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

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

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.

The expanding genetic and clinical landscape associated with Meier-Gorlin syndrome

High-throughput sequencing has become a standard first-tier approach for both diagnostics and research-based genetic testing. Consequently, this hypothesis-free testing manner has revealed the true breadth of clinical features for many established genetic disorders, including Meier-Gorlin syndrome (MGORS). Previously known as ear-patella short stature syndrome, MGORS is characterized by growth delay, microtia, and patella hypo/aplasia, as well as genital abnormalities, and breast agenesis in females. Following the initial identification of genetic causes in 2011, a total of 13 genes have been identified to date associated with MGORS. In this review, we summarise the genetic and clinical findings of each gene associated with MGORS and highlight molecular insights that have been made through studying patient variants. We note interesting observations arising across this group of genes as the number of patients has increased, such as the unusually high number of synonymous variants affecting splicing in CDC45 and a subgroup of genes that also cause craniosynostosis. We focus on the complicated molecular genetics for DONSON, where we examine potential genotype-phenotype patterns using the first 3D structural model of DONSON. The canonical role of all proteins associated with MGORS are involved in different stages of DNA replication and in addition to summarising how patient variants impact on this process, we discuss the potential contribution of non-canonical roles of these proteins to the pathophysiology of MGORS.

Image Genetic Analysis and Application Research Based on QRFPR and Other Neural Network-Related SNP Loci

The development of neuroimaging technology and molecular genetics has produced a large amount of imaging genetics data, which has greatly promoted the study of complex mental diseases. However, because the feature dimension of the data is too high, the correlation measure assumes that the data obey Gaussian distribution, and traditional algorithms often cannot explain these two types of data well. This article mainly studies image genetics analysis and its application based on neural network. In this paper, based on the theory and application technology of neural network, the tree structure is established by prior knowledge, that is, each SNP site is used as a leaf node of the tree, and the LD block and genome formed by the linkage imbalance of multiple SNP sites are used as intermediate nodes. Then, the hierarchical relationship of features was introduced. On this basis, a sparse learning method based on tree structure guidance is used to select features from multiple features of multiple SNPs locus regression candidate brain regions. Finally, the identification of SNPs in feature selection is used to predict quantitative traits of brain regions. The distribution of the typical vector values obtained by the algorithm in the experimental data is basically consistent with the distribution of the median of the actual data, and the correlation coefficient obtained is closest to the actual correlation coefficient in the data set. The average correlation coefficient of the algorithm reaches 82.3%, which is about 4.2% higher than the control algorithm. Experimental results show that this method can not only significantly improve the regression performance but also detect the risk gene SNPs loci with spatial clustering features and functional interpretation significance. It is practical and effective to use it in clinical trials.

Evaluation of a computer-based facial dysmorphology analysis algorithm (Face2Gene) using standardized textbook photos

BACKGROUND

Genetic syndromes often have ocular involvement. Ophthalmologists may have difficulty identifying dysmorphic features in genetic syndrome evaluations. We investigated the sensitivity and specificity of Face2Gene (F2G), a digital image analysis software trained on integrating dysmorphic features, by analysing patient photos from genetics textbooks.

METHODS

We analysed all clear facial photos contained within the textbooks Smith's Recognizable Patterns of Human Malformation and Genetic Diseases of the Eye using F2G under standard lighting conditions. Variables captured include colour versus grey scale photo, the gender of the patient (if known), age of the patient (if known), disease categories, diagnosis as listed in the textbook, and whether the disease has ophthalmic involvement (as described in the textbook entries). Any photos rejected by F2G were excluded. We analysed the data for accuracy, sensitivity, and specificity based on disease categories as outlined in Smith's Recognizable Patterns of Malformation.

RESULTS

We analysed 353 photos found within two textbooks. The exact book diagnosis was identified by F2G in 150 (42.5%) entries, and was included in the top three differential diagnoses in 191 (54.1%) entries. F2G is highly sensitive for craniosynostosis syndromes (point estimate [PE] 80.0%, 95% confidence interval [CI] 56.3-94.3%, P = 0.0118) and syndromes with facial defects as a major feature (PE 77.8%, 95% CI 52.4-93.6%, P = 0.0309). F2G was highly specific (PE > 83percentage with P < 0.001) for all disease categories.

CONCLUSIONS

F2G is a useful tool for paediatric ophthalmologists to help build a differential diagnosis when evaluating children with dysmorphic facial features.

The microcephaly gene Donson is essential for progenitors of cortical glutamatergic and GABAergic neurons

Biallelic mutations in DONSON, an essential gene encoding for a replication fork protection factor, were linked to skeletal abnormalities and microcephaly. To better understand DONSON function in corticogenesis, we characterized Donson expression and consequences of conditional Donson deletion in the mouse telencephalon. Donson was widely expressed in the proliferation and differentiation zones of the embryonic dorsal and ventral telencephalon, which was followed by a postnatal expression decrease. Emx1-Cre-mediated Donson deletion in progenitors of cortical glutamatergic neurons caused extensive apoptosis in the early dorsomedial neuroepithelium, thus preventing formation of the neocortex and hippocampus. At the place of the missing lateral neocortex, these mutants exhibited a dorsal extension of an early-generated paleocortex. Targeting cortical neurons at the intermediate progenitor stage using Tbr2-Cre evoked no apparent malformations, whereas Nkx2.1-Cre-mediated Donson deletion in subpallial progenitors ablated 75% of Nkx2.1-derived cortical GABAergic neurons. Thus, the early telencephalic neuroepithelium depends critically on Donson function. Our findings help explain why the neocortex is most severely affected in individuals with DONSON mutations and suggest that DONSON-dependent microcephaly might be associated with so far unrecognized defects in cortical GABAergic neurons. Targeting Donson using an appropriate recombinase is proposed as a feasible strategy to ablate proliferating and nascent cells in experimental research.

The cerebral cortex constitutes the largest part of the mammalian brain and is generated prenatally by highly proliferative progenitors. Genes encoding proteins that are essential for chromosomal segregation, mitotic division, DNA repair, and DNA damage response are frequently mutated in individuals diagnosed with microcephaly, a clinical condition characterized by cerebrocortical hypotrophy. Recent findings suggest that biallelic mutations in DONSON, a replication fork stabilization factor, cause microcephaly and skeletal defects, but this has not been formally tested. Here, we find that Cre-mediated Donson deletion in progenitors of cortical glutamatergic and cortical GABAergic neurons causes extensive programmed cell death at early stages of cortical development in mice. Cell death is induced in the proliferation zones and the postmitotic differentiation zones of the targeted progenitors. Mice undergoing Donson ablation in glutamatergic progenitors do not develop the hippocampus and dorsolateral neocortex, which leads to a dorsal shift of the early-generated piriform cortex. Donson deletion in GABAergic progenitors eliminates the vast majority of GABAergic neurons and oligodendrocyte precursors arising in the targeted lineage. We thus establish that Donson is essential for diverse early telencephalic progenitors. Targeting Donson might be used to kill off highly proliferating cells in experimental and probably therapeutic settings.

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.