Background fluorescence estimation and vesicle segmentation in live cell imaging with conditional random fields

OUR OFFICES @CHENNAI/ TRICHY / KARUR / ERODE / MADURAI / SALEM / COIMBATORE / BANGALORE / HYDRABAD
CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111
ECWAY TECHNOLOGIES
IEEE SOFTWARE | EMBEDDED | MECHANICAL | ROBOTICS PROJECTS DEVELOPMENT
Visit: www.ecwaytechnologies.com | www.ecwayprojects.com Mail to: ecwaytechnologies@gmail.com
BACKGROUND FLUORESCENCE ESTIMATION AND VESICLE SEGMENTATION
IN LIVE CELL IMAGING WITH CONDITIONAL RANDOM FIELDS
By
A
PROJECT REPORT
Submitted to the Department of electronics &communication Engineering in the
FACULTY OF ENGINEERING & TECHNOLOGY
In partial fulfillment of the requirements for the award of the degree
Of
MASTER OF TECHNOLOGY
IN
ELECTRONICS &COMMUNICATION ENGINEERING
APRIL 2016

CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111
ECWAY TECHNOLOGIES
CERTIFICATE
Certified that this project report titled “Background Fluorescence Estimation and Vesicle
Segmentation in Live Cell Imaging With Conditional Random Fields” is the bonafide work of
Mr. _____________Who carried out the research under my supervision Certified further, that to
the best of my knowledge the work reported herein does not form part of any other project report
or dissertation on the basis of which a degree or award was conferred on an earlier occasion on
this or any other candidate.
Signature of the Guide Signature of the H.O.D
Name Name

CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111
ECWAY TECHNOLOGIES
DECLARATION
I hereby declare that the project work entitled “Background Fluorescence Estimation and
Vesicle Segmentation in Live Cell Imaging With Conditional Random Fields” Submitted to
BHARATHIDASAN UNIVERSITY in partial fulfillment of the requirement for the award of the
Degree of MASTER OF APPLIED ELECTRONICS is a record of original work done by me the
guidance of Prof.A.Vinayagam M.Sc., M.Phil., M.E., to the best of my knowledge, the work
reported here is not a part of any other thesis or work on the basis of which a degree or award was
conferred on an earlier occasion to me or any other candidate.
(Student Name)
(Reg.No)
Place:
Date:

CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111
ECWAY TECHNOLOGIES
ACKNOWLEDGEMENT
I am extremely glad to present my project “Background Fluorescence Estimation and Vesicle
Segmentation in Live Cell Imaging With Conditional Random Fields” which is a part of my
curriculum of third semester Master of Science in Computer science. I take this opportunity to
express my sincere gratitude to those who helped me in bringing out this project work.
I would like to express my Director,Dr. K. ANANDAN, M.A.(Eco.), M.Ed., M.Phil.,(Edn.),
PGDCA., CGT., M.A.(Psy.)of who had given me an opportunity to undertake this project.
I am highly indebted to Co-OrdinatorProf. Muniappan Department of Physics and thank from
my deep heart for her valuable comments I received through my project.
I wish to express my deep sense of gratitude to my guide
Prof. A.Vinayagam M.Sc., M.Phil., M.E., for her immense help and encouragement for
successful completion of this project.
I also express my sincere thanks to the all the staff members of Computer science for their kind
advice.
And last, but not the least, I express my deep gratitude to my parents and friends for their
encouragement and support throughout the project.

CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111
ECWAY TECHNOLOGIES
ABSTRACT:
Image analysis applied to fluorescence live cell microscopy has become a key tool in
molecular biology since it enables to characterize biological processes in space and time at the
subcellular level. In fluorescence microscopy imaging, the moving tagged structures of interest,
such as vesicles, appear as bright spots over a static or nonstatic background. In this paper, we
consider the problem of vesicle segmentation and time-varying background estimation at the
cellular scale. The main idea is to formulate the joint segmentation-estimation problem in the
general conditional random field framework. Furthermore, segmentation of vesicles and
background estimation are alternatively performed by energy minimization using a min cut-max
flow algorithm. The proposed approach relies on a detection measure computed from intensity
contrasts between neighboring blocks in fluorescence microscopy images. This approach permits
analysis of either 2D + time or 3D + time data. We demonstrate the performance of the so-called
C-CRAFT through an experimental comparison with the state-of-the-art methods in fluorescence
video-microscopy. We also use this method to characterize the spatial and temporal distribution of
Rab6 transport carriers at the cell periphery for two different specific adhesion geometries.

CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111
ECWAY TECHNOLOGIES
INTRODUCTION:
The joint advances in molecular biology and optics have revolutionized investigation
methods in biology. Over the last two decades, progress in light microscopy and fluorescence
molecule tagging have typically enabled to analyze transport pathways that permit exchanges
between intracellular compartments. Vesicular transport carriers are mainly involved in the
communications between cell compartments, connected by multiple routes. They are known to
actively move on microtubules and actin filaments networks via molecular motors [1]. In live cell
fluorescence microscopy images, vesicles often appear as bright spots with intensity that varies
along time over a time-varying and cluttered background. Localization and morphology
assessment of these small objects over time is then crucial to provide valuable information for
quantitative traffic analysis.
However, the manual detection of vesicles over a cluttered time-varying background is
known to be tedious and subjective. Fluorescence images are relatively complex to analyze,
depending on the optical setup, the properties of the detectors and the photophysics inherent to the
diverse fluorescent probes. Automatic methods have the obvious advantage of being quicker and
reproducible. Computational imaging methods have been developed first to robustly detect and
track vesicles over a static background. Data are most often massively collected and need to be
processed automatically. Accordingly, one needs to address both the methodological and
computational issues involved in detecting multiple small moving subcellular objects in order to
more accurately quantify membrane transport from fluorescence microscopy image data.
Our biological motivation is related to the mechanisms regulating the targeting and
transport of proteins to the place where they operate within the cell. In this paper, we focus on the
Rab6 protein as a typical intracellular membrane-associated protein which is either:
i) free in the cytosol (diffusion);
ii) ii) anchored to moving transport carriers (vesicles) between the Golgi and the
periphery of the cell;
iii) iii) attached to the Golgi membrane
Rab6 is known to promote vesicle trafficking from Golgi to Endoplasmic Reticulum or to plasma
membrane. Here, we address the issue of segmenting small vesicles in the cluttered time-varying

CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111
ECWAY TECHNOLOGIES
cytosol. In our study, micro-fabricated patterns have been used to enforce cells to have circular or
crossbow normalized shapes. Micro-patterns impose constraints on the cytoskeleton and the
location of organelles (e.g. Golgi apparatus) is thus better controlled. These micro-patterns also
influence the spatial distribution of Rab6 transport carriers as confirmed with probabilistic density
maps as designed in, However, the direct influence of the micro-patterns on the spatial
dissemination of this trafficking vesicles has so far not been completely characterized. New
computational methods and appropriate image processing algorithms are then required to quantify
the influence of micro-patterns on Rab6 trafficking distribution.
In this paper, we present a statistical Bayesian approach in the framework of conditional
random fields for background estimation and vesicle segmentation. Within this approach, we have
designed a robust detection measure for fluorescence microscopy based on the distribution of
neighbor patch similarity. We formulate the vesicle segmentation and background estimation as a
global energy minimization problem. An iterative scheme to jointly segment vesicles and
background is proposed for 2D−3D fluorescence image sequences. Preliminary ideas were
described in,In this paper, we provide the following improvements and contributions:
• a novel robust thresholding procedure for the patch-based detection measure;
• a new spatial regularization term weighted by intensity contrasts that preserves vesicle
contours;
• an extension of the method devoted to the processing of 2D+time data and 3D+time data
within the same framework;
• a quantitative comparison with state-of-the-art methods on a large set of synthetic image
sequences with a cluttered time-varying background;
• a quantitative validation of the vesicle segmentation method on 2D and 3D micro-
patterned cells expressing GFP-Rab6.
The remainder of the paper is organized as follows. The state-of-the-art methods for
particle detection and object/background separation in fluorescence microscopy imaging are
presented in Section II. Section III presents our C-CRAFT(Conditional RAndom Fields for protein
Transport Carriers segmentation) method which can handle cluttered time-varying background. In

CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111
ECWAY TECHNOLOGIES
Section IV, the performance of the C-CRAFT method is compared to existing methods on 2D
synthetic and real fluorescence microscopy image sequences. Finally, we use the C-CRAFT
method to quantify the spatial distribution of Rab6 transport carrier trafficking for crossbow and
circular-shaped cells. Section V contains concluding remarks.

CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111
ECWAY TECHNOLOGIES
CONCLUSION:
We have proposed an original method in the framework of conditional random fields for
jointly segmenting vesicles and estimating background in fluorescence live cell microscopy. We
have introduced a novel detection measure based on contrast between neighboring image patches.
It allows us to effectively take into account the local context in fluorescence images. The vesicle
supports and background intensities are recovered alternatively by employing a min cut-max flow
minimization algorithm. The method can process both 2D+time and 3D+time data. We also have
conducted an extensive experimental comparison of our method with six state-of-the-art methods
for spot detection and background estimation.
This comparison demonstrates the better performance of the C-CRAFT method for vesicle
segmentation and background estimation in fluorescence video-microscopy with cluttered
timevarying background. It can be tested online. As the C-CRAFT method relies on a detection
measure based on intensity contrast, it could be applied to the segmentation of any structure in
fluorescence microscopy. Nevertheless, this approach has been specifically developed for vesicle
traffic analysis on a time-varying background. It would require additional experiments to evaluate
the potential of the method for other applications in bioimaging. Finally, the proposed analysis of
Rab6-trafficking in micropatterned cells confirmed that the vesicle trafficking concentrates at the
three corner points of the crossbow-shaped cells (main adhesion sites), while the vesicle
destination distribution is almost uniform for circular-shaped cells, as expected.

CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111
ECWAY TECHNOLOGIES
REFERENCES:
[1] K. Schauer, T. Duong, C. S. Gomes-Santos, and B. Goud, “Studying intracellular trafficking
pathways with probabilistic density maps,” Methods Cell Biol., vol. 118, pp. 325–343, 2013.
[2] N. Phansalkar, S. More, A. Sabale, and M. Joshi, “Adaptive local thresholding for detection
of nuclei in diversity stained cytology images,” in Proc. IEEE Int. Conf. Commun. Signal Process.,
Feb. 2011, pp. 218–220.
[3] A. Raj, P. van den Bogaard, S. A. Rifkin, A. van Oudenaarden, and S. Tyagi, “Imaging
individual mRNA molecules using multiple singly labeled probes,” Nature Methods, vol. 5, no.
10, pp. 877–879, 2008.
[4] L. Yang et al., “An adaptive non-local means filter for denoising livecell images and improving
particle detection,” J. Struct. Biol., vol. 172, no. 3, pp. 233–243, 2010.
[5] N. Chenouard, I. Bloch, and J.-C. Olivo-Marin, “Multiple hypothesis tracking for cluttered
biological image sequences,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, no. 11, pp. 2736–
2750, Nov. 2013.
[6] P. Ruusuvuori et al., “Evaluation of methods for detection of fluorescence labeled subcellular
objects in microscope images,” BMC Bioinformat., vol. 11, no. 1, p. 248, 2010.
[7] K. Li and T. Kanade, “Nonnegative mixed-norm preconditioning for microscopy image
segmentation,” in Proc. Inf. Process. Med. Imag., vol. 21. 2009, pp. 362–373.
[8] D. Hu, P. Sarder, P. Ronhovde, S. Orthaus, S. Achilefu, and Z. Nussinov, “Automatic
segmentation of fluorescence lifetime microscopy images of cells using multiresolution
community detection—A first study,” J. Microsc., vol. 253, no. 1, pp. 54–64, 2013.
[9] G. Li et al., “3D cell nuclei segmentation based on gradient flow tracking,” BMC Cell Biol.,
vol. 8, no. 1, p. 40, 2007. [32] M. K. Bashar, K. Komatsu, T. Fujimori, and T. J. Kobayashi,
“Automatic extraction of nuclei centroids of mouse embryonic cells from fluorescence microscopy
images,” PLoS ONE, vol. 7, no. 5, p. 1, 2012.

Background fluorescence estimation and vesicle segmentation in live cell imaging with conditional random fields

Recomendados

Recomendados

Más contenido relacionado

Último

Último (20)

Destacado

Destacado (20)

Background fluorescence estimation and vesicle segmentation in live cell imaging with conditional random fields