Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Using deep-neural-network-driven facial recognition to identify distinct Kabuki syndrome 1 and 2 gestalt

Abstract

Kabuki syndrome (KS) is a rare genetic disorder caused by mutations in two major genes, KMT2D and KDM6A, that are responsible for Kabuki syndrome 1 (KS1, OMIM147920) and Kabuki syndrome 2 (KS2, OMIM300867), respectively. We lack a description of clinical signs to distinguish KS1 and KS2. We used facial morphology analysis to detect any facial morphological differences between the two KS types. We used a facial-recognition algorithm to explore any facial morphologic differences between the two types of KS. We compared several image series of KS1 and KS2 individuals, then compared images of those of Caucasian origin only (12 individuals for each gene) because this was the main ethnicity in this series. We also collected 32 images from the literature to amass a large series. We externally validated results obtained by the algorithm with evaluations by trained clinical geneticists using the same set of pictures. Use of the algorithm revealed a statistically significant difference between each group for our series of images, demonstrating a different facial morphotype between KS1 and KS2 individuals (mean area under the receiver operating characteristic curve = 0.85 [p = 0.027] between KS1 and KS2). The algorithm was better at discriminating between the two types of KS with images from our series than those from the literature (p = 0.0007). Clinical geneticists trained to distinguished KS1 and KS2 significantly recognised a unique facial morphotype, which validated algorithm findings (p = 1.6e−11). Our deep-neural-network-driven facial-recognition algorithm can reveal specific composite gestalt images for KS1 and KS2 individuals.

This is a preview of subscription content, access via your institution

Access options

Buy article

Get time limited or full article access on ReadCube.

$32.00

All prices are NET prices.

Fig. 1: On the left is the score distribution for KDM6A vs KMT2D, and on the right is the ROC curve obtained by using DeepGestalt analysis.
Fig. 2: On the left is the score distribution for KDM6A vs KMT2D, and on the right is the ROC curve obtained by using DeepGestalt analysis.
Fig. 3:  On the left is the composite gestalt based upon 17 KDM6A individual’s pictures form our collaborative dataset, and on the right is the composite gestalt based upon 17 KMT2D individual’s pictures from our collaborative dataset.
Fig. 4: Distribution of scores for each subgroup of clinicians in differentiating between KS1 and KS2 individuals (n = 60).

Data availability

The data (patient’s facial pictures) that supports the findings of this study are available from the French research program PHRC AOM-09-070 (ClinicalTrials. gov identifier: NCT01314534), but restrictions apply to the availability of these data, which were used under license for the current study, and so are not publicly available. Data are however available from the authors upon reasonable request and with permission of patients and physicians in charge of the patients.

References

  1. Ng SB, Bigham AW, Buckingham KJ, Hannibal MC, McMillin MJ, Gildersleeve HI, et al. Exome sequencing identifies MLL2 mutations as a cause of Kabuki syndrome. Nat Genet. 2010;42:790–3.

    Article  CAS  Google Scholar 

  2. Lederer D, Grisart B, Digilio MC, Benoit V, Crespin M, Ghariani SC, et al. Deletion of KDM6A, a Histone Demethylase Interacting with MLL2, in Three Patients with Kabuki Syndrome. Am J Hum Genet. 2012;90:119–24.

    Article  CAS  Google Scholar 

  3. Miyake N, Mizuno S, Okamoto N, Ohashi H, Shiina M, Ogata K, et al. KDM6A point mutations cause Kabuki syndrome. Hum Mutat. 2013;34:108–10.

    Article  CAS  Google Scholar 

  4. Bögershausen N, Gatinois V, Riehmer V, Kayserili H, Becker J, Thoenes M, et al. Mutation Update for Kabuki Syndrome Genes KMT2D and KDM6A and Further Delineation of X-Linked Kabuki Syndrome Subtype 2. Hum Mutat. 2016;37:847–64.

    Article  Google Scholar 

  5. Gilissen C, Hehir-Kwa JY, Thung DT, van de Vorst M, van Bon BWM, Willemsen MH, et al. Genome sequencing identifies major causes of severe intellectual disability. Nature. 2014;511:344–7.

    Article  CAS  Google Scholar 

  6. Zou J, Huss M, Abid A, Mohammadi P, Torkamani A, Telenti A. A primer on deep learning in genomics. Nat Genet. 2018. https://doi.org/10.1038/s41588-018-0295-5

  7. Liehr T, Acquarola N, Pyle K, St-Pierre S, Rinholm M, Bar O, et al. Next generation phenotyping in Emanuel and Pallister-Killian syndrome using computer-aided facial dysmorphology analysis of 2D photos. Clin Genet. 2018;93:378–81.

    Article  CAS  Google Scholar 

  8. Basel-Vanagaite L, Wolf L, Orin M, Larizza L, Gervasini C, Krantz ID, et al. Recognition of the Cornelia de Lange syndrome phenotype with facial dysmorphology novel analysis. Clin Genet. 2016;89:557–63.

