Graph-regularized 3D shape reconstruction from highly anisotropic and noisy images
- 191 Downloads
Analysis of microscopy images can provide insight into many biological processes. One particularly challenging problem is cellular nuclear segmentation in highly anisotropic and noisy 3D image data. Manually localizing and segmenting each and every cellular nucleus is very time-consuming, which remains a bottleneck in large-scale biological experiments. In this work, we present a tool for automated segmentation of cellular nuclei from 3D fluorescent microscopic data. Our tool is based on state-of-the-art image processing and machine learning techniques and provides a user-friendly graphical user interface. We show that our tool is as accurate as manual annotation and greatly reduces the time for the registration.
KeywordsCell nuclei detection Shape reconstruction 3D fluorescent microscopic data Nuclear segmentation
We gratefully acknowledge core funding from the Sloan Kettering Institute (to G.R.), from the Ernst Schering foundation (to S.H.) and from the Max Planck Society (to G.R. and S.H.). Part of this work was done while C.W., S.H., P.D. and G.R. were at the Friedrich Miescher Laboratory of the Max Planck Society and while C.W. was at the Machine Learning Group at TU-Berlin.
- 3.Coelho, L.P., Shariff, A., Murphy, R.F.: Nuclear segmentation in microscope cell images: a hand-segmented dataset and comparison of algorithms. In IEEE International Symposium on Biomedical Imaging: From Nano to Macro, (2009)Google Scholar
- 10.Pécot, T., Singh, S., Caserta, E., Huang, K., Machiraju, R., Leone, G.: Non parametric cell nuclei segmentation based on a tracking over depth from 3D fluorescence confocal images. In 9th IEEE International Symposium on Biomedical Imaging (ISBI), 170–173, (2012)Google Scholar
- 15.Mitchell I.M.: A toolbox of level set methods. In UBC Department of Computer Science Technical Report, TR-2007-11, (2007)Google Scholar
- 18.Lou, X., Koethe, U., Wittbrodt, J., Hamprecht, F. A.: Learning to segment dense cell nuclei with shape prior. In CVPR (2012)Google Scholar
- 19.Gonzalez, R.C., Woods, R.E.: Digital Image Processing. Prentice Hall, Upper Saddle River (2008)Google Scholar
- 20.Lou, X., Koethe, U., Wittbrodt, J., Hamprecht, F.A.: Improved automatic detection and segmentation of cell nuclei in histopathology images. In IEEE on Computer Vision and Pattern Recognition (CVPR)(2012)Google Scholar
- 21.Weisstein, E. W.: “Ellipse”. From MathWorld—A Wolfram Web Resource. http://mathworld.wolfram.com/Ellipse.html
- 26.Vapnik, V.: The Nature of Statistical Learning Theory. Volume 8 of Statistics for Engineering and Information Science. Springer, Berlin (1995)Google Scholar
- 27.Smola, A. J., Schölkopf, B.: Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. Volume 64 of Adaptive Computation and Machine Learning. MIT Press, Cambridge (2001)Google Scholar
- 30.Widmer, C., Kloft, M., Görnitz, N., Rätsch, G.: Efficient training of graph-regularized multitask SVMs. In ECML2012, pp. 633–647, Springer, Berlin (2012)Google Scholar
- 32.Elsasser, W.M.: Outline of a theory of cellular heterogeneity. In Proceedings of the National Academy of Sciences, 5126–5129, (1984)Google Scholar