4

International Journal of Advanced Technology and Engineering Exploration, Vol 3(25)
ISSN (Print): 2394-5443 ISSN (Online): 2394-7454
http://dx.doi.org/10.19101/IJATEE.2016.325004
217
Detection of lung cancer using image processing techniques
Prathamesh Gawade*
and R.P. Chauhan
Department of Physics (Instrumentation), NIT, Kurukshetra, Haryana
©2016 ACCENTS
1.Introduction
Cancer can be explained as uncontrolled cell growth
having ability to spread all over the body. Our body
contains red blood cells (RBC’s). The main function
is to supply fresh oxygen (O2) to all parts of the body
with the help of blood flow, due to which blood
appears red [1]. In the lungs, tissue receives oxygen
(O2) because of RBC’s only.
The genetic content of erythrocytes has high
concentration of haemoglobin. The cell membrane
consists of proteins and lipids which is backbone of
psychological cell function. They do not contain any
important part of cell, which includes haemoglobin.
Around 20 lakhs new RBC’s are produced per second
[2]. The cells are produced in the bone marrow and
rotate throughout the body for about 4 months to &
fro in arteries and veins. Each rotation takes about 20
seconds. Approximately 75% of the cells & majority
concentration of blood in the human body are red
blood cells [3, 4]. Young Dutch biologist Jan
Swammerdam described it perfectly with an early
microscope in 1658. Lung cancer, also called as
carcinoma [5] is a malignant lung tumour defined by
uncontrolled cell growth in tissues of the lung [6].
*Author for correspondence
If left undiagnosed, this growth penetrates beyond the
lung by the process of ‘metastasis’-which produces
agency (as cancer cells) from initial site of disease to
another part of body [7].
Most cancers also known as primary lung cancers are
carcinomas which start it in the lungs [8]. There are
two main types are carcinoma 1) small-cell lung
cancer and 2) non-small-cell lung cancer [9]. The
most common symptoms are coughing (including
blood coughing), weight loss, breath shortness, and
minute as well as severe chest pains [10]. These
cancer cells disturbs the cycle of RBC production and
degradation. Internally they change the structure and
composition of plasma membrane i.e. the outer
structure of the cell in such a way that these RBC’s
do not die as per the corresponding lifetime. As a
result the RBC count goes on increasing and more
and more number of cell gets accumulated resulting
in shortening of veins and arteries and ultimate
bursting. These outcomes into blood through cough
etc.
Image processing is used to analyse images at the
lowest level provided any quality. These operations
do not increase probability of image information
content, but they decrease it if entropy is an
Research Article
Abstract
The diagnosis of lung cancer at an early stage is of utmost importance if it is meant to degrade high mortality rate. The
global lung screening program points to visualise positron emission tomography (PET) and computed tomography (CT)
examinations amongst most aged groups at risk to enhance the early detection rate. Although use of invasive techniques,
symptoms hardly appear until disease is advanced making it difficult for radiologist to identify lesions. Unfortunately,
most lung cancer patients suffering at advanced stages result in dismal with five-year survival rate of 17.8% and for
distant tumours, being only 4%. Genuine and precise information is the basis of disease control initiatives. More than
85% of the disease is related to tobacco consumption. In addition, genetic factors, exposure to environmental pollutants,
second hand smoking inflate disease rapidly. Remedies including chemotherapy, radiotherapy, surgery, epidermal
receptive drugs escalate survival rate and quality of life. This method is more about diagnosing at early and crucial stages
with intelligent computational techniques with various distortion removals by segmentation techniques and algorithms
which is the root concept of image processing. Detection of CT images obtained from cancer institutes is analysed using
MATLAB.
Keywords
Lung cancer, MATLAB, CT images, Distortion removal, Segmentation, Mortality rate.

