Representation Learning of Resting State fMRI with Variational Autoencoder

Azad

Computational and Mathematical Methods in Medicine

et al. 2022

Substantial information related to human cerebral conditions can be decoded through various noninvasive evaluating techniques like fMRI. Exploration of the neuronal activity of the human brain can divulge the thoughts of a person like what the subject is perceiving, thinking, or visualizing. Furthermore, deep learning techniques can be used to decode the multifaceted patterns of the brain in response to external stimuli. Existing techniques are capable of exploring and classifying the thoughts of the human subject acquired by the fMRI imaging data. fMRI images are the volumetric imaging scans which are highly dimensional as well as require a lot of time for training when fed as an input in the deep learning network. However, the hassle for more efficient learning of highly dimensional high-level features in less training time and accurate interpretation of the brain voxels with less misclassification error is needed. In this research, we propose an improved CNN technique where features will be functionally aligned. The optimal features will be selected after dimensionality reduction. The highly dimensional feature vector will be transformed into low dimensional space for dimensionality reduction through autoadjusted weights and combination of best activation functions. Furthermore, we solve the problem of increased training time by using Swish activation function, making it denser and increasing efficiency of the model in less training time. Finally, the experimental results are evaluated and compared with other classifiers which demonstrated the supremacy of the proposed model in terms of accuracy.

Section: Introductionmentioning

confidence: 99%

Brain Decoding Using fMRI Images for Multiple Subjects through Deep Learning

Azad

Computational and Mathematical Methods in Medicine

et al. 2022

“…Our VAE model was able to learn a non-linear feature set (or "latent space") effectively using large-scale adult rsfMRI data. Our preliminary results in adults 29 demonstrated that the fully trained VAE model could disentangle generative factors of rsfMRI data and encode the learned representations as latent variables. Noteworthy, generated VAE representations in the latent space were robust over varying signal quality of rsfMRI.…”

Section: Introductionmentioning

confidence: 85%

Towards A More Informative Representation of the Fetal-Neonatal Brain Connectome using Variational Autoencoder

Kim

Asis-Cruz

et al. 2022

Preprint

Self Cite

Recent advances in functional magnetic resonance imaging (fMRI) have helped elucidate previously inaccessible trajectories of early-life prenatal and neonatal brain development. To date, the interpretation of fetal-neonatal fMRI data has relied on linear analytic models, akin to adult neuroimaging data. However, unlike the adult brain, the fetal and newborn brain develops extraordinarily rapidly, far outpacing any other brain development period across the lifespan. Consequently, conventional linear computational models may not adequately capture these accelerated and complex neurodevelopmental trajectories during this critical period of brain development along the prenatal-neonatal continuum. To obtain a nuanced understanding of fetal-neonatal brain development, including non-linear growth, for the first time, we developed quantitative, systems-wide representations of neuronal circuitry in a large sample (>700) of fetuses, preterm, and full-term neonates using an unsupervised deep generative model called Variational Autoencoder (VAE), a model previously shown to be superior to linear models in representing complex resting state data in healthy adults. Here, we demonstrated that non-linear brain features, i.e., latent variables, derived with the VAE, carried important individual neural signatures, leading to improved representation of prenatal-neonatal brain maturational patterns and more accurate and stable age prediction compared to linear models. Using the VAE decoder, we also revealed distinct functional brain networks spanning the sensory and default mode networks. Using the VAE, we are able to reliably capture and quantify complex, non-linear fetal-neonatal functional neural connectivity. This will lay the critical foundation for detailed mapping of healthy and aberrant functional brain signatures that have their origins in fetal life.

“…The surface is thus essentially a graph with a fixed structure, and only the values associated with the voxels change over time. Although cortical surface data has previously been mapped to a sphere and then been mapped to a 2D image using polar coordinates [24], in this work we view the location of each vertex as a graph to retain as much distance information as possible.…”

Section: Biological Datamentioning

confidence: 99%

“…Classically, latent factor analysis for fMRI data is done with some form of matrix factorization, such as principal component analysis [39], ICA [2,4,31], or dictionary learning [28]. Recently these matrix factorizations have been extended to tensor factorizations/analysis [30], restricted Boltzmann machines (RBM)s [19], and static autoencoders [13,24]. In the field of neuronal populations, however, a recent approach finds latent factors using a recurrent autoencoder [33].…”

Section: Introductionmentioning

confidence: 99%

Spatio-temporally separable non-linear latent factor learning: an application to somatomotor cortex fMRI data

Geenjaar¹,

Kashyap²,

Lewis³

et al. 2022

Preprint

Functional magnetic resonance imaging (fMRI) data contain complex spatiotemporal dynamics, thus researchers have developed approaches that reduce the dimensionality of the signal while extracting relevant and interpretable dynamics. Recently, the feasibility of latent factor analysis, which can identify the lowerdimensional trajectory of neuronal population activations, has been demonstrated on both spiking and calcium imaging data. In this work, we propose a new framework inspired by latent factor analysis and apply it to functional whole-brain data from the human somatomotor cortex. Models of fMRI data that can perform whole-brain discovery of dynamical latent factors are understudied. The benefits of approaches such as linear independent component analysis models have been widely appreciated, however, nonlinear extensions of these models present challenges in terms of identification. Deep learning methods provide a way forward, but new methods for efficient spatial weight-sharing are critical to deal with the high dimensionality of the data and the presence of noise. Our approach generalizes weight sharing to non-Euclidean neuroimaging data by first performing spectral clustering based on the structural and functional similarity between voxels. The spectral clusters and their assignments can then be used as patches in an adapted multi-layer perceptron (MLP)-mixer model to share parameters among input points. To encourage temporally independent latent factors, we use an additional total correlation term in the loss. Our approach is evaluated on data with multiple motor sub-tasks to assess whether the model captures disentangled latent factors that correspond to each sub-task. Then, to assess the latent factors we find further, we compare the spatial location of each latent factor to the motor homunculus. Finally, we show that our approach captures task effects better than the current gold standard of source signal separation, independent component analysis (ICA).Preprint. Under review.