Zhang Jing, Zhao Jian, Lin Haonan, Tan Yuying, Cheng Ji-Xin
Department of Biomedical Engineering, Boston University, Boston, Massachusetts 02215, United States.
Department of Electrical & Computer Engineering, Boston University, Boston, Massachusetts 02215, United States.
J Phys Chem Lett. 2020 Oct 15;11(20):8573-8578. doi: 10.1021/acs.jpclett.0c01598. Epub 2020 Sep 25.
Hyperspectral stimulated Raman scattering (SRS) by spectral focusing can generate label-free chemical images through temporal scanning of chirped femtosecond pulses. Yet, pulse chirping decreases the pulse peak power and temporal scanning increases the acquisition time, resulting in a much slower imaging speed compared to single-frame SRS using femtosecond pulses. In this paper, we present a deep learning algorithm to solve the inverse problem of getting a chemically labeled image from a single-frame femtosecond SRS image. Our DenseNet-based learning method, termed as DeepChem, achieves high-speed chemical imaging with a large signal level. Speed is improved by 2 orders of magnitude with four subcellular components (lipid droplet, endoplasmic reticulum, nuclei, cytoplasm) classified in MIA PaCa-2 cells and other cell types which were not used for training. Lipid droplet dynamics and cellular response to dithiothreitol in live MIA PaCa-2 cells are demonstrated using this computationally multiplex method.
通过光谱聚焦的高光谱受激拉曼散射（SRS）可以通过啁啾飞秒脉冲的时间扫描生成无标记化学图像。然而，脉冲啁啾会降低脉冲峰值功率，时间扫描会增加采集时间，导致与使用飞秒脉冲的单帧SRS相比成像速度慢得多。在本文中，我们提出了一种深度学习算法来解决从单帧飞秒SRS图像中获取化学标记图像的逆问题。我们基于DenseNet的学习方法，称为DeepChem，实现了具有大信号水平的高速化学成像。在未用于训练的MIA PaCa-2细胞和其他细胞类型中对四个亚细胞成分（脂滴、内质网、细胞核、细胞质）进行分类时，速度提高了2个数量级。使用这种计算复用方法展示了活MIA PaCa-2细胞中的脂滴动力学和细胞对二硫苏糖醇的反应。
