EFFICIENT day cancer is grabbing our world. Cancer is

EFFICIENT CANCER DETECTION METHOD FOR DIFFERENT
CANCER DISEASES: A REVIEW

 

Amrutha Sunil

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

Divya D

Department of Computer Science and Engineering
Mahatma Gandhi University Kottayam

      Department of Computer Science and
Engineering
                 Mahatma Gandhi University
Kottayam

Adi Shankara Institute Of Engineering and Technology

Adi Shankara Institute Of Engineering and Technology

                                 Kalady,
Kerala

                                       
Kalady, Kerala

 

 

 

                Abstract – : Day by day cancer is grabbing
our world. Cancer is a serious and common threat to human life. It is estimated
that 8.2 million people died due to cancer. Cancer is the result of abnormal
cell division and growth with the potential to invade or spread to the other
parts of the body. There are more than 200 different types of cancer. Some are
liver, lungs, skin, blood and breast etc. Lifestyles, environmental facts and
genetics can be the major reasons for cancer. Early detection of cancer
increases the possibility of successful treatment and a healthy life. Cancer
treatment is really a fight between cancer attack and chemo soldiers. The paper
is dealing with blood, liver, lungs, breast and brain cancer detection methods.
Recognising the possible warning sign of cancer and taking proper action leads
to early diagnosis.

 

 

                Index Terms = Image fusion,
Image processing, neural network

 

I.  Introduction

                Cancer detecting is a multistage
process. Sometimes the cancer is discovered by chance or from screening, that
is checking for cancer in people who have no symptoms. It can help the doctors
to find and treat several types of cancer at its early stage.

Cancer detection
involves radiological imaging. The common imaging method used to detect cancer
and to monitor its spreading is CT scans (computed tomography) using X-rays. It
provides cross-sectional imaging by the computer about hard tissues. MRI
(magnetic resonance imaging) provides information about soft tissues. MRI uses
powerful magnetic fields.

The paper contains an
overview of skin, blood, breast, liver, lungs, and brain cancer detection
methods. Brain cancer detection is enhanced through image fusion which allows
combination of features of different modality images1. To result
in an easy and reliable method to detect cancer tissue through fusion, it
should include the application of Discrete wavelet transform (DWT) and Neural
network2.  Breast cancer
detection can be done by combining thermography and high frequency excitation techniques4.  The paper provides a description of RF
effects on human body and simulation results. To validate the method a
multilayer 3D breast model is simulated. Detecting lungs7 and
liver5 cancer is a difficult task. The work proposes 2D and 3D CT
scan method to detect the cancerous cells effectively.

 

 

 

II. METHODOLOGIES

Brain Cancer

Brain Cancer detection
is done by image fusion technique 1. This process combines
multimodality images through image processing. For acquiring an enhanced image,
several operations are performed on the image. Image processing is defined as
signal processing, in which an image is taken as input and output may be an
image or features of that image.

 

 

                       Fig 2 : CT image of Brain tumor

 

 

The overall step in
brain tumor detection is  illustrated in
fig 1.

The first step is
image acquisition. It refers to the process of collecting the real world CT and
MRI images and storing it in the database. Fig shows the sample CT image of
brain that have infected cancer cells. Then the number of pixel in the image is
changed to obtain a new version of original image, this process is called
resampling. To increase the brightness, contrast and to reduce the variations
due to noise are done by image processing. 
The 2 method applied for enhancements are contrast enhancement and noise
removal. Contrast enhancement does not change the values that represent the
image instead, it modifies the color mapping and make it more bright. Noise
removal is process of extracting the necessary information by removing the
unwanted details from an image.

Next stage is image
decomposition using DWT. It is done by passing the images through the filters
at different level of decomposition. By taking the coefficients of the
decomposed images, fusion of the images are performed.  DWT is a numerical tool that is used to
discretely sample the wavelets and it produces high pass and low pass wavelet
series. The low frequency coefficient shows the gross approximations of the
source images and high frequency coefficients correspond to sharper brightness
in the image. Apply certain fusion rules on the obtained coefficients to merge
and then apply inverse DWT on the fused coefficient to obtain a fused image.
Then the output is given as input to the segmentation stage. The activity of
segmentation is the extraction of affected regions from the image, from which
information can easily be understood. The segmented image is used fot the
detection of cancer by using Feed forward neural network2
classifier to extract the tumor cells from non tumor cells.

