EXTRACTION AND CLASSIFICATION OF BLEBS IN HUMAN EMBRYONIC STEM CELL

IDL - International Digital Library
Of Technology & Research
Volume 1, Issue 2, Mar 2017 Available at: www.dbpublications.org
International e-Journal For Technology And Research-2017
IDL - International Digital Library 1 | P a g e Copyright@IDL-2017
EXTRACTION AND CLASSIFICATION
OF BLEBS IN HUMAN EMBRYONIC
STEM CELL
1
Lakshmi Thara. R
PG Scholor,
Electronics and Communication Engg,
Sri Venkateshwara College of
Engineering, Sriperumbudur,
Chennai-602117.
ABSTRACT
A main objective of this paper is
to extract bleb from the human
embryonic stem cells. Blebbing is an
important biological indicator in
determining the health of human
embryonic stem cells (hESC). Especially,
areas of a bleb sequence in a video are
often used to distinguish two cells
blebbing behaviours in HESC; dynamic
and apoptotic blessings. Here analyses
active contour segmentation method for
bleb extraction in hESC videos and
introduces a bio-inspired score function
to improve the performance in bleb
extraction. The full bleb formation
consists of bulb expansion and retraction.
Blebs change their size and image
properties dynamically in both processes
and between frames. Therefore, adaptive
parameters are needed for each
segmentation method. A score function
derived from the change of bleb area and
orientation between consecutive frames
2
S.P.Sivagnana Subramanian
Asst.Professor
Electronics and Communication
Engg, Sri Venkateshwara College of
Engineering, Sriperumbudur,
Chennai-602117.
with cuckoo optimization is proposed
which provides adaptive parameters for
bleb extraction in videos and classified
using artificial neural networks (ANN).
Index terms: Stem Cells, Human
Embryonic Stem Cell (hESC), artificial
neural network (ANN).
1. INTRODUCTIONS
In November of last 1999, groups in
the United States led by James Thomson
and John Gearhart published data
describing the derivation of candidate
human pluripotent embryonic stem (ES)
and embryonic germ (EG) cell lines from
blastocysts or primordial germ cells,
respectively (Thomson et al., 1998;
Shamblott et al., 1998). Readers will
probably agree that few if any previous
scientific papers reporting the
characterisation of cultured cell lines would
have attracted a similar degree of public
attention. The interest stems in part from
the ethical controversy surrounding the
origins of the cells but chiefly from the
widespread conviction that their availability

will profoundly alter our approaches to
many problems in human biology and
medicine. Several features define ES cells
(below), but the two key properties that
make these cells so remarkable are these:
ES cells can be grown in vitro and
expanded in number indefinitely in the
primitive undifferentiated state
characteristic of the embryonic cells from
which they are derived, and throughout
long periods of cultivation in vitro they
retain a key property of those embryonic
cells – pluripotency, or the ability to
develop into any cell type in the adult body.
The scope of even the more obvious
applications envisioned for human cells
with these properties is breath taking: new
approaches to the study of human
embryonic development and disorders
thereof,
such as birth defects and embryonic
tumours; access to hitherto-unexplored
territories of human embryonic gene
expression for modern genomics data
mining; new tools for the discovery of
polypeptide growth and differentiation
factors that might find application in tissue
regeneration and repair; new means to
creating human disease models in vitro for
basic research, drug discovery and
toxicology; a potential answer to the issue
of the chronic shortage of tissue for
transplantation in the treatment of
degenerative diseases, and an end to the use
of immunosuppressive therapy in
transplantation, if cloning techniques can be
used to derive stem cells from a patient’s
own tissue; new delivery systems for gene
therapy. Given the potential applications of
these cells, and the ethical controversy
regarding the use of in vitro fertilised
embryos or tissue from aborted foetuses to
derive them, the widespread public
discussion of these issues is understandable,
warranted, and welcome. However, since
the sheer volume of commentary on human
ES cell ethics, scientific applications and
commercial potential now threatens to
overwhelm the peer-reviewed scientific
literature on the subject, we will focus here
on human ES cells themselves: the
background to their discovery, their known
properties, and what we need to learn about
them before we begin to use them to
address the futuristic agenda outlined
above.
2. HUMAN EMBRYONIC STEM
CELLS
As stated earlier, human embryonic
germ (EG) cells share many of the
characteristics of human ES cells, but
differ in significant ways. Human EG cells
are derived from the primordial germ
cells, which occur in a specific part of the
embryo/fetus called the gonadal ridge, and
which normally develop into mature
gametes (eggs and sperm). Gearhart and
his collaborators devised methods for
growing pluripo-tent cells derived from
human EG cells. The process requires the
generation of embryoid bodies from EG
cells, which consists of an unpredictable
mix of partially differentiated cell types
[10]. The embryoid body-derived cells
resulting from this process have high
proliferative capacity and gene expression
patterns that are representative of multiple
cell lineages. This suggests that the
embryoid body-derived cells are
progenitor or precursor cells for a variety
of differentiated cell types [11]. The
characterization of stem cell cultures has
two main purposes: monitoring the
genomic integrity of the cells and tracking

