Extracting representations of cognition across neuroimaging studies improves brain decoding

PLoS Comput Biol. 2021 May 3;17(5):e1008795. doi: 10.1371/journal.pcbi.1008795. eCollection 2021 May.

Abstract

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.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Brain / diagnostic imaging*
  • Brain / physiology*
  • Cognition / physiology*
  • Computational Biology
  • Functional Neuroimaging / statistics & numerical data*
  • Humans
  • Linear Models
  • Magnetic Resonance Imaging / statistics & numerical data
  • Mathematical Concepts
  • Models, Neurological
  • Models, Psychological
  • Nerve Net / physiology
  • Stochastic Processes
  • Task Performance and Analysis

Grant support

This project has received funding from the European Union’s Horizon 2020 Framework Programme for Research and Innovation under grant agreement N785907 (Human Brain Project SGA2). Arthur Mensch was supported by a grant from the Labex DigiCosme (AMPHI project). Julien Mairal was supported by the ERC grant SOLARIS (N714381) and a grant from ANR (MACARON project ANR-14-CE23-0003-01). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.