSS individuals, through the Face2Gene suite, confirming the existence of highly overlapping facial gestalt of both conditions. The present findings indicate that ARID1B could be considered a contributing gene not only in CSS but also in NCBRS phenotype, although the main gene related to this latter condition is the SMARCA2 gene (MIM#600014), another component of the BAF complex. So, ARID1B study should be considered in such individuals.

Enabling Global Clinical Collaborations on Identifiable Patient Data: The Minerva Initiative

The clinical utility of computational phenotyping for both genetic and rare diseases is increasingly appreciated; however, its true potential is yet to be fully realized. Alongside the growing clinical and research availability of sequencing technologies, precise deep and scalable phenotyping is required to serve unmet need in genetic and rare diseases. To improve the lives of individuals affected with rare diseases through deep phenotyping, global big data interrogation is necessary to aid our understanding of disease biology, assist diagnosis, and develop targeted treatment strategies. This includes the application of cutting-edge machine learning methods to image data. As with most digital tools employed in health care, there are ethical and data governance challenges associated with using identifiable personal image data. There are also risks with failing to deliver on the patient benefits of these new technologies, the biggest of which is posed by data siloing. The Minerva Initiative has been designed to enable the public good of deep phenotyping while mitigating these ethical risks. Its open structure, enabling collaboration and data sharing between individuals, clinicians, researchers and private enterprise, is key for delivering precision public health.

Differentiation of MISSLA and Fanconi anaemia by computer-aided image analysis and presentation of two novel MISSLA siblings

Variants in DONSON were recently identified as the cause of microcephaly, short stature, and limb abnormalities syndrome (MISSLA). The clinical spectra of MISSLA and Fanconi anaemia (FA) strongly overlap. For that reason, some MISSLA patients have been clinically diagnosed with FA. Here, we present the clinical data of siblings with MISSLA featuring a novel DONSON variant and summarize the current literature on MISSLA. Additionally, we perform computer-aided image analysis using the DeepGestalt technology to test how distinct the facial features of MISSLA and FA patients are. We show that MISSLA has a specific facial gestalt. Notably, we find that also FA patients feature facial characteristics recognizable by computer-aided image analysis. We conclude that computer-assisted image analysis improves diagnostic precision in both MISSLA and FA.

Evaluation of Face2Gene using facial images of patients with congenital dysmorphic syndromes recruited in Japan

An increasing number of genetic syndromes present a challenge to clinical geneticists. A deep learning-based diagnosis assistance system, Face2Gene, utilizes the aggregation of "gestalt," comprising data summarizing features of patients' facial images, to suggest candidate syndromes. Because Face2Gene's results may be affected by ethnicity and age at which training facial images were taken, the system performance for patients in Japan is still unclear. Here, we present an evaluation of Face2Gene using the following two patient groups recruited in Japan: Group 1 consisting of 74 patients with 47 congenital dysmorphic syndromes, and Group 2 consisting of 34 patients with Down syndrome. In Group 1, facial recognition failed for 4 of 74 patients, while 13-21 of 70 patients had a diagnosis for which Face2Gene had not been trained. Omitting these 21 patients, for 85.7% (42/49) of the remainder, the correct syndrome was identified within the top 10 suggested list. In Group 2, for the youngest facial images taken for each of the 34 patients, Down syndrome was successfully identified as the highest-ranking condition using images taken from newborns to those aged 25 years. For the oldest facial images taken at ≥20 years in each of 17 applicable patients, Down syndrome was successfully identified as the highest- and second-highest-ranking condition in 82.2% (14/17) and 100% (17/17) of the patients using images taken from 20 to 40 years. These results suggest that Face2Gene in its current format is already useful in suggesting candidate syndromes to clinical geneticists, using patients with congenital dysmorphic syndromes in Japan.

The facial dysmorphology analysis technology in intellectual disability syndromes related to defects in the histones modifiers

Genetic syndromes are frequently associated with Intellectual Disability (ID), as well as craniofacial dysmorphisms. A group of ID syndromes with typical abnormal face related to chromatin remodeling defects, have been recognized, coining the term chromatinopathies. This is a molecular heterogeneous subset of congenital disorders caused by mutations of the various components of the Chromatin-Marking System (CMS), including modifiers of DNA and chromatin remodelers. We performed a phenotypic study on a sample of 120 individuals harboring variants in genes codifying for the histones enzymes, using the DeepGestalt technology. Three experiments (two multiclass comparison experiments and a frontal face-crop analysis) were conducted, analyzing respectively a total of 181 pediatric images in the first comparison experiment and 180 in the second, all individuals belonging predominantly to Caucasian population. The classification results were expressed in terms of the area under the curve (AUC) of the receiver-operating-characteristic curve (ROC). Significant values of AUC and low p-values were registered for all syndromes in the three experiments, in comparison with each other, with other ID syndromes characterized by recognizable craniofacial dysmorphisms and with unaffected controls. Final findings indicated that this group of diseases is characterized by distinctive dysmorphisms, which result pathognomonic. A correct interrogation and use of adequate informatics aids, could become a valid support for clinicians.