the expression of proteins associated with
pluripotency. Genomic analysis is
necessary to ensure stem cells maintained
in culture have not undergone
chromosomal changes through
chromosomal loss or duplication, or
changes in their epigenetic profiles.
Proteomic analysis ensures that the cells
are expressing the factors necessary to
maintain pluripotency. Confirmation of
the differentiated state by analysing key
genetic and protein markers ensures
identification and propagation of the
correct cell type. This section provides an
overview of different analysis methods for
stem cells including karyotyping, single-
nucleotide polymorphism (SNP) analysis,
epigenetic profiling, flow cytometry and
immunocytochemistry, RT-qPCR, digital
PCR, western blotting, biomarker analysis,
and teratoma formation. A variety of
factors affect stem cell cultures. Stem cell
cultures must be periodically assessed for
changes in morphology, karyotype, and
ability to differentiate. Adaptation to
culture conditions and maintenance in
culture of any cell type will change the
population. As cells divide and are
passaged, the composition of the
population changes due to selective
pressures on the cells. Additionally, cells
that grow and divide
Fig1 Stem cells process
Factors Media composition
Cell density
Feeder cell type/density
Growth factors/additives
Feeder free culture
Passage method
Number of passages
Freezing and thawing protocols
Microbial contamination
Possible changes
Chromosomal

Phenotype/morphology
Differentiation Pluripotency loss Epigenetic
changes Tumorigenesis Loss of self-
renewal ability.
A number of techniques are used for
genetic characterization of stem cells:
karyotyping, fluorescence in situ
hybridization (FISH), comparative
genomic hybridization, single nucleotide
polymorphism (SNP) analysis, and
epigenetic profiling. Some types of stem
cells, particularly embryonic stem cells
(ESCs)[13] and induced pluripotent stem
cells (iPSCs), are more prone to being
genetically unstable and should be
observed frequently for chromosomal
changes. Stem cells express both unique
and specific combinations of
transcription factors, cell surface
proteins, and cytoplasmic proteins.
Techniques used for stem cell analysis
and characterization include flow
cytometry, array-based analysis of the
transcriptome, immunocytochemistry,
western blots, and biomarker analysis.
Different classes and types of stem cells
are characterized by different
combinations of markers. In addition to
confirming that stem cell lines are stable,
markers can be used for screening during
the reprogramming of somatic (adult)
cells into induced pluripotent stem cells
(iPSCs) or to follow the progression of
stem cell differentiation[7,5,3].
3. ACTIVE CONTOUR MODEL
Active contour model, also called
snakes, is a framework in computer vision
for delineating an object outline from a
possibly noisy 2D image. The snakes model
is popular in computer vision, and snakes
are greatly used in applications like object
tracking, shape recognition, segmentation,
edge detection and stereo matching.
A snake is an energy minimizing,
deformable spline influenced by constraint
and image forces that pull it towards object
contours and internal forces that resist
deformation. Snakes may be understood as
a special case of the general technique of
matching a deformable model to an image
by means of energy minimization.[1] In
two dimensions, the active shape model
represents a discrete version of this
approach, taking advantage of the point
distribution model to restrict the shape
range to an explicit domain learned from a
training set.Snakes do not solve the entire
problem of finding contours in images,
since the method requires knowledge of the
desired contour shape beforehand. Rather,
they depend on other mechanisms such as
interaction with a user, interaction with
some higher level image understanding
process, or information from image data
adjacent in time or space.
3.1 Energy Formulation
A simple elastic snake is defined by
a set of n points vi where i=0…..n-1, the
internal elastic energy term Einternal, and the
external edge-based energy term Eexternal.
The purpose of the internal energy term is
to control the deformations made to the
snake, and the purpose of the external
energy term is to control the fitting of the
contour onto the image. The external
energy is usually a combination of the
forces due to the image itself Eimage and
the constraint forces introduced by the
user Econ. The energy function of the snake
is the sum of its external energy and
internal energy, or

