Representation learning of resting state fMRI with variational auto-encoder
(Kim, Zhang, Han, Choi, Liu. 2020. biorxiv, doi: https://doi.org/10.1101/2020.06.16.155937)
Resting state functional magnetic resonance imaging (rs-fMRI) data exhibits complex but structured patterns. However, the underlying origins are unclear and entangled in rs-fMRI data. Here we establish a variational auto-encoder, as a generative model trainable with unsupervised learning, to disentangle the unknown sources of rs-fMRI activity. After being trained with large data from the Human Connectome Project, the model has learned to represent and generate patterns of cortical activity and connectivity using latent variables. Of the latent representation, its distribution reveals overlapping functional networks, and its geometry is unique to each individual. Our results support the functional opposition between the default mode network and the task positive network, while such opposition is asymmetric and non-stationary. Correlations between latent variables, rather than cortical connectivity, can be used as a more reliable feature to accurately identify subjects from a large group, even if only a short period of data is available per subject.
Task-evoked functional connectivity does not explain functional connectivity differences between rest and task conditions
(Lynch, Lu, Wen, Zhang, Saykin, Liu. 2018. Human Brain Mapping, 39(12): 4939-4948)
Musical Imagery Involves Wernicke’s area in Bilateral and Anti-Correlated Network Interactions
(Zhang, Chen, Wen, Lu, Liu. 2017. Scientific Reports, 7:17066)
Spontaneous activity is organized by visual streams
(Lu, Jeong, Wen, Liu. 2017. Human Brain Mapping 38: 4613-4630)
Imaging white-matter functional organization
(Marussich, Lu, Wen, Liu. 2017. NeuroImage, 146: 128-1141)
Influences of high-level features, gaze, and scene transitions on cortical responses to natural movies
(Lu, Hung, Wen, Marussich, Liu. 2016. Plos ONE, 11(8): e0161797)
Scale-free electrophysiology contributes to global fMRI
(Wen and Liu. 2016. J Neurosci. 32:6030-6040).
Separation of oscillatory and fractal dynamics in electrophysiological signals
(Wen and Liu, 2016. Brain Topography. 29:13-26).
Neuroelectrical decomposition of resting state fMRI
(Liu et al., 2014. Cerebral Cortex 24: 3080-3089)