Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Feb 9;12(1):2230.
doi: 10.1038/s41598-021-02411-y.

Convolutional mesh autoencoders for the 3-dimensional identification of FGFR-related craniosynostosis

Eimear O' Sullivan #  1   2   3 , Lara S van de Lande #  4   5   6 , Athanasios Papaioannou  1   2   3 , Richard W F Breakey  1   2 , N Owase Jeelani  1   2 , Allan Ponniah  7 , Christian Duncan  8 , Silvia Schievano  1   2 , Roman H Khonsari  9 , Stefanos Zafeiriou #  3 , David J Dunaway #  1   2
Affiliations

Convolutional mesh autoencoders for the 3-dimensional identification of FGFR-related craniosynostosis

Eimear O' Sullivan et al. Sci Rep. .

Abstract

Clinical diagnosis of craniofacial anomalies requires expert knowledge. Recent studies have shown that artificial intelligence (AI) based facial analysis can match the diagnostic capabilities of expert clinicians in syndrome identification. In general, these systems use 2D images and analyse texture and colour. They are powerful tools for photographic analysis but are not suitable for use with medical imaging modalities such as ultrasound, MRI or CT, and are unable to take shape information into consideration when making a diagnostic prediction. 3D morphable models (3DMMs), and their recently proposed successors, mesh autoencoders, analyse surface topography rather than texture enabling analysis from photography and all common medical imaging modalities and present an alternative to image-based analysis. We present a craniofacial analysis framework for syndrome identification using Convolutional Mesh Autoencoders (CMAs). The models were trained using 3D photographs of the general population (LSFM and LYHM), computed tomography data (CT) scans from healthy infants and patients with 3 genetically distinct craniofacial syndromes (Muenke, Crouzon, Apert). Machine diagnosis outperformed expert clinical diagnosis with an accuracy of 99.98%, sensitivity of 99.95% and specificity of 100%. The diagnostic precision of this technique supports its potential inclusion in clinical decision support systems. Its reliance on 3D topography characterisation make it suitable for AI assisted diagnosis in medical imaging as well as photographic analysis in the clinical setting.

PubMed Disclaimer

Conflict of interest statement

A.P. and S.Z. currently work with Huawei Technologies Co., Ltd. They were with Imperial College London and University College London during the experiments, respectively. The other authors declare no competing interests.

Figures

Figure 1
Figure 1
t-SNE embeddings of face-only (a), head-only (b), and combined head-and-face (c) models from left to right respectively. In all cases, distinct clusters emerge for healthy and syndromic samples. The clearest disambiguation between samples is observed for the face-only model.
Figure 2
Figure 2
Confusion matrices for the face-only, head-only, and combined head-and-face models in order from left to right. Top row: binary classification. Bottom row: multi-class classification.
Figure 3
Figure 3
t-SNE embeddings for all samples, including the atypical Crouzon case, for the face-only (a), head-only (b), and combined head-and-face (c) models.
Figure 4
Figure 4
Mesh templates. (a) Face only template, (b) Head and Face template, (c) Head only template.
See this image and copyright information in PMC

References

    1. Slater BJ, et al. Cranial sutures: A brief review. Plast. Reconstr. Surg. 2008;121:170e–178e. doi: 10.1097/01.prs.0000304441.99483.97. - DOI - PubMed
    1. Stricker S, Mundlos S. FGF and ROR2 receptor tyrosine kinase signaling in human skeletal development. Curr. Top. Dev. Biol. 2011;97:179–206. doi: 10.1016/B978-0-12-385975-4.00013-9. - DOI - PubMed
    1. Van De Lande LS, Greig AV, Dunaway DJ. Plastic Surgery-Principles and Practice. Elsevier; 2022. Craniosynostosis; pp. 267–282.
    1. Basel-Vanagaite L, et al. Recognition of the Cornelia de Lange syndrome phenotype with facial dysmorphology novel analysis. Clin. Genet. 2016;89:557–563. doi: 10.1111/cge.12716. - DOI - PubMed
    1. Cerrolaza, J. J., et al. Identification of dysmorphic syndromes using landmark-specific local texture descriptors. In 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI) 1080–1083 (IEEE, 2016).

Publication types