Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.19110 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913868551290880 |
|---|---|
| author | Singh, Vishwa Mohan Asiares, Alberto Gaston Villagran Schuhmacher, Luisa Sophie Rendall, Kate Weißbrod, Simon Rügamer, David Körte, Inga |
| author_facet | Singh, Vishwa Mohan Asiares, Alberto Gaston Villagran Schuhmacher, Luisa Sophie Rendall, Kate Weißbrod, Simon Rügamer, David Körte, Inga |
| contents | Diffusion Tensor Imaging (DTI) tractography offers detailed insights into the structural connectivity of the brain, but presents challenges in effective representation and interpretation in deep learning models. In this work, we propose a novel 2D representation of DTI tractography that encodes tract-level fractional anisotropy (FA) values into a 9x9 grayscale image. This representation is processed through a Beta-Total Correlation Variational Autoencoder with a Spatial Broadcast Decoder to learn a disentangled and interpretable latent embedding. We evaluate the quality of this embedding using supervised and unsupervised representation learning strategies, including auxiliary classification, triplet loss, and SimCLR-based contrastive learning. Compared to the 1D Group deep neural network (DNN) baselines, our approach improves the F1 score in a downstream sex classification task by 15.74% and shows a better disentanglement than the 3D representation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19110 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An Interpretable Representation Learning Approach for Diffusion Tensor Imaging Singh, Vishwa Mohan Asiares, Alberto Gaston Villagran Schuhmacher, Luisa Sophie Rendall, Kate Weißbrod, Simon Rügamer, David Körte, Inga Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Diffusion Tensor Imaging (DTI) tractography offers detailed insights into the structural connectivity of the brain, but presents challenges in effective representation and interpretation in deep learning models. In this work, we propose a novel 2D representation of DTI tractography that encodes tract-level fractional anisotropy (FA) values into a 9x9 grayscale image. This representation is processed through a Beta-Total Correlation Variational Autoencoder with a Spatial Broadcast Decoder to learn a disentangled and interpretable latent embedding. We evaluate the quality of this embedding using supervised and unsupervised representation learning strategies, including auxiliary classification, triplet loss, and SimCLR-based contrastive learning. Compared to the 1D Group deep neural network (DNN) baselines, our approach improves the F1 score in a downstream sex classification task by 15.74% and shows a better disentanglement than the 3D representation. |
| title | An Interpretable Representation Learning Approach for Diffusion Tensor Imaging |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2505.19110 |