Extracting representations of cognition across neuroimaging studies improves brain decoding

TL;DR

This paper introduces a new method for analyzing neuroimaging data across multiple studies, enhancing brain decoding accuracy by identifying common brain representations of mental processes without requiring a unified theoretical model.

Contribution

The authors present a novel multi-study analysis approach that boosts statistical power and uncovers shared brain networks across diverse cognitive tasks, without a joint psychological model.

Findings

Improves decoding performance in 80% of tested studies.

Identifies common brain networks predictive of mental processes.

Provides reusable brain network representations and a multi-study decoding tool.

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.