LUNG CANCER DETECTION USING CNN | 2021-2022

CHAPTER 1
INTRODUCTION
Cancer is a group of diseases characterized by the uncontrolled growth and spread of abnormal
cells. If the spread is not controlled, it can result in death. Lung cancer was the most common
cancer in worldwide, contributing 2,093,876 of the total number of new cases diagnosed in
2018.

The incidence rate has been declining since the mid- 1980s in men, but only since the mid-
2000s in women, because of gender differences in historical patterns of smoking uptake and
cessation. From 2005 to 2015, lung cancer incidence rates decreased by 2.5% per year in men
and 1.2% per year in women. Symptoms do not usually occur until the cancer is advanced,
and may include persistent cough, sputum streaked with blood, chest pain, and voice change,
worsening shortness of breath, and recurrent pneumonia or bronchitis.

risk include rubber manufacturing, paving, roofing, painting, and chimney sweeping. Risk is
also probably increased among people with a history of tuberculosis. Genetic susceptibility
(e.g., family history) plays a role in the development of lung cancer, especially in those who
develop the disease at a young age.

The medical images taken in most of the earlier studies comprise of computed tomography
(CT), magnetic resonance, and mammography images. Computed tomography (CT) of the
chest uses special x-ray equipment to examine abnormalities found with other imaging tests
and to Cigarette smoking is by far the most important risk factor for lung cancer; 80% of lung
cancer deaths in the US are still caused by smoking. Risk increases with both quantity and
duration of smoking. Cigar and pipe smoking also increase risk. Exposure to radon gas released
from soil and building materials is thought to be the second-leading cause of lung cancer in the
US.

Other risk factors include occupational or environmental exposure to secondhand smoke,

asbestos (particularly among smokers), certain metals (chromium, cadmium, arsenic), some
organic chemicals, radiation, air pollution, and diesel exhaust. Some specific occupational
exposures that increase help diagnose the cause of unexplained cough, shortness of breath, chest
pain, fever, and other chest symptoms. CT scanning is fast, painless, noninvasive, and accurate.
A CT scan of the chest can help find problems such as infection, lung cancer, blocked blood
flow in the lung (pulmonary embolism), and other lung problems. Many times, a CT scan is
ordered by a doctor after noticing something abnormal in an X-ray. The expert doctor of this
domain uses these images for analysis to detect and identify the various levels of lung cancer
by using suitable techniques. The different laboratory and clinical steps are being used
DEPT OF ECE,BLDEA’,CET,VIJAYPUR 1
 LUNG CANCER DETECTION USING CNN | 2021-2022

including chemical treatment to destroy or stop the duplications of malignant cell, targeted
therapy and also radiotherapy. All these procedures adopted to identify and detect the cancer
diseases are lengthy, costlier and more painful for the patients. Thus, to overcome all these
problems suitable machine learning techniques for processing these medical images were used
which comprise of CT scan images. CT scan images are preferred compared to others.
Due to the lack of proactive health, time shortages and modernized living standards, today’s
world scenario are changing drastically, so the major non-communicable disease like cancer
has materialized in both genders. The loss of human life in 2018 is estimated at 9.6 million and
specifically in lung cancer, 1.76 million deceased. The total new cancer diagnosis is estimated
at 1,762,450 and deaths are estimated at 606,880, in 2019 in the US. For the analysis of the
proposed method CT image is sufficient also the visibility of soft tissue is better.

Due of enormous pervasiveness of smoking and air contamination around the globe, lung
malignancy is a lethal ailment and thus global problem in ongoing decades. Lung Cancer
constitute 41% of cancer burden in India. It happens when cells in the lung mutate. They
grow disorderly and cluster together to form a tumor.

