Abstract
Fluorescence microscopy imaging technologies play an important role in a large number of scientific studies on cancer progression mechanisms and biological activity patterns. However, both the large fluorescence microscopy image scale and varying number of objects of interest prevent such images from accurate and efficient analyses by humans. Therefore, the development of efficient, accurate, and automated motion tracking approaches is necessary and critical to enable such fluorescence microscopy image analyses. It has been demonstrated that traditional approaches detecting individual objects in each image frame and next linking detected objects between adjacent frames work well when sequences of images have a high signal to noise ratio and capture a limited number of tracking objects of interest. Less subject to these constraints, particle filtering has been preferably used in diverse tracking analyses. Specifically, particle filtering approaches using the Gaussian function for object state characterization can produce robust tracking results even when objects are densely distributed in clumps. However, due to the complexity of object morphology and the limitation of microscopy image resolution, intensities of objects do not always follow the Gaussian distribution. Despite the fact that deep learning algorithms have been emerged to improve the particle filtering performance, the required large training data scale limits their practical applications in many scenarios. In this work, we extend the particle filtering approach by developing non-Gaussian models and the corresponding tracking management strategy. With a gradient-based segmentation algorithm, objects in image sequences are extracted and modeled by states. The evolution of these states can be used to recover object motion trajectories and quantitatively characterize object motion behaviors. Experiments on both artificial and real biomedical time-lapse fluorescence image data for 2D and 3D space demonstrate the robustness and accuracy of our generalized approach.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Arulampalam, M.S., Maskell, S., Gordon, N., Clapp, T.: A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE Trans. Signal Process. 50(2), 174–188 (2002)
Cheezum, M.K., Walker, W.F., Guilford, W.H.: Quantitative comparison of algorithms for tracking single fluorescent particles. Biophys. J. 81(4), 2378–2388 (2001)
Debeir, O., Van Ham, P., Kiss, R., Decaestecker, C.: Tracking of migrating cells under phase-contrast video microscopy with combined mean-shift processes. IEEE Trans. Med. Imaging 24(6), 697–711 (2005)
Delgado-Gonzalo, R., Chenouard, N., Unser, M.: A new hybrid Bayesian-variational particle filter with application to mitotic cell tracking. In: 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp. 1917–1920. IEEE, Piscataway (2011)
Doucet, A., Godsill, S., Andrieu, C.: On sequential Monte Carlo sampling methods for Bayesian filtering. Stat. Comput. 10(3), 197–208 (2000)
Genovesio, A., Liedl, T., Emiliani, V., Parak, W.J., Coppey-Moisan, M., Olivo-Marin, J.C.: Multiple particle tracking in 3-d+ t microscopy: method and application to the tracking of endocytosed quantum dots. IEEE Trans. Image Process. 15(5), 1062–1070 (2006)
Godinez, W., Rohr, K.: Tracking multiple particles in fluorescence time-lapse microscopy images via probabilistic data association. IEEE Trans. Med. Imaging 34(2), 415–432 (2015)
Gudla, P.R., Nakayama, K., Pegoraro, G., Misteli, T.: Spotlearn: Convolutional neural network for detection of fluorescence in situ hybridization (fish) signals in high-throughput imaging approaches. In: Cold Spring Harbor Symposia on Quantitative Biology, vol. 82, pp. 57–70. Cold Spring Harbor Laboratory Press, New York (2017)
Kong, J., Wang, F., Teodoro, G., Liang, Y., Zhu, Y., Tucker-Burden, C., Brat, D.J.: Automated cell segmentation with 3d fluorescence microscopy images. In: 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI), pp. 1212–1215. IEEE, Piscataway (2015)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Li, G., Liu, T., Tarokh, A., Nie, J., Guo, L., Mara, A., Holley, S., Wong, S.T.: 3d cell nuclei segmentation based on gradient flow tracking. BMC Cell Biol. 8(1), 40 (2007)
