Computational Analysis of Cell Dynamics in Videos with Hierarchical-Pooled Deep-Convolutional Features

Journal of computational biology: A journal of computational molecular cell biology

HengLi^1¹  FengqianPang^1² 

[1] Address correspondence to:Prof. Zhiwen LiuDepartment of Information and ElectronicsBeijing Institute of TechnologyBeijing 100081China^2;Department of Information and Electronics, Beijing Institute of Technology, Beijing, China^1

关键词: cell dynamics;    deep convolutional features;    deep convolutional networks;    hierarchical pooling;   

DOI  :  10.1089/cmb.2018.0023

学科分类：生物科学（综合）

来源: Mary Ann Liebert, Inc. Publishers

【 摘 要 】

Computational analysis of cellular appearance and its dynamics is used to investigate physiological properties of cells in biomedical research. In consideration of the great success of deep learning in video analysis, we first introduce two-stream convolutional networks (ConvNets) to automatically learn the biologically meaningful dynamics from raw live-cell videos. However, the two-stream ConvNets lack the ability to capture long-range video evolution. Therefore, a novel hierarchical pooling strategy is proposed to model the cell dynamics in a whole video, which is composed of trajectory pooling for short-term dynamics and rank pooling for long-range ones. Experimental results demonstrate that the proposed pipeline effectively captures the spatiotemporal dynamics from the raw live-cell videos and outperforms existing methods on our cell video database.

【 授权许可】

Unknown