Identifying facial phenotypes of genetic disorders using deep learning

Syndromic genetic conditions, in aggregate, affect 8% of the population¹. Many syndromes have recognizable facial features² that are highly informative to clinical geneticists^3-5. Recent studies show that facial analysis technologies measured up to the capabilities of expert clinicians in syndrome identification^6-9. However, these technologies identified only a few disease phenotypes, limiting their role in clinical settings, where hundreds of diagnoses must be considered. Here we present a facial image analysis framework, DeepGestalt, using computer vision and deep-learning algorithms, that quantifies similarities to hundreds of syndromes. DeepGestalt outperformed clinicians in three initial experiments, two with the goal of distinguishing subjects with a target syndrome from other syndromes, and one of separating different genetic subtypes in Noonan syndrome. On the final experiment reflecting a real clinical setting problem, DeepGestalt achieved 91% top-10 accuracy in identifying the correct syndrome on 502 different images. The model was trained on a dataset of over 17,000 images representing more than 200 syndromes, curated through a community-driven phenotyping platform. DeepGestalt potentially adds considerable value to phenotypic evaluations in clinical genetics, genetic testing, research and precision medicine.

Facial recognition software in clinical dysmorphology

PURPOSE OF REVIEW

The current review aims to discuss the incorporation of facial recognition software into the clinical practice of dysmorphology and medical genetics.

RECENT FINDINGS

Facial recognition software has improved the process of generating a differential diagnosis for rare genetic syndromes, and recent publications demonstrate utility in both research and clinical applications. Software programs are freely available to verified medical providers and can be incorporated into routine clinic encounters.

SUMMARY

As facial recognition software capabilities improve, two-dimensional image capture with artificial intelligence interpretation may become a useful tool within many areas of medicine. Geneticists and researchers can use such software to enhance their differential diagnoses, to study similarities and differences between patient cohorts, and to improve the interpretation of genomic data. Pediatricians and subspecialists may use tools to identify patients who may benefit from a genetic evaluation, and educators can use these tools to interest students in the study of dysmorphoplogy and genetic syndromes.

A Dysmorphology Based Systematic Approach Toward Perinatal Genetic Diagnosis in a Fetal Autopsy Series

BACKGROUND

This retrospective study assesses the contribution of genetic disorders in fetuses undergoing postmortem evaluation and the performance of a clinical dysmorphology based systematic approach toward genetic diagnosis.

MATERIALS AND METHODS

Ninety fetuses, including spontaneous losses and terminated pregnancies, underwent a postmortem evaluation including dysmorphological examination, radiological studies, and histopathological examination. Genetic testing including karyotyping, biochemical testing, Sanger sequencing, and exome sequencing were performed selectively.

RESULTS

A genetic etiology was concluded in 48 fetuses (55%). As a standalone test, dysmorphological examination was able to ascertain a definite genetic diagnosis in sixteen cases, histopathology in six; and karyotyping, biochemical testing and exome sequencing in two cases each (Total 28). Additionally, dysmorphology findings indicated possible genetic disorder in 20 cases.

CONCLUSION

Genetic etiologies contribute significantly to fetuses undergoing autopsy in this series. A systematic approach to postmortem fetal evaluation guided by dysmorphological examination provides high diagnostic yield toward perinatal genetic diagnosis.

Failure to shorten the diagnostic delay in two ultra-orphan diseases (mucopolysaccharidosis types I and III): potential causes and implications

Background

Rare diseases are often un- or misdiagnosed for extended periods, resulting in a long diagnostic delay that may significantly add to the burden of the disease. An early diagnosis is particularly essential if a disease-modifying treatment is available. The purpose of this study was to assess the extent of the diagnostic delay in the two ultra-rare diseases, i.e., mucopolysaccharidosis I (MPS I) and III (MPS III), both of which are lysosomal storage disorders with different phenotypic severities (MPS 1 is characterized by the severe Hurler and the more attenuated non-Hurler phenotypes, MPS III is characterized by the severe rapidly progressing (RP) phenotype and more attenuated slowly progressing (SP) phenotype). We investigated whether the diagnostic delay changed over the previous decades.

