Repository logo
 

Explaining anatomical shape variability: supervised disentangling with a variational graph autoencoder

Simple item page
dc.contributor.authorKiechle, Johannes
dc.contributor.authorMiller, Dylan
dc.contributor.authorSlessor, Jordan
dc.contributor.authorPietrosanu, Matthew
dc.contributor.authorKong, Linglong
dc.contributor.authorBeaulieu, Christian
dc.contributor.authorCobzas, Dana
dc.date.accessioned2025-07-31T20:22:04Z
dc.date.available2025-07-31T20:22:04Z
dc.date.issued2023
dc.descriptionPresented on April 18, 2023, at the IEEE 20th International Symposium on Biomedical Imaging (ISBI) Conference in Cartagena, Colombia.
dc.description.abstractThis work proposes a modular geometric deep learning framework that isolates shape variability associated with a given scalar factor (e.g., age) within a population (e.g., healthy individuals). Our approach leverages a novel graph convolution operator in a variational autoencoder to process 3D mesh data and learn a meaningful, low-dimensional shape descriptor. A supervised disentanglement strategy aligns a single component of this descriptor with the factor of interest during training. On a toy synthetic dataset and a high-resolution diffusion tensor imaging (DTI) dataset, the proposed model is better able to disentangle the learned latent space with a simulated factor and patient age, respectively, relative to other state-of-the-art methods. The relationship between age and shape estimated in the DTI analysis is consistent with existing neuroimaging literature.
dc.identifier.urihttps://hdl.handle.net/20.500.14078/4028
dc.language.isoen
dc.rightsAll Rights Reserved
dc.subjectanatomical shape analysis
dc.subjectgraph convolution
dc.subjecthippocampus
dc.subjectlatent space disentanglement
dc.titleExplaining anatomical shape variability: supervised disentangling with a variational graph autoencoderen
dc.typeArticle

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Explaining_Anatomical_Shape_Variability_2023.pdf
Size:
2.66 MB
Format:
Adobe Portable Document Format
Download

Collections

Department of Computer Science