DeepPrep: an accelerated, scalable and robust pipeline for neuroimaging preprocessing empowered by deep learning

作者：Jianxun Ren, Ning An, Lin Cong, Youjia Zhang, Zhenyu Sun, Wei Zhang, Shiyi Li, Ning Guo, Weigang Cui, Qingyu Hu, Weiwei Wang, Xuehai Wu, Yinyan Wang, Tao Jiang, Theodore D. Satterthwaite, Danhong Wang, Hesheng Liu · 发表于：Nature Methods · 年份：2025 · DOI：10.1038/s41592-025-02599-1 · 被引用次数：21 · 研究领域：Functional Brain Connectivity Studies、Advanced Neuroimaging Techniques and Applications、Advanced MRI Techniques and Applications

Neuroimaging has entered the era of big data. However, the advancement of preprocessing pipelines falls behind the rapid expansion of data volume, causing substantial computational challenges. Here we present DeepPrep, a pipeline empowered by deep learning and a workflow manager. Evaluated on over 55,000 scans, DeepPrep demonstrates tenfold acceleration, scalability and robustness compared to the state-of-the-art pipeline, thereby meeting the scalability requirements of neuroimaging. DeepPrep is a preprocessing pipeline for functional and structural MRI data from humans. Deep learning-based modules and an efficient workflow allow DeepPrep to handle large datasets.