Disentangling hippocampal shape variations: A study of neurological disorders using mesh variational autoencoder with contrastive learning
Faculty Advisor
Date
2025
Keywords
disentangled representation learning, deep learning, contrastive learning, neurological disorders, medical imaging, diffusion tensor image, Mesh Variational Autoencoder, hippocampal shape variations
Abstract (summary)
This paper presents a comprehensive study focused on disentangling hippocampal shape variations from diffusion tensor imaging (DTI) datasets within the context of neurological disorders. Leveraging a Mesh Variational Autoencoder (VAE) enhanced with Supervised Contrastive Learning, our approach aims to improve interpretability by disentangling two distinct latent variables corresponding to age and the presence of diseases. In our ablation study, we investigate a range of VAE architectures and contrastive loss functions, showcasing the enhanced disentanglement capabilities of our approach. This evaluation uses synthetic 3D torus mesh data and real 3D hippocampal mesh datasets derived from the DTI hippocampal dataset. Our supervised disentanglement model outperforms several state-of-the-art (SOTA) methods like attribute and guided VAEs in terms of disentanglement scores. Our model distinguishes between age groups and disease status in patients with Multiple Sclerosis (MS) using the hippocampus data. Our Mesh VAE with Supervised Contrastive Learning shows the volume changes of the hippocampus of MS populations at different ages, and the result is consistent with the current neuroimaging literature. This research provides valuable insights into the relationship between neurological disorder and hippocampal shape changes in different age groups of MS populations using a Mesh VAE with Supervised Contrastive loss.
Publication Information
Rabbi, J., Kiechle, J., Beaulieu, C., Ray, N., & Cobzas, D. (2025). Disentangling hippocampal shape variations: A study of neurological disorders using mesh variational autoencoder with contrastive learning. Journal of Machine Learning for Biomedical Imaging, 2 (pp. 2268-2293). https://doi.org/10.59275/j.melba.2024-267f
Notes
Item Type
Article
Language
Rights
Attribution (CC BY)
