IRJET - Lung Disease Prediction using Image Processing and CNN Algorithm

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 03 | Mar 2020 www.irjet.net p-ISSN: 2395-0072
© 2020, IRJET | Impact Factor value: 7.34 | ISO 9001:2008 Certified Journal | Page 4877
LUNG DISEASE PREDICTION USING IMAGE PROCESSING AND CNN
ALGORITHM
Shivani Kasar1,Darshan Hujband2, Abhijeet Ahire3, Jyoti Rahade4
1,2,3,4Student, Dept. of Information Technology, Matoshri College of Engineering and Research Centre,
Maharashtra, India
------------------------------------------------------------------------------***-----------------------------------------------------------------------------
Abstract - Lung Cancer could be a Disease of uncontrolled
cell growth in tissues of the lung. Discovery of carcinoma in
its initial stage is that the key of its cure. All in all, a
measure for earlier than schedule stage lung disease
determination essentially incorporates those using X-beam
midsection movies, CT, MRI so forth. In numerous parts of
the planet far reaching screening by CT or MRI isn't yet
pragmatic, in order that midsection radiology stays in
starting and most elementary system. Firstly, we'll utilize
some systems are key to the errand of medicinal picture
mining, Lung Field Segmentation, processing, Feature
Extraction, Classification utilizing neural system and SVMs.
The routines utilized as part of this paper work states to
group computerized X-beam midsection movies into two
classes: ordinary and weird. Diverse learning examinations
were performed on two distinctive information sets, made
by method for highlight choice and SVMs prepared with
diverse parameters; the outcomes are checked out and
reported.
Keywords: Classification, Pattern Identification, CNN,
CT...
1. INTRODUCTION
Lung Cancer may be a noteworthy reason for Mortality
within the western world as exhibited by the striking
factual numbers distributed consistently by the American
Carcinoma Society. They demonstrate that the 5-year
survival rate for patients with lung malignancy are often
enhanced from a standard of 14% up to 49% if the ailment
is analyzed and treated at its initial stage. Medicinal
pictures as a significant piece of therapeutic
determination and treatment were specializing in these
pictures permanently. These pictures incorporate success
of concealed data that misused by doctors in selecting
contemplated choices around a patient. Then again,
removing this important shrouded data may be a basic
first stride to their utilization. This reason inspires to
utilize information digging systems abilities for productive
learning extraction & find concealed lung. Mining Medical
pictures includes numerous procedures. Medicinal data
processing may be a promising zone of computational
insight connected to a consequently break down patient’s
records going for the disclosure of latest information
valuable for restorative choice making. Affected
information is anticipated not just to increment exact
determination and effective infection treatment,
additionally to enhance security by diminishing blunders.
The systems during this paper arrange the advanced X-
beam midsection movies in two classes: ordinary and
strange. The normal ones are those portraying a solid
patient. The irregular ones incorporate style of lung
tumor; we'll utilize a typical arrangement technique
specifically SVMs & neural systems.
1.1 Aim
Aim of this paper is to automate the classification process
for the primary prediction of carcinoma. To justify this
research, it includes classification algorithm i.e. Neural
Network and for optimization GA (Genetic Algorithm) is
utilized. Evaluation would be done on the thought of
correctly classified sample data. For testing and training
diacom images has been used
1.2 Motivation of the Project
Lung Cancer is a Disease of uncontrolled cell growth in
tissues of the lung. Discovery of Lung Cancer in its initial
stage is the key of its cure. All in all, a measure for ahead of
schedule stage lung disease determination essentially
incorporates those using X-beam midsection movies, CT,
MRI and so forth. In numerous parts of the world far
reaching screening by CT or MRI is not yet pragmatic, so
that midsection radiology stays in starting and most basic
system.
1.3 Objectives
To proposed Some techniques are essential to the task of
medical image mining, Lung Field Segmentation,
processing, Feature Extraction, Classification using neural
network and SVMs. The methods utilized during this paper

work states to classify digital X-ray chest films into two
categories: normal and abnormal. Different learning
experiments were performed on two different data sets,
created by means of feature selection and SVMs trained
with different parameters; the results are compared and
reported.
2. LITERATURE SURVEY
Paper 1: Using Some Data Mining Techniques for
Early Diagnosis of Lung Cancer.
Lung cancer may be a disease of uncontrolled cell growth
in tissues of the lung, carcinoma is one in every of the
foremost common and deadly diseases within the world.
Detection of carcinoma in its early stage is that the key of
its cure. In general, a measure for early stage carcinoma
diagnosis mainly includes those utilizing X-ray chest films,
CT, MRI, etc.
Paper 2: A Fully Automated Method for Lung
Nodule Detection from Postero-Anterior Chest
Radiographs.
In this paper, we present a fully automated system
processing digital post ero-anterior (PA) chest
radiographs, that starts by producing an accurate
segmentation of the lung field area. The segmented lung
area includes even those parts of the lungs hidden behind
the heart, the spine, and the diaphragm, which are usually
excluded from the methods presented in the literature.
Paper 3: An Approach for Discretization and
Feature Selection of Continuous-Valued
Attributes in Medical Images for Classification
Learning.
We then propose a new supervised approach which
combines discretization and feature selection to select the
most relevant features which can be used for classification
purpose. The classification technique to be used is
Associative Classifiers. The features used are Horlick
Texture features extracted from MRI Images.
Paper 4: Diagnosis of Lung Cancer Prediction
System Using Data Mining Classification
Techniques
In this study, we briefly examine the potential use of
classification based data mining techniques such as Rule
based, Decision tree, Naïve Bayes and Artificial Neural
Network to massive volume of healthcare data. The
healthcare industry collects huge amounts of healthcare
data which, unfortunately, are not “mined” to discover
hidden information.
3. ARCHITECTURE
3.1 Problem Statement / Definition
The existing system is Time consuming process, and it's
very difficult to detect it in its early stages as its symptoms
appear only within the advanced stages. Implementing the
system to automate the classification process for the first
prediction of carcinoma.
3.2 Proposed Architecture
Proposed system is to introduce a singular “Predictive
Diagnostic System”. The first image is transformed to gray
scale image. After that, removal of the noises and contrast
enhancement is finished for obtaining the improved
images. After image acquisition the system perform pre-
processing on image understand affected regions and their
characteristics in style of data. This data is classed using
CNN. CNN classify it as normal or diseases lung and
identify lung diseases.
Figure 3.1: Proposed Architecture Diagram