Fig 1.1 Normal lung CT image Fig 1.2 Abnormal lung CT image

As shown in Fig 1.1. A normal lung would look completely black in a CT scan. The lungs are
a pair of spongy, air-filled organs located on either side of the chest (thorax). The trachea
(windpipe) conducts inhaled air into the lungs through its tubular branches, called bronchi.
The bronchi then divide into smaller and smaller branches (bronchioles), finally becoming
microscopic.
As shown in Fig 1.2 A The term lung disease refers to many disorders affecting the lungs,such as
asthma, COPD, infections like influenza, pneumonia and tuberculosis, lung cancer, and many
other breathing problems. The chest wall is symmetric, without deformity, and is atraumatic in

DEPT OF ECE,BLDEA’,CET,VIJAYPUR 2
 LUNG CANCER DETECTION USING CNN | 2021-2022

appearance. No tenderness is appreciated upon palpation of the chest wall.The patient does not
exhibit signs of respiratory distress.
The cause of lung cancer stays obscure and prevention become impossible hence the early
detection of lung cancer is the only one way to cure. Size of tumour and how fast it spread
determine the stage of cancer. Lung cancer spreading widely all over the world. Death and health
issue in many countries with a 5-year survival rate of only 10–16%. In some cases, the nodules
are not clear and required a trained eye and considerable amount of time to detect. Additionally,
most pulmonary nodules are not cancerous as they can also be due to non- cancerous growths,
scar tissue, or infections. Even though many researchers use machine learning frameworks. The
problem with these methods is that, in order to evaluate the best performance, many parameters
need to be hand-crafted which is making it difficult to reproduce the better results. Classification
is an important part of computation that sort images into groups according to their similarities. In
the structure of cancer cell, where most of the cells are overlapped with each other. Hence early
detection of cancer is more challenging task. After an extensive study, we found that ensemble
classifier was performed well when compared with the other machine learning algorithms. The
existing CAD system used for early detection of lung cancer with the help of CT images has been
unsatisfactory because of its low sensitivity and high False Positive Rates (FPR).

Convolutional Neural Networks (CNN) trained using deep learning techniques have come to
dominate pattern detection, recognition, segmentation and classification applications in both
medical and non-medical fields. Indeed, where sufficient training data is available, CNNs have
largely superseded the previous generation of Radiomic/texture analysis methods described
above. In our own work, once we had collected and curated sufficiently large training sets by the
end of 2016, our CNN based techniques started to outperform the previous state-of-the-art texture
and SVM based method. While a detailed exposition of such techniques is beyond the scope of
this article, it is worth understanding the main differences to previous methods and their
advantages.

There are types of lung cancer and this cancer can be diagnosed by doctors with their procedure
and to reduce the human efforts or human error for which we have developed a code in which we
take the CT scan image and we define the properties and through the various algorithms we can
able to detect the image is cancerous or not. In this world not only men but women also suffering
from the same dangerous disease. After the detection, the life span of the patient suffering from
the lung cancer is very less. If the CT scans have taken in the form of Dicom format, CT scans

DEPT OF ECE,BLDEA’,CET,VIJAYPUR 3
 LUNG CANCER DETECTION USING CNN | 2021-2022

are taken from studies of 61 patients. Database have 60 images We have proposed a design that
reads JPEG converted Dicom Format images of lungs and scans these images for any abnormality
through image processing techniques.

We can cure lung cancer, only if you identifying the yearly stage. So here, we use machine
learning algorithms to detect the lung cancer. This can be made faster and more accurate. In this
study we propose machine learning strategies to improve cancer characterization. Inspired by
learning from CNN approaches, we propose new algorithm, proportion-PNN, to characterize
cancer types.

DEPT OF ECE,BLDEA’,CET,VIJAYPUR 4
 LUNG CANCER DETECTION USING CNN | 2021-2022

CHAPTER 2

LITERATURE SURVEY

This section describes the different systems for detecting lung cancer detection using
convolution neural network (CNN).

Swati Mukherjee proposed a method to classify the lung nodule by computed tomography
images where the lung segmentation take place by applying thresholding and region growing
technique, thereby the image features are extracted. The extracted features were used to apply
as input to the various classifiers such support vector machine, KNN, then the classifier
decides and classify benign and malignant images. The author proposes Convolutional neural
network classifier for identifying lung nodules which gives an accuracy of about 84.6%. Also
sensitivity of 82.5% and specificity of 86.7% are achieved. It is noted that the degree of treating
the diseases will be higher as the dataset quantity increases. The author proposes a model
which is used to identify cancerous part of the lung by applying the methods of deep learning
of neural network; the model gives an accuracy of classification of about 90% and also the
model unable to find the nature and category of cancer disease.

