Abstract
In this paper, we consider the problem of estimating multiple sparse, co-activated brain regions from functional magnetic resonance imaging (fMRI) observations belonging to different classes. More precisely, we propose a method to analyze similarities and differences in functional connectivity between children and young adults. Often, analysis is conducted on each class separately, and differences across classes are identified with an additional postprocessing step using adequate statistical tools. Here, we propose to rely on a generalized fused Lasso penalty, which allows us to make use of the entire data set in order to estimate connectivity patterns that are either shared across classes, or specific to a given group. By using the entire population during the estimation, we hope to increase the power of our analysis. The proposed model falls in the category of population-wise matrix decomposition, and a simple and efficient alternating direction method of multipliers algorithm is introduced to solve the associated optimization problem. After validating our approach on simulated data, experiments are performed on resting-state fMRI imaging from the Philadelphia neurodevelopmental cohort data set, comprised of normally developing children from ages 8 to 21. Developmental differences were observed in various brain regions, as a total of three class-specific resting-state components were identified. Statistical analysis of the estimated subject-specific features, as well as classification results (based on age groups, up to 81% accuracy, n = 583 samples) related to these components demonstrate that the proposed method is able to properly extract meaningful shared and class-specific sub-networks.
| Original language | English (US) |
|---|---|
| Article number | 7962262 |
| Pages (from-to) | 2165-2175 |
| Number of pages | 11 |
| Journal | IEEE Transactions on Medical Imaging |
| Volume | 37 |
| Issue number | 10 |
| DOIs | |
| State | Published - Oct 2018 |
Fingerprint
Keywords
- Sparse models
- brain development
- functional connectivity
- joint lasso penalty
ASJC Scopus subject areas
- Software
- Radiological and Ultrasound Technology
- Computer Science Applications
- Electrical and Electronic Engineering
Cite this
Fused Estimation of Sparse Connectivity Patterns From Rest fMRI - Application to Comparison of Children and Adult Brains. / Zille, Pascal; Calhoun, Vince D.; Stephen, Julia M.; Wilson, Tony W; Wang, Yu Ping.
In: IEEE Transactions on Medical Imaging, Vol. 37, No. 10, 7962262, 10.2018, p. 2165-2175.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Fused Estimation of Sparse Connectivity Patterns From Rest fMRI - Application to Comparison of Children and Adult Brains
AU - Zille, Pascal
AU - Calhoun, Vince D.
AU - Stephen, Julia M.
AU - Wilson, Tony W
AU - Wang, Yu Ping
PY - 2018/10
Y1 - 2018/10
N2 - In this paper, we consider the problem of estimating multiple sparse, co-activated brain regions from functional magnetic resonance imaging (fMRI) observations belonging to different classes. More precisely, we propose a method to analyze similarities and differences in functional connectivity between children and young adults. Often, analysis is conducted on each class separately, and differences across classes are identified with an additional postprocessing step using adequate statistical tools. Here, we propose to rely on a generalized fused Lasso penalty, which allows us to make use of the entire data set in order to estimate connectivity patterns that are either shared across classes, or specific to a given group. By using the entire population during the estimation, we hope to increase the power of our analysis. The proposed model falls in the category of population-wise matrix decomposition, and a simple and efficient alternating direction method of multipliers algorithm is introduced to solve the associated optimization problem. After validating our approach on simulated data, experiments are performed on resting-state fMRI imaging from the Philadelphia neurodevelopmental cohort data set, comprised of normally developing children from ages 8 to 21. Developmental differences were observed in various brain regions, as a total of three class-specific resting-state components were identified. Statistical analysis of the estimated subject-specific features, as well as classification results (based on age groups, up to 81% accuracy, n = 583 samples) related to these components demonstrate that the proposed method is able to properly extract meaningful shared and class-specific sub-networks.
AB - In this paper, we consider the problem of estimating multiple sparse, co-activated brain regions from functional magnetic resonance imaging (fMRI) observations belonging to different classes. More precisely, we propose a method to analyze similarities and differences in functional connectivity between children and young adults. Often, analysis is conducted on each class separately, and differences across classes are identified with an additional postprocessing step using adequate statistical tools. Here, we propose to rely on a generalized fused Lasso penalty, which allows us to make use of the entire data set in order to estimate connectivity patterns that are either shared across classes, or specific to a given group. By using the entire population during the estimation, we hope to increase the power of our analysis. The proposed model falls in the category of population-wise matrix decomposition, and a simple and efficient alternating direction method of multipliers algorithm is introduced to solve the associated optimization problem. After validating our approach on simulated data, experiments are performed on resting-state fMRI imaging from the Philadelphia neurodevelopmental cohort data set, comprised of normally developing children from ages 8 to 21. Developmental differences were observed in various brain regions, as a total of three class-specific resting-state components were identified. Statistical analysis of the estimated subject-specific features, as well as classification results (based on age groups, up to 81% accuracy, n = 583 samples) related to these components demonstrate that the proposed method is able to properly extract meaningful shared and class-specific sub-networks.
KW - Sparse models
KW - brain development
KW - functional connectivity
KW - joint lasso penalty
UR - http://www.scopus.com/inward/record.url?scp=85023746657&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85023746657&partnerID=8YFLogxK
U2 - 10.1109/TMI.2017.2721640
DO - 10.1109/TMI.2017.2721640
M3 - Article
C2 - 28682248
AN - SCOPUS:85023746657
VL - 37
SP - 2165
EP - 2175
JO - IEEE Transactions on Medical Imaging
JF - IEEE Transactions on Medical Imaging
SN - 0278-0062
IS - 10
M1 - 7962262
ER -