Text2Brain: Synthesis of Brain Activation Maps from Free-form Text Query
This provides a tool for neuroscientists to retrieve priors and generate hypotheses from a large knowledge base, addressing limitations of existing meta-analytic tools.
The authors tackled the challenge of synthesizing brain activation maps from free-form text queries by proposing Text2Brain, a neural network approach that combines a transformer-based text encoder and a 3D image generator, trained on 13,000 neuroimaging studies, and demonstrated it can generate anatomically-plausible patterns.
Most neuroimaging experiments are under-powered, limited by the number of subjects and cognitive processes that an individual study can investigate. Nonetheless, over decades of research, neuroscience has accumulated an extensive wealth of results. It remains a challenge to digest this growing knowledge base and obtain new insights since existing meta-analytic tools are limited to keyword queries. In this work, we propose Text2Brain, a neural network approach for coordinate-based meta-analysis of neuroimaging studies to synthesize brain activation maps from open-ended text queries. Combining a transformer-based text encoder and a 3D image generator, Text2Brain was trained on variable-length text snippets and their corresponding activation maps sampled from 13,000 published neuroimaging studies. We demonstrate that Text2Brain can synthesize anatomically-plausible neural activation patterns from free-form textual descriptions of cognitive concepts. Text2Brain is available at https://braininterpreter.com as a web-based tool for retrieving established priors and generating new hypotheses for neuroscience research.