Complete Model Identification Using Independent Vector Analysis: Application to the Fusion of Task FMRI Data

Akhonda, M. A. B. S.; Gabrielson, Ben; Calhoun, Vince D.

doi:10.1109/dslw51110.2021.9523414

Cited by 3 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We test the performance of the proposed method on both simulated and real data. Using simulation results, we show that SI-IVA outperforms the eigenanalysis-based approach as in [13,14] with respect to the correctly estimated number of subgroups. With real fMRI data, we demonstrate that the subgroups identified by SI-IVA are interpretable and meaningful.…”

Section: Subgroup Identification By Eigen-analysismentioning

confidence: 97%

“…Since the components in each SCV come from individual subjects, the index of the correlated components can be used to identify subjects that belong to the same subgroup. Based on [14], for each SCV covariance matrix Ĉn, the number of eigenvalues that are greater than one and the corresponding eigenvectors can be used to identify the number of subgroups and the index of subjects that belong to each subgroup. In the rest of this paper, we refer this method as eigenanalysis based on hard thresholding (EHT).…”

Section: Subgroup Identification By Eigenanalysismentioning

confidence: 99%

“…Although IVA-CS is a promising approach for the subgroup identification problem, it relies heavily on user-defined parameters. One way to alleviate this issue is to apply eigenanalysis to covariance matrices as proposed in [13,14]. These papers focus on complete model identification, i.e., identifying the number of all correlated signals across multiple datasets, and as a result, their computational complexity grows significantly with the number of datasets, making them impractical when there are more than a couple of datasets.…”

Section: Introductionmentioning

confidence: 99%

“…Obviously, for the subgroup identification problem what we are interested in is a method that can effectively work with a large number of datasets, which correspond to each subject's fMRI data. In this paper, we leverage the strengths of these two approaches, use of IVA with the multivariate Gaussian model (IVA-G) to reliably reveal the correlation structure of latent variables across large number of datasets [10], and use of eigenanalysis of covariance matrices to identify the highly correlated subgroups revealed by IVA-G as in [13,14].…”

Section: Introductionmentioning

confidence: 99%

“…Since the correlation structure of the underlying datasets are captured through SCVs, SI-IVA is fundamentally different from the aforementioned two-step procedure in [9]. Inspired by [13,14], we propose to use eigenanalysis with Geshgorin disc theorem (GDT) on the SCV covariance matrices for…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Independent Vector Analysis Based Subgroup Identification from Multisubject fMRI Data

Yang

Akhonda

Ghayem

et al. 2022

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Identification of homogeneous subgroups of subjects plays a key role in the study of precision medicine. While there are a number of approaches based on the clustering of low-level features such as behavioral variables, work that makes use of fully multivariate nature of medical imaging data is very limited. Given that the individual variability in brain functional networks obtained from functional magnetic resonance imaging (fMRI) data is noted as being both significant and consistent like fingerprints, its use provides a particularly appealing approach to this challenging problem. We present a completely data-driven approach, subgroup identification using independent vector analysis (SI-IVA), which leverages the desirable properties of IVA to uncover the relationship across subjects along with the discovery of subgroup structures revealed by Gershgorin disc theorem. We show that SI-IVA outperforms an eigenanalysisbased approach by simulations. We then apply the method to real fMRI data obtained from patients of during resting state to identify group differences in multiple relevant brain regions including primary somatosensory and motor cortex, which demonstrates that SI-IVA provides interpretable and meaningful results.

show abstract

Section: Subgroup Identification By Eigen-analysismentioning

confidence: 97%

Section: Subgroup Identification By Eigenanalysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Independent Vector Analysis Based Subgroup Identification from Multisubject fMRI Data

Yang

Akhonda

Ghayem

et al. 2022

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

show abstract

Coupled CP Tensor Decomposition with Shared and Distinct Components for Multi-Task Fmri Data Fusion

Borsoi

Lehmann

Akhonda

et al. 2023

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Discovering components that are shared in multiple datasets, next to dataset-specific features, has great potential for studying the relationships between different subjects or tasks in functional Magnetic Resonance Imaging (fMRI) data. Coupled matrix and tensor factorization approaches have been useful for flexible data fusion, or decomposition to extract features that can be used in multiple ways. However, existing methods do not directly recover shared and dataset-specific components, which requires post-processing steps involving additional hyperparameter selection. In this paper, we propose a tensor-based framework for multi-task fMRI data fusion, using a partially constrained canonical polyadic (CP) decomposition model. Differently from previous approaches, the proposed method directly recovers shared and dataset-specific components, leading to results that are directly interpretable. A strategy to select a highly reproducible solution to the decomposition is also proposed. We evaluate the proposed methodology on real fMRI data of three tasks, and show that the proposed method finds meaningful components that clearly identify group differences between patients with schizophrenia and healthy controls.

show abstract

Symmetric data-driven fusion of diffusion tensor MRI: Age differences in white matter

et al. 2023

View full text Add to dashboard Cite

In the past 20 years, white matter (WM) microstructure has been studied predominantly using diffusion tensor imaging (DTI). Decreases in fractional anisotropy (FA) and increases in mean (MD) and radial diffusivity (RD) have been consistently reported in healthy aging and neurodegenerative diseases. To date, DTI parameters have been studied individually (e.g., only FA) and separately (i.e., without using the joint information across them). This approach gives limited insights into WM pathology, increases the number of multiple comparisons, and yields inconsistent correlations with cognition. To take full advantage of the information in a DTI dataset, we present the first application of symmetric fusion to study healthy aging WM. This data-driven approach allows simultaneous examination of age differences in all four DTI parameters. We used multiset canonical correlation analysis with joint independent component analysis (mCCA + jICA) in cognitively healthy adults (age 20–33, n = 51 and age 60–79, n = 170). Four-way mCCA + jICA yielded one high-stability modality-shared component with co-variant patterns of age differences in RD and AD in the corpus callosum, internal capsule, and prefrontal WM. The mixing coefficients (or loading parameters) showed correlations with processing speed and fluid abilities that were not detected by unimodal analyses. In sum, mCCA + jICA allows data-driven identification of cognitively relevant multimodal components within the WM. The presented method should be further extended to clinical samples and other MR techniques (e.g., myelin water imaging) to test the potential of mCCA+jICA to discriminate between different WM disease etiologies and improve the diagnostic classification of WM diseases.

show abstract

Complete Model Identification Using Independent Vector Analysis: Application to the Fusion of Task FMRI Data

Cited by 3 publications

References 24 publications

Independent Vector Analysis Based Subgroup Identification from Multisubject fMRI Data

Independent Vector Analysis Based Subgroup Identification from Multisubject fMRI Data

Coupled CP Tensor Decomposition with Shared and Distinct Components for Multi-Task Fmri Data Fusion

Symmetric data-driven fusion of diffusion tensor MRI: Age differences in white matter

Contact Info

Product

Resources

About