Vince D. Calhoun
Georgia Institute of Technology
PsychologyNeuroscienceFunctional magnetic resonance imagingComputer scienceSchizophrenia
What is this?
Publications 1149
#1Chen Qiao (Xi'an Jiaotong University)H-Index: 6
#2Yan Shi (Xi'an Jiaotong University)
Last. Yu-Ping Wang (Tulane University)H-Index: 23
view all 5 authors...
Abstract How to design deep neural networks (DNNs) for the representation and analysis of high dimensional but small sample size data is still a big challenge. One solution is to construct a sparse network. At present, there exist many approaches to achieve sparsity for DNNs by regularization, but most of them are carried out only in the pre-training process due to the difficulty in the derivation of explicit formulae in the fine-tuning process. In this paper, a log-sum function is used as the r...
#1Hiroshi MoriokaH-Index: 6
#2Vince D. Calhoun (Georgia Institute of Technology)H-Index: 97
Last. Aapo Hyvärinen (UH: University of Helsinki)H-Index: 51
view all 3 authors...
Abstract Accumulating evidence from whole brain functional magnetic resonance imaging (fMRI) suggests that the human brain at rest is functionally organized in a spatially and temporally constrained manner. However, because of their complexity, the fundamental mechanisms underlying time-varying functional networks are still not well understood. Here, we develop a novel nonlinear feature extraction framework called local space-contrastive learning (LSCL), which extracts distinctive nonlinear temp...
#1Enrico Premi (University of Brescia)H-Index: 21
#2Viviana Cristillo (University of Brescia)H-Index: 5
Last. Maria CotelliH-Index: 32
view all 14 authors...
Abstract In the present study, we aim at investigating whether education modulates dynamical properties of time-varying whole-brain network connectivity (the chronnectome) in Frontotemporal dementia (FTD) at a given level of symptom severity. Dynamic connectivity parameters were evaluated in 128 FTD patients using independent component analysis, sliding-time window correlation and k-means approach to resting state-MRI data. We evaluated the relationship between education, a proxy measure of cogn...
#1Qunfang Long (UMBC: University of Maryland, Baltimore County)H-Index: 3
#2Suchita Bhinge (UMBC: University of Maryland, Baltimore County)H-Index: 4
Last. Tulay Adali (UMBC: University of Maryland, Baltimore County)H-Index: 57
view all 4 authors...
The extraction of common and distinct biomedical signatures among different populations allows for a more detailed study of the group-specific as well as distinct information of different populations. A number of subspace analysis algorithms have been developed and successfully applied to data fusion, however they are limited to joint analysis of only a couple of datasets. Since subspace analysis is very promising for analysis of multi-subject medical imaging data as well, we focus on this probl...
#1Maria J. Knol (EUR: Erasmus University Rotterdam)H-Index: 5
#2Raymond A. Poot (EUR: Erasmus University Rotterdam)H-Index: 23
Last. Dianne H.K. van Dam-Nolen (EUR: Erasmus University Rotterdam)H-Index: 1
view all 120 authors...
The size of the human head is determined by growth in the first years of life, while the rest of the body typically grows until early adulthood. Such complex developmental processes are regulated by various genes and growth pathways. Rare genetic syndromes have revealed genes that affect head size, but the genetic drivers of variation in head size within the general population remain largely unknown. To elucidate biological pathways underlying the growth of the human head, we performed the large...
#1Dongmei Zhi (CAS: Chinese Academy of Sciences)H-Index: 3
#2Wenyue Wu (CSU: Central South University)H-Index: 1
Last. Hongyu Long (CSU: Central South University)H-Index: 7
view all 13 authors...
DNA hypermethylation is widely observed in temporal lobe epilepsy (TLE), in which NR4A1 knockdown has been reported to be able to alleviate seizure severity in mouse model, while the underlying methylation-imaging pathway modulated by aberrant methylation levels of NR4A1 remains to be clarified in patients with TLE. Using multi-site canonical correlation analysis with reference, methylation levels of NR4A1 in blood were used as priori to guide fusion of three MRI features: functional connectivit...
#1Kuaikuai Duan (Georgia Institute of Technology)H-Index: 1
#2Jiayu ChenH-Index: 19
Last. Martine Hoogman (Radboud University Nijmegen)H-Index: 27
view all 18 authors...
Most psychiatric disorders are highly heritable and associated with altered brain structural and functional patterns. Data fusion analyses on brain imaging and genetics, one of which is parallel independent component analysis (pICA), enable the link of genomic factors to brain patterns. Due to the small to modest effect sizes of common genetic variants in psychiatric disorders, it is usually challenging to reliably separate disorder-related genetic factors from the rest of the genome with the ty...
#1Kuaikuai Duan (Georgia Institute of Technology)H-Index: 1
#2Rogers F. Silva (Georgia Institute of Technology)H-Index: 10
Last. Jingyu Liu (Georgia Institute of Technology)H-Index: 31
view all 4 authors...
Multimodal data fusion is a topic of great interest. Several fusion methods have been proposed to investigate coherent patterns and corresponding linkages across modalities, such as joint independent component analysis (jICA), multiset canonical correlation analysis (mCCA), mCCA+jICA, and parallel ICA. JICA exploits source independence but assumes shared loading parameters. MCCA maximizes correlation linkage across modalities directly but is limited to orthogonal features. While there is no theo...
#1Ashkan Faghiri (Georgia Institute of Technology)H-Index: 3
#2Armin Iraji (Georgia Institute of Technology)H-Index: 9
Last. Vince D. Calhoun (Georgia Institute of Technology)H-Index: 97
view all 5 authors...
#2Vince D. Calhoun (Georgia Institute of Technology)H-Index: 97
Last. Michal Assaf (Yale University)H-Index: 17
view all 9 authors...
Abstract Schizophrenia and autism spectrum disorder (ASD) are nosologically distinct neurodevelopmental disorders with similar deficits in social cognition, including the ability to form mental representations of others (i.e., mentalizing). However, the extent of patient deficit overlap in underlying neural mechanisms is unclear. Our goal was to examine deficits in mentalizing task-related (MTR) activity modulation in schizophrenia and ASD and the relationship of such deficits with social functi...