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

Pascolini, Giulia; Fleischer, Nicole; Ferraris, Alessandro; Majore, Silvia; Grammatico, Paola

doi:10.1038/s10038-019-0598-0

Cited by 9 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A minor facial similarity was registered in the SETD5-KdVS comparison. All three conditions were distinctly recognized by the DeepGestalt technology and the obtained results seem to indicate that this group of disorders are all characterized by distinctive dysmorphisms, confirming what has recently been illustrated in a clinical phenotyping study on ID syndromes related to mutations in histones modifiers [14] .…”

Section: Discussionsupporting

confidence: 86%

DeepGestalt analysis of the SETD5-associated intellectual disability syndrome

Pascolini¹

2020

JTGG

Self Cite

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

Section: Discussionsupporting

confidence: 86%

DeepGestalt analysis of the SETD5-associated intellectual disability syndrome

Pascolini¹

2020

JTGG

Self Cite

View full text Add to dashboard Cite

show abstract

“…Initial studies have evaluated the ability of this network to correctly detect a syndrome in a patient image, suggesting good sensitivity (eg, [14][15][16][17][18][19][20][21]). It has been shown that such tools can also be trained for yet unknown syndromes by demonstrating that a new syndrome has a specific gestalt that can be distinguished from other syndromes (eg, [22][23][24][25][26][27][28][29]). DeepGestalt can only detect a specific syndrome if a minimum number of images of that syndrome is included in the training set.…”

Section: Introductionmentioning

confidence: 99%

Validation of 3 Computer-Aided Facial Phenotyping Tools (DeepGestalt, GestaltMatcher, and D-Score): Comparative Diagnostic Accuracy Study

Reiter,

Pantel,

Danyel

et al. 2024

J Med Internet Res

View full text Add to dashboard Cite

Background While characteristic facial features provide important clues for finding the correct diagnosis in genetic syndromes, valid assessment can be challenging. The next-generation phenotyping algorithm DeepGestalt analyzes patient images and provides syndrome suggestions. GestaltMatcher matches patient images with similar facial features. The new D-Score provides a score for the degree of facial dysmorphism. Objective We aimed to test state-of-the-art facial phenotyping tools by benchmarking GestaltMatcher and D-Score and comparing them to DeepGestalt. Methods Using a retrospective sample of 4796 images of patients with 486 different genetic syndromes (London Medical Database, GestaltMatcher Database, and literature images) and 323 inconspicuous control images, we determined the clinical use of D-Score, GestaltMatcher, and DeepGestalt, evaluating sensitivity; specificity; accuracy; the number of supported diagnoses; and potential biases such as age, sex, and ethnicity. Results DeepGestalt suggested 340 distinct syndromes and GestaltMatcher suggested 1128 syndromes. The top-30 sensitivity was higher for DeepGestalt (88%, SD 18%) than for GestaltMatcher (76%, SD 26%). DeepGestalt generally assigned lower scores but provided higher scores for patient images than for inconspicuous control images, thus allowing the 2 cohorts to be separated with an area under the receiver operating characteristic curve (AUROC) of 0.73. GestaltMatcher could not separate the 2 classes (AUROC 0.55). Trained for this purpose, D-Score achieved the highest discriminatory power (AUROC 0.86). D-Score’s levels increased with the age of the depicted individuals. Male individuals yielded higher D-scores than female individuals. Ethnicity did not appear to influence D-scores. Conclusions If used with caution, algorithms such as D-score could help clinicians with constrained resources or limited experience in syndromology to decide whether a patient needs further genetic evaluation. Algorithms such as DeepGestalt could support diagnosing rather common genetic syndromes with facial abnormalities, whereas algorithms such as GestaltMatcher could suggest rare diagnoses that are unknown to the clinician in patients with a characteristic, dysmorphic face.

show abstract

“…20,[22][23][24][25][26] However, these techniques have been widely applied to analyze syndromic genetic conditions that have easily recognizable effects on facial morphologic features compared with the more subtle facial features of patients with CAH. [27][28][29][30][31] at the hospital pediatric clinics by consecutive sampling. Hispanic ethnicity was classified by the investigators.…”

Section: Introductionmentioning

confidence: 99%

“…Earlier facial analyses have relied on sets of manually engineered features, such as facial width-to-height ratio, masculinity index, or Euclidean distances between facial landmarks . However, these techniques have been widely applied to analyze syndromic genetic conditions that have easily recognizable effects on facial morphologic features compared with the more subtle facial features of patients with CAH …”

Section: Introductionmentioning

confidence: 99%

Assessment of Facial Morphologic Features in Patients With Congenital Adrenal Hyperplasia Using Deep Learning

et al. 2020

View full text Add to dashboard Cite

IMPORTANCECongenital adrenal hyperplasia (CAH) is the most common primary adrenal insufficiency in children, involving excess androgens secondary to disrupted steroidogenesis as early as the seventh gestational week of life. Although structural brain abnormalities are seen in CAH, little is known about facial morphology. OBJECTIVE To investigate differences in facial morphologic features between patients with CAH and control individuals with use of machine learning. DESIGN, SETTING, AND PARTICIPANTS This cross-sectional study was performed at a pediatric tertiary center in Southern California, from November 2017 to December 2019. Patients younger than 30 years with a biochemical diagnosis of classical CAH due to 21-hydroxylase deficiency and otherwise healthy controls were recruited from the clinic, and face images were acquired. Additional controls were selected from public face image data sets. MAIN OUTCOMES AND MEASURES The main outcome was prediction of CAH, as performed by machine learning (linear discriminant analysis, random forests, deep neural networks). Handcrafted features and learned representations were studied for CAH score prediction, and deformation analysis of facial landmarks and regionwise analyses were performed. A 6-fold cross-validation strategy was used to avoid overfitting and bias. RESULTS The study included 102 patients with CAH (62 [60.8%] female; mean [SD] age, 11.6 [7.1] years) and 59 controls (30 [50.8%] female; mean [SD] age, 9.0 [5.2] years) from the clinic and 85 controls (48 [60%] female; age, <29 years) from face databases. With use of deep neural networks,a mean (SD) AUC of 92% (3%) was found for accurately predicting CAH over 6 folds. With use of classical machine learning and handcrafted facial features, mean (SD) AUCs of 86% (5%) in linear discriminant analysis and 83% (3%) in random forests were obtained for predicting CAH over 6 folds.There was a deviation of facial features between groups using deformation fields generated from facial landmark templates. Regionwise analysis and class activation maps (deep learning of regions) revealed that the nose and upper face were most contributory (mean [SD] AUC: 69% [17%] and 71%[13%], respectively). CONCLUSIONS AND RELEVANCEThe findings suggest that facial morphologic features in patients with CAH is distinct and that deep learning can discover subtle facial features to predict CAH.Longitudinal study of facial morphology as a phenotypic biomarker may help expand understanding of adverse lifespan outcomes for patients with CAH.

show abstract

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

Cited by 9 publications

References 25 publications

DeepGestalt analysis of the SETD5-associated intellectual disability syndrome

DeepGestalt analysis of the SETD5-associated intellectual disability syndrome

Validation of 3 Computer-Aided Facial Phenotyping Tools (DeepGestalt, GestaltMatcher, and D-Score): Comparative Diagnostic Accuracy Study

Assessment of Facial Morphologic Features in Patients With Congenital Adrenal Hyperplasia Using Deep Learning

Contact Info

Product

Resources

About