Prof.Anuradha Deshpande proposed Identification of lung nodules by applying computed

tomography images where it produces the sensitivity results of 90%, thereby patient survival
rate becomes higher. The region of interest are retrieved by using methods such as wiener
filter, image slicing. The nodule size of 3mm is obtained to recognize lung cancer in the
primary stage.
Abbas khosravi ,Amin Khatami proposed a method to classify the lung nodule by computed
tomography images where the lung segmentation take place by applying thresholding and
region growing technique, thereby the image features are extracted. The extracted features
were used to apply as input to the various classifiers such support vector machine, KNN, then
the classifier decides and classify benign and malignant images. The author proposes
Convolutional neural network classifier for identifying lung nodules which gives an accuracy
of about 84.6%. Also sensitivity of 82.5% and specificity of 86.7% are achieved. It is noted
that the degree of treating the diseases will be higher as the dataset quantity increases. The
author proposes a model which is used to identify cancerous part of the lung by applying the
methods of deep learning of neural network; the model gives an

accuracy of classification of about 90% and also the model unable to find the nature and
category of cancer disease.
DEPT OF ECE,BLDEA’,CET,VIJAYPUR 5
 LUNG CANCER DETECTION USING CNN | 2021-2022

Vijayakumar T proposes a model which gives an accuracy of 83.11% which classifies benign
and malignant images using support vector machine form computed tomography images. The
classification is achieved depends on the collected fractal features from Brownian motion
model. Recognition of lung cancer nodules from CT images is presented where the model uses
various classifiers to detect the cancer, the classifiers such as support vector machine were
utilizes which improves the efficiency and thereby reduces the error rate.
Lilia Amirah ,Haryanto presented a system which classifies the lung cancer nodules depends
on the size of nodules between 3mm-10mm from LIDC dataset. The system uses the methods
of machine learning such as K-Nearest Neighbor, Random Forest; the system gives an
accuracy of classification of 82%. Deep Convolutional neural network is trained from CT
images of LIDC dataset to classify the malignant and benign images. The network provides a
sensitivity of 78.9% using back propagation methods by extracting the image features.

Rachid Sammoudapresented a classification model based on principal component analysis

using CT images which achieves an accuracy of about 90% by applying principal component
analysis method. The model uses lung organ segmentation as a first step, lung nodule
segmentation as next step and classification of cancerous and noncancerous images in the last
step. The system identifies the malignancy of disease in the primary stage by undergoing
different steps of the disease. The detecting phase first step consists of preprocessing and
segmentation which improves the accuracy of classification by adopting support vector
machine and fuzzy logic classifiers. The classifier identifies and classifies the images based
on the degree intensities of images as benign and malignant tumor. Convolutional neural
network by employing deep learning techniques does lung segmentation in CT images were
used. The challenging task for the radiologist is to identify malignancy of lung diseases hence
deep CNN model assist much in this task as lung cancer images have different degree of
opacities in region of interest.

DEPT OF ECE,BLDEA’,CET,VIJAYPUR 6
 LUNG CANCER DETECTION USING CNN | 2021-2022

CHAPTER 3

METHODOLOGY

input images

Pre - processing

Segmentation

Classification

Fig 3.1: Steps involved detecting Lung

Cancer

•Above fig 3.1 Is to improve the detection of lung cancer from the CT images there are four
main steps involved. At each step, various techniques are applied which resulted in different
accuracies in detecting the lung cancer. Firstly, the lung CT images is preprocessed to remove
any noises that exists in the image. Secondly, the image is segmented to get Region of Interest
(ROI). Thirdly, feature extraction is applied to extract features like energy, entropy, variance.
Finally, CNN classification algorithm is applied on the extracted features of the lung X-Ray
image to classify whether it is cancerous or non-cancerous

DEPT OF ECE,BLDEA’,CET,VIJAYPUR 7
 LUNG CANCER DETECTION USING CNN | 2021-2022

Steps involved detecting Lung Cancer

1.Input images:
Image classification is where a computer can analyses an image and identify the ‘class’
theimage falls under. (Or a probability of the image being part of a ‘class’.) A class is
essentially a label, for instance, ‘car’, ‘animal’, ‘building’ and so on. For example, you input
an image of a sheep. Image classification is the process of the computer analyzing the image
and telling you it’s a sheep. (Or the probability that it’s a sheep.)