3.2 Internal Energy
The internal energy of the snake is
composed of the continuity of the
contour Ecount and the moothness of the
contour Ecurv.
This
can be
expan
ded as
W
here
α(s) and β(s) are user-defined weights; these
control the internal energy function's sensitivity
to the amount of stretch in the snake and the
amount of curvature in the snake, respectively,
and thereby control the number of constraints
on the shape of the snake.
In practice, a large weight α(s) for the
continuity term penalizes changes in distances
between points in the contour. A large
weight β(s) for the smoothness term penalizes
oscillations in the contour and will cause the
contour to act as a thin plate.
3.3 Image Energy
Energy in the image is some
function of the features of the image. This
is one of the most common points of
modification in derivative methods.
Features in images and images themselves
can be processed in many and various
ways.
For an image I(x,y), lines, edges, and
terminations present in the image, the general
formulation of energy due to the image is
Where wline, wedge, wtrem are weights of these
salient features. Higher weights indicate that
the salient feature will have a larger
contribution to the image force.
4. IMPLEMENTATION RESULTS
The frames in the video are phase
contrast images. The videos were
acquired using 2xobjective with
512x512resolution. Each video frame is
acquired at 0.001 seconds time interval.
The input video is shown in figure.
Fig 2 Input Stem cells
The command window gives
information about the frame rate, here 25
frames are attained per second. The
resolution of video is 512x512 and this
video is acquired in color format. The
Video capture is done in RGB space
which is not efficient for
preprocessing. Unlike RGB, HSV
separates luma, or the image intensity, from
chroma or the color information. This is
very useful in many applications. The color
information is usually much more noisy
than the HSV information. Hence RGB can
be converted into HSV. HSV color space is
used for processing.
Median filter is applied to clean the
image from acquisition noise.
v(m,n)=median{y(m-k,n-l),(k,l)
The segmentation is done by using region
based active contour. This method handles
the topological changes automatically during
the evolution of the curve, and implemented
conveniently on a uniform grid. The image
shows the thin white line which signifies the
area of bleb region.

