Mining brain region connectivity for alzheimer's disease study via sparse inverse covariance estimation

Sun, Liang; Patel, Rinkal; Li, Jun; Chen, Kewei; Wu, Teresa; Li, Jing; Reiman, Eric M.; Ye, Jieping

doi:10.1145/1557019.1557162

Cited by 50 publications

(39 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Examples of works can be found in [13,8,7]. There have been a few works in the data mining community as well: In [16], the authors derive the brain region connections for Alzheimer's patients, and recently [5] that leverages tensor decomposition in order to discover the underlying network of the human brain. Most related to the present work is the work of Valdes et al [19], wherein the authors propose an autoregressive model (similar to MODEL0) and solve it using regularized regression.…”

Section: Related Workmentioning

confidence: 99%

Good-Enough Brain Model: Challenges, Algorithms, and Discoveries in Multisubject Experiments

et al. 2014

View full text Add to dashboard Cite

Given a simple noun such as apple, and a question such as is it edible?, what processes take place in the human brain? More specifically, given the stimulus, what are the interactions between (groups of) neurons (also known as functional connectivity) and how can we automatically infer those interactions, given measurements of the brain activity? Furthermore, how does this connectivity differ across different human subjects?In this work we present a simple, novel good-enough brain model, or GEBM in short, and a novel algorithm SPARSE-SYSID, which are able to effectively model the dynamics of the neuron interactions and infer the functional connectivity. Moreover, GEBM is able to simulate basic psychological phenomena such as habituation and priming (whose definition we provide in the main text).We evaluate GEBM by using both synthetic and real brain data. Using the real data, GEBM produces brain activity patterns that are strikingly similar to the real ones, and the inferred functional connectivity is able to provide neuroscientific insights towards a better understanding of the way that neurons interact with each other, as well as detect regularities and outliers in multi-subject brain activity measurements. Categories and Subject Descriptors KeywordsBrain Activity Analysis; System Identification; Brain Functional Connectivity; Control Theory; Neuroscience Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from permissions@acm.org. real GeBM CCA) brain activity for a particular voxel (results by LS and CCA are similar to the one in Fig. 2 for all voxels). By minimizing the sum of squared errors, both algorithms that solve for MODEL 0 resort to a simple line that increases very slowly over time, thus having a minimal squared error, given linearity assumptions. Comparison of true brain activity and brain activity generated using the LS, and CCA solutions to MODEL 0 . Clearly, MODEL 0 is not able to capture the trends of the brain activity, and to the end of minimizing the squared error, produces an almost straight line that dissects the real brain activity waveform. Proposed approach: GeBMFormulating the problem as MODEL 0 is not able to meet the requirements for our desired solution. However, we have not exhausted the space of possible formulations that live within our set of simplifying assumptions. In this section, we describe GEBM, our proposed approach which, under the assumptions that we have already made in Section 2, is able to meet our requirements remarkably well.In order to come up with a more accurate m...

show abstract

Section: Related Workmentioning

confidence: 99%

Good-Enough Brain Model: Challenges, Algorithms, and Discoveries in Multisubject Experiments

et al. 2014

View full text Add to dashboard Cite

show abstract

“…lem of brain network discovery, which aims at inferring the functional connectivities among a set of predefined non-overlapping brain regions. Previous studies usually focus on inferring a network for a single subject or treating a collection of subjects as a single subject by concatenating the data of multiple subjects [10,14]. As the increasing availability of neuroimaging data in recent years, we usually have one or more collections of subjects in brain datasets.…”

Section: Introductionmentioning

confidence: 99%

Unified and Contrasting Graphical Lasso for Brain Network Discovery

Kong

Ragin

2017

Proceedings of the 2017 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

The analysis of brain imaging data has attracted much attention recently. A popular analysis is to discover a network representation of brain from the neuroimaging data, where each node denotes a brain region and each edge represents a functional association or structural connection between two brain regions. Motivated by the multi-subject and multi-collection settings in neuroimaging studies, in this paper, we consider brain network discovery under two novel settings: 1) unified setting: Given a collection of subjects, discover a single network that is good for all subjects. 2) contrasting setting: Given two collections of subjects, discover a single network that best discriminates two collections. We show that the existing formulation of graphical Lasso (GLasso) cannot address above problems properly. Two novel models, UGLasso (Unified Graphical Lasso) and CGLasso(Contrasting Graphical Lasso), are proposed to address these two problems respectively. We evaluate our methods on synthetic data and two realworld functional magnetic resonance imaging (fMRI) datasets. Empirical results demonstrate the effectiveness of the proposed methods.

show abstract

“…From a marketing perspective, the ability to infer this graph from the given user activities is useful since it allows companies to target influential individuals on the network. Another example of net- work construction can be found in the study of functional brain networks [4,5,18] which has become quite popular recently. These networks can be constructed by measuring the correlation of the activity of different brain regions in a functional magnetic resonance imaging (fMRI) scan.…”

Section: Introductionmentioning

confidence: 99%

Identifying Deep Contrasting Networks from Time Series Data: Application to Brain Network Analysis

Lee¹,

Kong²,

Bao³

et al. 2017

Proceedings of the 2017 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

The analysis of multiple time series data, which are generated from a networked system, has attracted much attention recently. This technique has been used in a wide range of applications including functional brain network analysis of neuroimaging data and social influence analysis. In functional brain network analysis, the activity of different brain regions can be represented as multiple time series. An important task in the analysis is to identify the latent network from the observed time series data. In this network, the edges (functional connectivity) capture the correlation between different time series (brain regions). Conventional network extraction approaches usually focus on capturing the connectivity through linear measures under unsupervised settings. In this paper, we study the problem of identifying deep nonlinear connections under group-contrasting settings, where we have two groups of time series samples, and the goal is to identify nonlinear connections that are discriminative across the two groups. We propose a method called GCC (Graph Construction CNN) which is based on deep convolutional neural networks for the task of network construction. The CNN in our model learns a nonlinear edge-weighting function to assign discriminative values to the edges of a network. Experiments on a real-world ADHD dataset show that our proposed method can effectively identify the nonlinear connections among different brain regions. We also demonstrate the extensibility of our proposed framework by combining it with an autoencoder to capture subgraph patterns from the constructed networks.

show abstract

Mining brain region connectivity for alzheimer's disease study via sparse inverse covariance estimation

Cited by 50 publications

References 29 publications

Good-Enough Brain Model: Challenges, Algorithms, and Discoveries in Multisubject Experiments

Good-Enough Brain Model: Challenges, Algorithms, and Discoveries in Multisubject Experiments

Unified and Contrasting Graphical Lasso for Brain Network Discovery

Identifying Deep Contrasting Networks from Time Series Data: Application to Brain Network Analysis

Contact Info

Product

Resources

About