    Article  CAS  Google Scholar 

  9. Hadj-Rabia S, Schneider H, Navarro E, Klein O, Kirby N, Huttner K, et al. Automatic recognition of the XLHED phenotype from facial images. Am J Med Genet A. 2017;173:2408–14.

    Article  CAS  Google Scholar 

  10. Hurst ACE. Facial recognition software in clinical dysmorphology. Curr Opin Pediatr. 2018;30:701–6.

    Article  Google Scholar 

  11. Pantel JT, Zhao M, Mensah MA, Hajjir N, Hsieh T-C, Hanani Y, et al. Advances in computer-assisted syndrome recognition by the example of inborn errors of metabolism. J Inherit Metab Dis. 2018;41:533–9.

    Article  Google Scholar 

  12. Dudding-Byth T, Baxter A, Holliday EG, Hackett A, O’Donnell S, White SM, et al. Computer face-matching technology using two-dimensional photographs accurately matches the facial gestalt of unrelated individuals with the same syndromic form of intellectual disability. BMC Biotechnol. 2017;17:90.

    Article  Google Scholar 

  13. Moon J-E, Lee S-J, Ko CW. A de novo KMT2D mutation in a girl with Kabukisyndrome associated with endocrine symptoms: a case report. BMC Med Genet. 2018;19:102.

    Article  Google Scholar 

  14. Li Y, Bögershausen N, Alanay Y, Simsek Kiper PO, Plume N, Keupp K, et al. A mutation screen in patients with Kabuki syndrome. Hum Genet déc. 2011;130:715–24.

    Article  CAS  Google Scholar 

  15. Mısırlıgil M, Yıldız Y, Akın O, Odabaşı Güneş S, Arslan M, Ünay B. A Rare Cause of Hyperinsulinemic Hypoglycemia: Kabuki Syndrome. J Clin Res Pediatr Endocrinol. 2020. Online ahead of print.

  16. Lederer D, Shears D, Benoit V, Verellen-Dumoulin C, Maystadt I. A three generation X-linked family with Kabuki syndrome phenotype and a frameshift mutation in KDM6A. Am J Med Genet A. 2014;164A:1289–92.

    Article  Google Scholar 

  17. So PL, Luk HM, Yu KPT, Cheng SSW, Hau EWL, Ho SKL, et al. Clinical and molecular characterization study of Chinese Kabuki syndrome in Hong Kong. Am J Med Genet A. 2021;185:675–86.

    Article  CAS  Google Scholar 

  18. Dentici ML, Di Pede A, Lepri FR, Gnazzo M, Lombardi MH, Auriti C, et al. Kabuki syndrome: clinical and molecular diagnosis in the first year of life. Arch Dis Child. 2015;100:158–64.

    Article  Google Scholar 

  19. Banka S, Lederer D, Benoit V, Jenkins E, Howard E, Bunstone S, et al. Novel KDM6A (UTX) mutations and a clinical and molecular review of the X-linked Kabuki syndrome (KS2). Clin Genet. 2015;87:252–8.

    Article  CAS  Google Scholar 

  20. Gurovich Y, Hanani Y, Bar O, Nadav G, Fleischer N, Gelbman D, et al. Identifying facial phenotypes of genetic disorders using deep learning. Nat Med. 2019;25:60–4.

    Article  CAS  Google Scholar 

  21. Van der Donk R, Jansen S, Schuurs-Hoeijmakers JHM, Koolen DA, Goltstein LCMJ, Hoischen A, et al. Next-generation phenotyping using computer vision algorithms in rare genomic neurodevelopmental disorders. Genet Med. 2018. https://doi.org/10.1038/s41436-018-0404-y

Download references

Acknowledgements

We deeply thank all clinicians and biologists involved in diagnostic and data sharing for this study. We thank the French Kabuki Association for their help for this study. We thank Nicole Fleischer and Sarah Savage for advice and assistance related to the algorithm for this project.

Funding

Part of this work was supported by the French Ministry of Health (Programme Hospitalier de Recherche Clinique national, AOM 07-090), Fondation Maladies Rares, and the French Kabuki Association http://www.syndromekabuki.fr/.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to David Genevieve.

Ethics declarations

Competing interests

DG was a consultant for the Takeda Society in 2018. Takeda did not have any role in this study.

Ethical approval

All clinical geneticist consents for participation were obtained through a survey where their responses were also collected.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Rouxel, F., Yauy, K., Boursier, G. et al. Using deep-neural-network-driven facial recognition to identify distinct Kabuki syndrome 1 and 2 gestalt. Eur J Hum Genet 30, 682–686 (2022). https://doi.org/10.1038/s41431-021-00994-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41431-021-00994-8

This article is cited by

Search

Quick links