CONCLUSION
The Conclusion of this project is that different phases of
image processing were applied on Lung modules. From
these different image processing techniques, the fuzzy
filter will provide the efficient de noising. Segmentation
done by marker based watershed algorithm, gives various
region of image. GLCM is employed to extract the various
features of image and which takes less time for generating
the result. This results are felt SVM Classifier, which
classifies the nodules as benign or malignant. SVM
classifier provides 92.5% accuracy.
REFERENCES
[1] ZakariaSulimanZubi and RemaAsheibaniSaad, “Using
Some Data Mining Techniques for Early Diagnosis of Lung
Cancer,” Recent Researches in Artificial Intelligence,
Knowledge Engineering and Data Bases, Libya, 2007.
[2] Paola Campadelli, Elena Casiraghi, and Diana Artioli, “A
Fully Automated Method for Lung Nodule Detection From
Postero-Anterior Chest Radiographs,” In Proc. of IEEE
TRANSACTIONS ON MEDICAL IMAGING, VOL. 25, NO. 12,
DECEMBER 2006.
[3] JabaSheela L and Dr.V.Shanthi, “An Approach for
Discretization and Feature Selection Of Continuous-Valued
Attributes in Medical Images for Classification Learning,”
International Journal of Computer Theory and
Engineering, Vol. 1, No.2,June2009.
[4] V.Krishnaiah, Dr.G.Narsimha, Dr.N.Subhash Chandra.
2013, “Diagnosis of Lung Cancer Prediction System Using
Data Mining Classification Techniques,” International
Journal of Computer Science and Information
Technologies, Vol. 4 (1), 2013, 39 – 45.
[5] Brain Cancer Detection From Mri: A Machine Learning
Approach (Tensorflow) Aaswad Sawant#1, Mayur
Bhandari #2, Ravikumar Yadav#3, Rohan Yele#4, Mrs.
Sneha Bendale#5,Department Of Computer Engineering,
Terna Engineering College, Mumbai University, India
[6] Heart Disease Prediction Using Data Mining Ajad Patel,
Sonali Gandhi, Swetha Shetty,Prof. Bhanu Tekwani, Dept.
Of Information Technology, Vidyalankar Institute Of
Technology, Maharashtra, India
[7] A. S. Abdullah and R. R. Rajalaxmi, ``A data mining
model for predicting the coronary heart disease using
random forest classi_er,'' in Proc. Int. Conf. Recent Trends
Comput. Methods, Commun. Controls, Apr. 2012,pp.
22_25.
[8] W. H. Organisation, " World Health Report," on Latest
global cancer data: Cancer burden rises to 18.1 million new
cases and 9.6 million cancer deaths in 2018
[9] Comani, A. Tartaro, A. Lagatta, G. Morana, S. Di Luzio,
and G. L. Romani, "Magnetocardiographic functional
imaging and integration with 3-D MRI reconstruction of
the heart: preliminary results for source localization
during myocardium activation," Physica Medica-European
Journal of Medical Physics, vol. 19, pp. 119-130, Apr-Jun
2003.
[10] M. Embrechts, B. Szymanski, K. Sternickel, T. Naenna,
R. Bragaspathi, and I. Ieee, "Use of machine learning for
classification of magnetocardiograms," in 2003 Ieee
International Conference on Systems, Man and
Cybernetics, Vols 1-5, Conference Proceedings, ed, 2003,
pp. 1400-1405.
[11] J. Weston, S. Mukherjee, O. Chapelle, M. Pontil, T.
Poggio, and V. Vapnik, "Feature selection for SVMs," in
Advances in Neural Information Processing Systems 13.
vol. 13, T. K. Leen, T. G. Dietterich, and V. Tresp, Eds., ed,
2001, pp. 668-674

IRJET - Lung Disease Prediction using Image Processing and CNN Algorithm

Recommended

Recommended

More Related Content

What's hot

What's hot (20)

Similar to IRJET - Lung Disease Prediction using Image Processing and CNN Algorithm

Similar to IRJET - Lung Disease Prediction using Image Processing and CNN Algorithm (20)

More from IRJET Journal

More from IRJET Journal (20)

Recently uploaded

Recently uploaded (20)

IRJET - Lung Disease Prediction using Image Processing and CNN Algorithm