2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS)
A novel approach for detection of Lung Cancer
using Digital Image Processing and Convolution
Neural Networks
Rohit Y. Bhalerao Department of
Computer Engineering, VIVA Institute
of Technology,
Virar, India
rohitbhalerao1997@gmail.com
Rachana K. Gaitonde Department of
Computer Engineering, VIVA Institute
of Technology,
Virar, India
rachana.gaitonde16@gmail.com
Abstract— Biomedical Image Processing is the latest emerging
tool in medical research used for the early detection of cancers.
Artificial Intelligence can be used in the medical field to diagnose
diseases at an early stage. Computed Tomography (CT Scans) of lungs
of the patients from Lung Image Database Consortium (LIDC) is used
as input data for image processing. In pre-processing stage conversion
of RGB image to gray-scale image takes place because RGB images
are too complex to process. Gray-scale image is further converted to
Binary image. After Image Processing, the input images become more
efficient and refined. These are input for the Convolution Neural
Network. Convolution Filtering, Max Pooling filtering are steps in
CNN which train the data to predict whether lung image is cancerous
(malignant) or non-cancerous (benign). Deep Learning is a newer
branch of Artificial Intelligence research will help in better
performance in CNN based systems. The proposed system will also
take into account the processing power and time delay of the cancer
detection process for efficiency.
Keywords— CNN, Deep Learning, LIDC, image processing, CT
scan, watershed segmentation.
I. INTRODUCTION
Lung Cancer is the most common cancer among men and the
third most common cancer in women. 85% of all lung cancer
cases are related to smoking and consumption of tobacco.
Around 20% of all mortality in cancer is due to lung cancer. 2.1
million new cases were registered and 1.8 million deaths were
accounted in 2018 alone. The five-year survival rate for tumors
detected at an early stage is 56%, i.e, if detected at an early
stage, treatments can prevent mortality and spread of tumor for
atmost 5 years, if not more or fully diagnosed. Early detection
of tumor can decrease mortality rate by 20% among individuals.
Cancer cells multiply as the infection spreads, and tumors
increase in size gradually. A large population of cancer patients
are from an economically poor background and might not be
978-1-5386-9533-3/19/$31.00 ©2019 IEEE
Harsh P. Jani
Department of Computer Engineering,
VIVA Institute of Technology, Virar,
India harsh.jani97@gmail.com
Vinit Raut
Asst. Professor, Department of Computer Engineering,
VIVA Institute of Technology,
Virar, India vinitraut@viva-
technology.org
able to afford healthcare or expertise and imaging., let alone
consultation and diagnosis. Artificial Intelligence will play an
important role in a demographic where expensive health care
can be replaced by a computerized system.
Image Processing is a method to convert an image into digital
form and perform some operations on it, in order to get an
enhanced image or to extract some useful information from it.
It includes acquiring input images, noise removal, enhancement
and segmentation. In Image Processing, the RGB images will
be converted to grayscale and binary. Images will be enhanced
and noise will be removed using filters. Blurred effect will be
eliminated if any. This improves the quality of input image [13].
The Image Processing Toolbox in MATLAB is used to perform
the Image Processing stages. Many different algorithms are
possible for each stage in image processing [14].
Deep Learning is used for the classification of CT Scan
Images as cancerous/non-cancerous. The process of feature
extraction in Convolution Neural Networks is such that features
are defined and computed by the algorithm itself. During the
training stage, input and an output label are provided. Based on
the given data, the algorithm analyses the features/patterns and
for a training data, forms a set of parameters and feature
extraction [15]. Based on the computations, the new data can be
tested for prediction of a correct output. Convolution Neural
Networks consist of an input and an output layer, and multiple
hidden layers. The input layers accept inputs and the number of
output layers define the number of outputs in the result.
Convolution layers are used to define features and parameters.
Pooling layers bring together the computations with similar
permutation. The convolution filter will form a spatially dense
output by assigning a common value to a set of matrix pixels.
