Semi-automatic Background Detection in Microscopic Images

Authors: Alessandro Bevilacqua, Alessandro Gherardi, Ludovico Carozza, Filippo Piccinini

Abstract:

The last years have seen an increasing use of image analysis techniques in the field of biomedical imaging, in particular in microscopic imaging. The basic step for most of the image analysis techniques relies on a background image free of objects of interest, whether they are cells or histological samples, to perform further analysis, such as segmentation or mosaicing. Commonly, this image consists of an empty field acquired in advance. However, many times achieving an empty field could not be feasible. Or else, this could be different from the background region of the sample really being studied, because of the interaction with the organic matter. At last, it could be expensive, for instance in case of live cell analyses. We propose a non parametric and general purpose approach where the background is built automatically stemming from a sequence of images containing even objects of interest. The amount of area, in each image, free of objects just affects the overall speed to obtain the background. Experiments with different kinds of microscopic images prove the effectiveness of our approach.

Keywords: Microscopy, flat field correction, background estimation, image segmentation.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1055431

References:

[1] A. Sacan, H. Ferhatosmanoglu, and H. Coskun, "Celltrack: an opensource software for cell tracking and motility analysis," Bioinformatics, vol. 24, no. 14, pp. 1647-1649, 2008.
[2] Emilie Flaberg, Per Sabelstrnaöm, Christer Strandh, and LaszloSzekely, "Extended field laser confocal microscopy (eflcm): Combining automated gigapixel image capture with in silico virtual microscopy," BMC Med Imaging, vol. 8, pp. 1-13, 2008.
[3] E. D. Cheng, S. Challa, R. Chakravorty, and J. Markham, "Microscopic cell segmentation by parallel detection and fusion algorithm," in Proc. of the 10th IEEE International Workshop on Multimedia Signal Processing, 2008, pp. 94-100.
[4] Y. G. Patel, K. S. Nehal, I. Aranda, Y. Li, A. C. Halpern, and M. Rajadhyaksha, "Confocal reflectance mosaicing of basal cell carcinomas in mohs surgical skin excisions," Journal of Biomedical Optics, vol. 12, no. 3, pp. 034027-1-034027-10, May/June 2007.
[5] Kang Li, Mei Chen, Takeo Kanade, Eric Miller, Lee Weiss, and Phil Campbell, "Cell population tracking and lineage construction with spatiotemporal context," Medical Image Analysis, vol. 12, no. 5, pp. 546-566, Oct. 2008.
[6] F. Sadeghian, Z. Seman, A. R. Ramli, B. H. Abdul Kahar, and M. Saripan, "A framework for white blood cell segmentation in microscopic blood images using digital image processing," Biological Procedures Online, vol. 11, pp. 196-206, December 2009.
[7] N. N. Kachouie and P. W. Fieguth, "Background estimation for microscopic cellular images," in IEEE International Conference on Image Processing, San Diego, CA, USA, October 12-15, 2008, pp. 3040-3043.
[8] Kang Li and Takeo Kanade, "Nonnegative mixed-norm preconditioning for microscopy image segmentation," Lecture Notes in Computer Science, vol. 5636, pp. 362-373, 2009.