Evaluating Face2Gene as a Tool to Identify Cornelia de Lange Syndrome by Facial Phenotypes
Characteristic or classic phenotype of Cornelia de Lange syndrome (CdLS) is associated with a recognisable facial pattern. However, the heterogeneity in causal genes and the presence of overlapping syndromes have made it increasingly difficult to diagnose only by clinical features. DeepGestalt techn...
Main Authors: | , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-02-01
|
Series: | International Journal of Molecular Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/1422-0067/21/3/1042 |
id |
doaj-331f54f77c4743ba89e27ef88d573b9d |
---|---|
record_format |
Article |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ana Latorre-Pellicer Ángela Ascaso Laura Trujillano Marta Gil-Salvador Maria Arnedo Cristina Lucia-Campos Rebeca Antoñanzas-Pérez Iñigo Marcos-Alcalde Ilaria Parenti Gloria Bueno-Lozano Antonio Musio Beatriz Puisac Frank J. Kaiser Feliciano J. Ramos Paulino Gómez-Puertas Juan Pié |
spellingShingle |
Ana Latorre-Pellicer Ángela Ascaso Laura Trujillano Marta Gil-Salvador Maria Arnedo Cristina Lucia-Campos Rebeca Antoñanzas-Pérez Iñigo Marcos-Alcalde Ilaria Parenti Gloria Bueno-Lozano Antonio Musio Beatriz Puisac Frank J. Kaiser Feliciano J. Ramos Paulino Gómez-Puertas Juan Pié Evaluating Face2Gene as a Tool to Identify Cornelia de Lange Syndrome by Facial Phenotypes International Journal of Molecular Sciences cornelia de lange syndrome face2gene facial recognition deep learning |
author_facet |
Ana Latorre-Pellicer Ángela Ascaso Laura Trujillano Marta Gil-Salvador Maria Arnedo Cristina Lucia-Campos Rebeca Antoñanzas-Pérez Iñigo Marcos-Alcalde Ilaria Parenti Gloria Bueno-Lozano Antonio Musio Beatriz Puisac Frank J. Kaiser Feliciano J. Ramos Paulino Gómez-Puertas Juan Pié |
author_sort |
Ana Latorre-Pellicer |
title |
Evaluating Face2Gene as a Tool to Identify Cornelia de Lange Syndrome by Facial Phenotypes |
title_short |
Evaluating Face2Gene as a Tool to Identify Cornelia de Lange Syndrome by Facial Phenotypes |
title_full |
Evaluating Face2Gene as a Tool to Identify Cornelia de Lange Syndrome by Facial Phenotypes |
title_fullStr |
Evaluating Face2Gene as a Tool to Identify Cornelia de Lange Syndrome by Facial Phenotypes |
title_full_unstemmed |
Evaluating Face2Gene as a Tool to Identify Cornelia de Lange Syndrome by Facial Phenotypes |
title_sort |
evaluating face2gene as a tool to identify cornelia de lange syndrome by facial phenotypes |
publisher |
MDPI AG |
series |
International Journal of Molecular Sciences |
issn |
1422-0067 |
publishDate |
2020-02-01 |
description |
Characteristic or classic phenotype of Cornelia de Lange syndrome (CdLS) is associated with a recognisable facial pattern. However, the heterogeneity in causal genes and the presence of overlapping syndromes have made it increasingly difficult to diagnose only by clinical features. DeepGestalt technology, and its app Face2Gene, is having a growing impact on the diagnosis and management of genetic diseases by analysing the features of affected individuals. Here, we performed a phenotypic study on a cohort of 49 individuals harbouring causative variants in known CdLS genes in order to evaluate Face2Gene utility and sensitivity in the clinical diagnosis of CdLS. Based on the profile images of patients, a diagnosis of CdLS was within the top five predicted syndromes for 97.9% of our cases and even listed as first prediction for 83.7%. The age of patients did not seem to affect the prediction accuracy, whereas our results indicate a correlation between the clinical score and affected genes. Furthermore, each gene presents a different pattern recognition that may be used to develop new neural networks with the goal of separating different genetic subtypes in CdLS. Overall, we conclude that computer-assisted image analysis based on deep learning could support the clinical diagnosis of CdLS. |
topic |
cornelia de lange syndrome face2gene facial recognition deep learning |
url |
https://www.mdpi.com/1422-0067/21/3/1042 |
work_keys_str_mv |
AT analatorrepellicer evaluatingface2geneasatooltoidentifycorneliadelangesyndromebyfacialphenotypes AT angelaascaso evaluatingface2geneasatooltoidentifycorneliadelangesyndromebyfacialphenotypes AT lauratrujillano evaluatingface2geneasatooltoidentifycorneliadelangesyndromebyfacialphenotypes AT martagilsalvador evaluatingface2geneasatooltoidentifycorneliadelangesyndromebyfacialphenotypes AT mariaarnedo evaluatingface2geneasatooltoidentifycorneliadelangesyndromebyfacialphenotypes AT cristinaluciacampos evaluatingface2geneasatooltoidentifycorneliadelangesyndromebyfacialphenotypes AT rebecaantonanzasperez evaluatingface2geneasatooltoidentifycorneliadelangesyndromebyfacialphenotypes AT inigomarcosalcalde evaluatingface2geneasatooltoidentifycorneliadelangesyndromebyfacialphenotypes AT ilariaparenti evaluatingface2geneasatooltoidentifycorneliadelangesyndromebyfacialphenotypes AT gloriabuenolozano evaluatingface2geneasatooltoidentifycorneliadelangesyndromebyfacialphenotypes AT antoniomusio evaluatingface2geneasatooltoidentifycorneliadelangesyndromebyfacialphenotypes AT beatrizpuisac evaluatingface2geneasatooltoidentifycorneliadelangesyndromebyfacialphenotypes AT frankjkaiser evaluatingface2geneasatooltoidentifycorneliadelangesyndromebyfacialphenotypes AT felicianojramos evaluatingface2geneasatooltoidentifycorneliadelangesyndromebyfacialphenotypes AT paulinogomezpuertas evaluatingface2geneasatooltoidentifycorneliadelangesyndromebyfacialphenotypes AT juanpie evaluatingface2geneasatooltoidentifycorneliadelangesyndromebyfacialphenotypes |