Prathamesh Gawade et al.
218
information measure. The main requirement of
processing is to improve pixel intensity by converting
from discrete to digital image, segmenting to pixels,
carrying out mathematical operations on pixels, and
reconstructing of image with better quality [11]. Pre-
processing of CT images is the initial step in image
analysis followed by segmentation process and ended
with some morphological operations are applied to
detect the cancer spots/cells in the image. Also it can
be used to determine the amount of spreading of
cancer i.e. what percentage of lung is affected with
cancer. The morphological operations are basically
applied by comparing the size and shape of the
cancer cell with normal cell, and then the infected
cells images displayed onto grey scale image with
maximum intensity (255). The sequencing of the
paper is as follows. Section II describes the
prescribed methodology, in detail with mathematical
operations performed on the image using various
filtering methods followed by segmentation. Section
III shows the results of the developed methodology
using a MATLAB image. Finally, section IV defines
the conclusion and application of the method in
diagnostics of various diseases.
2.Methodology
The algorithm is proposed as is given in Figure 1 as
follows:
Figure 1 Algorithm for cancer detection
The design is explained below as follows:
2.1Input image
For any type of cancer, firstly image of internal parts
of the body should be obtained. CT scan also known
as X-ray computed tomography makes use of X-ray
for capturing the images from various angles and
merge these images to generate cross sectional
tomographic image of particular areas of scanned
tissues i.e. it allows the person to see the status inside
body without non-invasive techniques [12]. The
lungs are the prime important organs of respiration in
humans as well as other animals. In mammals and
majority of the vertebrates, two lungs are located on
either side of the heart near to backbone. Their role is
to take oxygen from the atmosphere and transfer it
into the bloodstream, and to give out carbon dioxide
from the bloodstream into the atmosphere. Humans
have 2 lungs, right & left. They are situated inside the
thoracic cavity of chest. The right lung being bigger
than the left, shares space with the heart. The lungs
together weigh approximately 1.4 kg. Plural sac in
which lungs are enclosed allows inner and outer
walls to slip over each other without more friction.
This sac encloses each lung and also divides each
lung into sections called lobes.
The right lung has 3 lobes and the left has two. The
lobes are further classified into bronchopulmonary
segments and lobules. The lungs possess a unique
blood supply, receiving deoxygenated blood from the
heart for receiving oxygen (i.e. pulmonary
circulation) and a distinguished supply of oxygenated
blood (the bronchial circulation). The tissue of the
lungs can be struck by a number of diseases,
including pneumonia and lung cancer. Chronic
diseases such as chronic obstructing pulmonary
disease and emphysema (damaging alveoli’s in the
lungs) can be linked to smoking or exposure to
harmful substances. Diseases such as bronchitis can
also involve the respiratory tract. The image of
affected lungs and normal lungs is quite different and
easily differentiable. These CT images are converted
to grayscale images.
2.2Grayscale image
In the computing world, a grayscale image is a digital
image, in which the value of each pixel is an
individual sample, i.e., it carries only intensity or
amplitude. Images of this kind, also known as white
(highest intensity) & black (lowest intensity) images,
consist exclusive shades of gray [13].Grayscale
images are the result of measuring the intensity of
light at each pixel in a single band of the light

