Riemannian Geometry Boosts Representational Similarity Analyses of Dense Neural Time Series

Barachant, Alexandre; J, King

doi:10.1101/232710

Cited by 5 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While this cluster was missed by the tsSVM approach, it could be identified from the errors made by the CSP + SVM approach. As recently demonstrated, our results show that Riemannian distances provide a more precise clustering [45]. Importantly, here, this clustering benefited from our RSP method as a specific channel location was assigned to each entry of the dissimilarity matrix.…”

Section: Discussionsupporting

confidence: 61%

See 1 more Smart Citation

The Riemannian spatial pattern method: mapping and clustering movement imagery using Riemannian geometry

et al. 2021

View full text Add to dashboard Cite

Objective. Over the last decade, Riemannian geometry has shown promising results for motor imagery classification. However, extracting the underlying spatial features is not as straightforward as for applying common spatial pattern (CSP) filtering prior to classification. In this article, we propose a simple way to extract the spatial patterns obtained from Riemannian classification: the Riemannian spatial pattern (RSP) method, which is based on the backward channel selection procedure. Approach. The RSP method was compared to the CSP approach on ECoG data obtained from a quadriplegic patient while performing imagined movements of arm articulations and fingers. Main results. Similar results were found between the RSP and CSP methods for mapping each motor imagery task with activations following the classical somatotopic organization. Clustering obtained by pairwise comparisons of imagined motor movements however, revealed higher differentiation for the RSP method compared to the CSP approach. Importantly, the RSP approach could provide a precise comparison of the imagined finger flexions which added supplementary information to the mapping results. Significance. Our new RSP method illustrates the interest of the Riemannian framework in the spatial domain and as such offers new avenues for the neuroimaging community. This study is part of an ongoing clinical trial registered with ClinicalTrials.gov, NCT02550522.

show abstract

Section: Discussionsupporting

confidence: 61%

“…Importantly, these distance values can be directly used for mapping the brain regions that are activated during the imagination of a specific movement as well as for the clustering of these different movements. Indeed, Riemannian distances have been shown to provide an efficient way for the clustering of neural representations [45].…”

Section: Introductionmentioning

confidence: 99%

The Riemannian spatial pattern method: mapping and clustering movement imagery using Riemannian geometry

et al. 2021

View full text Add to dashboard Cite

show abstract

“…All analyses were performed using Python 3.8.5 and involved the following open-source Python packages. Functional connectivity estimation and centering were performed with Nilearn 0.7.1 [92] and PyReimann 0.2.6 [114], respectively. All steps to generate and align connectivity manifolds were generated using Brainspace 0.1.1 [60].…”

Section: Methodsmentioning

confidence: 99%

Distinct patterns of cortical manifold expansion and contraction underlie human sensorimotor adaptation

Gale

Areshenkoff

Standage

et al. 2022

Preprint

View full text Add to dashboard Cite

Sensorimotor learning is a dynamic, systems-level process that involves the combined action of multiple neural systems distributed across the brain. Although we understand a great deal about the specialized cortical systems that support specific components of action (such as reaching), we know less about how cortical systems function in a coordinated manner to facilitate adaptive behaviour. To address this gap in knowledge, our study measured human brain activity using functional MRI (fMRI) while participants performed a classic sensorimotor adaptation task, and used a manifold learning approach to describe how behavioural changes during adaptation relate to changes in the landscape of cortical activity. During early adaptation, we found that areas in parietal and premotor cortex exhibited significant contraction along the cortical manifold, which was associated with their increased covariance with regions in higher-order association cortex, including both the default mode and fronto-parietal networks. By contrast, during late adaptation, when visuomotor errors had been largely reduced, we observed a significant expansion of visual cortex along the cortical manifold, which was associated with its reduced covariance with association cortex and its increased intraconnectivity. Lastly, we found that individuals who learned more rapidly exhibited greater covariance between regions in the sensorimotor and association cortices during early adaptation. Together, these findings are consistent with a view that sensorimotor adaptation depends on changes in the integration and segregation of neural activity across more specialized regions of unimodal cortex with regions in association cortex implicated in higher-order processes. More generally, they lend support to an emerging line of evidence implicating regions of the default mode network in task-based performance.

show abstract

“…The methods described in this section were implemented and tested in python by using pyriemann [1], scikit-learn [8] and mne [7] libraries.…”

Section: Transfer Learningmentioning

confidence: 99%

Searching for Unique Neural Descriptors of Primary Colours in EEG Signals: A Classification Study

et al. 2021

View full text Add to dashboard Cite

Identifying unique descriptors for primary colours in EEG signals will open the way to Brain-Computer Interface (BCI) systems that can control devices by exposure to primary colours. This study is aimed to identify such unique descriptors in visual evoked potentials (VEPs) elicited in response to the exposure to primary colours (RGB: red, green, and blue) from 31 subjects. For that, we first created a classification method with integrated transfer learning that can be suitable for an online setting. The method classified between the three RGB classes for each subject, and the obtained average accuracy over 23 subjects was 74.48%. 14 out of 23 subjects were above the average level and the maximum accuracy was 93.42%. When cross-session transfer learning was evaluated, 86% of the subjects tested showed an average variation of 5.0% in the accuracy comparing with the source set.

show abstract

Riemannian Geometry Boosts Representational Similarity Analyses of Dense Neural Time Series

Cited by 5 publications

References 5 publications

The Riemannian spatial pattern method: mapping and clustering movement imagery using Riemannian geometry

The Riemannian spatial pattern method: mapping and clustering movement imagery using Riemannian geometry

Distinct patterns of cortical manifold expansion and contraction underlie human sensorimotor adaptation

Searching for Unique Neural Descriptors of Primary Colours in EEG Signals: A Classification Study

Contact Info

Product

Resources

About