_version_ |
1725034356385251328 |
spelling |
doaj-331f54f77c4743ba89e27ef88d573b9d2020-11-25T01:42:55ZengMDPI AGInternational Journal of Molecular Sciences1422-00672020-02-01213104210.3390/ijms21031042ijms21031042Evaluating Face2Gene as a Tool to Identify Cornelia de Lange Syndrome by Facial PhenotypesAna Latorre-Pellicer0Ángela Ascaso1Laura Trujillano2Marta Gil-Salvador3Maria Arnedo4Cristina Lucia-Campos5Rebeca Antoñanzas-Pérez6Iñigo Marcos-Alcalde7Ilaria Parenti8Gloria Bueno-Lozano9Antonio Musio10Beatriz Puisac11Frank J. Kaiser12Feliciano J. Ramos13Paulino Gómez-Puertas14Juan Pié15Unit of Clinical Genetics and Functional Genomics, Department of Pharmacology-Physiology, School of Medicine, University of Zaragoza, CIBERER-GCV02 and ISS-Aragon, E-50009 Zaragoza, SpainDepartment of Paediatrics, Hospital Clínico Universitario “Lozano Blesa”, E-50009 Zaragoza, SpainDepartment of Paediatrics, Hospital Clínico Universitario “Lozano Blesa”, E-50009 Zaragoza, SpainUnit of Clinical Genetics and Functional Genomics, Department of Pharmacology-Physiology, School of Medicine, University of Zaragoza, CIBERER-GCV02 and ISS-Aragon, E-50009 Zaragoza, SpainUnit of Clinical Genetics and Functional Genomics, Department of Pharmacology-Physiology, School of Medicine, University of Zaragoza, CIBERER-GCV02 and ISS-Aragon, E-50009 Zaragoza, SpainUnit of Clinical Genetics and Functional Genomics, Department of Pharmacology-Physiology, School of Medicine, University of Zaragoza, CIBERER-GCV02 and ISS-Aragon, E-50009 Zaragoza, SpainUnit of Clinical Genetics and Functional Genomics, Department of Pharmacology-Physiology, School of Medicine, University of Zaragoza, CIBERER-GCV02 and ISS-Aragon, E-50009 Zaragoza, SpainMolecular Modelling Group, Centro de Biología Molecular Severo Ochoa, CBMSO (CSIC-UAM), E-28049 Madrid, SpainSection for Functional Genetics, Institute of Human Genetics, University of Lübeck, 23562 Lübeck, GermanyDepartment of Paediatrics, Hospital Clínico Universitario “Lozano Blesa”, E-50009 Zaragoza, SpainIstituto di Ricerca Genetica e Biomedica, Consiglio Nazionale delle Ricerche, I-56124 Pisa, ItalyUnit of Clinical Genetics and Functional Genomics, Department of Pharmacology-Physiology, School of Medicine, University of Zaragoza, CIBERER-GCV02 and ISS-Aragon, E-50009 Zaragoza, SpainSection for Functional Genetics, Institute of Human Genetics, University of Lübeck, 23562 Lübeck, GermanyUnit of Clinical Genetics and Functional Genomics, Department of Pharmacology-Physiology, School of Medicine, University of Zaragoza, CIBERER-GCV02 and ISS-Aragon, E-50009 Zaragoza, SpainMolecular Modelling Group, Centro de Biología Molecular Severo Ochoa, CBMSO (CSIC-UAM), E-28049 Madrid, SpainUnit of Clinical Genetics and Functional Genomics, Department of Pharmacology-Physiology, School of Medicine, University of Zaragoza, CIBERER-GCV02 and ISS-Aragon, E-50009 Zaragoza, SpainCharacteristic or classic phenotype of Cornelia de Lange syndrome (CdLS) is associated with a recognisable facial pattern. However, the heterogeneity in causal genes and the presence of overlapping syndromes have made it increasingly difficult to diagnose only by clinical features. DeepGestalt technology, and its app Face2Gene, is having a growing impact on the diagnosis and management of genetic diseases by analysing the features of affected individuals. Here, we performed a phenotypic study on a cohort of 49 individuals harbouring causative variants in known CdLS genes in order to evaluate Face2Gene utility and sensitivity in the clinical diagnosis of CdLS. Based on the profile images of patients, a diagnosis of CdLS was within the top five predicted syndromes for 97.9% of our cases and even listed as first prediction for 83.7%. The age of patients did not seem to affect the prediction accuracy, whereas our results indicate a correlation between the clinical score and affected genes. Furthermore, each gene presents a different pattern recognition that may be used to develop new neural networks with the goal of separating different genetic subtypes in CdLS. Overall, we conclude that computer-assisted image analysis based on deep learning could support the clinical diagnosis of CdLS.https://www.mdpi.com/1422-0067/21/3/1042cornelia de lange syndromeface2genefacial recognitiondeep learning |