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, Athanasios Papaioannou, Roman Khonsari, Danail Stoyanov, N. U. Owase Jeelani, Silvia Schievano, David J. Dunaway, Matthew J. Clarkson

Abstract: Highlights•New insights to improve the diagnosis of craniofacial syndromes.•More interpretable tools to automatically diagnose craniofacial patients.•Latent interpolation statistically approximates surgical procedures.•Class preserving data augmentation for head meshes based on spectral geometry.