Results

The diagnostic delay, which is defined as the time between the first visit to a medical doctor for disease-related symptoms and the final diagnosis, was assessed using telephone interviews with patients diagnosed between 1988 and 2017 and/or their parents or legal guardian(s). In addition, the medical charts were reviewed. For MPS I (n = 29), the median diagnostic delay was 8 months (range 1-24 months) for Hurler patients and 28 months (range 2-147 months) for non-Hurler patients. For MPS III (n = 46), the median diagnostic delay was 33 months (range 1-365 months). No difference was observed between the RP and SP phenotypic groups. Comparing the diagnostic delay over time using 5-year time intervals, no reduction in the diagnostic delay was observed for MPS I or MPS III.

Conclusions

In the Netherlands, the time to diagnosis for patients with MPS I and MPS III has not changed between 1988 and 2017, and an extensive delay still exists between the first visit to a medical doctor for disease-related symptoms and the final diagnosis. The numerous campaigns launched to increase awareness, leading to earlier diagnosis of these rare disorders, particularly of MPS I, have failed to achieve their goal. Robust selected screening protocols embedded in national guidelines and newborn screening for disorders that meet the criteria for population screening may be the only effective approaches for reducing the diagnostic delay.

Computer-Aided Recognition of Facial Attributes for Fetal Alcohol Spectrum Disorders

OBJECTIVES

To compare the detection of facial attributes by computer-based facial recognition software of 2-D images against standard, manual examination in fetal alcohol spectrum disorders (FASD).

METHODS

Participants were gathered from the Fetal Alcohol Syndrome Epidemiology Research database. Standard frontal and oblique photographs of children were obtained during a manual, in-person dysmorphology assessment. Images were submitted for facial analysis conducted by the facial dysmorphology novel analysis technology (an automated system), which assesses ratios of measurements between various facial landmarks to determine the presence of dysmorphic features. Manual blinded dysmorphology assessments were compared with those obtained via the computer-aided system.

RESULTS

Areas under the curve values for individual receiver-operating characteristic curves revealed the computer-aided system (0.88 ± 0.02) to be comparable to the manual method (0.86 ± 0.03) in detecting patients with FASD. Interestingly, cases of alcohol-related neurodevelopmental disorder (ARND) were identified more efficiently by the computer-aided system (0.84 ± 0.07) in comparison to the manual method (0.74 ± 0.04). A facial gestalt analysis of patients with ARND also identified more generalized facial findings compared to the cardinal facial features seen in more severe forms of FASD.

CONCLUSIONS

We found there was an increased diagnostic accuracy for ARND via our computer-aided method. As this category has been historically difficult to diagnose, we believe our experiment demonstrates that facial dysmorphology novel analysis technology can potentially improve ARND diagnosis by introducing a standardized metric for recognizing FASD-associated facial anomalies. Earlier recognition of these patients will lead to earlier intervention with improved patient outcomes.

Facial dysmorphism is influenced by ethnic background of the patient and of the evaluator

The evaluation of facial dysmorphism is a critical step toward reaching a diagnostic. The aim of the present study was to evaluate the ability to interpret facial morphology in African children with intellectual disability (ID). First, 10 experienced clinicians (five from Africa and five from Europe) rated gestalt in 127 African non-Down Syndrome (non-DS) patients using either the score 2 for 'clearly dysmorphic', 0 for 'clearly non dysmorphic' or 1 for 'uncertain'. The inter-rater agreement was determined using kappa coefficient. There was only fair agreement between African and European raters (kappa-coefficient = 0.29). Second, we applied the FDNA Face2Gene solution to assess Down Syndrome (DS) faces. Initially, Face2Gene showed a better recognition rate for DS in Caucasian (80%) compared to African (36.8%). We trained the Face2Gene with a set of African DS and non-DS photographs. Interestingly, the recognition in African increased to 94.7%. Thus, training improved the sensitivity of Face2Gene. Our data suggest that human based evaluation is influenced by ethnic background of the evaluator. In addition, computer based evaluation indicates that the ethnic of the patient also influences the evaluation and that training may increase the detection specificity for a particular ethnic.

Array comparative genomic hybridization and genomic sequencing in the diagnostics of the causes of congenital anomalies

The aim of this review is to provide the current state of knowledge about the usefulness of modern genetic technologies in uncovering the causality of isolated and multiple congenital anomalies. Array comparative genomic hybridization and next-generation sequencing have revolutionized the clinical approach to patients with these phenotypes. Both technologies enable early diagnosis, especially in clinically challenging newborn populations, and help to uncover genetic defects associated with various phenotypes. The application of both complementary methods could assist in identifying many variants that may simultaneously be involved in the development of a number of isolated or multiple congenital anomalies. Both technologies carry serious variant misinterpretation risks as well. Therefore, the methods of variant classification and accessible variant databases are mentioned. A useful strategy of clinical genetic testing with the application of both methodologies is presented. Finally, future directions and challenges are briefly commented on in this review.