Neuroimaging studies are often limited by the number of subjects and cognitive processes that can be feasibly interrogated. However, a rapidly growing number of neuroscientific studies have collectively accumulated an extensive wealth of results. Digesting this growing literature and obtaining novel insights remains to be a major challenge, since existing meta-analytic tools are constrained to keyword queries. In this paper, we present Text2Brain, an easy to use tool for synthesizing brain activation maps from open-ended text queries. Text2Brain was built on a transformer-based neural network language model and a coordinate-based meta-analysis of neuroimaging studies. Text2Brain combines a transformer-based text encoder and a 3D image generator, and was trained on variable-length text snippets and their corresponding activation maps sampled from 13,000 published studies. In our experiments, we demonstrate that Text2Brain can synthesize meaningful neural activation patterns from various free-form textual descriptions. Text2Brain is available at https://braininterpreter.com as a web-based tool for efficiently searching through the vast neuroimaging literature and generating new hypotheses.

神经影像学研究通常受到可以切实询问的受试者数量和认知过程的限制。然而，越来越多的神经科学研究共同积累了丰富的成果。消化这些不断增长的文献并获得新颖的见解仍然是一个主要挑战，因为现有的元分析工具仅限于关键字查询。在本文中，我们介绍了 Text2Brain，一个易于使用的工具，用于从开放式文本查询中合成大脑激活图。Text2Brain 建立在基于变换器的神经网络语言模型和基于坐标的神经影像学研究元分析之上。Text2Brain 结合了一个基于转换器的文本编码器和一个 3D 图像生成器，并接受了可变长度文本片段及其从 13,000 项已发表研究中抽取的相应激活图的训练。在我们的实验中，我们证明了 Text2Brain 可以从各种自由形式的文本描述中合成有意义的神经激活模式。Text2Brain 可在 https://braininterpreter.com 上找到，它是一种基于网络的工具，可有效搜索大量神经影像学文献并生成新假设。