Microscopic Digital Image Segmentation And feature Extraction of Acute Leukemia

International Journal of Science and Engineering Applications
Volume 5 Issue 5, 2016, ISSN-2319-7560 (Online)
www.ijsea.com 228
Microscopic Digital Image Segmentation And
feature Extraction of Acute Leukemia
Alaa Shakir Ahmed
AL Mansoura University Faculty of Engineering
Electronics and Communication Department
Mansoura - Egypt.
Dr. M. Morsy
Mansoura - Egypt.
Mohy Eldin A. Abo-Elsoud
Mansoura - Egypt.
Abstract— The goal of this paper is to identify and show the
differences in the properties of Acute lymphoblastic leukemia (ALL)
and normal white blood cells. This paper was conducted on a set of
microscopic digital images of blood samples that got it from the
“Oncology Center - Faculty of Medicine - Mansoura University
Hospital - Egypt” is made up of 50 microscope image samples of
Cancerous blood and 50 microscope image of the blood samples is
not Cancerous (normal blood). The microscope blood images are
undergo to chain of pre-processing steps which include resizing
image such as (512*512, 256*256, 128*128) and contrast
enhancement. By executing K-means clustering on the resultant
images, the cell's nucleus under consideration is obtained then these
segmented images enter sub-image stage. The next step is Extracted
Features that included: Shape features (Area, Perimeter,
Compactness, Solidity, Eccentricity, and Elongation); texture features
(Homogeneity, Energy, Correlation, Entropy, and Contrast); color
features and Fractal Dimension.
Keywords — (Digital Image Processing , Acute Leukemia ,
Normal White Blood Cell ,Contrast Enhancement , K-Means
Clustering , Features Extraction)
I. INTRODUCTION
Acute lymphoblastic leukemia (ALL), also known as acute
lymphocytic leukemia, or acute lymphoid leukemia, is an acute
form of leukemia, or cancer of the white blood cells,
distinguished by the overproduction and cumulation of
cancerous, immature white blood cells, known as lymphoblasts
[1]. Leukemia is "a cancer of the blood cells (WBC). It starts in
the bone marrow when abnormal cells (infected WBC)
redouble out of control To the extent that normal blood cells
(uninfected WBC) are incapable to develop". Which usually
affects blood, bone marrow, and lymph nodes. It is
distinguished by proliferation of abnormal white blood cells
(leukocytes) in the bone marrow without responding to cell
outgrowth inhibitors [2]. Four Most Common Kinds of
Leukemia:
1. Acute myeloid leukemia (AML) influence myeloid
cells and grows rapidly. Leukemic blasts cells gather in the
bone marrow and blood. About 15,000 Americans was
diagnosed with AML in 2013. Most (about 8,000) was 65 or
older, and about 870 children and teens will infect this disease.
2. Acute lymphoblastic leukemia (ALL) affects lymphoid
cells and grows rapidly. Leukemic blast cells usually collect in
the blood and bone marrow. More than 6,000 Americans was
diagnosed with ALL in 2013. Most of them (more than 3,600)
were children and teens.
3. Chronic myeloid leukemia (CML) influences in
myeloid cells and typically grows slowly at first. Blood tests
show a rise in the number of white blood cells. The abnormal
blood cells work okay. May be there are a small number of
leukemic blast cells in the bone marrow Nearly 6,000
Americans was diagnosed with CML in 2013. Nearly half
(about 2,900) were 65 or older and only Nearly 170 children
and teens will infect this disease.
4. Chronic lymphocytic leukemia (CLL) influences in
lymphoid cells and usually grows rapidly. Blood tests show a
rise in the number of the white blood cells. The actin of the
abnormal cells nearly as well as the normal white blood cells
[3], [4], Figure (1) shows the Kinds of Leukemia.
Figure (1) Kinds of Leukemia

