A microscopic image classification system for high-throughput cell-cycle screening

Tuan D. Pham, Dat T. Tran, X. Zhou, Stephen T.C. Wong

Research output: Contribution to journalArticlepeer-review

5 Scopus citations


Computerized high-throughput screening of cells using fluorescent microscopic imaging technology will tremendously help scientists gain the understanding of complex cellular processes that lead to drug discovery and disease treatment. Manual image analysis of cell images is very time-consuming, potentially inaccurate and poorly reproducible. Therefore the automation of cell-cycle screening, which has not been much explored, is critical for further biological downstream analysis. For such automation task, image classification of cell phases is considered to be most difficult. In this paper we present several computational models for the classification of cell nuclei in different mitotic phases recorded over a period of twenty-four hours at every fifteen minutes using time-lapse fluoresence microscopy. The experimental results have shown that the proposed methods are effective and can be useful for automating cell screening.

Original languageEnglish (US)
Pages (from-to)67-77
Number of pages11
JournalIC-MED International Journal of Intelligent Computing in Medical Sciences and Image Processing
Issue number1
StatePublished - 2007


  • Cell-image classification
  • Fuzzy integrals
  • Fuzzy-set algorithms
  • Gaussian mixture models
  • Markov models
  • Microscopic imaging

ASJC Scopus subject areas

  • Computer Science(all)
  • Radiology Nuclear Medicine and imaging


Dive into the research topics of 'A microscopic image classification system for high-throughput cell-cycle screening'. Together they form a unique fingerprint.

Cite this