Variational AutoEncoder For Regression: Application to Brain Aging Analysis

  title={Variational AutoEncoder For Regression: Application to Brain Aging Analysis},
  author={Qingyu Zhao and Ehsan Adeli and Nicolas Honnorat and Tuo Leng and Kilian M. Pohl},
  journal={Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention},
  • Qingyu Zhao, E. Adeli, K. Pohl
  • Published 11 April 2019
  • Computer Science
  • Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
While unsupervised variational autoencoders (VAE) have become a powerful tool in neuroimage analysis, their application to supervised learning is under-explored. [] Key Method Performing a variational inference procedure on this model leads to joint regularization between the VAE and a neural-network regressor. In predicting the age of 245 subjects from their structural Magnetic Resonance (MR) images, our model is more accurate than state-of-the-art methods when applied to either region-of-interest (ROI…
Auto-encoding graph-valued data with applications to brain connectomes
This article develops a nonlinear latent factor model for summarizing the brain graph in both unsupervised and supervised settings that builds on methods for hierarchical modeling of replicated graph data, as well as variational auto-encoders that use neural networks for dimensionality reduction.
Recent Advances in Variational Autoencoders With Representation Learning for Biomedical Informatics: A Survey
The ability of VAEs to synthesize new data with more representation variance at state-of-art levels provides hope that the chronic scarcity of labeled data in the biomedical field can be resolved.
Deep Generative Analysis for Task-Based Functional MRI Experiments
A generalized additive model is used in which the effects of each regressor remain separable, the product of a spatial map produced by a variational autoencoder and a (potentially nonlinear) gain modeled by a covariate-specific Gaussian Process, which yields group-level effect maps comparable or superior to the ones obtained with standard fMRI analysis software.
Disentangled representations: towards interpretation of sex determination from hip bone
A new paradigm for better interpretability of class differences was proposed and the features encoded by the model, that distinguish the different classes were found to be consistent with expert knowledge.
LSSL: Longitudinal Self-Supervised Learning
This paper applies its model, named Longitudinal Self-Supervised Learning (LSSL), to two longitudinal neuroimaging studies to show its unique advantage in extracting the `brain-age' information from the data and in revealing informative characteristics associated with neurodegenerative and neuropsychological disorders.
Longitudinal self-supervised learning
Unifying Brain Age Prediction and Age-Conditioned Template Generation with a Deterministic Autoencoder
This work proposes a novel deep learning based approach to unify biological brain age estimation and age-conditioned template creation in a single, consistent model by developing a deterministic autoencoder that successfully disentangles age-related morphological changes and subject-specific variations.
Learning to synthesise the ageing brain without longitudinal data
Learning Cortical Parcellations Using Graph Neural Networks
It is found that graph neural networks accurately learn low-dimensional representations of functional brain connectivity that can be naturally extended to map the cortices of new datasets, and how some hyperparameter choices including training and testing data duration, network architecture, and algorithm choice affect model performance is described.
Bidirectional Modeling and Analysis of Brain Aging with Normalizing Flows
An initial evaluation of the normalizing flow brain aging model shows that it can accurately predict brain age while also being able to generate age-specific brain morphology templates that realistically represent the typical aging trend in a healthy population.


Truncated Gaussian-Mixture Variational AutoEncoder
A novel generative process is proposed, in which a Gaussian-mixture is used to model a few major clusters in the data, and use a non-informative uniform distribution to capture the remaining data, called tGM-VAE.
beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
Learning an interpretable factorised representation of the independent data generative factors of the world without supervision is an important precursor for the development of artificial
Variational Autoencoder with Truncated Mixture of Gaussians for Functional Connectivity Analysis
This work embeds a truncated Gaussian-Mixture model in a Variational Autoencoder framework to obtain a general joint clustering and outlier detection approach, tGM-VAE, which when applied to synthetic data with known ground-truth is more accurate in clustering connectivity patterns than existing approaches.
Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images
This work shows that deep spatial autoencoding models can be efficiently used to capture normal anatomical variability of entire 2D brain MR images and shows that constraints on the latent space and adversarial training can further improve the segmentation performance over standard deep representation learning.
Variational Autoencoded Regression: High Dimensional Regression of Visual Data on Complex Manifold
This paper proposes a new high dimensional regression method by merging Gaussian process regression into a variational autoencoder framework, and introduces a strategy to learn the latent space as well as the encoder and decoder so that the result of the regressed responded coincide with the corresponding response in the data space.
Chained regularization for identifying brain patterns specific to HIV infection
Auto-Encoding Variational Bayes
A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.
Supervised Representation Learning: Transfer Learning with Deep Autoencoders
This paper proposes a supervised representation learning method based on deep autoencoders for transfer learning that consists of an embedding layer and a label encoding layer that minimize the difference between domains explicitly and encode label information in learning the representation.
Semi-supervised Learning with Deep Generative Models
It is shown that deep generative models and approximate Bayesian inference exploiting recent advances in variational methods can be used to provide significant improvements, making generative approaches highly competitive for semi-supervised learning.