Early Detection of Lung Cancer

Early Detection of Lung Cancer

Aswathy N Iyer

Dept Of Electronics And Communication Engineering Amal Jyothi College Of Engineering

Kottayam, Kerela

Lymie Jose

Dept Of Electronics And Communication Engineering Amal Jyothi College Of Engineering

Kottayam, Kerela

Anumol Thomas

Dept Of Electronics And Communication Engineering

Amal Jyothi College Of Engineering Kottayam, Kerela

AbstractLung cancer is one of the most threatening cancers to cure and provide treat. The early detection of lung cancer is helpful in medical field to lower the chance of danger. A conventional Technique that helps detection methods so easier is computed tomography (CT) scan. When there is a large number of CT scans that should be observed by radiologists is a time spending process, so as to reduce radiologists workload computer aided detection(CAD) systems are used. A lung cancer detection system using image processing in CAD is designed to detect and classify the presence of lung cancer in CT- images. In this study, MATLAB have been used through every procedures made. There are three main processes used throughout the report; Pre-processing, feature extraction and finally the classification process. In image processing procedures, process such as image pre-processing, segmentation and feature extraction have been discussed in detail. We are aiming to get the more accurate results by using various enhancement and segmentation techniques. The proposed method plays a vital role in detecting a small notable change in the size of detected nodule to study and measure the growth of tumour over a period to the radiologists.

Keywords Computed Tomography (CT), Computer Aided Detection (CAD), Lung cancer detection system (LCDS), Watershed Segmentation, ROI, Thresholding, morphologic, Metastasis.

1. INTRODUCTION

   The mortality rate of lung cancer is the highest among all other types of cancer. Lung cancer is one of the most serious cancers in the world, with the smallest survival rate after the diagnosis, with a gradual increase in the number of deaths every year. Lung cancer is a disease in which a cell growth is present in tissues of the lung Survival from lung cancer is directly related to its growth at its detection time. But people do have a higher chance of survival if the cancer can be detected in the early stages. Lung cancer can be divided into two main groups, non-small cell lung cancer and small cell lung cancer. These assigned of the lung cancer types are depends on their cellular characteristics. As for the stages, in general there are four

   stages of lung cancer; I through IV. Staging is based on tumor size and tumor and lymph node location. The earlier the detection is, the higher the chances of successful treatment. An estimated 85% of lung cancer cases in males and 75% in females are caused by cigarette smoking.

   Medical imaging is a method used to create images of the human part or complete body for the medical diagnostics purpose and detailed examination about the particular diseases. The recent progress in computerized medical image reconstruction and the related developments in its analysis methods and computer-aided diagnosis system has made medical imaging into one of the most important fields of scientific imaging. The evolution of CT( Computed Tomography) imaging has made a vital role in the detection of many type of cancer . CT scan is an imaging method that uses X-rays. CT scans are mainly used in imaging and diagnosis of the body parts such as brain, liver, chest, abdomen and pelvis and spine. It is one of the main detection mechanisms in lung cancer. For detecting the lung cancer at its early stages, the CT images undergo image processing which includes pre-processing, feature extraction and lung cancer identification

2. METHADOLOGY

   Overall, there are three main processes used throughout the report; Pre-processing, feature extraction and finally the classification process. MATLAB is used in every process made throughout the project. Process involved in the lung cancer detection system for the project can be view in Figure 1.

   Figure 1

   The image is captured by the help of CT machines and it is given for

   further processings

   1. Image pre-processing

      In the image Pre-processing stage we started with image enhancement; the aim of image enhancement is to improve the interpretability or perception of information in images for human viewers, or to provide better input for other automated image processing techniques Therefore, all the image have been undergoing several pre-processing process. Image pre-processing process involved is smoothing, enhancement, and segmentation is done.

      i) Image Enhancement

      Image enhancement techniques can be divided into two broad categories: Spatial domain methods and frequency domain methods. Unfortunately, there is no general theory for determining what good image enhancement is when it comes to human perception. If it looks good, it is good! However, when image enhancement techniques are used as pre-processing tools for other image processing techniques, then quantitative measures can determine which techniques are most appropriate. In our image enhancement stage we used three techniques: Gabor filter, auto-enhancement and Fast Fourier transform techniques.

      ii). Image Segmentation

      Image segmentation is an essential process for most image analysis subsequent tasks. In particular, many of the existing techniques for image description and recognition depend highly on the segmentation results. We used Thresholding and watershed segmentation techniques. Thresholding is one of the most powerful tools for image segmentation. The segmented image obtained from

      Thresholding has the advantages of smaller storage space, fast processing speed and ease in manipulation, compared with gray level image which usually contains 256 levels. Therefore, thresholding techniques have drawn a lot of attention during the past 20 years. Watershed segmentation extracts seeds indicating the presence of objects or background at specific image locations. The marker locations are then set to be regional minima within the topological surface (typically, the gradient of the original input image) and the watershed algorithm is applied.

