A semi-supervised method for multi-subject FMRI functional alignment

Turek, Javier S.; Willke, Theodore L.; Chen, Po-Hsuan; Ramadge, Peter J.

doi:10.1109/icassp.2017.7952326

Cited by 11 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hyperalignment (DHA) [27]; Semi-Supervised SRM (SS-SRM) [31]; and Local Discriminant Hyperalignment (LDHA) [10].…”

Section: Methodmentioning

confidence: 99%

“…Like the original paper [27], we consider 3 hidden layer (C = 5) for DHA, the number of units in the intermediate layers are considered L × V , and deep network is trained by using η = 10 −4 learning rate. For SS-SRM, we also considered γ = 1.0 and α = 0.5 [31]. It is worth noting that this paper employs BrainIAK library 1 for running SRM and SS-SRM.…”

Section: Methodmentioning

confidence: 99%

“…Turek et al proposed a Semi-Supervised SRM (SS-SRM) that simultaneously applies the alignment and performs the analysis. This method still used the unsupervised SRM [7] for alignment, which were based on unsupervised features (L SRM in [31]) and the semi-supervised Multinomial Logistic Regression for Classification Analysis [31]. Yousefnezhad et al developed LDHA, where this method applied the locality information (i.e., the nearest neighbors of both within-class and between-classes neural activities) for improving the performance of classification [10].…”

Section: Related Workmentioning

confidence: 99%

“…It is worth noting that in most of fMRI problems, we have: L, S ≤ T ≤ V . These time complexity can significantly increase the runtime of SHA in comparison with other stateof-the-art techniques, e.g., the time complexity of SRM in BrainIAK library is O ζ −1 τ ST V , where τ is the number of iterations [31], [48].…”

Section: E Time Complexity and Runtime Analysismentioning

confidence: 99%

See 3 more Smart Citations

Supervised Hyperalignment for Multisubject fMRI Data Alignment

Yousefnezhad

Selvitella

Han

et al. 2021

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

Hyperalignment has been widely employed in Multivariate Pattern (MVP) analysis to discover the cognitive states in the human brains based on multi-subject functional Magnetic Resonance Imaging (fMRI) datasets. Most of the existing HA methods utilized unsupervised approaches, where they only maximized the correlation between the voxels with the same position in the time series. However, these unsupervised solutions may not be optimum for handling the functional alignment in the supervised MVP problems. This paper proposes a Supervised Hyperalignment (SHA) method to ensure better functional alignment for MVP analysis, where the proposed method provides a supervised shared space that can maximize the correlation among the stimuli belonging to the same category and minimize the correlation between distinct categories of stimuli. Further, SHA employs a generalized optimization solution, which generates the shared space and calculates the mapped features in a single iteration, hence with optimum time and space complexities for large datasets. Experiments on multi-subject datasets demonstrate that SHA method achieves up to 19% better performance for multiclass problems over the state-of-the-art HA algorithms.

show abstract

“…Hyperalignment (DHA) [27]; Semi-Supervised SRM (SS-SRM) [31]; and Local Discriminant Hyperalignment (LDHA) [10].…”

Section: Methodmentioning

confidence: 99%

Section: Methodmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: E Time Complexity and Runtime Analysismentioning

confidence: 99%

See 2 more Smart Citations

Supervised Hyperalignment for Multisubject fMRI Data Alignment

Yousefnezhad

Selvitella

Han

et al. 2021

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

show abstract

“…For example, a fast SRM implementation has been introduced for rapidly analyzing large datasets with reduced memory demands [43]. The robust SRM algorithm tolerates subject specific outlying response elements [44], and the semi-supervised SRM capitalizes on categorical stimulus labels when available [45]. Finally, estimating the SRM from functional connectivity data rather than response time series circumvents the need for a single shared stimulus across subjects; connectivity SRM allows us to derive a single shared response space across different stimuli with a shared connectivity profile [46].…”

Section: Shared Response Model (Srm)mentioning

confidence: 99%

BrainIAK: The Brain Imaging Analysis Kit

Kumar¹,

Anderson²,

Antony³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Functional magnetic resonance imaging (fMRI) offers a rich source of data for studying the neural basis of cognition. Here, we describe the Brain Imaging Analysis Kit (BrainIAK), an open-source, free Python package that provides computationally-optimized solutions to key problems in advanced fMRI analysis. A variety of techniques are presently included in BrainIAK: intersubject correlation (ISC) and intersubject functional connectivity (ISFC), functional alignment via the shared response model (SRM), full correlation matrix analysis (FCMA), a Bayesian version of representational similarity analysis (BRSA), event segmentation using hidden Markov models, topographic factor analysis (TFA), inverted encoding models (IEM), an fMRI data simulator that uses noise characteristics from real data (fmrisim), and some emerging methods. These techniques have been optimized to leverage the efficiencies of high performance compute (HPC) clusters, and the same code can be seamlessly transferred from a laptop to a cluster. For each of the aforementioned techniques, we describe the data analysis problem that the technique is meant to solve, and how it solves that problem; we also include an example Jupyter notebook for each technique and an annotated bibliography of papers that have used and/or described that technique. In addition to the sections describing various analysis techniques in BrainIAK, we have included sections describing the future applications of BrainIAK to real-time fMRI, tutorials that we have developed and shared online to facilitate learning the techniques in BrainIAK, computational innovations in BrainIAK, and how to contribute to BrainIAK. We hope that this manuscript helps readers to understand how BrainIAK might be useful in their research.

show abstract

Graph Hyperalignment for Multi-subject fMRI Functional Alignment

Chen

Zhang

2019

Graph Learning in Medical Imaging

View full text Add to dashboard Cite

A semi-supervised method for multi-subject FMRI functional alignment

Cited by 11 publications

References 19 publications

Supervised Hyperalignment for Multisubject fMRI Data Alignment

Supervised Hyperalignment for Multisubject fMRI Data Alignment

BrainIAK: The Brain Imaging Analysis Kit

Graph Hyperalignment for Multi-subject fMRI Functional Alignment

Contact Info

Product

Resources

About