A transformer-Based neural language model that synthesizes brain activation maps from free-form text queries
A transformer-Based neural language model that synthesizes brain activation maps from free-form text queries
复制标题
基于 Transformer 的神经语言模型，可根据自由格式的文本查询合成大脑激活图
DOI：
10.1016/j.media.2022.102540
复制
发表时间：
2022
影响因子：
10.9
通讯作者：
Sabuncu, Mert R.
中科院分区：
文献类型：
--
作者：
Ngo, Gia H.;Nguyen, Minh;Chen, Nancy F.;Sabuncu, Mert R.
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.消化这些不断增长的文献并获得新颖的见解仍然是一个重大挑战，因为现有的元分析工具仅限于关键字查询。 In this paper, we presentText2Brain, 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 结合了基于 Transformer 的文本编码器和 3D 图像生成器，并接受了可变长度文本片段及其从 13,000 份已发表研究中采样的相应激活图的训练。在我们的实验中，我们证明 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文献并生成新的假设。
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 presentText2Brain, 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.