Pattern classification precedes region-average hemodynamic response in early visual cortex

Kohler, Peter J.; Fogelson, Sergey V.; Reavis, Eric A.; Meng, Ming; Guntupalli, J. Swaroop; Hanke, Michael; Halchenko, Yaroslav O.; Connolly, Andrew C.; Haxby, James V.; Tse, Peter U.

doi:10.1016/j.neuroimage.2013.04.019

Cited by 22 publications

(19 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, our results add to a growing body of evidence showing the higher sensitivity of MVPA compared with univariate analyses (e.g. Jimura and Poldrack, 2012; Kohler et al , 2013). …”

Section: Discussionsupporting

confidence: 77%

Neural predictors of evaluative attitudes toward celebrities

Izuma

Shibata

Matsumoto

et al. 2016

Social Cognitive and Affective Neuroscience

View full text Add to dashboard Cite

Our attitudes toward others influence a wide range of everyday behaviors and have been the most extensively studied concept in the history of social psychology. Yet they remain difficult to measure reliably and objectively, since both explicit and implicit measures are typically confounded by other psychological processes. We here address the feasibility of decoding incidental attitudes based on brain activations. Participants were presented with pictures of members of a Japanese idol group inside an functional magnetic resonance imaging scanner while performing an unrelated detection task, and subsequently (outside the scanner) performed an incentive-compatible choice task that revealed their attitude toward each celebrity. We used a real-world election scheme that exists for this idol group, which confirmed both strongly negative and strongly positive attitudes toward specific individuals. Whole-brain multivariate analyses (searchlight-based support vector regression) showed that activation patterns in the anterior striatum predicted each participant’s revealed attitudes (choice behavior) using leave-one-out (as well as 4-fold) cross-validation across participants. In contrast, attitude extremity (unsigned magnitude) could be decoded from a distinct region in the posterior striatum. The findings demonstrate dissociable striatal representations of valenced attitude and attitude extremity and constitute a first step toward an objective and process-pure neural measure of attitudes.

show abstract

“…In general, our results add to a growing body of evidence showing the higher sensitivity of MVPA compared with univariate analyses (e.g. Jimura and Poldrack, 2012; Kohler et al , 2013). …”

Section: Discussionsupporting

confidence: 77%

Neural predictors of evaluative attitudes toward celebrities

Izuma

Shibata

Matsumoto

et al. 2016

Social Cognitive and Affective Neuroscience

View full text Add to dashboard Cite

show abstract

“…Rather than being confined to lower-level sensory classifications, MVPA has also been successful in decoding higher-order functions (Cole, Etzel, Zacks, Schneider, & Braver, 2011; Soon, Brass, Heinze, & Haynes, 2008). Application of MVPA in a sliding window approach has also highlighted its utility in decoding dynamics, with above-chance classifications observed earlier than equivalent univariate approaches in trial-locked analyses applied to both fMRI (Kohler et al, 2013) and MEG (Borst, Ghuman, & Anderson, 2016; Sudre et al, 2012). Overall, findings from the application of MVPA algorithms to task activations emphasize their considerable utility in capturing richer and more specific cognitive representations in space and time.…”

Section: Increasing the Sensitivity Of Network Components Via Multmentioning

confidence: 99%

From connectome to cognition: The search for mechanism in human functional brain networks

2017

View full text Add to dashboard Cite

Recent developments in functional connectivity research have expanded the scope of human neuroimaging, from identifying changes in regional activation amplitudes to detailed mapping of large-scale brain networks. However, linking network processes to a clear role in cognition demands advances in the theoretical frameworks, algorithms, and experimental approaches applied. This would help evolve the field from a descriptive to an explanatory state, by targeting network interactions that can mechanistically account for cognitive effects. In the present review, we provide an explicit framework to aid this search for “network mechanisms”, which anchors recent methodological advances in functional connectivity estimation to a renewed emphasis on careful experimental design. We emphasize how this framework can address specific questions in network neuroscience. These span ambiguity over the cognitive relevance of resting-state networks, how to characterize task-evoked and spontaneous network dynamics, how to identify directed or “effective” connections, and how to apply multivariate pattern analysis at the network level. In parallel, we apply the framework to highlight the mechanistic interaction of network components that remain “stable” across task domains and more “flexible” components associated with on-task reconfiguration. By emphasizing the need to structure the use of diverse analytic approaches with sound experimentation, our framework promotes an explanatory mapping between the workings of the cognitive mind and the large-scale network mechanisms of the human brain.

