O'Sullivan, E;
van de Lande, LS;
Papaioannou, A;
Breakey, RWF;
Jeelani, NO;
Ponniah, A;
Duncan, C;
... Dunaway, DJ; + view all
(2021)
Craniofacial Syndrome Identification Using Convolutional Mesh Autoencoders.
SSRN
Preview |
Text
SSRN-id3795325.pdf - Accepted Version Download (17MB) | Preview |
Abstract
Background: 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. While these are powerful tools for photographic analysis, they 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. // Methods: 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). // Findings: 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 makes it suitable for AI assisted diagnosis in medical imaging as well as photographic analysis in the clinical setting. // Interpretation: Our study demonstrates the use of 3D convolutional mesh autoencoders for the diagnosis of syndromic craniosynostosis. The topological nature of the tool presents opportunities for this method to be applied as a diagnostic tool across a number of 3D imaging modalities.
| Type: | Working / discussion paper |
|---|---|
| Title: | Craniofacial Syndrome Identification Using Convolutional Mesh Autoencoders |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.2139/ssrn.3795325 |
| Publisher version: | http://dx.doi.org/10.2139/ssrn.3795325 |
| Language: | English |
| Additional information: | This preprint is an early stage research paper that has not been peer-reviewed. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Population Health Sciences > UCL GOS Institute of Child Health UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Population Health Sciences > UCL GOS Institute of Child Health > Developmental Biology and Cancer Dept |
| URI: | https://discovery-pp.ucl.ac.uk/id/eprint/10135709 |
Archive Staff Only
 |
View Item |
