Extracting representations of cognition across neuroimaging studies improves brain decoding.
Cognitive brain imaging is accumulating datasets about the neural substrate of many different mental processes. Yet, most studies are based on few subjects and have low statistical power. Analyzing data across studies could bring more statistical power; yet the current brain-imaging analytic framewo...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2021-05-01
|
Series: | PLoS Computational Biology |
Online Access: | https://doi.org/10.1371/journal.pcbi.1008795 |
id |
doaj-c93b3d22c35c4172af0e6c6a4f303f16 |
---|---|
record_format |
Article |
spelling |
doaj-c93b3d22c35c4172af0e6c6a4f303f162021-05-29T04:33:03ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582021-05-01175e100879510.1371/journal.pcbi.1008795Extracting representations of cognition across neuroimaging studies improves brain decoding.Arthur MenschJulien MairalBertrand ThirionGaël VaroquauxCognitive brain imaging is accumulating datasets about the neural substrate of many different mental processes. Yet, most studies are based on few subjects and have low statistical power. Analyzing data across studies could bring more statistical power; yet the current brain-imaging analytic framework cannot be used at scale as it requires casting all cognitive tasks in a unified theoretical framework. We introduce a new methodology to analyze brain responses across tasks without a joint model of the psychological processes. The method boosts statistical power in small studies with specific cognitive focus by analyzing them jointly with large studies that probe less focal mental processes. Our approach improves decoding performance for 80% of 35 widely-different functional-imaging studies. It finds commonalities across tasks in a data-driven way, via common brain representations that predict mental processes. These are brain networks tuned to psychological manipulations. They outline interpretable and plausible brain structures. The extracted networks have been made available; they can be readily reused in new neuro-imaging studies. We provide a multi-study decoding tool to adapt to new data.https://doi.org/10.1371/journal.pcbi.1008795 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Arthur Mensch Julien Mairal Bertrand Thirion Gaël Varoquaux |
spellingShingle |
Arthur Mensch Julien Mairal Bertrand Thirion Gaël Varoquaux Extracting representations of cognition across neuroimaging studies improves brain decoding. PLoS Computational Biology |
author_facet |
Arthur Mensch Julien Mairal Bertrand Thirion Gaël Varoquaux |
author_sort |
Arthur Mensch |
title |
Extracting representations of cognition across neuroimaging studies improves brain decoding. |
title_short |
Extracting representations of cognition across neuroimaging studies improves brain decoding. |
title_full |
Extracting representations of cognition across neuroimaging studies improves brain decoding. |
title_fullStr |
Extracting representations of cognition across neuroimaging studies improves brain decoding. |
title_full_unstemmed |
Extracting representations of cognition across neuroimaging studies improves brain decoding. |
title_sort |
extracting representations of cognition across neuroimaging studies improves brain decoding. |
publisher |
Public Library of Science (PLoS) |
series |
PLoS Computational Biology |
issn |
1553-734X 1553-7358 |
publishDate |
2021-05-01 |
description |
Cognitive brain imaging is accumulating datasets about the neural substrate of many different mental processes. Yet, most studies are based on few subjects and have low statistical power. Analyzing data across studies could bring more statistical power; yet the current brain-imaging analytic framework cannot be used at scale as it requires casting all cognitive tasks in a unified theoretical framework. We introduce a new methodology to analyze brain responses across tasks without a joint model of the psychological processes. The method boosts statistical power in small studies with specific cognitive focus by analyzing them jointly with large studies that probe less focal mental processes. Our approach improves decoding performance for 80% of 35 widely-different functional-imaging studies. It finds commonalities across tasks in a data-driven way, via common brain representations that predict mental processes. These are brain networks tuned to psychological manipulations. They outline interpretable and plausible brain structures. The extracted networks have been made available; they can be readily reused in new neuro-imaging studies. We provide a multi-study decoding tool to adapt to new data. |
url |
https://doi.org/10.1371/journal.pcbi.1008795 |
work_keys_str_mv |
AT arthurmensch extractingrepresentationsofcognitionacrossneuroimagingstudiesimprovesbraindecoding AT julienmairal extractingrepresentationsofcognitionacrossneuroimagingstudiesimprovesbraindecoding AT bertrandthirion extractingrepresentationsofcognitionacrossneuroimagingstudiesimprovesbraindecoding AT gaelvaroquaux extractingrepresentationsofcognitionacrossneuroimagingstudiesimprovesbraindecoding |
_version_ |
1721422607713042432 |