Using the low-pass monogenic signal framework for cell/background classification on multiple cell lines in bright-field microscope images
Several cell detection approaches which deal with bright-field microscope images utilize defocusing to increase image contrast. The latter is related to the physical light phase through the transport of intensity equation (TIE). Recently, it was shown that it is possible to approximate the solution of the TIE using a low-pass monogenic signal framework. The purpose of this paper is to show that using the local phase of the aforementioned monogenic signal instead of the defocused image improves the cell/background classification accuracy.
Materials and methods
The paper statement was tested on an image database composed of three cell lines: adherent CHO, adherent L929, and Sf21 in suspension. Local phase and local energy images were generated using the low-pass monogenic signal framework with axial derivative images as input. Machine learning was then employed to investigate the discriminative power of the local phase. Three classifier models were utilized: random forest (RF), support vector machine (SVM) with a linear kernel, and SVM with a radial basis function (RBF) kernel.
The improvement, averaged over cell lines, of classifying \(5 \times 5\) sized patches extracted from the local phase image instead of the defocused image was \(7.3\) % using the RF, \(11.6\) % using the linear SVM, and \(10.2\) % when a RBF kernel was employed instead of the linear one. Furthermore, the feature images can be sorted by increasing discriminative power as follows: at-focus signal, local energy, defocused signal, local phase. The only exception to this order was the superiority of local energy over defocused signal for suspended cells.
Local phase computed using the low-pass monogenic signal framework considerably outperforms the defocused image for the purpose of pixel-patch cell/background classification in bright-field microscopy.
KeywordsMonogenic signal Cell detection Bright-field microscopy Transport of intensity equation Local phase Machine learning
- 3.Ali R, Szilagyi T, Gooding M, Christlieb M, Brady M (2010) On the use of low-pass filters for image processing with inverse Laplacian models. J Math Imaging Vis 43:1–10Google Scholar
- 4.Becattini G, Mattos L, Caldwell D (2011) A novel framework for automated targeting of unstained living cells in bright field microscopy. In: Proceedings of the IEEE international symposium on biomedical imaging: from nano to macro, pp 195–198Google Scholar
- 6.Breiman L (2011) Random forests. Mach Learn 45(1):5–32Google Scholar
- 7.Chang CC, Lin CJ (2001) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):27:1–27:27. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm
- 9.Hamilton WR (1844) II. On quaternions; or on a new system of imaginaries in algebra. Lond Edinb Dublin Philos Mag J Sci 25(163):10–13Google Scholar
- 11.Khoshgoftaar T, Golawala M, Van Hulse J (2007) An empirical study of learning from imbalanced data using random forest. In: Proceedings of the IEEE International Conference on Tools with, Artificial Intelligence, vol 2, pp 310–317 Google Scholar
- 17.Nattkemper T, Ritter H, Schubert W (1999) Extracting patterns of lymphocyte fluorescence from digital microscope images. Intell Data Anal Med Pharmacol 99:79–88Google Scholar
- 18.Popescu G (2011) Quantitative phase imaging of cells and tissues. McGraw-Hill, New YorkGoogle Scholar
- 19.Poularikas AD (2010) Handbook of formulas and tables for signal processing, vol 13. CRC Press, Boca Raton, FLGoogle Scholar
- 21.Scholkopf B, Smola AJ (eds) (2001) Learning with kernels. MIT Press, Cambridge, MAGoogle Scholar
- 22.Stein EM (1970) Singular integrals and differentiability properties of functions Elias M. Stein, vol 2. Princeton University Press, Princeton, NJGoogle Scholar
- 24.Tscherepanow M, Zöllner F, Hillebrand M, Kummert F (2008) Automatic segmentation of unstained living cells in bright-field microscope images. In: Advances in mass data analysis of images and signals in medicine, biotechnology, chemistry and food industry (Lecture notes in computer science), vol 5108. Springer, Berlin, pp 158–172Google Scholar