Lung Cancer Detection

Declaration

We hereby declare that this written submission represents our own ideas in our own words and where other's ideas or words have been included, have adequately cited and referenced the original sources. We also declare that we have adhered to all the principles of academic honesty and integrity and have not misrepresented or fabricated or falsified any idea /data /fact /source in our submission.

Acknowledgement

it is not possible to prepare without the assistance and encouragement of other people colleagues and teachers.

We would like to place on record our deep sense of gratitude to Mr. Abhishek Kashyap for their generous guidance, help and useful suggestions we would like to thank Jaypee Institute of Information Technology, Noida, for their invaluable guidance and assistance, without which the accomplishment of the task would have never been possible. We also thank them for giving this opportunity to explore into real world and realize the interrelation of theoretical concepts and its practical application. We also wish to extend my thanks to other classmates for their insightful comments and constructive suggestions to improve the quality of this project work.

Abstract

Lung cancer is the common cause of death among people all over the world. Early recognition of lung cancer can increase the chance of survival among people. The overall 6-year endurance rate for lung cancer patients increases from 12 to 45% if the disease is sensed in time. Although Computed Tomography (CT) can be more effective than X-ray. However, problem appeared to merge due to time constraint in detecting the present of lung cancer regarding on the several diagnosing methods used. Hence, a lung cancer detection system using image processing is used to classify the present of lung cancer in an CT- images. In this study, MATLAB have been used through every process made. In image processing measures, method such as image pre-processing, segmentation and feature extraction have been discussed in detail. We are targeting to get the more precise results by using various improvement and segmentation techniques.

Chapter 1

Introduction

1.1 Lung Cancer Detection

Lung cancer is a disease of abnormal cells multiplying and growing into a tumor. Lung cancer is one of the most serious cancers in the world, with the smallest survival rate after the identification, with a steady increase in the number of deaths every year. But people do have a higher chance of survival if the cancer can be identified in the early stages. Currently, CT are said to be more effective than plain chest x-ray in identifying and diagnosing the lung cancer. The purpose is to find the early stage of lung cancer and more accurate result by using various enhancement and segmentation techniques.

Figure 1.1 Lung Cancer

1.2 Objective

• Early detection is necessary to reduce the death rates in the society.
• To be familiar with Image Processing Technique.
• To be familiar with abnormal lung cancer cell's shape.
• Accurate early detection information should be analysed.

1.3 Block Diagram

Figure 1.2 Flow Chart for Detection

Chapter 2

Literature Survey

2.1 Image processing

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. Image processing generally involves extraction of useful information from an image. This useful information may be the dimensions of an engineering component, size of diagnosed tumour, or even a 3-d view of an unborn baby. The main areas of application of image processing are bio-medical, engineering, quality control, face detection, traffic control etc. It is among rapidly growing technologies today, with its applications in various aspects of a business. Image Processing forms core research area within engineering and computer science disciplines too. Image Processing basically includes the following three steps:

• Importing the image with optical scanner or by digital photography.
• Analysing and manipulating the image which includes data compression and image enhancement and spotting patterns that are not seen by human eyes.
• Output is the last stage in which result can be altered image or report that is based on image analysis.

2.1.1 Needs

The needs of image processing are as follows

• VisualisationObserve the objects that are not visible.
• Image Sharpening and RestorationTo create a better image.
• Image RetrievalSeek for the image of interest.
• Measurement of PatternMeasures various objects in an image.
• Image RecognitionDistinguish the objects in an image.

2.1.2 Types

There are two types of methods used for Image Processing that are Analog and Digital Image processing. Analog or visual techniques of image processing can be used for the hard copies like printouts and photographs. Image analysts use various fundamentals of interpretation while using these visual techniques. The image processing is not just confined to area that has to be studied but on knowledge of analyst. Association is another important tool in image processing through visual techniques. So analysts apply a combination of personal knowledge and collateral data to image processing.

