“LUNG CANCER DETECTION FROM CT IMAGES USING

DEEP LEARNING TECHNIQUES”

A Project Report
Submitted in Partial Fulfillment of the Requirement for the Award of the Degree of

BACHELOR OF TECHNOLOGY
(Electronic & Communication)
To

VEER BAHADUR SINGH PURVANCHAL UNIVERSITY

JAUNPUR

Under the Supervision of

Mr. P C Yadav
(Assistant Professor)

Submitted By:

Aviral Chaurasia (195209)

Ayush Singh (195206)
Prashant Kumar Rai (195232)

DEPARTMENT OF ELECTRONIC ENGINEERING

UNSIET, VBSPU, JAUNPUR
February, 2023
 CANDIDATE'S DECLARATION

We, Aviral Chaurasia (195209), Ayush Singh (195206) and Prashant Rai (195232), Student of
B.Tech (Electronic & Communication Engineering) at Uma Nath Singh Institute of
Engineering and Technology, VBS Purvanchal University, Jaunpur, declare that the work
presented in this project titled “Lung Cancer Detection using Deep Learning Techniques”,
submitted to Department of Electronics Engineering for the award of Bachelor of Technology
degree in Electronic Engineering. All the work done in this project is entirely our own except for
the reference quoted. To the best of our knowledge, this work has not been submitted to any other
university or Institution for award of any degree.

Date: 28th February, 2023 Aviral Chaurasia (195209)

Place: Conference Hall, Prashant Kr Rai (195232)
UNSIET, Jaunpur
Ayush Singh (195206)
B. Tech (ECE), 4th Year
 ABSTRACT

Following synopsis is submitted as a part of coursework for the award of Bachelor of Technology
degree in Electronics Engineering. We will use MATLAB Programming Language, Image
Processing Toolbox to develop a system to perform Lung Cancer Detection on a given CT Scan
Image. We will create a system called “Lung Cancer Detection from CT Images Using Deep
Learning”. It can detect an object at a granular level and it can identify theshape of that object
also. We have used several Image Processing operations discussed in the class to perform several
tasks. We have also implemented from Google Scholar and topics discussed in the class in our
system.
 ACKNOWLEDGEMENT

It is our proud privilege and duty to acknowledge the kind of help and guidance received from
several people in preparation of this report. It would not have been possible to prepare this
synopsis in this form without their valuable help, cooperation and guidance. First and foremost,
we wish to record our sincere gratitude to my supervisor Mr. PC Yadav for their constant support
and encouragement in preparation of this report and for making available library and laboratory
facilities needed to prepare this report. Our guiding teacher on project “Lung Cancer Detection
Using CT Scan Images By Deep Learning” was very helpful to us in giving the necessary
background information and inspiration in choosing this topic for the project. Their contributions
and technical support in preparing this synopsis are greatly acknowledged. Last but not the least,
we wish to thank our parents for financing our studies in this college as well as for constantly
encouraging us to learn engineering. Their personalsacrifice in providing this opportunity to learn
engineering is gratefully acknowledgement.

4
 TABLE OF CONTENTS

Chapters Index Page No

01 Introduction 6
- Cancerous & Non-Cancerous Cell
02 System Requirement 7-8
- Software & Hardware Required
- Dataset Requirement
9
03 Design & Analysis

04 Image Processing Operations 10-12

- Preprocessing
- Image Enhancement
- Image Segmentation (Threshold)
- Feature Extraction
4.1 Proposed Method 13-15
4.2 Performance Analysis

05 Objectives 16

06 Result & Conclusion 17

07 Future Work 18

08 Sources & References 19

List of Figures:
- Flow Chart
- Block Diagram

5
 CHAPTER- 1
INTRODUCTION

Cancer is a condition in which cells in the body become uncontrolled. Lung cancer starts in the
lungs and spreads to lymph nodes or other organs, such as the brain, inside the body. Cancer can
potentially spread to the lungs from other organs. Various CT-Scan pictures were obtained from
various hospitals and various techniques such as image
Segmentation and Sobel filter have been utilized in this research. Early detection of lung tumor is
done by using many imaging techniques such as Computed Tomography (CT), & Magnetic
Resonance Imaging (MRI). Detection means classifying tumor two classes:

(i) Non-Cancerous tumor (benign)

(ii) Cancerous tumor (malignant)

Figure 1

Page | 6
 CHAPTER-2
SYSTEM REQUIREMENT

HARDWARE SPECIFICATION:

We shall need following hardware requirements to develop and run our project,
▪ i3 Processor Based Computer or higher
▪ Architecture: 64bits
▪ Memory: 1 GB
▪ RAM: 2GB Recommended
▪ Hard Disk Drive: 50 GB

SOFTWARE SPECIFICATION:

We shall need following Software to develop and run our project.