 

Blood Cancer

  

        Fig
3: Normal and leukemia affected Blood cells

 

Cancer which affects
the white blood cells are called Leukemia. Human blood consists of White blood
cells, Red blood cells, plasma and platelets. A person’s body who is suffering
from leukemia produces too many blood cells of certain type than another. They
do not function properly from normal cells. Leukemia is grouped in to 2 ways
Acute and Chronic. Lymphoid cells and myeloid cells are the 2 type of abnormal
white blood cells that can turn into leukemia.

Blood cancer can be
identified by

 

 

   Fig 4: Blood cancer detection process 3

 

Microscopic image
acquisition is the process of collecting and storing microscopic image of blood
cells with significant magnification 3. Next step is image
pre-processing. Due to excessive staining the image may contain noise. This
noise has to be removed to improve the quality of image using proper technique
and also remove the background of the image because our focus is
only the white blood cells. In image segmentation the image is partitioned into
multiple segments. An automatic image segmentation will gives the accurate
results and will be able to differentiate the blast cell from the normal cells.
Blast cells are abnormal immature white blood cells. Then the
feature of each blood cell is extracted to differentiate each cells with
others. The feature extraction is dealing with texture, color, geometrical and
statistical. The feature of blast cells include scanty cytoplasm, round, all
blast cells are uniform and usually contains single nucleoli inside nucleus. Next
is Image classification, here the K-nearest neighbour classifier classifies a
cell as normal cell or blast cell. It is done by comparing the extracted
features.

 

Breast Cancer

Now a day this is one
of the common reasons for the death of women. Breast cancer can be diagnosed
effectively if it is detected at its early stage. Mammography, ultra sound,
MRI, thermography are the common methods for detecting breast cancer. But they
suffer from lack of accuracy, reliability and high cost. In order to provide
accuracy and to lower the cost magneto-thermal approach is used for the breast
cancer detection.

  This method is based on the combination of
Electro-Magnetic and thermal analysis4. The breast tissue is
excited firstly with the radio frequency source and then measures the
temperature distribution of breast tissue. 
RF excitation causes more accurate result and provides additional
signatures such as SAR for breast cancer detection. SAR is one of the important
measurement factors for energy absorption. Breast model comprises of 4 layers
Skin, fat, gland and a malignant layer. Dielectric properties of the layers are
assumed to be frequency dependent. While the conductivity increases with the
frequency, the permittivity decreases. The frequency dependency is modelled
using linear model. The RF excitation of the breast tissue provides reliable
data due to higher temperature difference between malignant and normal tissue.  After exciting the tissue EM analysis is
performed. The electric field distribution near the tumor cells is higher than
the rest of the breast tissue.it is due to the dielectric properties of tumor
are different from the rest of the breast and it absorbs more energy.

 

Liver Cancer

Liver cancer rates are
increasing day by day. The disease can only be identified at the final stage
since it doesn’t show any symptoms. The chance of defeating the disease is
greater if it is identified at its early stage. To make the task of detecting
the disease an effectively and efficiently less time consuming, simpler and
test are adopted.

 

                         

 

                  Fig 5:
CT image of liver cancer

 

MRI and CT scan images
are taken as input to the system. First step is noise removal and then region
based segmentation is performed. There are 4 types of segmentation5
techniques; they are thresholding, boundary based, hybrid and region based. CT
image is sufficient and low cost method compared to MRI. Tissues can be clearly
visible in CT scan and it identifies normal and abnormal structures in the
body. To improve the quality of CT images, noise removal is done. Next step is
the image segmentation: it is a process of pixel classification which is done
by partitioning into the new subsets by assigning individual pixels to classes.
Here region based segmentation is used which assume that neighbouring pixels
within the same region should have similar values. Threshold value is computed
at multiple times until a final value is derived using wavelet transformation6.
The final value justifies whether the clustered image carrying the affected
part is cancer cells or not. If all the values are within the same range then
they are cancer affected cells and if variations are out of boundary then it is
considered to be no cancer cells.