These values decide the output for that image.
577
 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS)
II. RELATED WORK
In 2012, Mokhled S. Al Tarawneh published a comparison
paper between different Image Processing techniques and the
algorithms they use for a CAD system for lung cancer detection.
The main aim of the paper is to detect features for accurate
comparisons between images with different processing
techniques [1]. Three steps are Image enhancement,
segmentation and feature extraction. The aim of image
enhancement is to improve quality of image to provide better
input for classification. Gabor filter, auto enhancement and fast-
fourier transform improve enhancement rate. Thresholding
and Watershed methods are used for segmentation, of which,
watershed provides a better quality of segmentation. Feature
extraction uses binarization and masking approach.
Binarization and Masking, on combined implementation, gives
an optimal result.
In December 2017, Suren Makaju, P.W.C Prasad, Abeer
Alsadoon and A.K. Singh worked on CAD system of lung
cancer with CT Scan Images as primary focus. They believe the
that CT Scan Images are the best input data for this research [2].
The proposed model uses noise removal algorithms before
image processing. It uses the same segmentation as the current
system, i.e., watershed algorithm and promotes a well-defined
feature extraction before classification using SVM. The author
has used images from LIDC dataset and the system gives a 92%
accuracy and 50% specificity.
In May 2015, Md. Badrul Alam Miah and Mohammad Abu
Yousuf proposed a Neural Network based CAD system for
early detection and diagnosis. ANN and fuzzy clustering, IP,
Curvelet transform, multinomial Bayesian algorithm, back
propagation, gray-coefficient mass estimation and SVM are the
basis of these observations. The goal is to create a fast and
robust, more accurate system having a rotation, scaling and
translation variant feature extraction [3]. A dataset of 300
images acquired from hospitals is used. Steps in proposed
system are Image acquisition, processing, binarization,
segmentation using thresholding, feature extraction and neural
network classification. Steps in Image processing are grayscale
conversion, normalization, noise reduction, binarization and
removing unwanted portion of image. Feature extraction uses
features like center of image, ratio of height to width, average
distance between black pixels and the center, etc. Neural
networks is used for classification with two outputs. The system
gives an accuracy of 96.67%, higher than all existing systems.
In March 2014, Prof. Sanjeev N. Jain and Bhagyashri G. Patil
proposed few methods to detect cancerous cells from CT Scans
of Lungs. The purpose of this paper is to find the cancerous cells
and give more accurate result by using various
segmentation techniques such as thresholding and watershed
segmentation. In thresholding, a threshold value is set to
differentiate object of interest from the background. If the pixel
value is greater than the threshold value then it belongs to the
object else it is in the background. Thus the region of interest
can be extracted by using thresholding approach. In watershed
segmentation, the background and the object are separated
using different markers : internal markers associated with
object of interest and external markers associated with
background. It is simple, intuitive and fast method [4].
According to the research, watershed segmentation approach
has more accuracy (85.27%) than thresholding approach
(81.24%).
In 2017, authors Pooja R. Katre and Anuradha Thakare
described the various image processing techniques for detecting
lung cancer. In their proposed approach for noise removal and
enhancement, method Median Filter is used. The best part about
median filter is it removes noise without blurring the image. It
preserves the edges of the regions [5]. It is used to remove salt
and pepper noise from the image. In enhancement stage gabor
filter is used as it gives better result compared to fast fourier and
auto enhancement. The purpose of this paper is to detect the
tumour at an early stage. CT scan images are taken as input.
After Image Processing is the feature extraction stage in which
the area, perimeter, Eccentricity of the image is calculated.
Support Vector Machine algorithm is used to classify the data.
The features mentioned above help to identify the size of the
tumour and from that, the stage of the cancer is detected.
In 2017, from China, Lei Fan and his group of researchers made
use of deep learning algorithm for CAD lung cancer detection.