➢ Windows 7,8,10 or higher
➢ DICOM Converter
➢ Language: MATLAB
➢ Version: 9.0 R2016a
And we need following toolbox in order to make it work in MATLAB,
➢ Image Acquistion Toolbox
➢ Image Processing Toolbox
➢ Neural Network Toolbox

DATASET REQUIRED:
We also need following input images to import the image,
➢ Medical Imaging including CT Image of Lung Cancer

Dataset for training is obtained from Lung Image Database consist of 1000 CT scans of both
large and small tumors saved in Digital Imaging and Communications in Medicine (DICOM)
format. We have downloaded from KAGGLE.

Page | 7
 Figure 2

Dataset Images Contains the following CT Images:

1- Test Images
2- Train Images
3- Valid Images
- adenocarcinoma
- large cell carcinoma
- normal cell

Resolution of Dataset Images:

Dimension: 265*190
Width: 265
Height: 190

Page | 8
 CHAPTER-3
DESIGN & ANALYSIS

- This project is start with collecting a number of Computed Tomography (CT) Scanned Images
from the available database.
- This image will be further being processed, enhanced & segmented then load the image into the
MATLAB for finding the accuracy and other parameter.
- This techniques helps to detect cancer & help for diagnosis solution. This Computed Tomography
(CT) scanned images are used as an input image, after getting the input image we plot the
histogram.
- After seeing the histogram, we analyse the histogram, detect the noise & we removed the noise
from the input image by using different filtration techniques whch are used for denoising.
- In next we do the gray scale imaging & then thresholding operation is done & after that we apply
the histogram equalization, these all above operations comes under image acquisition & image
enhancement.
- In next step Image segmentation will be done, there are different types of image segmentation are
available.
- Then we do the morphological operation to the resultant image so that we can get clear &
accurate region of the image.
- We are aiming to get more accurate result by using image enhancement techniques & image
segmentation operation.

Block Diagram:

Pre-processing Operation

Input CT Image Image Enhancement & Restoration Filtering Segmentation

(Thresholding)
(Using Histogram Equalization/ CLAHE)

_______________ ______________ ___________________________

Image Filling Feature Extraction
Dilation
(Morphological Operation) (Parameters)

Fig3. Systematic Diagram

Page | 9
 1. Image Processing Operations

This project consists of four major stages, the first stage is image acquisition, the second stage is
Image Processing Techniques, third stage is consists of Image segmentation operations & the
fourth or the last stage is Feature extraction of any image.

Pre-Processing Operations

Gray Scale Image

Plot Histogram

Noise Detection

Denoise the Noisy Image

Using Filter

Fig4. Algorithm for Preprocessing of CT Image

Noise: We have detected Salt & Pepper Noise present in the Gray Level CT Scan Images.
Noise tells unwanted information in digital images. Noise produces undesirable effects
such as artifacts, unrealistic edges, unseen lines, corners, blurred objects and disturbs
background scenes.

Fig5. Salt & Pepper Noisy Image

Page | 10
 All the stages are having some basic operations & steps which are necessary to fulfill
the requirements & to complete the stage step by steps.

Input CT Scan Lung Cancer Image from Dataset

IMAGE ACQUISITION
Convert the Input Image into Gray Scale Images

Plot the Histogram & Detect the Noise

Preprocessing
3
Noise Free Image By Filters
IMAGE ENHANCEMENT
Enhance Image Using CLAHE/Histogram Equalization

Apply Threshold Segmentation

IMAGE SEGMENTATION
Compute Morphological Operations
FEATURE EXTRACTION

Final Accuracy & Other Parameters Obtained

DEEP LEARNING
APPROACH Classification of Cancer

Cancer No Cancer
Detected Detected
BENIGN Malignant

Fig 6. Diagrammatic Representation of proposed system

The description of all the stages & steps are given below:

A) IMAGE ACQUISITION: It starts with the collection of CT Images of lung of different

persons from the record or available data base. This CT Images are further used as input to
the system. After this we can proceed for further operations.

B) IMAGE ENHANCEMENT: It is a technique which is used to improve the quality of the

Page | 11
 image & to get the better image than the provided one, it provide clear, better & accurate
parameter of the desired region. It improves the image quality and remove the noise from the
image. For this purpose, noise removal from the images, image filtering techniques are use,
which will helpful to detect cancer parameter during processing.

