English

Fusing multimodal neuroimaging data with a variational autoencoder

Machine Learning 2021-05-05 v1 Signal Processing

Abstract

Neuroimaging studies often involve the collection of multiple data modalities. These modalities contain both shared and mutually exclusive information about the brain. This work aims at finding a scalable and interpretable method to fuse the information of multiple neuroimaging modalities using a variational autoencoder (VAE). To provide an initial assessment, this work evaluates the representations that are learned using a schizophrenia classification task. A support vector machine trained on the representations achieves an area under the curve for the classifier's receiver operating characteristic (ROC-AUC) of 0.8610.

Keywords

Cite

@article{arxiv.2105.01128,
  title  = {Fusing multimodal neuroimaging data with a variational autoencoder},
  author = {Eloy Geenjaar and Noah Lewis and Zening Fu and Rohan Venkatdas and Sergey Plis and Vince Calhoun},
  journal= {arXiv preprint arXiv:2105.01128},
  year   = {2021}
}
R2 v1 2026-06-24T01:44:49.151Z