www.ijsea.com 229
Figure (2) and Figure (3) how the difference between normal
(Non-Cancerous) blood smear and abnormal (Cancerous)
blood smear the one affected with Acute Leukemia.
Figure (2) Non-Cancerous Blood Smear (Normal)
Figure (3) Cancerous Blood Smear (Abnormal)
II. DIGITAL IMAGE PROCESSING
(METHODS)
The procedure of Segmentation and Features extraction for
Acute lymphoblastic leukemia (ALL) in microscopic blood
images consists of pre-processing (resize and contrast image),
segmentation using (k-means clustering), feature extraction
(shape – texture – color – HD) .The proposed system is shown
in Fig. (4).
Fig.(4). System Overview
A. Pre-processing
Pre-processing methods can be splitted into the two groups
according to the goal of the processing:
First: - Image resizing such as 512*512, 256*256 and 128 *
128.
Second: - Contrast enhancement by employ the “fspecial”
function with the “unsharp masking” filter has the
effectiveness of making edges and fine detail in the image
more crisp [5], then apply this mask filter on image by using
“imfilter” function with Boundary Option “replicate” that Input
array values outside the bounds of the array are assumed to
equal the nearest array border value [6].
Algorithm: Pre-processing using unsharp (Filtering)
 Read input image (X).
 Use Y = imresize (X, [512*512]).
 Create new variable color filtered for having same
attribute that of input image using unsharp masking
filter.
 Apply boundary option replicate filter algorithm on s
Merge all three planes together eparated RGB planes.
 Merge all three planes together.
 Output (Y) shown in Fig. (5).
(X) Input Image (Y) Resize 512*512
& Contrast Image
Fig. (5)
B. Segmentation
Segmentation is executed in two stages for extracting WBC
nucleus from the blood microscopic images using color based
clustering. Initial segmentation are completed by K-means
clustering followed by nearest neighbor classification in
L*a*b* space. K-means is a semi supervised clustering
technique which is employ to create K clusters from n
observations. It is aiming to achieve partition such that objects
within each cluster are as near to each other as possible, and as
far from object in the other clusters as possible [7]. Each pixel
of an object is classified into four clusters based on
corresponding a* and b* values in L*a*b* color space as
shown in Fig. (6). This four clusters represents four regions i.e.
RBC, WBC nucleus, cytoplasm and background stain. It was
observed that WBC cytoplasm and RBC are classified into
same cluster. In order to overcome the undesirable overlapping
of regions, a second stage segmentation is performed using
nearest neighbor classification. In the second stage we choose a
Database ALL
image
Database
Normal image
Pre-Processing
(Resize and Contrast)
Segmentation By
(K-Means Clustering)
Features Extraction
(Shape – Texture –
Color – HD)

www.ijsea.com 230
sample region randomly from each of the four clusters acquired
using K–means. The mean color of the each sample regions are
calculated in a*b* space and those values act as color
indicators. here each pixel in the L*a*b* space is distributing
into any of the four classes by computing the Euclidean
distance between that pixel and each color index. Each pixel of
the whole image will be labeled to a specific color depending
on the minimum distance from each index. The nucleus
segmented RGB image is reconstructed from the labeled
image. We have only considered the cluster which contains
blue nucleus as it is required for feature extraction and hence
leukemia detection. Few left out holes in the nucleus creates
problem during texture extraction and hence they are filled
using morphological reconstruction [8].
Fig. (6)
Algorithm Segmentation using K-means clustering
 Read Enhancement image (Y).
 [l a b] = Convert To L*A*B space
 A_B = Merge A*B space
 [ r c ] = get size (A_B)
 A_B_new = reshape(A_B, r*c , 2)
 Apply K-means clustering and output as shown in Fig.
(7).
Normal Image K-means Output
Abnormal Image K-means Output
Fig. (7)
C. Sub Imaging
Sub images including single nucleus per sub image are
obtained using bounding box technique [9]. Using image
morphology [10] only those sub images are selected which
contains only lymphocytes. The nucleus sub images of
neutrophils, eosinophil’s, and basophils are not considered for
feature extraction as they are not associated with lymphocytic
leukemia.
Fig. (8). shows the major steps and examples of
input/output images:
Step one) Input Image
Step tow) Sobel edge enhancing: - It's enhances the borders of
the membranes [11].
Step three) Structured image dilation: - The morphological
operator named dilation [12] has been employed to better
connect to the separated points of the membrane border and
make the perimeter of cell as a connected item (thicker more
than one pixel).
Step four) Hole filling: -This step include of filling internal
holes of the connected element with the largest area in the
processed image [13, 14].
Fig. (9) shows separated Nucleus Sub Images using Bounding
box technique.
Fig. (8)
Input Image
Sobel Edge
Dilation
Hole filling