In this paper, image processing is not applied on CT scans of
lungs. The images are directly fed as an input to convolutional
neural network which consist of two convolutional layers, two
max pooling layers, one fully connected layer and one output
layer [6]. Rectified linear unit (ReLU) are applied between
convolutional and max pooling layers. The system gives an
overall accuracy of 67.7%. It concludes that Support vector
machines has lower classification accuracy than 3D
convolutional neural network in the same number of input
samples.
In 2017, authors Qing Wu and Wenbing Zhao published a paper
to propose a CAD based Lung cancer detection system. In their
system, neural network based algorithm, EDM (Entropy
Degradation Method) is proposed to detect SCLC (small cell
lung cancer) from CT scan images [7]. The training and testing
data are lung CT scan images which are provided by the
National Cancer Institute. Five scans from each group are
randomly selected to train the model. The images with SCLC
are labelled as cluster 1 while others are labelled as cluster 0.
The paper proposes early stage detection of lung cancer.
In another paper by authors Anita Chaudhary and Sonit Sukhraj
Singh, the proposed CAD system has techniques to detect the
tumour at an early stage using Image Processing. In image
enhancement stage, Gabor filter enhancement technique, Auto
Enhancement Technique and Fast Fourier Transform
Technique is used out of which the Gabor Filter Enhancement
Technique is the most suitable one. According to the research,
the Watershed segmentation approach is more accurate than the
Thresholding segmentation approach [8]
578
 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS)
In 2017, Deep Prakash Kaucha and others proposed a system to
increase accuracy, sensitivity and specificity in LCD using
CAD system. This study aims at maximizing effectiveness from
strategic deployment of different techniques at different stages
[9]. The existing system with its flow diagram is studied, which
uses K Means for clustering, Gray Level Co-occurrence Matrix
(GLCM) for feature extraction and Back Propagation for
classification. The proposed model uses Discrete Wavelet
Transform for segmentation, GLCM for feature extraction,
SVM for classification with database from LIDC and
implementation in MATLAB. ROC curve for True Positive and
False Positive in existing and proposed systems show an
improvement in performance. The system shows an accuracy of
95.16%, sensitivity of 98.21% and specificity of 78.69%.
In 2017, authors S. Kalaivani, Pramit Chatterjee, Shikhar Juyal
and Rishi Gupta of VIT University, Tamil Nadu proposed a
simple CAD system for Lung Cancer Detection, knowing the
importance of research in the field of Cancer research. The
paper talks about Lung Cancer and its effects. The data used
is from the The Cancer Imaging Archive. The images are
converted to grayscale, improved using Histogram Equalization
and segmented using Thresholding. Feature Extraction is
performed by calculating certain properties in the binary image
[10]. Back Propogation network is used for classification as
ANN can perform multiple parallel calculations. This simple
system gives an accuracy of 78% and can be helpful to
radiologists.
In 2014, Prof. L.M. Deshpande and Mr. Vijay A. Gajdhane
acquired CT Scan images from various hospitals for lung cancer
detection using Image Processing. Noise reduction filters,
thresholding, segmentation using watershed segmentation and
feature extraction were studies to propose a methodology using
MATLAB. Input images were passed through smoothing,
enhancement and then segmented using marker-controlled
watershed segmentation [11]. Features like area, perimeter,
eccentricity were extracted for the dataset and classification
was done using Maximum margin classifier.
In 2016, Prajwal Rao, Nishal Pereira and Raghuram Srinivasan
proposed a Convolution Neural Network based system for the
screening and detection of Lung Cancer from CT Scan Images.
Data from the LIDC was used for the system. The data and its
label is the input for the system. The CNN architecture consists
of one input layer, two convolution layers, a max pooling layer
and a fully connected layer and an output layer [12]. In the first
convolution layer, the output is 78 features. After the second
convolution layer, the CNN network learns the features
hierarchically and avoids the need for a specific feature
engineering. The max pooling layer reduces the data
dimensions. The fully connected layer gives two outputs by
combining all the features for a input image. The system was
compared to an ANN system with 50 neurons for accuracy. An
accuracy of 75% is obtained in comparison the ANN based
system.