219
spectrum. They can also be obtained from a full
colour image. The reason behind choosing grayscale
image is even minimum pixel intensity is also helpful
in detecting changes in the cells. In fact a gray colour
is one in which the R, G, B planes have equal
amplitude, the brightness levels represented as a
number from decimal 0 to 255. For every pixel in an
RGB grayscale image, G = B = R. The intensity
varies in proportion with the number representing the
brightness levels of the RGB colours. Black is
represented by R = G = B = 0 and white is
represented by R = G = B = 255.
2.3High pass filter
As the name suggests, it passes the frequency above
certain cut-off frequency and attenuates all the
frequency below the cut-off frequency. A high pass
filter is mainly used for sharpening images. It is done
when contrast is enhanced between the adjacent areas
with increase or decrease in brightness level. A high
pass filter sets high threshold cut-off to obtain
information of an image while cutting the low
frequency data. The basis of the high pass filter is
designed to increase the amplitude of the median
pixel relative to adjacent pixels. The kernel array
generally contains a single value at its center, which
is completely surrounded by other values. The values
may be defined in terms of positive or negative.
2.4Median filtering
It is a nonlinear digital filter used to remove some
noise in the image. To detect some edge in the image,
firstly noise should be removed up to some threshold
value and then edge removal is performed. Hence the
median filter is placed before edge detector. Its main
feature is it removes noise without edge removal.
Median filter is same as that of averaging filter, in
which each output image pixel is set corresponding to
the average value of neighbouring pixel of the input
image. The median filter is more sensitive to mean
values and less sensitive to extreme values of pixel
which helps in noise reduction.
2.5Threshold segmentation
Threshold segmentation is one of the easiest
segmentation methods. The pixels are divided
depending upon their amplitude levels. There are
various types of segmentation depending on
parameters like threshold values of pixels, edge
based, region based, clustering etc.
It relates grayscale image to binary image, also called
as mapping. After this operation, image is divided
into 2 pixel values only, 0 & 1. If there is an image
which contains dark structure on bright background,
then thresholding can be used to separate the
structure. Also to set a particular threshold value,
many sub algorithms can be used e.g. histogram
estimation, optimal thresholding, iterative
thresholding, K means clustering. In K means
clustering, grayscale image is divided into K
segments i.e. K-1 threshold values, thereby reducing
variance. Many images which are made of pixels
contains more than one value e.g. RGB. If we
separate these pixel values for R, B & G, they are
called channels.
2.6Watershed algorithm
It can be explained using a practical idea. Consider a
surface immersed into the lake with a hole at minima,
so that water will start filling through that hole and
will go on increasing. If 2 such surfaces very close to
each other are placed then a point will come where
the water will overlap and mix from both the surface.
At that point only, dams are built so that water does
not mix. These dams are watershed lines and by the
process of filling water, surface separation can be
done. There are many methods to carry out this
algorithm. One of the most common watershed
algorithms was introduced by F.Meyer called ‘Meyer
watershed algorithm’. This algorithm applies only to
grayscale image [14].
2.7Morphological operations
According to Wikipedia, mathematical morphology
is a technique to evaluate segmented
structures/images based on random functions, set
theories etc. It is strictly applied to digital images
only. E.g. binary morphological operations explores a
particular grayscale image with simple, predefined
shapes, and concluding how this shape fits into the
image provided or what part of the image gets missed
due to this shape.
3.Experimental result and analysis
For implementation of this above method, real time
images of cancer patients have been obtained from
institutes. Since cancer in CT image have more
intensity level than background, it becomes very easy
to extract image from CT image for further analysis.
The working methodology is as follows:

220
3.1Processing grayscale image with median filter
The proposed work flow is given in Figure 2.
Figure 2 Algorithm for preprocessing of CT scan
image
The CT scanned Image with cancer infected lung
obtained from the institute is given in Figure 3.
Figure 3 CT Image of cancer infected lungs
The CT image is converted to grayscale image to
perform mathematical operations shown in Figure 4.
Figure 4 Grayscale image
Now it is ready to carry out further mathematical
operations, the image is passed through a high pass
filter to enhance the information needed shown in
Figure 5.
Figure 5 High pass filtered image
Further enhancement of the image for detailed
analysis is done using median filtering. For this we
add salt and pepper noise to reduce noise from the
image, so that the image is distortion less shown in
Figure 6.
Figure 6 Salt and pepper noisy image
Final pre-processing is done by passing salt and
pepper noise through a median filter which will allow
removing noise completely from the image while
restoring edges shown in Figure 7.
Figure 7 Median filtered image

221
The median filtered passed through various
segmentations shown in Figure 8.
Figure 8 Segmentation process
The segmented image is shown as follows in Figure
9.
Figure 9 Threshold segmented image
The heart of this process is watershed algorithm. It
will identify the areas affected by cancer in the
infected lung with the help of which we could
differentiate cancerous lung tissue with normal lung
tissue as shown in Figure 10.
Figure 10 Watershed image
The output of the watershed image contains pixels of
infected lung tissues which are not labelled. These
pixels are in the form of watershed lines. Figure 11
shows the output image after successful
Morphological operations. This figure clearly
represents left lung being more infected by cancer
with background stating the cancer region as
compared to right lung of the given CT scan image.
Figure 11 Output image with input image after
morphological operations
4.Conclusion and future work
The above method is processed in two steps 1)
Processing of noisy input image using filter and
segmentation 2) Morphological operations on CT
image. The cancer affected lungs region can be
observed in the final output image to CT input image
provided. The proposed method can also be applied
to some other cancer types like breast cancer, skin
cancer etc. Also it finds its application in the medical
research as well.
Acknowledgment
A very grateful thank to Dr. Mayuresh Kiran
M.B.B.S., M.D. (Pharmacology). Dy. General
Manager-Medical Services, Centaur Pharmaceuticals,
Mumbai who made significant contribution in
improvement of the research paper by providing CT
scan images for lung cancer affected patients.
Conflicts of interest
The authors have no conflicts of interest to declare.
References
[1] Lipowsky R, Sackmann E. Preface to volume 1a from
cells to vesicles: introduction and overview.
Handbook of Biological Physics. 1995.
[2] Lemjabbar-Alaoui H, Hassan OU, Yang YW,
Buchanan P. Lung cancer: Biology and treatment
options. BBA Reviews on Cancer. 2015; 1856(2):189-
210.