 

 

Lung Cancer

It is also called as
lung carcinoma. The symptoms of lung cancer are chest pain, coughing, breathing
problem etc. There is a chance for the cancer cells to move towards to blood
and lymph fluid surrounding the lung tissue. Statistical studies say that about
25% of cancer death is due to lung cancer. Early stage detection can save many
lives.

 

            

 

                   Fig 6: CT image of lung
cancer

 

The first step is
image acquisition, where the CT images are collected and taken as input to the
system. After acquisition the image is passed to image preprocessing system
where several conversion and removal take place. In gray scale conversion
technique the RGB image is converted to gray scale. Then the image is
normalized using the MATLAB function imresize. The result will contain noise,
they are removed by median filter. Median filtering7 is an image
processing salt and pepper noise removal system. This noise free gry scale
image is then transformed into pixels of 0’s and 1’s. From the original image
parts that are unwanted is to be removed from the binary image. Next step is
binarization, here the black and white images are generated. Segmentation is
done using threshold method. It uses 3 threshold values Thresh1, Thresh2,
Thresh3. According to this threshold values it is determined that whether the
lungs is affected or not. If the white pixel percentage is greater than Thresh1
then it is said that the whole lung is cancer affected. Right lung is affected
if the white pixel is greater than Thresh2, and left lung is affected if it is
greater than Thresh3.

 

                                III CONCLUSION

 

Any diseases can be
cured only if it is detected at the early stage. Cancer is now a wide range
spreading disease and its detection is a difficult task since its symptoms are
similar to ordinary disease. From the paper it is sure that enhanced image
processing is one of the methods to detect the cancer
early. There are 100s of cancers other that blood, breast, brain, liver and
lungs. Early detection and regular screening is the technique to acquire good
health and better treatment

 

 

References

1
R. K. Atyali and S. R. Khot, “An enhancement in
detection of   

     brain cancer through
image fusion,” 2016 IEEE International

     Conference on Advances in Electronics,
Communication and

     Computer Technology (ICAECCT), Pune, 2016, pp. 438-442.

2
Ambily P.K., Shine P.James,
Remya R.Mohan
“Brain tumor

      detection using image fusion and neural
network” International

     Journal of Engineering Research and
General Science  Volume 3,  

      Issue 2, March-April, 2015 ISSN 2091-2730 1383

3
M. Saritha, B. B. Prakash, K. Sukesh and B.
Shrinivas,

     “Detection of
blood cancer in microscopic images of human blood

      samples: A
review,” 2016 International Conference on Electrical,  

      Electronics, and Optimization Techniques
(ICEEOT), Chennai,

      2016, pp.596- 600.

4
S. Rahmatinia and B. Fahimi, “Magneto-Thermal
Modeling of

      Biological Tissues: A
Step Toward Breast Cancer Detection,”

       in IEEE Transactions
on Magnetics, vol. 53, no. 6, pp.

       1-4,
June 2017.

5 P. R. Anisha, C. K. K. Reddy and L. V. N. Prasad, “A
pragmatic

      approach for detecting
liver cancer using image processing and

      data mining
techniques,” 2015 International Conference on    

      Signal Processing and Communication
Engineering Systems,   

      Guntur, 2015,  pp. 352-357.

.6 
Priyanka Kumar1 , Shailesh Bhalerao2  Detection of tumor in

       liver using image segmentation IOSR Journal of Electronics and

       Communication Engineering (IOSR-JECE)
e-ISSN:  

       2278-2834,p- ISSN: 2278-8735.Volume 9,
Issue 2, Ver. VIII

      (Mar – Apr. 2014), PP 110-115

7  M. B. A. Miah and
M. A. Yousuf, “Detection of lung cancer

      from CT image using
image  processing and neural

      network,” 2015
International Conference on Electrical

      Engineering and Information Communication
Technology

      (ICEEICT),
Dhaka, 2015, pp.1-6.