Modeling resting state fMRI data via longitudinal supervised stochastic coordinate coding

Zhang, Wei; Lv, Jinglei; Zhang, Shu; Zhao, Yu; Liu, Tianming

doi:10.1109/isbi.2018.8363538

Cited by 4 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the last decade, sparse dictionary learning (SDL), widely known as the algorithm Online Dictionary Learning (ODL) (Mairal et al, 2010;Liu et al, 2010), has been successfully applied to identify the concurrent BCNs of the human brain and the non-human primate brain from fMRI datasets (Lv et al, 2015;Zhang et al, 2018). In this category, to satisfy the requirements of hierarchical organization of BCNs, we propose a novel Deep SDL algorithm that is a multilayer extension of conventional shallow SDL-based methods.…”

Section: Deep Sparse Dictionary Learningmentioning

confidence: 99%

“…In this work, we employ an in silico fMRI simulation method proposed previously (Zhang et al, 2018(Zhang et al, , 2019, using templates of BCNs (Smith et al, 2009) to test these proposed deep linear models. Specifically, we selected 12 BCNs (Table 3) that were originally derived using conventional shallow ICA (Smith et al, 2009).…”

Section: Simulated Fmri Datamentioning

confidence: 99%

“…In the last two decades, a variety of computational methods have been developed to detect BCNs, e.g., General Linear Modeling (GLM), Graph Theory, Independent Component Analysis (ICA), and Sparse Dictionary Learning (SDL) (Andersen et al, 1999;Calhoun et al, 2001;Lee et al, 2011;Lee et al, 2016;Lv et al, 2015;Zhang et al, 2017;Zhang et al, 2018;Zhang et al, 2019). However, these methods are based on a 'shallow' framework that cannot identify in unsupervised data-driven fashion the hierarchical and spatially overlapping organization of BCNs using resting-state fMRI (rsfMRI) or task-evoked fMRI (tfMRI) signals (Hu et al, 2018;Huang et al, 2018;Zhang et al, 2019;Zhang et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Linear Modeling of Hierarchical Functional Connectivity in the Human Brain

Zhang

Palacios

Mukherjee

2020

Preprint

Self Cite

View full text Add to dashboard Cite

The human brain exhibits hierarchical modular organization, which is not depicted by conventional fMRI functional connectivity reconstruction methods such as independent component analysis (ICA). To map hierarchical brain connectivity networks (BCNs), we propose a novel class of deep (multilayer) linear models that are constructed such that each successive layer decomposes the features of the preceding layer. Three of these are multilayer variants of Sparse Dictionary Learning (SDL), Non-Negative Matrix Factorization (NMF) and Fast ICA (FICA). We present a fourth deep linear model, Deep Matrix Fitting (MF), which incorporates both rank reduction for data-driven hyperparameter determination as well as a distributed optimization function. We also introduce a novel framework for theoretical comparison of these deep linear models based on their combination of mathematical operators, the predictions of which are tested using simulated resting state fMRI data with known ground truth BCNs. Consistent with the theoretical predictions, Deep MF and Deep SDL performed best for connectivity estimation of 1st layer networks, whereas Deep FICA and Deep NMF were modestly better for spatial mapping. Deep MF provided the best overall performance, including computational speed. These deep linear models can efficiently map hierarchical BCNs without requiring the manual hyperparameter tuning, extensive fMRI training data or high-performance computing infrastructure needed by deep nonlinear models, such as convolutional neural networks (CNNs) or deep belief networks (DBNs), and their results are also more explainable from their mathematical structure. These benefits gain in importance as continual improvements in the spatial and temporal resolution of fMRI reveal more of the hierarchy of spatiotemporal brain architecture. These new models of hierarchical BCNs may also advance the development of fMRI diagnostic and prognostic biomarkers, given the recent recognition of disparities between low-level vs high-level network connectivity across a wide range of neurological and psychiatric disorders.

show abstract

Section: Deep Sparse Dictionary Learningmentioning

confidence: 99%