Computer-aided Facial Analysis in Diagnosing Dysmorphic Syndromes in Indian Children

Narayanan, Dhanya Lakshmi; Ranganath, Prajnya; Aggarwal, Shagun; Dalal, Ashwin; Phadke, Shubha R.; Mandal, Kausik

doi:10.1007/s13312-019-1682-4

Cited by 21 publications

(24 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Studies of more recent versions of DeepGestalt suggested that ethnicity had no major influence on its sensitivity [ 26 , 29 ]. In our set of syndromic images, DeepGestalt’s sensitivity is remarkably high, which is in line with the previous studies highlighting DeepGestalt’s good general sensitivity [ 11 , 36 , 42 ]. This high sensitivity of DeepGestalt was confirmed for both groups of images, those of White persons and those of persons of other ethnicities.…”

Section: Discussionsupporting

confidence: 92%

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

Pantel¹,

Hajjir²,

Danyel³

et al. 2020

J Med Internet Res

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionsupporting

confidence: 92%

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

Pantel¹,

Hajjir²,

Danyel³

et al. 2020

J Med Internet Res

View full text Add to dashboard Cite

show abstract

“…Studies of more recent versions of DeepGestalt suggested that ethnicity had no major influence on its sensitivity [26,29]. In our set of syndromic images, DeepGestalt's sensitivity is remarkably high, which is in line with the previous studies highlighting DeepGestalt's good general sensitivity [11,36,42]. This high sensitivity of DeepGestalt was confirmed for both groups of images, those of White persons and those of persons of other ethnicities.…”

Section: Potential Confounderssupporting

confidence: 90%

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

Pantel¹,

Hajjir²,

Danyel³

et al. 2020

Preprint

View full text Add to dashboard Cite

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; <i>P</i><.001). A linear SVM running on DeepGestalt’s result vectors showed stronger differences (AUROC 0.89, 95% CI 0.87-0.92; <i>P</i><.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.

show abstract

“…Furthermore, the DeepGestalt technology has been demonstrated to not be influenced by ethnicity, according to previously published works, which analyzed the facial features of individuals with different ancestries and affected by diverse genetic conditions [15][16][17] . These studies showed that the technology identifies facial gestalt independently from an individual' s ancestry.…”

Section: Discussionmentioning

confidence: 99%

DeepGestalt analysis of the SETD5-associated intellectual disability syndrome

Pascolini¹

2020

JTGG

View full text Add to dashboard Cite

Aim: This is the first computer-assisted study focused on the craniofacial features of the intellectual disability (ID)/ developmental delay (DD) syndrome related to haploinsufficiency of the SETD5 gene (SET domain-containing protein 5, MIM#615743), which is a chromatin regulator. The purpose of this novel research is to better delineate the facial phenotype of this condition and identify the associated dysmorphic features to consider for clinical diagnosis. Methods: A total of 18 2D frontal images of previously published pediatric individuals (aged 1-14 years, Caucasian ethnicity) with SETD5 mutations (SETD5, cohort 1) were uploaded to the RESEARCH application of the Face2Gene online platform (V.19.1.3) (FDNA Inc., Boston, MA, USA). Images from this group of patients were compared with 36 photos of individuals with two other known chromatin disorders, specifically KBG (KBGS, cohort 2, 18 images) and Koolen-de Vries syndromes (KdVS, cohort 3, 18 images), which share with the SETD5-related ID syndrome a very similar facial gestalt and peculiar dysmorphisms. An additional cohort of 18 unaffected controls that were matched for age and ethnicity (Ctrl., controls, cohort 4) was also included in the comparison experiment. Results: Results obtained from the binary comparison analysis were expressed in terms of Area Under the Curve and its Receiver Operating Characteristic curve for aggregated splits. A high facial overlap between the SETD5-related phenotype and KBGS was demonstrated. Other conditions considered for the study were well recognized by the system and differentiated using the unaffected controls. Conclusion: This study confirms the presence of distinctive dysmorphic features that characterize the SETD5-related facial phenotype, providing observations about its possible role in facial morphogenesis.

show abstract

Computer-aided Facial Analysis in Diagnosing Dysmorphic Syndromes in Indian Children

Cited by 21 publications

References 6 publications

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

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

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

DeepGestalt analysis of the SETD5-associated intellectual disability syndrome

Contact Info

Product

Resources

About