www.ijsea.com 231
R max
Elongation =
R min (4)
Perimeter 2
Compactness =
Area (1)
Area
Solidity =
ConvexArea (2)
a2
- b2
Eccentricity =
a (3)
4 * pi * Area
Formfactor =
Perimeter2
(5)
Fig. (9). Separeted Nucleus Sub Images using Bounding box
technique
D. Feature Extraction:
Feature extraction in image processing involves reducing the
amount of resources required to describe a large set of data. In
the present paper broadly four types of features are extracted
(shape features, texture features, fractal dimension. In addition
also color features are extracted from the nucleus image).
A: Shape Feature:- According to the hematologist the shape
of the nucleus is an essential feature for distinguish of blasts.
boundary based shape features and Region are extracted for
shape analysis of the nucleus. All the features are extracted
from the binary equivalent image of nucleus with nonzero
pixels represents the nucleus region. For each nucleus we make
a quantitative evaluation by using the extracted features under
two classes. Region based and boundary based. These features
are as follows:
 Area: It was determined by computation the total number
of nonezero pixels within the image region.
 Perimeter: the perimeter was measured by computation
distance between the successive boundary pixels.
 Compactness: Compactness or roundedness is the measure
of a nucleus as defined in (1).
 Solidity: The solidity is the ratio of actual area and the
convex hull area and is also an essential feature for
classification a blast cell. This measure is defined in (2).
 Eccentricity: This parameter is used to measure how much
a shape of a nucleus deviates from being circular. It’s an
important feature since lymphocytes are more circular than
the blast. To measure this a relation is defined in (3).
where “a” is the major axis and “b” is the minor axis of the
equivalent ellipse representing the nucleus region.
 Elongation: Abnormal bulging of the nucleus It's also an
feature which indicates towards leukemia. Hence the
nucleus bulging is measured in terms of a ratio called
elongation. This is defined as the ratio between maximum
distance (Rmax) and minimum distance (Rmin) from the
center of gravity to the nucleus boundary and is given by
(4).
Where R max and R min are maximum and minimum radii
respectively.
 _ Formfactor: This is a dimensionless parameter which
changes with surface irregularities and is defined as (5).
B: Texture Feature-:The nucleus texture measurements were
performed on a gray scale version of the nucleus images. These
features were computed from the co-occurence matrices for
each nucleus image. This includes:
 Homogeneity: It is a measure of degree of variation.
 Energy: The energy are used to measure uniformity.
 Correlation: This represents the correlation between the
pixel values and its neighborhood.
 Entropy: It is usually used to measure the randomness.
 Contrast: The contrast is a measure of the intensity
contrast between a pixel and its neighbor over the entire
image.
C: Color Feature:- Since color is an important feature that
human perceiv ewhile visualizing it is considered for extraction
from nucleu sregions. Hence for each nucleus image the mean
color values in RGB color spaces are obtained. [15].
D: Fractal Dimension:- Fractals have been used in medicine
and science previously for several quantitative measurement
[16] [17]. the important measure that decided whether a
particular nucleus represents a lymphoblast or a mature
lymphocyte is the Perimeter roughness of nucleus. the more
convenient way to parameterize the cell boundary surface in
comparison to Euclidean geometry is fractal geometry.
Hausdorff dimension (HD) is a main feature for fractal
geometry and will be a main quantitative measure for cell
boundary roughness measurement. a procedure for Hausdorff
Dimension (HD) measurement using box counting method
[18]. The Hausdorff Dimension HD may then be obtaned as in
(6).
where, N the number of squares in the superimposed grid,
and N(s) the number of occupied squares or boxes (box
count). Higher HD denote to higher degree of roughness.
Table 1 displays the difference in the values of the shape
features for a pair of cancerous and noncancerous (normal)
Log(N)
HD =
Log(N(s)) (6)

www.ijsea.com 232
cell. Values indicate steep difference among the two sub-
images.
Table 1 Shape Feature Values
Features Cancerous 7 Normal 42
Area 2089.5 1056
Perimeter 407.79 280.98
Compactness 80.26 74.76
Convex Area 6175 2137
Solidity 0.657 0.494
Eccentricity 0.442 0.439
Elongation 123.06 100
Form Factor 64.35 47.20
Contrast 0.668 1.362
Correlation 0.756 0.634
Homomgeneity 0.839 0.810
Energy 0.159 0.192
Entropy 2.237 2.069
Mean 221.26 35.21
Standard Deviation 750.99 128.99
HausDroff 1.934 1.808
III. EXPERIMENTAL RESULT
The proposed technique has been applied on 100 blood
smear images obtained from “Oncology Center - Faculty of
Medicine - Mansoura University Hospital - Egypt” is made up
of 50 microscope image samples of blood infected , 50
microscope image of the blood samples is not infected.
A. Experiment
The experiment work of proposed system consist several
steps, all image are preprocessed by MATLAB to contrast
enhancement and resize be defined as in Table I. The system
segments all dataset image (cancer and normal image) ,and we
get separated nucleus sub Images using Bounding box
technique to extract all features.
B. Result Analysis
The experimental result has been developed by taking the
sub-images. The entire test images are gone through the
Preprocessing – Segmentation and from the sub-images obtain
Features Extraction.
Table.2
Pre-processing
(contrast – resize)
Time
Cancer
45 image
Normal
45 image
512*512 14.7313 14.778
256*256 13.412 13.7233
128*128 12.8222 12.2991
600*400 14.9824 145964
300*200 13.2879 13.1211
200*180 12.8286 12.8089
Table.3
Segmentation
K-Means
Time
Cancer
45 image
Normal
45 image
512*512 54.4611 52.575
256*256 14.5826 14.9145
128*128 8.1589 6.2723
600*400 49.5682 48.9681
300*200 13.5127 13.5717
200*180 12.5690 12.3620
Table.4
Sub – Image
Time
Cancer
45 image
Normal
45 image
512*512 9.47817 10.1307
256*256 3.8499 3.67331
128*128 3.42657 2.94794
600*400 7.92125 7.48196
300*200 3.88147 3.99509
200*180 3.7890 3.6025

