Variational Autoencoder with Truncated Mixture of Gaussians for Functional Connectivity Analysis

• Published in: Information Processing in Medical Imaging Vol. 11492; pp. 867 - 879
• Main Authors: Zhao, Qingyu, Honnorat, Nicolas, Adeli, Ehsan, Pfefferbaum, Adolf, Sullivan, Edith V., Pohl, Kilian M.
• Format: Book Chapter Journal Article
• Language: English
• Published: Switzerland Springer International Publishing AG 01.01.2019; Springer International Publishing
• Series: Lecture Notes in Computer Science
• ISBN: 3030203506; 9783030203504
• ISSN: 0302-9743; 1011-2499; 1611-3349
• DOI: 10.1007/978-3-030-20351-1_68

Resting-state functional connectivity states are often identified as clusters of dynamic connectivity patterns. However, existing clustering approaches do not distinguish major states from rarely occurring minor states and hence are sensitive to noise. To address this issue, we propose to model major states using a non-linear generative process guided by a Gaussian-mixture distribution in a low-dimensional latent space, while separately modeling the connectivity patterns of minor states by a non-informative uniform distribution. We embed this truncated Gaussian-Mixture model in a Variational AutoEncoder framework to obtain a general joint clustering and outlier detection approach, called tGM-VAE. When applied to synthetic data with known ground-truth, tGM-VAE is more accurate in clustering dynamic connectivity patterns than existing approaches. On the rs-fMRI data of 593 healthy adolescents from the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA) study, tGM-VAE identified meaningful major connectivity states. The dwell time of these states significantly correlated with age.