III. PROPOSED SOLUTION
The proposed system makes use of Convolution Neural
Networks which gives a better performance compared to other
machine learning algorithms like SVM, ANN and Naïve Bayes.
The feature extraction in CNN is defined by the algorithm itself
based on input data in the form of image and an output label.
The CNN layers define features and parameters for training.
Image Processing is performed on the data before feeding it to
the convolution network to improve the quality of data and to
detect and extract the Region of Interest. The
Accuracy in CNN based systems is less for lung cancer
detection systems using the LIDC database. LIDC is a very
important and well maintained database for biomedical access.
The proposed system aims at increasing the performance of
CNN based system in the classification of malignant and benign
tumours in CT Scan images for a better and early detection of
cancer probabilities.
Accuracy of CNN based systems can be improved by
improving the quality of input data or by providing a better
training or both. The CNN Network defined also plays a major
role in improving results. More layers means a better training
and a a more thoroughly performed computation on the
permutations of pixel densitites and related features in the
image.
The input images are pre-processed to improve the quality of
data sent into the CNN architecture. Preprocessing involves
binarization, normalization and noise removal. The normalized
images are trained in the deep learning network in sets of 30
images of normal, 30 images of benign and 30 images of
malignant tumour CT scan images. A single CPU 8 gigabyte
RAM takes around 4 hours of training for 20 images. This
dataset comprising a total of 90 images is trained for the training
module. The image is pre-processed to perform binarization,
noise removal and normalization. Each image is normalized to
256*256 pixels with zerocenter normalization. This will
introduce uniformity to the dataset. A set of 30 new images are
used for the testing phase.
A. Pre-processing
The images are converted to grayscale and then, to binary
image. Binary images are easier to process than RGB images.
Medical CT Scan images are mostly in grayscale by default, but
conversion removes any hardware errors during scanning
process or to remove any unrecognized component in RGB.
Matlab function rgb2gray is used for the same. Binarization
means to assign either a black or a white value (0 or 1) to each
pixel in the image. Matlab function im2bw is used for
binarization. The images are normalized to provide an uniform
data set to the convolution network. Matlab function imresize is
used to provide a uniform pixel size. This is not to be mistake
with the normalization in the CNN input layer. Noise in the
image (salt and pepper noise is most common) of any kind can
be mistaken for a tumor by the network. To avoid this common
mistake, the image is smoothened by removal of noise using the
579
 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS)

median filter. Median filter is more efficient because it removes architecture consists of 16 layers, as additional adjacent layers
the noise without distorting the image edges. Matlab function for decrease the chances of errors in performance. The list of layers
Median filter is medfilt2. The result of pre-processing is a is as follows:
normalized (uniform), binary image collection of a better quality
dataset. The processed images are fed as input to the CNN 1) imageInputLayer([227 227 3])
Network. 2) convolution2dLayer(5,20)
3) reluLayer
B. Convolution Neural Network 4) maxPooling2dLayer(2,'stride',2)
Previous implementation using 3D CNN Networks used an 5) convolution2dLayer(5,20)
architecture of 3D CNN, consisting of two different 6) reluLayer
convolution layers to obtain two sets of feature maps. The 7) maxPooling2dLayer(2,'stride',2)
second layer consists of two different max-pooling layers 8) convolution2dLayer(5,20)
applied on the feature maps. A convolution layer after the max- 9) reluLayer
pooling layer gives a set of resized feature maps. A second max- 10) maxPooling2dLayer(2,'stride',2)
pooling layer is applied to each feature map. This helps connect 11) fullyConnectedLayer(3)
convolution layer to multiple frames of data. The final layers 12) softmaxLayer
are fully connected layers and the dropout laye ReLU activation 13) classificationLayer()
is needed in each layer of the architecture. This entire
architecture is binded by a final fully-connected layer and a Input Layer provides the input image to the CNN network. The
softmax layer with constant learning rate. The architecture input to the network is a pre-processed image with zero-center
delivers an accuracy of 67.7%. normalization and empty transformations performed. The
image size is reduced to 227*227 with 3 input data types.