222
[3] Pierige F, Serafini S, Rossi L, Magnani M. Cell-based
drug delivery. Advanced Drug Delivery Reviews.
2008; 60(2):286-95.
[4] Villa CH, Anselmo AC, Mitragotri S, Muzykantov V.
Red blood cells: supercarriers for drugs, biologicals,
and nanoparticles and inspiration for advanced
delivery systems. Advanced Drug Delivery Reviews.
2016.
[5] Dubey AK, Gupta U, Jain S. Epidemiology of lung
cancer and approaches for its prediction: a systematic
review and analysis. Chinese Journal of Cancer. 2016;
35(1):71.
[6] Scagliotti GV, De Marinis F, Rinaldi M, Crino L,
Gridelli C, Ricci S, Matano E, Boni C, Marangolo M,
Failla G, Altavilla G. Phase III randomized trial
comparing three platinum-based doublets in advanced
non–small-cell lung cancer. Journal of Clinical
Oncology. 2002; 20(21):4285-91.
[7] Laccetti AL, Pruitt SL, Xuan L, Halm EA, Gerber DE.
Prior cancer does not adversely affect survival in
locally advanced lung cancer: A national SEER-
medicare analysis. Lung Cancer. 2016.
[8] World Health Organization. The world health report
2000: health systems: improving performance. World
Health Organization; 2000.
[9] O’REILLY KM, Mclaughlin AM, Beckett WS, Sime
PJ. Asbestos-related lung disease. Chest. 2007.
[10] Collins LG, Haines C, Perkel R, Enck RE. Lung
cancer: diagnosis and management. Am Fam
Physician. 2007; 75(1):56-63.
[11] Hricak H, Thoeni RF. Anatomy of the prostate gland.
In Pollack HM. Clinical urography. 2nd ed.
Philadelphia, Pa: Saunders; 2001.
[12] Larkins DB, Harvey W. Introductory computational
science using MATLAB and image processing.
Procedia Computer Science. 2010; 1(1):913-9.
[13] Johnson S. Stephen Johnson on digital photography.
O'Reilly Media, Inc.; 2006.
[14] Gonzalez RC, Woods RE. Digital image processing.
Prentice Hall; 2008.
Prathamesh. P. Gawade. I received
my B.Tech degree from Pune
University in Electronics Engineering
in 2012, currently pursuing M.Tech
degree from NIT kurukshhetra. I am
having 1 year of industrial experience
on graduate level. I presented a
technical paper in the area of Image
Processing in various conferences held at IIT delhi, IIT
BHU, IIT Guwahati & NIT kurukshetra. My area of
interest includes Image Processing, Signal anaylsis &
communication engineering.
Email: pg1911991@gmail.com@gmail.com
Dr. Rishi Pal Chauhan, He is an
Associate professor at NIT kurukshetra,
PhD in physics and has teaching
experience of 30 years. I am currently
working in field of radiation physics,
material science, and instrumentation
and have more than 150 research papers
published in SCI journals. Currently
guiding 12 students for PhD degree, 40 students for M.tech
degree and 20 students for M.Phil degree.

4

More Related Content

What's hot (20)

Similar to 4 (20)

More from SRI TECHNOLOGICAL SOLUTIONS (20)

Recently uploaded (20)

4