CLAHE Method: It is Contrast-limited adaptive histogram equalization (CLAHE).

It works on small areas of an image called tiles rather than the complete image. The
surrounding tiles are blended using bilinear interpolation to remove the false boundaries. This
algorithm can be used to improve image contrast

Figure 7

C) Image Segmentation: The main aim of segmentation is to change the representation of an

image into something that is easier to analyze.

- Thresholding: Thresholding is one of the most powerful tools for image segmentation. In
this we have a gray scale image given for a thresholding procedure it converts the RGB
image into a Binary image i.e. black and white image which has only two shades i.e black
and white which represent the level 0 and 1 only the threshold value for this will be lies
between 0 and 1 because it has only two levels., after achieving the threshold value; image
will be segmented based on it.
-

Figure 8

Page | 12
D) Feature Extraction: Feature plays a very important role in the area of image
processing.

3.1 OUR PROPOSED METHOD

Sobel Filter: After detecting the noise which is present in our data set of image we use a
suitable filter to remove the noise .
Here the noise is salt and pepper noise present so , we use sobel filter to remove this noise.
“THE SOBEL METHOD or SOBEL FILTER IS A GRADIENT BASED METHOD THAT
LOOKS FOR STRONG CHANGES IN THE FIRST DERIVATIVE OF AN IMAGE.”

The Sobel filter edge detector uses a pair of 3*3 convolution masks, one estimating the gradient
in the x - direction and the other in the Y – direction. The gradient magnitude is given by:

PERFORMANCE ANALYSIS

1- PSNR: The PSNR computes the peak signal-to-noise ratio, in decibels, between two images.
This ratio is used as a quality measurement between the original and a compressed image.
The higher the PSNR, the better the quality of the compressed, or reconstructed image.

2- SSIM: The Structural Similarity Index (SSIM) is a perceptual metric that quantifies image
quality degradation* caused by processing such as data compression or by losses in data
transmission.
Page | 13
3- MSE: The MSE represents the cumulative squared error between the compressed and the
original image, whereas PSNR represents a measure of the peak error.

4- Energy: The term energy describes the local change of a certain quality of the image. An
example of quality would be brightness or intensity. Energy is specifically important for
applications such as image compression

5- Contrast: It is created by the difference in luminance reflected from two adjacent surfaces. In
other words, contrast is the difference in visual properties that makes an object
distinguishable from other objects and the background.

6- Entropy: The entropy or average information of an image is a measure of the degree of

randomness in the image. The entropy is useful in the context of image coding : it is a lower
limit for the average coding length in bits per pixel which can be realized by an optimum
coding scheme without any loss of information .

Proposed Plan PSNR SSIM MSE Energy Contrast Entropy

Mean Filter 32.65 0.765 47.76 0.50 0.991 0.51

Gradient Filter 29.65 0.643 42.90 0.59 0.810 0.49
Convolution Filter 27.97 0.624 38.97 0.56 1.098 0.42
NLM Filter 34.65 0.599 49.76 0.61 1.987 0.61
Proposed Sobel Filter 38.99 0.494 51.87 0.64 2.011 0.68

Table.1

Page | 14
3.2. Graphical Representation of Performance Analysis

PERFORMANCE ANALYSIS
PSNR SSIM MSE Energy Contrast Entropy

51.87
49.76
47.76

42.9

38.99
38.97

34.65
32.65

29.65

27.97

2.011
1.987
1.098
0.991
0.765

0.643

0.624

0.599

0.494
0.81

0.68
0.64
0.61

0.61
0.59

0.56
0.51

0.49

0.42
0.5

MEAN FILTER GRADIENT FILTER CONVOLUTION NLM FILTER PROPOSED SOBEL

FILTER FILTER

Page | 15
 CHAPTER-4
OBJECTIVE

This Project is mainly based on Image Processing using Deep Learning Techniques. In this work
MATLAB have been used through every procedure made.

- To study the medical image processing under the concepts of MATLAB

- The Main Objective of this project is to find out the early stage of lung cancer and
explore the accuracy levels of various image processing techniques
- Enhancement of image using CLAHE Method
- Image Segmentation using Thresholding Approach

The objective of our work is to take any input CT Scan Image, Plot the Histogram of that image,
detect & analyze the noise accordingly. For Noise Removal operations, we use suitable filter. By
using these methods the work has been done on CT Images & the accuracy of the suitable filter is
shown as a result & several other parameters also. Image Processing techniques are widely use
bio-medical sector. Detection of lung cancer from Computed Tomography (CT) Images is done
by using MATLAB software.
For medical image processing many different types of images are used but Computer
Tomography (CT) scans are generally preferred because of less noise.