The CanNet architecture uses an input layer in which images
are 3D concatenated to create a linear volume. The input layer Convolution Layer uses two parameters; filter size and number
is followed by two Convolution layers, a max-pooling and a of filters. A 2-D convolution layer is applied which convolves
fully-connected layer and an output layer. The first convolution the filters vertically and horizontally through the image. It
layer produces 78 features, the second convolution layer detects calculates the dot product of the weights and and input for each
patterns in features, to learn feature exractions hierarchically feature, and adds a bias term, which is set to default value.
from the previous layer. Both layers are followed by a ReLU
layer to rectify all negative activations to zero. Max-pooling Rectified Linear Unit (ReLU) Layer applies a max function
layer reduces data size by reducing data dimensions. A dropout f(x)=max(x,0) to the matrix of the convolved image after
layer helps randomly avoiding neurons in the CNN network for convolution. It sets all the negative values in the dot products
allowing newer data to be tested on different neurons, and of the matrix to 0. All other values are unchanged. It increases
minimizing a influence of previous testing on new testing data the speed of training the network by removing negative
incase of similiarities. The fully-connected layer reduces the activations in the gradient, thus avoiding complex negative
architecture to two neurons, one for both of the desired outputs, computations.
benign and

Fig. 1. Architecture of CNN Network

malignant. It uses all features to create a top level image for
classification. CanNet architecture delivers an accuracy of 76%.
In the proposed system, data to the CNN architecture will be
individual slices of CT Scan images, to avoid a 3D
concatenation and will study individual instances of each data
to predict the presence of cancerous tumour in the input. The
Max-Pooling Layer with pool size [2,2] and stride [3,3] is
created after ReLU activation. This layer divides the input
matrix into rectangular pooling sub-regions, and calculates the
maximum in each region. It performs down-sampling and
makes an abstract representation of the features in each sub-
regions. It reduces the number of pixels which reduces the
computation of parameters in the input. A stride of 2*2 prevents

580
 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS)
overlapping of sub-regions. The Convolution, ReLU
and Max-Pooling layers are applied thrice in the sequence –
Convolution Layer -> ReLU Layer -> Max-Pooling Layer.
Fully Connected Layer is applied the sequence of Convolution,
ReLU and Max-Pooling layers. The input to fully connected
layer is a meaningful, low-dimensional invarient feature space.
The fully connected layer is used to get a non-linear
combination of the features. It holds a feature vector for the
input, which is needed for classification or regression and
categorization. The input size to the layer, ‘3’ specifies the three
types of desired outputs. A transfer function ‘tf’ shows input-
output relation in the layer. Fully Connected layer gives an end-
to-end training to the network.
Softmax Layer applies a softmax function to the output. The
softmax function applies probability distribution to the feature
vector produced in the fully connected layer. It maps the feature
vector over a predicted output class using probability
distribution.
Classification Layer assigns a probability value obtained from
the softmax layer to each of the mutually exclusive output
Fig. 2. System Flow Diagram
classes. It uses a cross-entropy function to assign each input
(probability distribution value) an output class.
C. System Flow Diagram
The CT Scan images are stored as a dataset divided into
malignant, beningn and normal images. 70 percent of the
dataset is pre-processed and stored as a training dataset. Pre-
processing invloves grayscale conversion, noise removal and
segmentation. This dataset is trained in the CNN Neural
Network with its labels. The remaining 30 percent of images
are used as a testing dataset. Images from the testing dataset are
pre-processed and sent into the neural network for
classification. The end result is the detection of normal, beningn
or malignant case along with tumor edge-detected using
watershed algorithm.
