GestaltMatcher: Overcoming the limits of rare disease matching using facial phenotypic descriptors

  title={GestaltMatcher: Overcoming the limits of rare disease matching using facial phenotypic descriptors},
  author={Tzung-Chien Hsieh and Aviram Bar-Haim and Shahida Moosa and Nadja Ehmke and Karen W. Gripp and Jean Tori Pantel and Magdalena Danyel and Martin Atta Mensah and Denise Horn and Stanislav Rosnev and Nicole Fleischer and Guilherme Bonini and Alexander Hustinx and Alexander Schmid and Alexej Knaus and Behnam Javanmardi and Hannah Klinkhammer and Hellen Lesmann and Sugirthan Sivalingam and Tom Kamphans and Wolfgang Meiswinkel and Fr{\'e}d{\'e}ric Ebstein and Elke Kr{\"u}ger and S{\'e}bastien K{\"u}ry and St{\'e}phane B{\'e}zieau and Axel Schmidt and Sophia Peters and Hartmut Engels and Elisabeth Mangold and Martina Krei{\ss} and Kirsten Cremer and Claudia Perne and Regina C. Betz and Tim Bender and Kathrin Grundmann-Hauser and Tobias B Haack and Matias Wagner and Theresa Brunet and Heidi Beate Bentzen and Luisa Averdunk and Kimberly Christine Coetzer and Gholson J. Lyon and Malte Spielmann and Christian Patrick Schaaf and Stefan Mundlos and Markus M. N{\"o}then and Peter M. Krawitz},
The majority of monogenic disorders cause craniofacial abnormalities with characteristic facial morphology. These disorders can be diagnosed more quickly by using computer-aided next-generation phenotyping tools, such as DeepGestalt. These tools have learned to associate facial phenotypes with the underlying syndrome through training on thousands of patient photographs. However, this "supervised" approach means that diagnoses are only possible if they were part of the training set. To improve… 
KBG Syndrome: Prospective Videoconferencing and Use of AI-driven Facial Phenotyping in 25 New Patients
A novel protocol for collection and reporting of data is created, including prospectively interviewing individuals and their families throughout eight countries via videoconferencing by a single clinician, and a set of recommendations regarding diagnostic and treatment approaches for KBG syndrome are provided.
Neural networks for classification and image generation of aging in genetic syndromes
Comparison of saliency maps revealed that key facial features learned by the neural network differed slightly with respect to age, and joint training real images with multiple different types of fake images created by a generative adversarial network showed up to 3.25% accuracy gain in classification accuracy.


Identifying facial phenotypes of genetic disorders using deep learning
A facial image analysis framework, DeepGestalt, is presented, using computer vision and deep-learning algorithms, that quantifies similarities to hundreds of syndromes and potentially adds considerable value to phenotypic evaluations in clinical genetics, genetic testing, research and precision medicine.
Diagnostically relevant facial gestalt information from ordinary photos
An automatic approach that implements recent developments in computer vision extracts phenotypic information from ordinary non-clinical photographs and models human facial dysmorphisms in a multidimensional 'Clinical Face Phenotype Space' that provides a novel method for inferring causative genetic variants from clinical sequencing data through functional genetic pathway comparisons.
Next-generation phenotyping using computer vision algorithms in rare genomic neurodevelopmental disorders
The results show that analysis of facial photos can be used to detect previously unknown facial gestalts for novel ID syndromes, which will facilitate both clinical and molecular diagnosis of rare and novel syndrome.
Identification of dysmorphic syndromes using landmark-specific local texture descriptors
This work presents a general framework for the detection of genetic disorders from facial pictures, combining geometrical and texture features, and computes optimal local image filters and soft neighborhood weighting matrices that enhance the discriminative ability of the system.
Efficiency of Computer-Aided Facial Phenotyping (DeepGestalt) in Individuals With and Without a Genetic Syndrome: Diagnostic Accuracy Study
A machine learning–based framework for the automated differentiation of DeepGestalt’s output on photos of individuals with and without a genetic syndrome is proposed and may help enhance it and similar computer-aided facial phenotyping tools.
Next generation phenotyping in Emanuel and Pallister‐Killian syndrome using computer‐aided facial dysmorphology analysis of 2D photos
The results show that NPG is able to help in the clinic, and could reduce the time patients spend in diagnostic odyssey, and it also helps to differentiate ES or PKS from each other and other patients with small supernumerary marker chromosomes, especially in countries with no access to more sophisticated genetic approaches apart from banding cytogenetics.
GeneMatcher Aids in the Identification of a New Malformation Syndrome with Intellectual Disability, Unique Facial Dysmorphisms, and Skeletal and Connective Tissue Abnormalities Caused by De Novo Variants in HNRNPK
This report demonstrates that new Web‐based approaches can be effective in helping investigators solve exome sequencing projects, and also highlights the newer paradigm of “reverse phenotyping,” where characterization of syndromic features follows the identification of genetic variants.
The Discovery of a LEMD2-Associated Nuclear Envelopathy with Early Progeroid Appearance Suggests Advanced Applications for AI-Driven Facial Phenotyping.
It is shown that a recurrent de novo mutation in LEMD2 causes a nuclear envelopathy whose prognosis in adolescence is relatively good in comparison to that of classical Hutchinson-Gilford progeria syndrome, and it is suggested that the application of artificial intelligence to the analysis of patient images can facilitate the discovery of new genetic disorders.
Bi-allelic TMEM94 Truncating Variants Are Associated with Neurodevelopmental Delay, Congenital Heart Defects, and Distinct Facial Dysmorphism.
The study suggests the genetic etiology of a recognizable dysmorphic syndrome with NDD and CHD and highlights the role of TMEM94 in early development.
De Novo and Inherited Pathogenic Variants in KDM3B Cause Intellectual Disability, Short Stature, and Facial Dysmorphism.
It is shown that individuals with a pathogenic variant in KDM3B have a facial gestalt, and that they show significant facial similarity compared to control individuals with ID, a syndrome characterized by ID, short stature, and facial dysmorphism.