Digital Processing techniques help in manipulation of the digital images by using computers. As raw data from imaging sensors from satellite platform contains deficiencies. To get over such flaws and to get originality of information, it has to undergo various phases of processing. The three general phases that all types of data have to undergo while using digital techniques are pre-processing, enhancement and display, information extraction.

Figure 2.1 Analog vs. Digital

2.2 Matlab

MATLAB is the abbreviation for matrix laboratory. It is a multi- paradigm numerical computing environment. A proprietary programming language developed by Math Work, MATLAB allows matrix manipulations, plotting of functions and data, implementation of Algorithms, creations of user interfaces, and interfacing with programs written in other languages, including C, C++, C#, Java, Fortan and Python. Although MATLAB is intended primarily for numerical computing, an optional toolbox uses the MuPAD symbolic engine, allowing access to symbolic computing abilities. An additional package, Simulink, adds graphical multi-domain simulation and model-based design for dynamic and embedded systems. The MATLAB application is built around the MATLAB scripting language. Common usage of the MATLAB application involves using the command window as an interactive mathematical shell or executing text files containing MATLAB code.

Chapter 3

Terminology and Working

3.1 Image Enhancement

Image enhancement techniques has two general categories: Spatial domain and frequency domain. According to human perception, there is no general theory for determining what decent image enhancement is. It is worthy, if it looks decent. However, when image pre-processing procedure implements image enhancement techniques then computable measures can determine which techniques are most appropriate. In our image enhancement stage we used three techniques: Noise Removal, greyscale conversion, Binarization, Inversion.

Figure 3.1 Image Enhancement

3.2 Noise Removal

Noise removal is the process of reducing the noise from an image. Images taken from camera picks up noise from variety of sources. Further use of these images will often require that noise be partially removed. In the proposed process, there is salt and pepper noise i.e. sparse light and dark elements. In this, pixels in the image are very different from their surrounding pixels. Generally, this type of noise only affects a small number of pixels.

Median Filter is used for removing salt and pepper type of noise. It is a non-linear filter and it is very good at maintaining image details. To run this filter, we have to consider each pixel in the image then sort the neighbouring pixels into order based upon their intensities. At last, replace the original value of the pixel with the median value from the list.

Noise. Noise Removal

Figure 3.2 Noise Removal

3.3 Thresholding

This technique is used to convert a greyscale image into binary image. Thresholding is the simplest method of image segmentation. The simplest thresholding methods replace each pixel in an image with a black pixel if the image intensity Ii,j is less than some fixed constant T (that is , Ii,j < T), or a white pixel if the image intensity is greater than that constant. To make thresholding completely automated for Number Plate Recognition System, it is necessary to select the threshold value T.

Greyscale Image. Binary Image

Figure 3.3 Thresholding

3.4 Morphology

Binary images may contain numerous imperfections. In particular, the binary regions produced by simple thresholding are distorted by noise and texture. Morphological image processing pursues the goals of removing these imperfections by accounting for the form and structure of the image. These techniques can be extended to greyscale images. Morphological image processing is a collection of non-linear operations related to the shape or morphology of features in an image. Morphological operations rely only on the relative ordering of pixel values, not on their numerical values, and therefore are especially suited to the processing of binary images. Morphological operations can also be applied to greyscale images such that their light transfer functions are unknown and therefore their absolute pixel values are of no or minor interest.

3.4.1 Types of Morphology

There are two types of morphology used in Lung Cancer Detection:

• Dilation

It can repair breaks.

It can repair intrusions.

It enlarges object.

Figure 3.4.1 Dilation

• Erosion

It can split apart joined objects.

It can split away extrusions.

It shrinks objects.