IV. IMPLEMENTATION
A. Implementation in MATLAB
The proposed system is implemented in MATLAB. MATLAB is a
high-performance computing environment and language for
productivity, research, development and analysis in the fields of
mathematics, science and computer technology. The LIDC database
consists of images in DICOM format, which are converted to .jpeg
using open source software MicroDicom converter. These images
were sorted and labels were generated. The image pre-processing in
MATLAB uses the directory to dataset and applies pre-processing
steps to the images and saves them in another folder. The Deep-
Learning Toolbox is available on MATLAB for Deep Learning and
CNN Neural Networks related aid. Designing the user interface in
possible on MATLAB using the GUIDE; GUI Designing
Environment. Two-dimensional or three-dimensional graphs can be
plotted on MATLAB with ease.
Images of types malignant, benign and normal are used as
a dataset for the system. These images are originally in .dicom
format and ar converted to .jpeg or .png format. 250 images of
each type are used for pre-processing and stored as a
preprocessed database in .png format. These images are used
for training by the CNN network, at 900 epochs. After training
is complete, the remaining images of each type in the dataset
can be tested. During testing, image processing is performed on
the selected image and then, it is fed into the CNN network. The
output is either normal, benign or malignant. Watershed
algorithm shows edges of tumor in benign or malignant image.
Accuracy can be calculated using confusion matrix. MATLAB
version 2018b allows graph plots to show the rates of training
the CNN network.
B. Discussion
The steps in Image Processing and deep learning are explained in the
tables Table 1 and Table 2 below.
581
 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS)

Table 1. Steps in Image Processing

Step Function Description
Grayscale Conversion rgb2gray Images are already in grayscale but conversion will avoid any
remaining rgb elements in data images.
Binary Conversion im2bw Binarization will give pixels either a value 0 or 1. (black/white)
Median Filter medfilt2 Median filter removes noise in image without distortion of edges.
Watershed Segmentation watershed_old Watershed Segmentation compares adjacent pixel values while
Thresholding compares pixel value to a threshold value.
Watershed segmentation is more efficient.
Dilation dilateBW Dilation is performed before segmentation to provide structural
element to image. (shapes such a sphere)
Plot Features plotfeatures(img) Features (tumor/ROI) is plotted as an edged polygon
Boundary plotting bwboundaries(x) Boundaries in the image are generated.

Table 2. Layers in Convolution Neural Network

Layer Layer Parameters Description Equations
Input Layer 227*227*3 227*227 pixel input image with 3 -
classes/labels
Convolution Layer (filtersize,numberOfFilters) 5*5 filter, 20 filters. Horizontal and Zero Padding = (K-1)/2
= (5,20) Vertical filters calculating dot product of Output = [(W–K+2P)/S]+1
pixel values. (convolved matrix) W - Input size, K - Filter size
P - Padding, S - Stride
Rectified Linear Unit - Activation function replaces negative f(x) = max(0, x)
computations in the convolved matrix by Changes negative activations to 0.
‘0’. This prevents complex calculations.
Max-pooling Layer (2,’stride’,2) Replaces every 2*2 submatrix by the İnput size: W1 * H1
maximum pixel value of the submatrix. Parameters: F, S
This retains the features of the image. Output size: W2 * H2
Stride prevents overlapping of where W2 = [(W1-F)/S]+1
submatrices, H2 = [(H1-F)/S]+1
W*H : width*height,
F : Spatial extent
S : Stride
Fully connected Layer (number of outputs) = (3) Number of outputs are specified in the y=σ (w1+w2+…..+wm)
parameter. The convolved matrix is σ : non-linear function
represented as as a non-linear feature y : feature vector
vector. w1,w2,…,wm : learnable
parameters
Softmax Layer - Calculates a probability distribution yr(x) = exp[ar(x)]k
j=1exp[aj(x)]
from the feature vector using maximum where 0≤yr≤1 and k
j=1yj=1.
entropy function. Maximum Entropy function : yr(x)

Classification Layer - Assigns an output class to the -

(Output) probabilistic value.
images were detected false negative.