Page | 16
 CHAPTER-5
RESULT & CONCLUSION

As we know Lung Cancer is one of the dangerous Diseases in the world. An image improvement
technique in developing for earlier disease detection and treatment stages. Correct Diagnosis and
curly detection of lung cancer can increase the survival rate. Image quality and accuracy is the
core factors of this research, image quality assessment as well as enhancement stage. This project
is based on the processing of computed tomography (CT) images. We also conclude that the lung
cancer can be detected in an early stage by using any one of this method and by following all the
four steps mentioned above. As we can see the median filter is chosen. After image processing
we go for segmentation approach here we use histogram and texture segmentation. After. used to
get individual lung and eliminate unnecessary parts By doing morphological operations, we get
not only the individual lung but also apparent the lung nodule then we extracts the Tumor by
comparison.

Page | 17
 CHAPTER-6
FUTURE WORK

We are aiming to get the more accurate results by using various enhancement and segmentation
technique, different segmentation strategies and calculations are the root idea of digital image.
processing the more accurate rent will be more helpful and good for the diagnosis solution and
the penon can have more chances of survival from this dangerous disease and we can do one
more thing apart from using different strategies we can use a fusion method of all this technique
or the hybrid methods to get the more accurate result. We can also develop the system as a real
time system in future It means the system will work at the time of diagnosis as well as with the
time when we take the (CT) images, the advantage of the real time system will be that it helps
the person to cure the disease as soon as possible and provides a help for curly treatment so the
survival chance can be increase. In future by parameter and area calculation of the tumor at the
time of detection we can also find that tumor has been in which stage.

I will work to find several other parameters in detection of cancerous cell while extracting the
features of the resultant images of lung. Parameters are as follows:
High Accuracy using latest advance filters, Classification of Lung Cancer, Entropy, Contrast, and
Energy.

Deep Learning Approach:

Deep learning is a subset of machine learning that uses neural networks with at least three
layers. Compared to a network with just one layer, a network with multiple layers can
deliver more accurate results. Both RNNs and CNNs are used in deep learning, depending
on the application. A Convolution Neural Network (CNN) is a network architecture for
deep learning that learns directly from data Deep learning is proven to be the best method
for medical image processing, lung nodule detection and classification, feature extraction
and lung cancer stage prediction. In Deep Learning, CNN is a type of artificial neural
network, which is widely used for image/object recognition and classification. Deep
Learning thus recognizes objects in an image by using a CNN.

Why CNN? Medical Imaging: CNNs can examine thousands of pathology reports to
visually detect the presence or absence of cancer cells in images.

The main Advantage of CNN compared to its predecessors is that it automatically detects
the important features without any human supervision.

Page | 18
 CHAPTER-7
REFERENCES

1- https://www.kaggle.com/datasets/mohamedhanyyy/chest-ctscan-images

2- https://www.academia.edu/4147898/Digital_image_processing_by_Rafael_C_Gonzalez_Rich
ard_E_Woods_2nd_Edition

3- Gonzalez R C and Woods R E 2008 Digital Image Processing Upper Saddle River (New
Jersey: Prentice Hall)

4- Kajal N et al 2015 Early Detection of Lung Cancer Using Image Processing Technique:
Review International Journal of Advent Research in Computer and Electronics (IJARCE)
2(2), E-ISSN: 2348-5523

5- Allaoui A E and Nasri M 2019 Medical Image Segmentation by Marker Controlled Threshold
and Mathematical Morphology 1LABO MATSI, ESTO, B.P 473, University Mohammed I
OUJDA, Maroko

6- R. D. Karthikeyan, R. G, V. V, G. B. C and K. M, "A Review of Lung Cancer Detection

using Image Processing," 2021 Smart Technologies, Communication and Robotics (STCR),
Sathyamangalam, India, 2021, pp. 1-4, doi: 10.1109/STCR51658.2021.9588835.

7- ] P. Mohamed Shakeel ,M.A .Burhanuddin ,M. I. Desa, Lung Cancer Detection from CT
Image Using Improved Profuse Clustering and Deep Learning Instantaneously Trained
Neural Networks, Measurement (2019),

Page | 19