Lin, G., Adiga, U., Olson, K., Guzowski, J.F., Barnes, C.A., Roysam, B.: A hybrid 3d watershed algorithm incorporating gradient cues and object models for automatic segmentation of nuclei in confocal image stacks. Cytometry A 56(1), 23–36 (2003)
Luo, D., Barker, J., McGrath, J., Daly, C.: Iterative multilevel thresholding and splitting for three-dimensional segmentation of live cell nuclei using laser scanning confocal microscopy. J. Comput.-Assist. Microsc. 10(4), 151–162 (1998)
Mozhdehi, R.J., Medeiros, H.: Deep convolutional particle filter for visual tracking. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 3650–3654. IEEE, Piscataway (2017)
Newby, J.M., Schaefer, A.M., Lee, P.T., Forest, M.G., Lai, S.K.: Convolutional neural networks automate detection for tracking of submicron-scale particles in 2d and 3d. Proc. Natl. Acad. Sci. 115(36), 9026–9031 (2018)
Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979)
Rathi, Y., Vaswani, N., Tannenbaum, A., Yezzi, A.: Tracking deforming objects using particle filtering for geometric active contours. IEEE Trans. Pattern Anal. Mach. Intell. 29(8), 1470 (2007)
Sage, D., Neumann, F.R., Hediger, F., Gasser, S.M., Unser, M.: Automatic tracking of individual fluorescence particles: application to the study of chromosome dynamics. IEEE Trans. Image Process. 14(9), 1372–1383 (2005)
Sbalzarini, I.F., Koumoutsakos, P.: Feature point tracking and trajectory analysis for video imaging in cell biology. J. Struct. Biol. 151(2), 182–195 (2005)
Shafique, K., Shah, M.: A noniterative greedy algorithm for multiframe point correspondence. IEEE Trans. Pattern Anal. Mach. Intell. 27(1), 51–65 (2005)
Smal, I., Niessen, W., Meijering, E.: Advanced particle filtering for multiple object tracking in dynamic fluorescence microscopy images. In: 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp. 1048–1051. IEEE, Piscataway (2007)
Smal, I., Meijering, E., Draegestein, K., Galjart, N., Grigoriev, I., Akhmanova, A., Van Royen, M., Houtsmuller, A.B., Niessen, W.: Multiple object tracking in molecular bioimaging by Rao-Blackwellized marginal particle filtering. Med. Image Anal. 12(6), 764–777 (2008)
Smal, I., Yao, Y., Galjart, N., Meijering, E.: Facilitating data association in particle tracking using autoencoding and score matching. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pp. 1523–1526. IEEE, Piscataway (2019)
Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th International Conference on Machine Learning, pp. 1096–1103. ACM, New York (2008)
Xu, C., Prince, J.L.: Snakes, shapes, and gradient vector flow. IEEE Trans. Image Process. 7(3), 359 (1998)
Yu, H.: Object tracking. https://github.com/hyu88/object_tracking_3d.git
Zhang, Y., Cheng, Z., Jin, Y., Si, K., Jin, X.: Detection and recognition of micro-nano fluorescent particle array based on AlexNet. In: IOP Conference Series: Materials Science and Engineering, vol. 504, p. 012035. IOP Publishing, Bristol (2019)
Zimmer, C., Labruyere, E., Meas-Yedid, V., Guillén, N., Olivo-Marin, J.C.: Segmentation and tracking of migrating cells in videomicroscopy with parametric active contours: A tool for cell-based drug testing. IEEE Trans. Med. Imaging 21(10), 1212–1221 (2002)
Acknowledgements
This research is supported in part by grants from National Institute of Health 7K25CA181503, 1U01CA242936, 5R01EY028450, 5R01CA214928, and 1R01CA236369, the Winship cancer Institute of Emory University pilot award under award number P30CA138292, and It’s The Journey & GA CORE breast cancer award.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Yu, H., Yoon, S.B., Kauffman, R., Wrammert, J., Marcus, A., Kong, J. (2021). Non-Gaussian Models for Object Motion Analysis with Time-Lapse Fluorescence Microscopy Images. In: Zhao, Y., Chen, (.DG. (eds) Modern Statistical Methods for Health Research. Emerging Topics in Statistics and Biostatistics . Springer, Cham. https://doi.org/10.1007/978-3-030-72437-5_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-72437-5_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-72436-8
Online ISBN: 978-3-030-72437-5
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)