V. RESULTS AND ANALYSIS
A total of 910 images were taken from LIDC as the dataset for Table 3. Results for three classes
the implementation. 257 images were labeled normal, 331 as Normal Beningn Malignant
beningn and 322 as malignant. 210 images of each class were Sensitivity 87.23% 91.73% 93.69%
pre-processed and trained in the CNN network. The remaining Specificity 95.98% 94.77% 96.20%
images were untrained and tested to get results. A total of 281 Precision 82% 93.27% 94.54%
images, 47 images of normal, 121 images of beningn and 113 Accuracy 94.46% 93.43% 95.16%
images of malignant class were tested. A accuracy is calculated Ratio (Training data : 210 : 47 210 : 121 210 : 113 //
using confusion matrix. For normal images, 10 images were Testing data) // 4.5 : 1 // 1.73 : 1 1.85 : 1
detected false negative, and 9 images of other detected false
positives. For beningn images, 10 images were detected false The accuracy of the system for classification of an image as one
negatives and 8 images were detected false positives. For of the three classes is calculated by adding the true positives,
malignant images, 6 images were detected false positive and 7 true negatives and false positives, false negatives of all the three
classes.

582
 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS)
True positives : 256 False positives : 23
True negatives : 512 False negatives : 23
Table 4. Cummulative Results
Sensitivity 91.75%
Specificity 95.70%
Precision 91.75%
Accuracy 94.34%
An overall accuracy of 94.34% is obtained from proposed system.
VI. FUTURE SCOPE
The LIDC dataset is a static dataset. Maintaining a dynamic
real-time database will help study the changes in lung cancer
cases over a time period. Increasing the number of
Convolutions in deep learning will improve the results of the
system variably, but will also affect the efficient and
performance time delay exponentially. The batch size for
training neural network can be increased for a high performance
GPU. The system can be tested on a set of different databases
like the RIDER or TCIA database. More accurate feature
plotting is possible boundary detection in tumor cells. The
overall accuracy of the system can be furthur improved in Deep
Learning.
VII. REFERENCE
[1] Md. Badrul Alam Miah et. al, “Detection of lung cancer from CT
Image using Image Processing and Neural Networks”, 2015
International Conference on Electrical Engineering and Information
Communication Technology, (ICEEICT), Dhaka, 2015, pg.1-6.
[2] P. R. Katre and A. Thakare, “Detection of Lung ancer Stages
using Image Processing and Data Classification Techniques”, 2017
2nd International Conference for Convergence in Technology (I2CT),
Mumbai, 2017, pg. 402-404.
[3] L. Fan et. al, “Lung nodule detection based on 3D Convolutional
Neural Networks”, 2017 International Conference on the Frontiers
and Advances in Data Science (FADS), pg. 7-10.
[4] Mr. Vijay A. Gajdhane and Prof. L. M . Deshpande,
“Detection of Lung Cancer Stages on CT scan Images by Using
Various Image Processing Techniques”, IOSR Journal of Computer
Engineering (IOSR - JCE), Volume 16 issue 5 (Sept – Oct 2014),
pg. 28-35, e-ISSN 2278-0661, p-ISSN 2278-8727.
[5] Mokhled S. Al Tarawneh, “Lung Cancer Detection Using
Image Processing Techniques”, Leonardo Electronic Journal of
Practices and Technologies, Issue 20, pg. 147-158, January-June 2012,
ISSN 1583-1078.
[6] Suren Makaju et. al, “Lung Cancer Detection using CT scan
images.”, 6th International Conference on Smart Computing and
Communications, ICSCC 2017, 7-8th December 2017, Kurukshetra,
India.