Figure 3.4.1 Erosion

3.5 Image Segmentation

Image segmentation is the process of partitioning a digital image into multiple segments (sets of pixels). The goal of segmentation is to simplify and/or change the representation of an image into something that is more meaningful or easier to analyse. Segmentation is typically used to locate objects and boundaries (lines, curves etc.) in images. More precisely, image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain characteristics. The result of segmentation is a set of segments that collectively cover the entire image. The segmented image achieved has the benefits of smaller storage space, fast processing speed and ease in manipulation

Figure 3.5 Image Segmentation

3.6 Feature Extraction

Feature extraction is a useful step that represents the final results, to determine the normality or abnormality of an image. Features to be extracted are Area, Perimeter, Roundness/ eccentricity.

(i)Area= it is a scalar value that is obtained by the summation of areas of pixel in the image that is registered as 1 in the binary image obtained.

(ii)Perimeter= it is a scalar value that is obtained by the summation of the interconnected outline of the registered pixel in the binary image.

(iii)Roundness= this is a matrix value that is 1 only for circular shape and it is <1 for any other shape.

Chapter 4

Algorithm

4.1 Algorithm for Lung Cancer Detection

• Input image.
• Conversion into greyscale and noise removal.
• Greyscale to binary image.
• Morphological process.
• Implementing segmentation
• Extraction of features
• Diagnosis result

4.1.1 Input Image

• Capture CT scanned image.
• Store the CT scanned image for further processing.

4.1.2 Conversion into Greyscale & Noise Removal

- Identify the intensity of the image.

if image intensity= high

Reduce intensity

else if intensity= low

increase intensity

Else

no change.

Convert into greyscale.

4.1.3 Greyscale to Binary Image

• Calculate approximate threshold value for the image.
• Convert the image into binary image using threshold value.

4.1.4 Morphological Process

• Analyse the binary image properly.
• Find out errors present.
• Remove all errors/disturbances using dilation & erosion technique.

4.1.5 Implementing Segmentation

• Filter noise level present in the image.
• Clip the defected lung from the image.
• Separate abnormal cells present in the lung.

4.1.6 Extraction of Features

• Observe the pixels of the image carefully.
• Write down the pixel value in order to find area, perimeter, roundness of the lung.

4.1.7 Diagnosis Result

- Successful detection of cancer cells.

Chapter 5

Result

On applying Image segmentation technique on lung CT image and then extracting the features of that, we are able to detect cancer cells in the lungs successfully.

Average intensity= 226.0

Area= 1024

Perimeter= 196.3

Roundness= 0.78

Figure 5.1 Diagnosis Result.

Chapter 6

6.1 Limitations

• Difficult to detect small seized abnormal cells.
• Result image after enhancement is not very clear as the initial message mage.

6.2 Conclusion

The project Lung Cancer Detection was developed as 4rd year major project of Electronics and Communication Engineering, JIIT. The project was designed keeping in mind to detect the early stage of lung cancer of an infected person. This project was a success in analysing the abnormal cell in the lung causing cancer although it has got its own limitations. From this project we learn about image processing cells producing cancer and various enhancement techniques. The basic focus of the project was in the image processing. Lung cancer is very dangerous and widespread disease in the world, this gives us the warning that the process of detection this disease plays a very important and essential role to avoid such a serious disease and to reduce the percentage of infected person.

6.3 Future Scope

Future scope may include the following work “

• Making extraction method possible for small sized abnormal cancer cell.
• Use of other advance techniques for lung cancer and comparing them with current method.

References

[1] D. Lin and C. Yan, Lung nodules identification rules extraction with neural fuzzy network, IEEE, Neural Information Processing, vol. 4, (2002).

[2 Beucher, S. and Meyer, F., The Morphological Approach of Segmentation: The Watershed

Transformation, Mathematical Morphology in Image Processing, E. Dougherty, ed., pp. 43-481, New York: Marcel Dekker, 1992.

[3] Nguyen, H. T., et al Watersnakes: Energy-Driven Watershed Segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 25, Number 3, pp.330-342, March 2003.

[4] Anita Chaudhary, Sonit Sukhraj Singh, Lung Cancer Detection On CT Images By using Image Processing, International Conference on Computing Sciences, 2012.

Cite this page