Abstract
In this paper we present two new methods of segmentation that we developed for nuclei and chromosomic probes – core objects for cytometry medical imaging. Our nucleic segmentation method is mathematically grounded on a novel parametric model of an image histogram, which accounts at the same time for the background noise, the nucleic textures and the nuclei’s alterations to the background. We adapted an Expectation-Maximisation algorithm to adjust this model to the histograms of each image and subregion, in a coarse-to-fine approach. The probe segmentation uses a new dome-detection algorithm, insensitive to background and foreground noise, which detects probes of any intensity. We detail our two segmentation methods and our EM algorithm, and discuss the strengths of our techniques compared with state-of-the-art approaches. Both our segmentation methods are unsupervised, automatic, and require no training nor tuning: as a result, they are directly applicable to a wide range of medical images. We have used them as part of a large-scale project for the improvement of prenatal diagnostic of genetic diseases, and tested them on more than 2,100 images with nearly 14,000 nuclei. We report 99.3% accuracy for each of our segmentation methods, with a robustness to different laboratory conditions unreported before.
Chapter PDF
Similar content being viewed by others
References
Hohmann, H., Michel, S., Reiber, W., Gunther, M., Claussen, U., von Eggeling, F.: How to enrich and analyse fetal cells from maternal blood. In: Fetal Cells and Fetal DNA in Maternal Blood, Karger, pp. 47–55 (2001)
Merchant, F.A., Castleman, K.R.: Strategies for automated fetal cell screening. Human Reproduction Update 8, 509–521 (2002)
Fang, B., Hsu, W., Lee, M.L.: On the accurate counting of tumor cells. IEEE Transactions on Nanobioscience 2, 94–103 (2003)
Tanaka, T., Murase, Y., Oka, T.: Classification of skin tumors based on shape features of nuclei. Medicine and Biology Society 3, 1064–1066 (2002)
Wu, K., Gauthier, D., Levine, M.D.: Live cell image segmentation. IEEE Transactions on Biomedical Engineering 42, 1–12 (1995)
Lin, G., Adiga, U., Olson, K., Guzowski, J., Barnes, C., Roysam, B.: A hybrid 3D watershed algorithm incorporating gradient cues and object models for automatic segmentation of nuclei in confocal image stacks. Cytometry 56A, 23–36 (2003)
Lehmann, T., Bredno, J., Spitzer, K.: On the design of active contours for medical image segmentation. Methods of Information in Medicine 42, 89–98 (2003)
Poon, S.S., Martens, U.M., Ward, R.K., Lansdorp, P.M.: Telomere length measurements using digital fluorescence microscopy. Cytometry 36, 267–278 (1999)
Clocksin, W.F., Lerner, B.: Automatic analysis of fluorescence in-situ hybridisation images. In: British Machine Vision Conference, pp. 666–674 (2000)
Pelikan, D.M.V., Mesker, W.E., Scherjon, S.A., Kanhai, H.H.H., Tanke, H.J.: Improvement of the Kleihauer-Betke test by automated detection of fetal erythrocytes in maternal blood. Cytometry Part B (Clinical Cytometry) 54B, 1–9 (2003)
de Solorzano, C.O., Garcia Rodriguez, E., Johnes, A., Pinkel, D., Gray, J., Sudar, D., Lockett, S.: Segmentation of confocal microscope images of cell nuclei in thick tissue sections. Journal of Microscopy 193, 212–226 (1999)
de Solorzano, C.O., Malladi, R., Lelievre, S., Lockett, S.: Segmentation of nuclei and cells using membrane related protein markers. Microscopy 201, 404–415 (2001)
Bamford, P., Lovell, B.: Method for accurate unsupervised cell nucleus segmentation. IEEE Engineering in Medicine and Biology 1, 133–135 (2001)
Netten, H., Young, I., van Vliet, L., Tanke, H., Vroljik, H., Sloos, W.: Automation of fluorescent dot counting in interphase cell nuclei. Cytometry 28, 1–10 (1997)
Theodoridis, S., Koutroumbas, K.: Pattern Recognition, 2nd edn. Elsevier, Amsterdam (2003)
Smith, S.W.: The scientist and engineer’s guide to digital signal processing, pp. 11–34. California Technical Publishing (1997)
Kutalik, Z., Razaz, M., Baranyi, J.: Automated spatial and temporal image analysis of bacterial cell growth. In: BMVA Spatiotemporal Image Processing (2004)
Felzenszwalb, P.F., Huttenlocher, D.P.: Distance transforms of sampled functions. Technical report, Cornell University, TR2004-1963 (2004)
Malpica, N., de Solorzano, C.O., Vaquero, J.J., Santos, A., Vallcorba, I., Garcia-Sagrado, J.M., del Pozo, F.: Applying watershed algorithms to the segmentation of clustered nuclei. Cytometry 28, 289–297 (1997)
Restif, C., Clocksin, W.: Comparison of segmentation methods for cytometric assay. In: Medical Image Understanding and Analysis, pp. 153–156 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Restif, C. (2006). Towards Safer, Faster Prenatal Genetic Tests: Novel Unsupervised, Automatic and Robust Methods of Segmentation of Nuclei and Probes. In: Leonardis, A., Bischof, H., Pinz, A. (eds) Computer Vision – ECCV 2006. ECCV 2006. Lecture Notes in Computer Science, vol 3954. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11744085_34
Download citation
DOI: https://doi.org/10.1007/11744085_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-33838-3
Online ISBN: 978-3-540-33839-0
eBook Packages: Computer ScienceComputer Science (R0)