[7] Sanjeev Jain and Bhagyashri G. Patil, “Cancer cells detection
using Digital Image Processing Methods”, International Journal of
Latest Research in Science and Technology, Volume 3(4), March
2014, pg. 45-49.
[8] Q. Wu and W. Zhao, “Small-Cell Lung Cancer Detection Using a
Supervised Machine Learning Algorithm”, 2017 International
Symposium on Computer Science and Intelligent Controls (ISCSIC),
Budapest 2017, pg. 88-91
[9] D. P. Kaucha et. al, “Early Detection of Lung Cancer using SVM
Classifier in Biomedical Image Processing”, IEEE International
Conference on Power, Control, Signals and Instrumentation
Engineering (ICPCSI-2017), Chennai, 2017, pg. 3143-3148.
[10] A. Chaudhary and S. S. Singh, “Lung Cancer Detection on CT
images by using Image Processing”, 2012 International Conference
on Computing Science, Phagwara, 2012, pg. 142-146.
[11] S. Kalaivani et. al, “Lung Cancer Detection Using Digital Image
Processing and Artificial Neural Networks”, International
Conference on Electronic, Communication and Aerospace
Technology (ICECA) Coimbatore, 2017, pg. 100-103.
[12] P. Rao et. al, “Convolution neural networks for lung cancer
screening in computed tomography (CT) scans”, 2016 2 nd International
Conference Conference on Contemporary Computing and Informatics
(IC3I), Noida, 2016, pg. 489-493.
[13] R. Golan et. al, "Lung nodule detection in CT images using deep
convolutional neural networks," 2016 International Joint Conference
on Neural Networks (IJCNN), Vancouver, BC, 2016, pp. 243-250
[14] W. Alakwaa et. al, “Lung Cancer Detection and Classification
with 3D Convolutional Neural Network (3D-CNN).” 2017
International Journal of Advanced Computer Science and Applications
(IJACSA), volume 8, no. 8, pg. 109-117.
[15] S. Prakash et. al, “An Automated System for the Detection of
Lung Cancer in CT data at Early Stages: Review,” 2017 International
Journal of Control Theory and Applications, pg. 133-144.
[16] https://en.wikipedia.org/wiki/Median_filter , last accessed on
01/10/2018
[17] https://in.mathworks.com/help/images/marker-controlled-
watershed- segmentation.html, last accessed on 19/08/2018
[18]https://www.google.co.in/search?q=convolution+neural+network
s&oq=convolution+neural+networks&gs_1=psy, last accessed
on 05/10/2018.
[19] https://www.wikipedia.com/lung_cancer, last accessed on
29/01/2019.
[20] https://en.wikipedia.org/wiki/Sensitivity_and_specificity, last
accessed on 14/02/2019.
[21] https://in.mathworks.com/help/deeplearning/index.html, last
accessed on 14/02/2019.
[22] C.V. Arulkumar et al., "Secure Communication in Unstructured
P2P Networks based on Reputation Management and Self
Certification", International Journal of Computer Applications, vol.
15, pp. 1-3, 2012.
[23] C.V. Arulkumar, G. Selvayinayagam and J. Vasuki,
“Enhancement in face recognition using PFS using Matlab,”
International Journal of Computer Science & Management Research,
vol. 1(1), pp. 282-288, 2012
[24] H. Anandakumar and K. Umamaheswari, “Supervised machine
learning techniques in cognitive radio networks during cooperative
spectrum handovers,” Cluster Computing, vol. 20, no. 2, pp. 1505–
1515, Mar. 2017.
[25] V. Arulkumar. "An Intelligent Technique for Uniquely
Recognising Face and Finger Image Using Learning Vector
Quantisation (LVQ)-based Template Key Generation," International
Journal of Biomedical Engineering and Technology 26, no. 3/4
(February 2, 2018): 237-49.
583