2. Pre-Processing:

Data preprocessing is a process of preparing the raw data and making it suitable for a machine
learning model. It is the first and crucial step while creating a machine learning model. Data
preprocessing is an integral step in Machine Learning as the quality of data and the useful
information that can be derived from it directly affects the ability of our model to learn;
therefore, it is extremely important that we preprocess our data before feeding it into our
model.

3. Segmentation:

Segmentation, the technique of splitting customers into separate groups depending on their
attributes or behavior, makes this possible. Customer segmentation in machine learning can
help you save money on marketing initiatives by reducing waste. A segmentation model is a
physical tool that can be developed within a spreadsheet or database that provides
calculations and rankings for identified critical elements that are necessary for you to meet
your objectives within a particular segment.

4. Feature Extraction:

Feature extraction for machine learning and deep learning. Feature extraction refers to the
process of transforming raw data into numerical features that can be processed while
preserving the information in the original data set. It yields better results than applying machine
learning directly to the raw data. In machine learning, pattern recognition, and
imageprocessing, feature extraction starts from an initial set of measured data and builds
derived values features intended to be informative and non-redundant, facilitating the

DEPT OF ECE,BLDEA’,CET,VIJAYPUR 8
 LUNG CANCER DETECTION USING CNN | 2021-2022

subsequent learning and generalization steps, and in some cases leading to better human
interpretations. Feature extraction is related todimensionalityreduction

5. Classification:

Image classification is a supervised learning problem define a set of target classes

(objects to identify in images), and train a model to recognize them using labeled example
photos. Early computer vision models relied on raw pixel data as the input to the model.
Image classification is the process of categorizing and labeling groups of pixels or vectors
within an image based on specific rules.

DEPT OF ECE,BLDEA’,CET,VIJAYPUR 9
 LUNG CANCER DETECTION USING CNN | 2021-2022

CHAPTER 4
IMPLEMENTATION
In the current study a CNN model is proposed , used for detection of lung cancer from the CT
images. Model designed with feature extraction, Segmentation and classification for input
image. The feature extraction is done by binarization ,Segmentation is done by
Watershed algorithm.

Binarization
Image binarization is the process of taking a grayscale image and converting it to blackand-
white, essentially reducing the information contained within the image from 256 shades of
gray to 2: black and white, a binary image. This is sometimes known as image thresholding,
although thresholding may produce images with more than 2 levels of gray. It is a form or
segmentation, whereby an image is divided into constituent objects. This is a task commonly
performed when trying to extract an object from an image. However, like many image
processing operations, it is not trivial, and is solely dependent on the content within the
image. The trick is images that may seem easy to convert to B&W are many times not.

WORKING
The process of binarization works by finding a threshold value in the histogram – a value that
effectively divides the histogram into two parts, each representing one of two objects
(or the object and the background). Most thresholding algorithms work by using some type
of information to make a decision about where the threshold is. Sometimes the information
is statistical and uses the mean, median, entropy, other times information is in the form of
shape characteristics of the histogram.

DEPT OF ECE,BLDEA’,CET,VIJAYPUR 10
 LUNG CANCER DETECTION USING CNN | 2021-2022

Segmentation
Watershed algorithms are used in image processing primarily for object segmentation
purposes, that is, for separating different objects in an image. Watershed algorithm is used
for segmentation in some complex images as if we apply simple thresholding and contour
detection then will not be able to give proper results. Watershed algorithm is based on
extracting sure background and foreground and then using markers will make watershed
run and detect the exact boundaries. This algorithm generally helps in detecting touching
and overlapping objects in image. For markers, it can be user defined like manually
clicking and getting the coordinates for markers and also using some defined algorithms
such as thresholding or any morphological
Operations

Watershed Algorithm for Image Segmentation

These are the following steps for image segmentation using watershed algorithm:

Step 1: Finding the sure background using morphological operation like opning and
dilation.

Step 2: Finding the sure foreground using distance transform.

Step 3: Unknown area is the area neither lies in foreground and background and used it as
a marker for watershed algorithm.

DEPT OF ECE,BLDEA’,CET,VIJAYPUR 11
 LUNG CANCER DETECTION USING CNN | 2021-2022

CHAPTER 5
RESULTS

Figure5.1 Input image

The below figure 5.1 Shows the input image.

