Novel cell segmentation and online SVM for cell cycle phase identification in automated microscopy

• Published in: Bioinformatics Vol. 24; no. 1; pp. 94 - 101
• Main Authors: Wang, Meng, Zhou, Xiaobo, Li, Fuhai, Huckins, Jeremy, King, Randall W., Wong, Stephen T.C.
• Format: Journal Article
• Language: English
• Published: Oxford Oxford University Press 01.01.2008; Oxford Publishing Limited (England)
• Subjects: Algorithms; Artificial Intelligence; Biological and medical sciences; Cell Cycle; Cell Nucleus - physiology; Cell Nucleus - ultrastructure; Fundamental and applied biological sciences. Psychology; General aspects; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Mathematics in biology. Statistical analysis. Models. Metrology. Data processing in biology (general aspects); Microscopy, Fluorescence - methods; Pattern Recognition, Automated - methods; Automation; Microscopy; Segmentation; Cell cycle; Identification; Method; Bioinformatics
• ISSN: 1367-4803; 1460-2059; 1367-4811
• DOI: 10.1093/bioinformatics/btm530

Motivation: Automated identification of cell cycle phases captured via fluorescent microscopy is very important for understanding cell cycle and for drug discovery. In this article, we propose a novel cell detection method that utilizes both the intensity and shape information of the cell for better segmentation quality. In contrast to conventional off-line learning algorithms, an Online Support Vector Classifier (OSVC) is thus proposed, which removes support vectors from the old model and assigns new training examples weighted according to their importance to accommodate the ever-changing experimental conditions. Results: We image three cell lines using fluorescent microscopy under different experiment conditions, including one treated with taxol. Then, we segment and classify the cell types into interphase, prophase, metaphase and anaphase. Experimental results show the effectiveness of the proposed system in image segmentation and cell phase identification. Availability: The software and test datasets are available from the authors. Contact: zhou@crystal.harvard.edu Supplementary information: Supplementary data are available at Bioinformatics online.