×

Image analysis and classification for high-throughput screening of embryonic stem cells. (English) Zbl 1383.92038

Zazzu, Valeria (ed.) et al., Mathematical models in biology. Bringing mathematics to life. Selected contributions based on the presentations at the workshop “Bringing maths to life”, Naples, Italy, October 27–29, 2014. Cham: Springer (ISBN 978-3-319-23496-0/hbk; 978-3-319-23497-7/ebook). 17-31 (2015).
In this chapter the authors describe first results related to the development of a multi-component software framework devoted to define automated morphological analysis and classification of Embryonic Stem Cells (ESCs) colonies. The colony-forming (CF) assay is widely used for monitoring the quality of ESC cultures as it currently offers the most sensitive and specific method to quantify the frequency of undifferentiated cells present in a culture and provides a reliable tool for evaluating quantitative changes in pluripotent cell numbers. In this article first results are discussed by developing and using automatic software tools, interfacing image processing modules with machine learning algorithms, for morphological analysis and classification of digital images of mouse ESC colonies grown under standardized assay conditions. The basic steps are extracted in every considered applications: Pre-processing, to reduce image artifacts caused by imperfections in the image acquisition process. Segmentation, to separate the cell colonies in each well image. Feature computation, to provide numerical descriptors of each segmented colony classification, to finally provide the discrimination and quantification of domed and flat colonies, based on the most discriminating features.
For the entire collection see [Zbl 1402.92011].

MSC:

92C55 Biomedical imaging and signal processing
94A08 Image processing (compression, reconstruction, etc.) in information and communication theory
PDFBibTeX XMLCite
Full Text: DOI