www.ijsea.com 233
Table.5
Features Extraction
Time
Cancer
45 image
Normal
45 image
512*512 16.898 17.0685
256*256 5.21939 5.31412
128*128 2.42911 2.84163
600*400 29.3403 29.1306
300*200 8.20683 8.09558
200*180 3.6898 3.45067
IV. CONCLUSION
This paper has present segmentation (K-means Clustering)
technique and features extraction (Shape – Texture – Color –
HD ) and BP – SCG neural network for classify. The system
was evaluated in MATLAB 2014 and using data base 50
infected images and 50 non – infected images. The system is
less computational requirement this make system well suited
for low cost hardware implementation.
V. ACKNOWLEDGMENTS
My deepest appreciation goes to my supervisor Professor Dr.
Mohy Eldin A. Abo-Elsoud and DR. Mohamed El-Said Morsy
for his help and support in advising me to keep improving my
knowledge and to keep believing in my abilities. A similar
level of gratitude is due to “Oncology Center - Faculty of
Medicine - Mansoura University Hospital - Egypt”, for
supplying me the medical images we have needed it. I also
would like to thank the Ministry of Science and Technology
on the support provided by us to achieve optimal scientific
degrees.
VI. REFERENCES
[1] K. Breden, T. Schorr, J. B. Schorr, “Blood” Colliers
Encyclopaedia,
[2] Children’s Hospital of Wisconsin Website.
http://www.chw.org
[3] Edward D. Ball, G. A. L. (2002). 100 Questions &
Answers about Leukemia Jones & Bartlett Publishers
[4] Bain, B. (2003). Leukemia diagnosis (Third ed.): John
Wiley & Sons.
[5] Website http://www.mathworks.com/help/images/filter-
images-usingpredefined-filters.html
[6] Website
http://www.mathworks.com/help/images/ref/imfilter.html
[7] K. S. Ravichandran and B. Ananthi. Color Skin
Segmentation using K– Means Cluster. International Journal
of Computational and Applied Mathematics, 4(2):153 – 157,
2009.
[8] S. Mohapatra and D. Patra, “Automated Cell Nucleus
Segmentation and Acute Leukemia Detection in Blood
Microscopic Images ,”International Conference on Systems in
Medicine and Biology. P( 51).16-18 December 2010, IIT
Kharagpur, India.
[9] R. C. Gonzalez and R. E. Woods. Digital Image
Processing. Addison Wesley, 2nd edition, 1992.
[10] A. K. Jain, Fundamentals of Digital Image Processing.
Pearson Education, 1st Indian edition, 2003.
[11] J.S. Lim “Two dimensional signal and image processing”
Prentice Hall 1990.
[12] R. C. Gonzalez, R. E. Woods, S.L. Eddins, “Digital
Image Processing Using MATLAB”, Pearson Prentice Hall
Pearson Education, Inc., New Jersey, USA, 2004.
[13] H. J. A. M. Heijmans (1994): Morphological Image
Operators,Academic Press, New York.
[14] Fabio Scotti,” Automatic Morphological Analysis for
Acute Leukemia Identification in Peripheral Blood
Microscope Images”, IEEE International Conference on
Computational Intelligence for Measurement Systems and
Applications Giardini Naxos, Italy,P98. 20-22 July 2005.
[15] The Wikipedia the Free Encylopedia Website.
http://en.wikipedia.org
[16] B. B. Mandelbrot. How long is the coast of Britain?
Statistical self similarity and fractional dimension. Science,
156:636 – 638, 1967.
[17] B. T. Milne. Measuring the fractal geometry of
landscapes. Applied Mathematics and Computation, 27:67 –
79, 1988.
[18] A. P. Pentland. Fractal based description of natural
scene.IEEE Transactions on Pattern Analysis and Machine
Intelligence, 6:661 –674,1984.

Microscopic Digital Image Segmentation And feature Extraction of Acute Leukemia

More Related Content

What's hot (19)

Viewers also liked (20)

Similar to Microscopic Digital Image Segmentation And feature Extraction of Acute Leukemia (20)

More from Editor IJCATR (20)

Recently uploaded (20)

Microscopic Digital Image Segmentation And feature Extraction of Acute Leukemia