Sparse Group Bases for Multisubject fMRI Data

Khalid, Muhammad Usman

doi:10.1109/access.2022.3194651

Cited by 5 publications

(18 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These common TCs were eventually correlated with MHRs and averaged SMs with RSNs; the atoms/sparse codes with the most significant correlation values were saved. One can refer to [43] for more details on this extraction.…”

Section: H Block Design Dataset Resultsmentioning

confidence: 99%

“…The proposed rswsDL algorithm a promising alternative to rACSD because it utilizes diversities across brains. There are some variations to the ACSD method, such as ShSSDL [42], and sgBACES [43] that do allow capturing cross-subject and subject-specific variations, but the main drawback of these methods is their limitation to task-related data only and inability to handle outliers. The proposed method can handle both, although we do not provide resting-state data analysis in this paper to avoid increasing the paper length.…”

Section: ) Swsdlmentioning

confidence: 99%

“…As discussed in [37], the SPM-12 toolbox [3] was used for preprocessing the block design dataset. In-depth description of the preprocessing procedures for this dataset, including masking, realignment, normalizing, and spatial smoothing, can be found in [43], [51], [52]. In order to eliminate motion artifacts, functional images were realigned to the first image.…”

Section: F Block Design Dataset Preprocessingmentioning

confidence: 99%

See 2 more Smart Citations

Robust Subject-Wise Dictionary Learning for fMRI

Khalid,

Albahlal

2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

This paper presents a robust subject-wise sequential dictionary learning (swsDL) algorithm named rswsDL for functional magnetic resonance imaging (fMRI) data where the negative impact of dimensionality reduction in the form of information loss and sensitivity to anomalous observations due to the assumption of Gaussian prior has been resolved by rotating the reduced dimensions to optimal direction and replacing the quadratic loss in the data fidelity term with α-divergence based loss function to counter the outliers, respectively. While dimensionality optimization guaranteed robustness to model order by maximizing signal intensity and smoothness, the robust loss function guaranteed decomposition stability against deviations from the Gaussian noise model. The proposed algorithm was derived by deploying spatial and temporal bases from the computationally fast sparse spatiotemporal blind source separation (ssBSS) method and solving a sequence of rank-1 matrix decomposition problems, where the l 1 /l 0 -norm penalty/constraint promoted sparsity, and the estimation of sparse representation matrices was accomplished using a block coordinate descent approach. This strategy allowed the utilization of multi-subject fMRI data to enhance the subject-wise source separation in a robust manner. It, therefore, can be considered a promising alternative to the state-of-the-art robust consistent adaptive sequential dictionary learning (rACSD) algorithm. The rswsDL and existing robust dictionary learning based source separation algorithms were applied to synthetic and experimental fMRI datasets to validate its performance. The rswsDL algorithm manifested a 16.7% increase in the mean correlation value over the rACSD algorithm.

show abstract

Section: H Block Design Dataset Resultsmentioning

confidence: 99%

Section: ) Swsdlmentioning

confidence: 99%

Section: F Block Design Dataset Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

Robust Subject-Wise Dictionary Learning for fMRI

Khalid,

Albahlal

2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Due to their model restricted to realize both (a) and (c) simultaneously by aggregating the common temporal dynamics across subjects, hybrid concatenation scheme (HCSDL) 51 , shared and subject-specific DL (ShSSDL) 52 , low-rank Tucker 2 model (LRT-2) 53 , sparse group bases (sgBACES) 50 , and sparse alternating rank-R/1 least squares (sRrR1LS) 54 merely learn common and subject-specific TCs/SMs and therefore cannot handle restingstate datasets or produce subject-wise dynamics. On the other hand, multi-subject DL (MSDL) 55 conceptualized only (b) and to some extent (c), resulting in its applicability to resting-state datasets only, and due to this, cannot accurately retrieve subject-wise responses.…”

Section: Related Workmentioning

confidence: 99%

“…For fMRI group analysis Eq. ( 1) is modified according to the sgBACES algorithm 50 as where m = {1, . .…”

Section: Introductionmentioning

confidence: 99%

A novel subject-wise dictionary learning approach using multi-subject fMRI spatial and temporal components

Khalid,

Nauman

2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

The conventional dictionary learning (DL) algorithms aim to adapt the dictionary/sparse code to individual functional magnetic resonance imaging (fMRI) data. Thus, lacking the capability to consolidate the spatiotemporal diversities offered by other subjects. Considering that subject-wise (sw) data matrix can be decomposed into the sparse linear combination of multi-subject (MS) time courses and MS spatial maps, two new algorithms, sw sequential DL (swsDL) and sw block DL (swbDL), have been proposed. They are based on the novel framework, defined by the mixing model, where base matrices prepared by operating a computationally fast sparse spatiotemporal blind source separation method over multiple subjects are employed to adapt the mixing matrices to sw training data. They solve the optimization models formulated using $$l_0$$ l 0 /$$l_1$$ l 1 -norm penalization/constraints through dictionary/sparse code pair update and alternating minimization approach. They are unique because no existing sparse DL method can incorporate MS spatiotemporal components while updating sw atoms/sparse codes, which can eventually be assembled using neuroscience knowledge to extract group-level dynamics. Various fMRI datasets are used to evaluate and compare the performance of the proposed algorithms with existing state-of-the-art algorithms. Specifically, overall, a $$14\%$$ 14 % increase in the mean correlation value and $$39\%$$ 39 % reduction in the mean computation time exhibited by swsDL and swbDL, respectively, over the adaptive consistent sequential dictionary algorithm.

show abstract

Three layered sparse dictionary learning algorithm for enhancing the subject wise segregation of brain networks

Khalid,

Nauman,

Akram

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Independent component analysis (ICA) and dictionary learning (DL) are the most successful blind source separation (BSS) methods for functional magnetic resonance imaging (fMRI) data analysis. However, ICA to higher and DL to lower extent may suffer from performance degradation by the presence of anomalous observations in the recovered time courses (TCs) and high overlaps among spatial maps (SMs). This paper addressed both problems using a novel three-layered sparse DL (TLSDL) algorithm that incorporated prior information in the dictionary update process and recovered full-rank outlier-free TCs from highly corrupted measurements. The associated sequential DL model involved factorizing each subject’s data into a multi-subject (MS) dictionary and MS sparse code while imposing a low-rank and a sparse matrix decomposition restriction on the dictionary matrix. It is derived by solving three layers of feature extraction and component estimation. The first and second layers captured brain regions with low and moderate spatial overlaps, respectively. The third layer that segregated regions with significant spatial overlaps solved a sequence of vector decomposition problems using the proximal alternating linearized minimization (PALM) method and solved a decomposition restriction using the alternating directions method (ALM). It learned outlier-free dynamics that integrate spatiotemporal diversities across brains and external information. It differs from existing DL methods owing to its unique optimization model, which incorporates prior knowledge, subject-wise/multi-subject representation matrices, and outlier handling. The TLSDL algorithm was compared with existing dictionary learning algorithms using experimental and synthetic fMRI datasets to verify its performance. Overall, the mean correlation value was found to be higher for the TLSDL than for the state-of-the-art subject-wise sequential DL (swsDL) technique.

show abstract

Sparse Group Bases for Multisubject fMRI Data

Cited by 5 publications

References 65 publications

Robust Subject-Wise Dictionary Learning for fMRI

Robust Subject-Wise Dictionary Learning for fMRI

A novel subject-wise dictionary learning approach using multi-subject fMRI spatial and temporal components

Three layered sparse dictionary learning algorithm for enhancing the subject wise segregation of brain networks

Contact Info

Product

Resources

About