Cellbow: a robust customizable cell segmentation program
- PDF / 3,760,497 Bytes
- 11 Pages / 595.276 x 785.197 pts Page_size
- 70 Downloads / 190 Views
METHOD Cellbow: a robust customizable cell segmentation program Huixia Ren, Mengdi Zhao, Bo Liu, Ruixiao Yao, Qi liu, Zhipeng Ren, Zirui Wu, Zongmao Gao, Xiaojing Yang, Chao Tang* Center for Quantitative Biology and Peking-Tsinghua Center for Life Sciences, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing 100871, China * Correspondence: [email protected] Received December 25, 2019; Revised April 20, 2020; Accepted May 28, 2020 Background: Time-lapse live cell imaging of a growing cell population is routine in many biological investigations. A major challenge in imaging analysis is accurate segmentation, a process to define the boundaries of cells based on raw image data. Current segmentation methods relying on single boundary features have problems in robustness when dealing with inhomogeneous foci which invariably happens in cell population imaging. Methods: Combined with a multi-layer training set strategy, we developed a neural-network-based algorithm — Cellbow. Results: Cellbow can achieve accurate and robust segmentation of cells in broad and general settings. It can also facilitate long-term tracking of cell growth and division. To facilitate the application of Cellbow, we provide a website on which one can online test the software, as well as an ImageJ plugin for the user to visualize the performance before software installation. Conclusions: Cellbow is customizable and generalizable. It is broadly applicable to segmenting fluorescent images of diverse cell types with no further training needed. For bright-field images, only a small set of sample images of the specific cell type from the user may be needed for training.
Keywords: deep neural network; cell segmentation; fluorescent cell imaging; bright-field cell imaging; lineage tracking Author summary: Using microscope to study cells growing and dividing is one of the common tasks in a biological lab. However, having taken the pictures of the cells is only half way through. A challenging and often time-consuming work is to recognize, label and track each individual cell from the raw image. These images usually vary greatly in their features and qualities depending on the focal field, experimental conditions, cell types, different labs, etc. Current methods are very limited to solve these generic problems. Here we employed a machine learning method to develop a robust software that is automated, flexible and customizable for this task.
INTRODUCTION Imaging has become a standard tool for the detection and analysis of cellular phenomena. Bright-field (BF) and fluorescent microscopy are widely used to quantify single-cell features [1]. The accurate quantification of such features critically depends on cell segmentation [2]. Segmentation (the identification of cell boundaries for individual cells) is based on cell edge properties in images [3]. In fluorescent images, the edge properties of cells are
very uniform, and only depend on the expression of fluorescent proteins (Fig. 1A). However, the typical appearance of a BF image depends on the imaging
Data Loading...