Fig 3 pre-processed output
Fig 4 segmented output
5.CONCLUSION
The bio-optimized segmentation
methods have better performances than
their conventional counterparts. With the
bio-inspired optimization metric, low
performance due to over-segmentation is
reduced. Bleb area detection by active
contour segmentation followed by
cuckoo search optimization is plausible.
The method yields high true positive rate
white it gives low false positive rate. The
method also matches the trend of the
ground truth experiment closely. To
improve the accuracy further, it is
necessary to investigate into getting more
frames per second to establish inter
frame relationship for detecting small
tiny bleb regions.
6. REFERENCE
1. Amit, M., Carpenter, M.K., Inokuma,
M.S., Chiu, C.P., Harris, C.P., Waknitz, M.A.
Itskovitz-Eldor, J., and Thomson, J.A. (2000).
Clonally derived human embryonic stem cell
lines maintain pluripotency and proliferative
potential for prolonged periods of culture. Dev.
Biol. 227,271-278.
2. Benjamin X. Guan, Bir Bhanu, Prue
Talbot, and Nikki Jo-Hao Weng, “Extraction of
blebs in human embryonic stem cells” IEEE
transaction on biomedical and health informatics,
vol. 13, no. 4, August 2016 .
3. Yuncheng Du, Hector M. Budman,
Thomas A. Duever, “Segmentation and
Quantitative Analysis of Normal and Apoptotic
Cells from Fluorescence Microscopy Images”
Elsevier international federation of automatic
control, vol. 49, June 2016.
4. Ngaam J. Cheung, Xue-Ming Ding, and
Hong-Bin Shen, “A Nonhomogeneous Cuckoo
Search Algorithm Based on Quantum

Mechanism for Real Parameter Optimization”
IEEE transaction on cybernetics, Jan 2016.
5. Benjamin X. Guan, Bir Bhanu, Prue
Talbot, and Sabrina Lin, “Bio-Driven Cell
Region Detection in Human Embryonic Stem
Cell Assay” IEEE transactions on computational
biology and bioinformatics vol. 11, no. 3, June
2014.
6. B.X. Guan, B. Bhanu, P. Talbot, and S.
Lin, “Automated Human Embryonic Stem Cell
Detection,” Proc. IEEE Second Int’l Conf.
Healthcare Informatics, Imaging and Systems
Biology, pp. 75-82, Sept. 2012.
7. E.Meijering, “Cell segmentation: 50
years down the road [life sciences],”IEEE Signal
Process.Mag., vol. 29, no. 5, pp. 140–145, Sep.
2012.
8. B. X. Guan, B. Bhanu, P. Talbot, and S.
Lin, “Detection of nondynamic blebbing single
unattached human embryonic stem cells,” in
Proc. IEEE Int. Conf. Image Process., Sep. 2012,
pp. 2293–2296.
9. B. X. Guan, B. Bhanu, P. Talbot, and S.
Lin, “Automated human embryonic stem cell
detection,” in Proc. 2nd IEEE Int. Conf. Health
Informat., Imag. Syst. Biol., Sep. 2012, pp. 75–
82.
10. Getreuer, P., 2012. Chan-Vese
segmentation. Image processing online, Volume
2, pp. 214-224.
11. Z. Yin, R. Bise, T. Kanade, and M. Chen,
“Cell segmentation in microscopy imagery
symposium on biomedical imaging,” in Proc. Int.
Symp. Biomed. Imag., 2010, pp. 125–128.
12. G. T. Charras, et al., “Life and times of a
cellular bleb,” Biophysical J., vol. 94, pp. 1836–
1853, Mar. 2008.
13. Chan, T. F. & Vese, L. A., 2001. Active
contours without edges. IEEE Transactions on
Image Proceessing, 10(2), pp. 266-2

EXTRACTION AND CLASSIFICATION OF BLEBS IN HUMAN EMBRYONIC STEM CELL

Recommended

Recommended

More Related Content

What's hot

What's hot (19)

Similar to EXTRACTION AND CLASSIFICATION OF BLEBS IN HUMAN EMBRYONIC STEM CELL

Similar to EXTRACTION AND CLASSIFICATION OF BLEBS IN HUMAN EMBRYONIC STEM CELL (20)

Recently uploaded

Recently uploaded (20)

EXTRACTION AND CLASSIFICATION OF BLEBS IN HUMAN EMBRYONIC STEM CELL