show abstract

“…For comparison purposes, we used single TR spatial observation (utilizing the spatial 280 information acquired during one Time to Repeat or (TR)). The maximum accuracy of 281 single TR observation in slow event-related fMRI was reported to be around the peak of 282 HRF at ~5 seconds, but with a small jitter across regions (Kohler et al, 2013). The HRF 283 peak has also been found to be jittered across people (~ 4 to 7 seconds) (Handwerker,284 Ollinger, & D'Esposito, 2004).…”

Section: Decreases 244mentioning

confidence: 99%

“…ST 99 embedding was also investigated for another type of stimulus classification in (Rao,100 Garg, & Cecchi, 2011) applying the same methods discussed by Fogelson and colleagues 101 (Fogelson et al, 2011). Another study investigated the variability of temporal dynamic 102 classification performance across single TR observations within the slow event-related 103 trails (Kohler et al, 2013). Their timepoint-by-timepoint MVPC showed that the peak of 104 classification accuracy was around the peak of region-average HRF; in some regions 105 prior to and in some regions after the region-average HRF peak.…”

Section: Introduction 69mentioning

confidence: 99%

“…Although considering the shape of HRF for 111 modeling brain activity, they assign the same stimulus label to the dynamic brain 112 response that is changing over time. The temporal dynamics of the BOLD signal to 113 stimuli of different classes, and within different brain regions are very likely different 114 (Chu et al, 2011;Kohler et al, 2013). Not considering such these differences may reduce 115 the sensitivity of the classifier and reduce the decoding accuracy.…”

Section: Introduction 69mentioning

confidence: 99%

See 1 more Smart Citation

Spatiotemporal Feature Selection Improves Prediction Accuracy of Multi-Voxel Pattern Classification

Choupan

Gal

Douglas

et al. 2019

Preprint

View full text Add to dashboard Cite

Machine 33 34 Highlights: 35• Spatiotemporal feature selection effect on MVPC was assessed in slow event-related 36 fMRI 37• Spatiotemporal feature selection improved brain decoding accuracy 38• From ~2-11 seconds after stimuli onset were the most informative part of each trial 39• Random forest outperformed support vector machines 40• Random forest benefited more from temporal changes compared with support vector 41 machine 42 Abstract 43The importance of spatiotemporal feature selection in fMRI decoding studies has not 44 been studied exhaustively. Temporal embedding of features allows the incorporation of 45 brain activity dynamics into multivariate pattern classification, and may provide enriched 46 information about stimulus-specific response patterns and potentially improve prediction 47 accuracy. This study investigates the possibility of enhancing the classification 48 performance by exploring spatial and temporal (spatiotemporal) domain, to identify the 49 optimum combination of the spatiotemporal features based on the classification 50 performance. We investigated the importance of spatiotemporal feature selection using a 51 slow event-related design adapted from the classic Haxby et al. (2001) study. Data were 52 collected using a multiband fMRI sequence with temporal resolution of 0.568 seconds. A 53 wide range of spatiotemporal observations was created as various combinations of 54 spatiotemporal features. Using both random forest, and support vector machine, 55 classifiers, prediction accuracies for these combinations were then compared with the 56 single time-point spatial multivariate pattern approach that uses only a single temporal 57 observation. The results showed that on average spatiotemporal feature selection 58 improved prediction accuracy. Moreover, the random forest algorithm outperformed the 59 support vector machine and benefitted from temporal information to a greater extent. As 60 expected, the most influential temporal durations were found to be around the peak of the 61 hemodynamic response function, a few seconds after the stimuli onset until ~4 seconds 62 after the peak of the hemodynamic response function. The superiority of spatiotemporal 63 feature selection over single time-point spatial approaches invites future work to design 64 systematic and optimal approaches to the incorporation of spatiotemporal dependencies 65 into feature selection for decoding. 66 67 68shown to alter the results of MVPC in block design experiments (Choupan et al., 2014; 130 Mourao-Miranda, Friston, & Brammer, 2007; Sapountzis, Schluppeck, Bowtell, & 131 Peirce, 2010). 132Following the previous works, this study is based on the hypothesis that by embedding 133 the temporal dynamics provided by fMRI into the process of multivariate brain pattern 134 recognition, more information contained in the BOLD signal can be utilized compared 135 with single TR methods, leading to a potential improvement in the prediction 136 performance. In particular, we predicted that not all of the temporal dynamics...

show abstract

Pattern classification precedes region-average hemodynamic response in early visual cortex

Cited by 22 publications

References 31 publications

Neural predictors of evaluative attitudes toward celebrities

Neural predictors of evaluative attitudes toward celebrities

From connectome to cognition: The search for mechanism in human functional brain networks

Spatiotemporal Feature Selection Improves Prediction Accuracy of Multi-Voxel Pattern Classification

Contact Info

Product

Resources

About