A deep learning-based segmentation pipeline for profiling cellular morphodynamics using multiple types of live cell microscopy
A deep learning-based segmentation pipeline for profiling cellular morphodynamics using multiple types of live cell microscopy
复制标题
DOI：
10.1016/j.crmeth.2021.100105
复制
发表时间：
2021-11-22
期刊：
影响因子：
--
通讯作者：
Lee, Kwonmoo
中科院分区：
文献类型：
--
作者：
Jang, Junbong;Wang, Chuangqi;Lee, Kwonmoo
为了准确分割细胞边缘并从活细胞成像数据中量化细胞形态动力学，我们开发了一个基于深度学习的管道，称为MARS-Net（基于多显微镜类型的准确和鲁棒分割网络）。MARS-Net利用迁移学习和来自多种类型显微镜的数据，以高精度定位细胞边缘。为了对不同类型的活细胞显微镜进行有效训练，MARS-Net包括一个预训练的VGG 19编码器，带有U-Net解码器和dropout层。我们训练MARS-Net上的电影相衬，旋转盘共聚焦，和全内反射荧光显微镜。MARS-Net比使用单一显微镜类型数据集训练的神经网络模型产生更准确的边缘定位。我们希望MARS-Net可以通过提供复杂活细胞数据集的精确像素级分割来加速细胞形态动力学的研究。
To accurately segment cell edges and quantify cellular morphodynamics from live-cell imaging data, we developed a deep learning-based pipeline termed MARS-Net (multiple-microscopy-type-based accurate and robust segmentation network). MARS-Net utilizes transfer learning and data from multiple types of microscopy to localize cell edges with high accuracy. For effective training on distinct types of live-cell microscopy, MARS-Net comprises a pretrained VGG19 encoder with U-Net decoder and dropout layers. We trained MARS-Net on movies from phase-contrast, spinning-disk confocal, and total internal reflection fluorescence microscopes. MARS-Net produced more accurate edge localization than the neural network models trained with single-microscopy-type datasets. We expect that MARS-Net can accelerate the studies of cellular morphodynamics by providing accurate pixel-level segmentation of complex live-cell datasets.