Automatic segmentation of adherent biological cell boundaries and nuclei from brightfield microscopy images
- 777 Downloads
The detection and segmentation of adherent eukaryotic cells from brightfield microscopy images represent challenging tasks in the image analysis field. This paper presents a free and open-source image analysis package which fully automates the tasks of cell detection, cell boundary segmentation, and nucleus segmentation in brightfield images. The package also performs image registration between brightfield and fluorescence images. The algorithms were evaluated on a variety of biological cell lines and compared against manual and fluorescence-based ground truths. When tested on HT1080 and HeLa cells, the cell detection step was able to correctly identify over 80% of cells, whilst the cell boundary segmentation step was able to segment over 75% of the cell body pixels, and the nucleus segmentation step was able to correctly identify nuclei in over 75% of the cells. The algorithms for cell detection and nucleus segmentation are novel to the field, whilst the cell boundary segmentation algorithm is contrast-invariant, which makes it more robust on these low-contrast images. Together, this suite of algorithms permit brightfield microscopy image processing without the need for additional fluorescence images. Finally our sephaCe application, which is available at http://www.sephace.com, provides a novel method for integrating these methods with any motorised microscope, thus facilitating the adoption of these techniques in biological research labs.
KeywordsSegmentation Registration Cell detection Level sets Monogenic signal Continuous intrinsic dimensionality
Unable to display preview. Download preview PDF.
- 1.Ali, R.: Applications of microscopy image analysis and modelling in characterising the mechanisms of hypoxia-mediated drug resistance. Ph.D thesis, University of Oxford, Oxford (2009)Google Scholar
- 2.Ali, R., Gooding, M., Christlieb, M., Brady, M.: Phase-based segmentation of cells from brightfield microscopy. In: Proceedings of the International Symposium Biomedical Imaging (ISBI), pp 57–60 (2007)Google Scholar
- 3.Ali, R., Gooding, M., Christlieb, M., Brady, M.: Advanced phase-based segmentation of multiple cells from brightfield microscopy images. In: Proceedings of the International Symposium Biomedical Imaging (ISBI), pp 181–184 (2008)Google Scholar
- 4.Ali, R., Szilagyi, T., Gooding, M., Christlieb, M., Brady, M.: On the use of lowpass filters for image processing with inverse laplacian models. J. Math. Imag. Vis. Under Rev. (2010)Google Scholar
- 5.Barber, P.R., Locke, R.J., Pierce, G.P., Rothkamm, K., Vojnovic, B.: Gamma-H2AX focicounting: image processing and control software for high-content screening. In: Proceedings of SPIE, San Jose, CA,USA, pp 64, 411M–64, 411M–10 (2007)Google Scholar
- 7.Bradbury, L.: Segmentation of bright-field cell images. Ph.D thesis, University of Waterloo, Ontario, Canada (2009)Google Scholar
- 11.Dice, L. (1945) Measures of the amount of ecologic association between species. Ecology 26:297–302Google Scholar
- 23.Rittscher J., Machiraju R., Wong S.T.C.: Microscopic Image Analysis for Life Science Applications, 1st edn. Artech House Publishers, USA (2008)Google Scholar
- 25.Selinummi, J., Ruusuvuori, P., Podolsky, I., Ozinsky, A., Gold, E., Yli-Harja, O., Aderem, A., Shmulevich, I.: Bright field microscopy as an alternative to whole cell fluorescence in automated analysis of macrophage images 4(10):e7497 (2009). doi: 10.1371/journal.pone.0007497
- 28.Tscherepanow M., Zollner F., Kummert F.: Classification of segmented regions in brightfield microscope images. ICPR 06(3), 972–975 (2006)Google Scholar
- 29.Tscherepanow M., Nickels N., Kummert F.: Recognition of unstained live drosophila cells in microscope image, pp. 169–176. IMVIP, Los Alamitos (2007)Google Scholar