Figure 5.2 binary image

Figure 5.2 shows the binary image, Binary images are images whose pixels have only
two possible intensity values. Numerically, the two values are often 0 for black and either
1 or 255 for white. The main reason binary images useful in the field of image processing
is because they allow easy separation of an object from the background. Binary
classification is used in the machine learning domain commonly. It is the simplest way
to classify the input into one of the two possible categories. For example, give the
attributes of apple-like Color, weight, etc

DEPT OF ECE,BLDEA’,CET,VIJAYPUR 12
 LUNG CANCER DETECTION USING CNN | 2021-2022

Figure 5.3 Noisy image

Figure 5.3 shows the image of noisy image, noise is typically defined as a random
variation in brightness or color information and it is frequently produced by technical
limits of the images collection sensor or by improper environmental circumstances.
Noisy data is meaningless data. The term has often been used as a synonym for corrupt
data. However, its meaning has expanded to include any data that cannot be understood
and interpreted correctly by machines, such as unstructured text

Figure 5.4 Background Subtracted

image
In the above fig.5.4 background subtraction technique is used for separating out
foreground elements from the background and is done by generating a foreground mask.
Background subtraction is a widely used approach to detect moving objects in a sequence
of frames from static cameras. The base in this approach is that of detecting moving
objects from the difference between the current frame and reference frame, which is often
called 'Background Image' or 'Background Model'.

DEPT OF ECE,BLDEA’,CET,VIJAYPUR 13
 LUNG CANCER DETECTION USING CNN | 2021-2022

Figure 5.5 Segmented Image

In the above fig.5.5, the image segmentation is performed. Image segmentation is a

method in which a digital image is broken down into various sub groups called image
segment, which helps in reducing the complexity of the image to make further processing
or analysis of the image simpler. Image segmentation is a method in which a digital image
is broken down into various subgroups called Image segments which helps in reducing
the complexity of the image to make further processing or analysis of the image simpler.
Segmentation in easy words is assigning labels to pixels.

Image segmentation is the task of clustering parts of an image together that belong to the
same object class. This process is also called pixel-level classification. In other words, it
involves partitioning images (or video frames) into multiple segments or objects.
Segmentation, the technique of splitting customers into separate groups depending on
their attributes or behavior, makes this possible. Customer segmentation in machine
learning can help you save money on marketing initiatives by reducing waste.

DEPT OF ECE,BLDEA’,CET,VIJAYPUR 14
 LUNG CANCER DETECTION USING CNN | 2021-2022

CHAPTER 6
ALGORITHM

Convolution Neural Network(CNN)

• Detailed steps of the convolution network are mentioned below.

• Image handling utilizing Convolutional neural systems (CNN) has been utilized in
different fields, for example, facial recognition, analyzing documents, historic
and environmental collections, understanding climate, drug discovery, video
analysis, advertising etc.

• CT scan images are considered for this ongoing research work. Due to high
complexity of lung cancer pathology images, predicting patient outcome from lung
cancer pathology images, predicting patient outcome from lung cancer is still very
challenging and will require large amount of data for model developments.
So, current focus is on developing patient outcome prediction models based on
image features extracted based on deep learning classification using CT scan
images.

• Eventually, using such deep learning techniques, it makes easy to process various
formats of data, such as imaging and genomic features.

• Processing of pictures with CNN includes various procedures, for example,

1. Image pre processing includes steps such as reading image, resize, remove
noise and other morphological operations. The objective of pictures
predealing with CNN is improving, restoring or redoing pictures, removing
unwanted distortions and enhancement.

2. Feature extraction incorporates eliminating different entities and selecting

more relevant ones and thus combing to a new reduced set of features. It
helps in compacting the images followed by isolating geometric traits (edges,
corners, and joints),facial features,etc

DEPT OF ECE,BLDEA’,CET,VIJAYPUR 15
 LUNG CANCER DETECTION USING CNN | 2021-2022

3. Segmentation is a division of an image into locales.

4. Recognition includes the identifying and detecting an object of feature in

image.

