Recent developments in multivariate pattern analysis for functional MRI

Yang, Zhi; Fang, Fang; Weng, Xuchu

doi:10.1007/s12264-012-1253-3

Cited by 47 publications

(37 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We found that we could improve the performance of TLSA by averaging all the training trials within each condition, reducing X to two rows. Averaging in this way, a common technique in multivariate decoding analyses of event-related fMRI (Yang et al, 2012), is helpful in reducing noise.…”

Section: Resultsmentioning

confidence: 99%

Decomposing spatiotemporal brain patterns into topographic latent sources

Gershman¹,

Blei²,

Norman³

et al. 2014

NeuroImage

View full text Add to dashboard Cite

This paper extends earlier work on spatial modeling of fMRI data to the temporal domain, providing a framework for analyzing high temporal resolution brain imaging modalities such as electroencapholography (EEG). The central idea is to decompose brain imaging data into a covariate-dependent superposition of functions defined over continuous time and space (what we refer to as topographic latent sources). The continuous formulation allows us to parametrically model spatiotemporally localized activations. To make group-level inferences, we elaborate the model hierarchically by sharing sources across subjects. We describe a variational algorithm for parameter estimation that scales efficiently to large data sets. Applied to three EEG data sets, we find that the model produces good predictive performance and reproduces a number of classic findings. Our results suggest that topographic latent sources serve as an effective hypothesis space for interpreting spatiotemporal brain imaging data.

show abstract

Section: Resultsmentioning

confidence: 99%

Decomposing spatiotemporal brain patterns into topographic latent sources

Gershman¹,

Blei²,

Norman³

et al. 2014

NeuroImage

View full text Add to dashboard Cite

show abstract

“…The variability in performance between classifiers with different learning strategies can provide different interpretations on how neurons are organized to encode stimuli features (Misaki et al, 2010; Yang et al, 2012). …”

Section: Neural Signature's Identificationmentioning

confidence: 99%

“…For example, classifiers may be able to distinguish face and furniture stimuli based on activation patterns in V1. However, without the a-priori knowledge that this region is known not to have category-preference, we can easily indulge in the fallacy of inferring the engagement of specific cognitive processes (categorization in V1) from patterns of activation (Yang et al, 2012). …”

Section: Reading Out Neural Contentsmentioning

confidence: 99%

The challenges of neural mind-reading paradigms

Vilarroya¹

2013

Front. Hum. Neurosci.

View full text Add to dashboard Cite

Neural mind-reading studies, based on multivariate pattern analysis (MVPA) methods, are providing exciting new studies. Some of the results obtained with these paradigms have raised high expectations, such as the possibility of creating brain reading devices. However, such hopes are based on the assumptions that: (a) the BOLD signal is a marker of neural activity; (b) the BOLD pattern identified by a MVPA is a neurally sound pattern; (c) the MVPA's feature space is a good mapping of the neural representation of a stimulus, and (d) the pattern identified by a MVPA corresponds to a representation. I examine here the challenges that still have to be met before fully accepting such assumptions.

show abstract

“…In fact, using a variety of multivariate pattern analysis (MVPA)(Norman et al, 2006), researchers have successfully decoded the category of viewed objects from BOLD signals in the ventral temporal cortex (Haxby et al, 2001); the subjective mnemonic status of visual stimuli using the BOLD patterns from a distributed network of parietal and frontal regions (Rissman et al, 2010); a sound category associated with sound-implying, silent, visual stimuli looking solely at patterns within the auditory cortex (Meyer et al, 2010); and free choices of abstract intentions from patterns in the medial prefrontal and parietal cortices (Soon et al, 2013). All this evidence suggests that although fMRI signal has insufficient temporal and spatial resolution to depict fine-scale neuronal events, spatiotemporal hemodynamic response patterns recorded via fMRI permit successful and robust decoding of low- to high-level representations of information (Haynes and Rees, 2006; Xu et al, 2012; Yang et al, 2012). …”

Section: Introductionmentioning

confidence: 99%

Using fMRI to decode true thoughts independent of intention to conceal

Yang¹,

Huang²,

Gonzalez-Castillo³

et al. 2014

NeuroImage

Self Cite

View full text Add to dashboard Cite

Multi-variate pattern analysis (MVPA) applied to BOLD-fMRI has proven successful at decoding complicated fMRI signal patterns associated with a variety of cognitive processes. One cognitive process, not yet investigated, is the mental representation of “Yes/No” thoughts that precede the actual overt response to a binary “Yes/No” question. In this study, we focus on examining: (1) whether spatial patterns of the hemodynamic response carry sufficient information to allow reliable decoding of “Yes/No” thoughts; and (2) whether decoding of “Yes/No” thoughts is independent of the intention to respond honestly or dishonestly. To achieve this goal, we conducted two separate experiments. Experiment 1, collected on a 3T scanner, examined the whole brain to identify regions that carry sufficient information to permit significantly above-chance prediction of “Yes/No” thoughts at the group level. In Experiment 2, collected on a 7T scanner, we focused on the regions identified in Experiment 1 to examine the capability of achieving high decoding accuracy at the single subject level. A set of regions—namely right superior temporal gyrus, left supra-marginal gyrus, and left middle frontal gyrus—exhibited high decoding power. Decoding accuracy for these regions increased with trial averaging. When 18 trials were averaged, the median accuracies were 82.5%, 77.5%, and 79.5%, respectively. When trials were separated according to deceptive intentions (set via experimental cues), and classifiers were trained on honest trials, but tested on trials where subjects were asked to deceive, the median accuracies of these regions still reached 66%, 75%, and 78.5%. These results provide evidence that concealed “Yes/No” thoughts are encoded in the BOLD signal, retaining some level of independence from the subject’s intentions to answer honestly or dishonestly. These findings also suggest the theoretical possibility for more efficient brain-computer interfaces where subjects only need to think their answers to communicate.

show abstract

Recent developments in multivariate pattern analysis for functional MRI

Cited by 47 publications

References 79 publications

Decomposing spatiotemporal brain patterns into topographic latent sources

Decomposing spatiotemporal brain patterns into topographic latent sources

The challenges of neural mind-reading paradigms

Using fMRI to decode true thoughts independent of intention to conceal

Contact Info

Product

Resources

About