Latent Disentanglement in Mesh Variational Autoencoders Improves the Diagnosis of Craniofacial Syndromes and Aids Surgical Planning

Simone Foti, Alexander J. Rickart, Bongjin Koo, Eimear O' Sullivan, Lara S. van de Lande +7 more
9/5/2023
eess.IVcs.LGq-bio.QM

No official code found. Best implementation: simofoti/CraniofacialSD-VAE (4 stars, last commit 2023-10-20).

Abstract

The use of deep learning to undertake shape analysis of the complexities of the human head holds great promise. However, there have traditionally been a number of barriers to accurate modelling, especially when operating on both a global and local level. In this work, we will discuss the application of the Swap Disentangled Variational Autoencoder (SD-VAE) with relevance to Crouzon, Apert and Muenke syndromes. Although syndrome classification is performed on the entire mesh, it is also possible, for the first time, to analyse the influence of each region of the head on the syndromic phenotype. By manipulating specific parameters of the generative model, and producing procedure-specific new shapes, it is also possible to simulate the outcome of a range of craniofacial surgical procedures. This opens new avenues to advance diagnosis, aids surgical planning and allows for the objective evaluation of surgical outcomes.

View on arXivView PDF

Code Implementations(1)

simofoti/CraniofacialSD-VAECommunity100%
40Shell, PythonOct 20, 20233 years ago

Similar Papers

Deep Generative Networks for Heterogeneous Augmentation of Cranial Defects

85% match2023

MedShapeNet -- A Large-Scale Dataset of 3D Medical Shapes for Computer Vision

85% match1 repo842023

Synthetic Brain Images: Bridging the Gap in Brain Mapping With Generative Adversarial Model

83% match2024

MASSM: An End-to-End Deep Learning Framework for Multi-Anatomy Statistical Shape Modeling Directly From Images

83% match2024

Towards the Discovery of Down Syndrome Brain Biomarkers Using Generative Models

83% match2024

Unsupervised Deep Generative Models for Anomaly Detection in Neuroimaging: A Systematic Scoping Review

82% match2025

Cite this paper

@article{foti2023latent,
  title  = {Latent Disentanglement in Mesh Variational Autoencoders Improves the Diagnosis of Craniofacial Syndromes and Aids Surgical Planning},
  author = {Simone Foti and Alexander J. Rickart and Bongjin Koo and Eimear O' Sullivan and Lara S. van de Lande and Athanasios Papaioannou and Roman Khonsari and Danail Stoyanov and N. u. Owase Jeelani and Silvia Schievano and David J. Dunaway and Matthew J. Clarkson},
  year   = {2023},
  eprint = {2309.10825},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2309.10825v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2309.10825.svg)](https://codeofpaper.com/paper/2309.10825)

Discussion