Fig 6.1: Block diagram CNN

CNN consist of following 4 layers as shown in Fig 6.1:

 Convolution Layer
 Pooling
 Flattening
 Fully Connected Layer

1. Convolution Layer:

In convolution layer, we extract different features pixel wise by using features

detectors/kernels. Perform numerous convolutions on input, where each operation uses a
different filter. This results in different feature maps. Convolutional layers convolve the
input and pass its result to the next layer. This is similar to the response of a neuron in
the visual cortex to a specific stimulus. Each convolutional neuron processes data only
for its receptivefield. Althoughfullyconnectedfeedforwardneuralnetworks can be used to
learn features and classify data, this architecture is generally impractical for larger inputs
such as high-resolution images.

DEPT OF ECE,BLDEA’,CET,VIJAYPUR 16
 LUNG CANCER DETECTION USING CNN | 2021-2022

2. Pooling

This decreases the training time and solves the problem of over fitting. Max Pooling
extracts out the highest pixel value out of a feature that has to be extracted. Convolutional
networks may include local and/or global pooling layers along with traditional
convolutional layers. Pooling layers reduce the dimensions of data by combining the
outputs of neuron clusters at one layer into a single neuron in the next layer. Local pooling
combines small clusters, tiling sizes such as 2 x 2 are commonly used. Global pooling
acts on all the neurons of the feature map. There are two common types of pooling in
popular use: max and average. Max pooling uses the maximum value of each local cluster
of neurons in the feature map, while average pooling takes the average. Value.
. Flattening

In flattening, we arrange the pooled feature into a single vector/column as an input for next
layer. In neural networks, each neuron receives input from some number of locations in
the previous layer. In a convolutional layer, each neuron receives input from only a
restricted area of the previous layer called the neuron's receptive field. Typically, the area
is a square (e.g. 5 by 5 neurons). Whereas, in a fully connected layer, the receptive field is
the entire previous layer. Thus, in each convolutional layer, each neuron takes input from
a larger area in the input than previous layers. This is due to applying the convolution over
and over, which takes into account the value of a pixel, as well as its surrounding pixels.
When using dilated layers, the number of pixels in the receptive field remains constant,
but the field is more sparsely populated as its dimensions grow when combining the effect
of several layers.

1.Fully Connected Layer

In fully connected layers, every neuron in one layer is connected to every neuron in another
layer. It is similar to multi-layer perceptron (MLP). This layer takes the inputs from the
previous feature analysis step and adds weights to predict the correct label Result of this
is the final classification decision. Each neuron in a neural network computes an output
value by applying a specific function to the input values received from the receptive field
in the previous layer. The function that is applied to the input values is determined by a
vector of weights and a bias (typically real numbers). Learning consists of iteratively
adjusting these biases and weight . The vector of weights and the bias are called filters and

DEPT OF ECE,BLDEA’,CET,VIJAYPUR 17
 LUNG CANCER DETECTION USING CNN | 2021-2022

represent particularfeatures of the input (e.g., a particular shape). A distinguishing feature

of CNNs is that many neurons can share the same filter. This reduces the memory footprint
because a single bias and a single vector of weights are used across all receptive fields that
share that filter, as opposed to each receptive field having its own bias and vector
weighting.

DEPT OF ECE,BLDEA’,CET,VIJAYPUR 18
 LUNG CANCER DETECTION USING CNN | 2021-2022

CHAPTER 7
CONCLUSION

In this modern era, lots of people are facing many problems with modern age
diseases. Lung cancer is one of the most common types of deadliest disease rising
over time among different countries. Lack of awareness and post-identification of
disease will be the major reason for more death rates. Computer-aided diagnosis
will be a perfect solution for all kind of peoples to diagnose with accurate results.
CAD system will not be a perfect replacement for professional doctors, but this aid
will help them a lot, by assisting practitioners, to make a perfect decision by
analyzing patient reports. Sometimes, practitioners may do some mistake due to
lack of experience or poor analysis of reports.So,it will act as a better remedy for
the current medical environment. More accurate decisions are taken, only if the
model used to train the system will be unambiguous. The presently system provides
better feature extraction and segmentation results. Further the study is to go with
classification and predict the result with highest accuracy will act as a better remedy
for the current medical environment. More accurate decisions are taken, only if the
model used to train the system will be unambiguous. The presently system provides
better feature extraction and segmentation results. Further the study is to go with
classification and predict the result with highest accuracy

DEPT OF ECE,BLDEA’,CET,VIJAYPUR 19
 LUNG CANCER DETECTION USING CNN | 2021-2022

CHAPTER 8

REFERENCES

[1] Senthil Kumar K, Kavethanjali V, and Preethi S , “Cancer statistics, 2021,” CA: A
Lung- pleura carcinoma detection using machine learning, vol. 67, no. 1, pp. 7–30, may
2021.

