DeepAI
Log In Sign Up

Fusing multimodal neuroimaging data with a variational autoencoder

05/03/2021
by   Eloy Geenjaar, et al.
6

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

11/02/2017

A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencoder

The detection of anomalous executions is valuable for reducing potential...
12/20/2018

Generating lyrics with variational autoencoder and multi-modal artist embeddings

We present a system for generating song lyrics lines conditioned on the ...
10/04/2021

Assessing glaucoma in retinal fundus photographs using Deep Feature Consistent Variational Autoencoders

One of the leading causes of blindness is glaucoma, which is challenging...
11/14/2020

Using Convolutional Variational Autoencoders to Predict Post-Trauma Health Outcomes from Actigraphy Data

Depression and post-traumatic stress disorder (PTSD) are psychiatric con...
10/09/2019

Multimodal representation models for prediction and control from partial information

Similar to humans, robots benefit from interacting with their environmen...
12/31/2015

Autoencoding beyond pixels using a learned similarity metric

We present an autoencoder that leverages learned representations to bett...