Ren Jianxun, An Ning, Lin Cong, Zhang Youjia, Sun Zhenyu, Zhang Wei, Li Shiyi, Guo Ning, Cui Weigang, Hu Qingyu, Wang Weiwei, Wu Xuehai, Wang Yinyan, Jiang Tao, Satterthwaite Theodore D, Wang Danhong, Liu Hesheng
Changping Laboratory, Beijing, China.
Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China.
Nat Methods. 2025 Mar;22(3):473-476. doi: 10.1038/s41592-025-02599-1. Epub 2025 Feb 6.
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.
神经影像学已进入大数据时代。然而,预处理流程的发展落后于数据量的快速增长,带来了巨大的计算挑战。在此,我们展示了DeepPrep,这是一种由深度学习和工作流管理器支持的流程。通过对超过55000次扫描进行评估,与最先进的流程相比,DeepPrep展现出了十倍的加速、可扩展性和稳健性,从而满足了神经影像学的可扩展性要求。