[2]. Amjad Rehman, Muhammad Kashif, and Ibrahim Abinadi, “Cancer statistics, 2021,”
CA: A Lung Cancer Detection and classification from chest CT scans using machine
learning, vol. 67, no. 1, pp. 1–31, may 2021.

[3]. Amrit Sreekumar, Kartika Rajan Nair, and Sneha Sudheer, “Cancer statistics, 2020,”
CA: Malignant Lung Nodule Detection using Deep learning, vol. 67, no. 1, pp. 02–29,
july2020.
[4]. Swati Mukherjee, and Proofs’. Bohra, “Cancer statistics, 2020,” CA: A Lung Cancer
Disease Diagnosis using machine Approach, vol. 67, no. 1, pp. 7–30, June 2020.

[5]. Suresh Makaju, P.W.C. Prasad, and Ameer AL Sadoon, “Cancer statistics, 2019,”
CA: A Small-Cell Lung Cancer detection using machine learning Algorithm, vol. 67, no. 1,
pp. 7–30, may 2019.

[6]. A. Elchouemi, Kavethanjali V, and Preethi S , “International Symposium on

computer science and intelligent controls, 2018,” CA: Lung Cancer detection using CT
Scan Images, vol. 67, no. 1, pp. 7–30, may 2018.

[7]. Al-Shargabi, B., & Al-Shami, F. A. (2019, December). An Experimental Study For
Breast Cancer Prediction Algorithms. In Proceedings Of The Second International
Conference On Data Science, E-Learning And Information Systems (Pp. 1-6).
[8]. JfMccarthy, M.K., Pe Hoffman, "Applications Of Machine Learning And High-
Dimensional Visualization In Cancer Detection, Diagnosis, And Management", Ann N
Y Acad Sci, Vol.62, Pp. 10201259, 2004.
[9]. Ac. Tan, D. Gilbert, "Ensemble Machine Learning On Gene Expression Data For
Cancer Classification.
[10].De Oliveira, J.P.S., Conci, A., Prez, M.G., Andaluz, V.H.: Segmentation Of Infrared
Images: A New Technology For Early Detection Of Breast Diseases. In: 2015 Ieee
International Conference On Industrial Technology (Icit), Pp. 1765–1771 (2015).

[11].Arbach, L., Reinhardt, J. M., Bennett, D. L., &Fallouh, G. (2003, May).

Mammographic Masses Classification: Comparison Between Backpropagation Neural
Network (Bnn), (Cnn), And Human Readers. In Ccece 2003-Canadian Conference On
Electrical And Computer Engineering. Toward A Caring And Humane Technology (Cat.

DEPT OF ECE,BLDEA’,CET,VIJAYPUR 20
 LUNG CANCER DETECTION USING CNN | 2021-2022

No. 03ch37436) (Vol. 3, Pp. 1441-1444). Ieee.

[12] S. A. Korkmaz, And M. Poyraz, ―A New Method Based For Diagnosis Of Breast
Cancer Cells From Microscopic Images: Dwee—Jht,‖ J. Med. Syst., Vol. 38, No. 9, P.
92, 2014.
[13] Vaishali C. Patil, Shrinivas R. Dhotre, “Lung Cancer Detection from Images of
Computer Tomography Scan”, International Journal of Advanced Research in
Computer and Communication Engineering , Vol. 5, Issue 7, July 2017.

[14] Alton Felix, Marcelo Oliveira, Aydan Machado, Jose Ranieri, “Using 3D Texture and
Margin Sharpness Features on Classification of Small Pulmonary Nodules” ,29th
SIBGRAPI Conference on Graphics, Patterns and Images, 2018.

[15] Sri Widodo, Ratnakar Nur Rahman, Bana Handbag, “Classification Of Lung Nodules
And Arteries In Computed Tomography Scan Image Using Principle Component
Analysis” 2nd International Conferences on Information Technology, Information Systems
and Electrical Engineering, 2

DEPT OF ECE,BLDEA’,CET,VIJAYPUR 21