arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.05234cs.CV
收藏

注意与解码:基于注意模型的四维fMRI任务状态解码

Attend and Decode: 4D fMRI Task State Decoding Using Attention Models

Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室)

Sam Nguyen, Brenda Ng, Alan D. Kaplan, Priyadip Ray

摘要:

功能性磁共振成像(fMRI)是一种神经成像模式,其在受试者休息或在不同条件下执行各种功能任务时捕获受试者大脑中的血氧水平。给定fMRI数据,推断任务的问题,称为任务状态解码,是具有挑战性的,由于高维(每个数据数亿个采样点)和复杂的时空血流模式固有的数据。在这项工作中,我们建议通过将其转换为4D时空分类问题来解决fMRI任务状态解码问题。我们提出了一种新的架构,称为大脑注意和解码(BAnD),使用残留的卷积神经网络的空间特征提取和自我注意力机制的时间建模。我们实现了显着的性能增益相比,以前的作品在7个任务的基准从大规模的人类连接组项目-年轻的成年人(HCP-YA)数据集。我们还研究了BAnD的提取功能看不见的HCP任务的可转移性,无论是通过冻结的空间特征提取层和重新训练的时间模型,或微调整个模型。来自BAnD的预训练特征在类似的任务中很有用,而对它们进行微调可以在看不见的任务/条件下产生有竞争力的结果。

英文摘要:

Functional magnetic resonance imaging (fMRI) is a neuroimaging modality that captures the blood oxygen level in a subject's brain while the subject either rests or performs a variety of functional tasks under different conditions. Given fMRI data, the problem of inferring the task, known as task state decoding, is challenging due to the high dimensionality (hundreds of million sampling points per datum) and complex spatio-temporal blood flow patterns inherent in the data. In this work, we propose to tackle the fMRI task state decoding problem by casting it as a 4D spatio-temporal classification problem. We present a novel architecture called Brain Attend and Decode (BAnD), that uses residual convolutional neural networks for spatial feature extraction and self-attention mechanisms for temporal modeling. We achieve significant performance gain compared to previous works on a 7-task benchmark from the large-scale Human Connectome Project-Young Adult (HCP-YA) dataset. We also investigate the transferability of BAnD's extracted features on unseen HCP tasks, either by freezing the spatial feature extraction layers and retraining the temporal model, or finetuning the entire model. The pre-trained features from BAnD are useful on similar tasks while finetuning them yields competitive results on unseen tasks/conditions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