   2. Feature Extraction

   The Image features Extraction stage is very important in our working in image processing techniques which using algorithms and techniques to detect and isolate various desired portions or shapes (features) of an image. Feature extraction is an essential stage that represents the final results to determine the normality or abnormality of an image.[7]

   These features act as the basis for classification process. Only these features were considered to be extracted; Average intensity, area, perimeter and eccentricity.

   The features are defined as follows:

   1. Area: it is a scalar value that gives the actual number of overall nodule pixel. It is obtained by the summation of areas of pixel in the image that is registered as 1 in the binary image obtained.

   2. Perimeter: It is a scalar value that gives the actual number of the outline of the nodule pixel. It is obtained by the summation of the interconnected outline of the registered pixel in the binary image.

   3. Roundness: Eccentricity: This matric value or roundness or circularity or irregularity index (I) is to 1 only for circular and it is <1 for any other shape. Here it is more circularity of the object

3. RESULT AND DISCUSSION

   CT image of Lung Cancer hav successfully undergo the image pre-processing procedure with four features: Average, intensity, area, perimeter and eccentricity.

   1. Results for image enhancement

      We can define image enhancement as away to improve the quality of image, so that the resultant image is better than the original one, the process of improving the quality of a digitally stored image by manipulating the image with MATLAB software. It is quite easy, for example, to make an image lighter or darker, or to increase or decrease contrast. MATLAB also supports many filters for altering images in various ways.

      1. Gabor filter enhancement technique

         The Gabor filter was originally introduced by Dennis Gabor, we used it for 2D images (CT images). The Gabor function has been recognized as a very useful tool in computer vision and image processing, especially for texture analysis, due to its optimal localization properties in both spatial and frequency domain.

      2. Auto Enhancement technique

         Auto enhancement, automatically adjusts and enhances the image (brightness, color and contrast) to optimum levels, and this is clearly observed by following (figure 3.2) as you see (a) is the original image and (b) is the image after applying auto enhancement MATLAB code. This method strongly depends on statistical operations such as mean, variance calculation.

      3. Fast Fourier Transform technique

      Fast Fourier Transform technique operates on Fourier transform of image. The frequency domain is a space in which each image value at image position F represents the amount that the intensity values in image I vary over a

      specific distance related to F. Fast Fourier Transform FFT is a faster version of the Discrete Fourier Transform (DFT).

   2. Results for segmentation

      Segmentation divides an image into its constituent regions or objects. The segmentation of medical images in 2D, slice by slice has many useful applications for the medical professional: visualization and volume estimation of objects of interest, detection of Abnormalities (e.g. tumors, etc.), tissue quantification and classification, and more.

      1. Thresholding approach

         Thresholding is a non-linear operation that converts a gray- scale image into a binary image where the two levels are assigned to pixels that are below or above the specified threshold value.

         One obvious way to extract the objects from the background is to select a threshold T that separates these modes. Then any point (x,y) for which f(x,y) > T is called an object point, otherwise, the point is called a background

         point. Threshold value based on this method will be between 0 and 1, after achieve this value we can segment an image based on it.

      2. Watershed Segmentation approach

      Separating touching objects in an image is one of the more difficult image processing operations, however it has no smoothing/generalization properties. The marker based watershed segmentation can segment unique boundaries from an image.

      According to our experimental subjective assessment in the segmentation stage the Watershed Segmentation approach has more accuracy and quality than Thresholding approach.

   3. Result for feature extraction

      Feature extraction is an essential stage that represents the final results to determine the normality or abnormality of an image. Features estimated for separated nodule has been found as follow:

      Average intensity: 226.0;

      Area: 1024;

      Perimeter: 196.3;

      Eccentricity: 0.78;

      These features act as the basis for classification process. Regarding on the type of the image processed, which is binary image, the only color presented is black and white. Thus, only three features were considered to be extracted; area, shape and perimeter. The features are defined as follows:

      1. Area: It is a scalar value that gives the actual number of overall nodule pixel. It is obtained by the summation of areas of pixel in the image that is registered as 1 in the binary image obtained.

      2. Perimeter: It is a scalar value that gives the actual number of the outline of the nodule pixel. It is obtained by the summation of the interconnected outline of the registered pixel in the binary image.

      3. Eccentricity: This matric value or roundness or circularity or irregularity index (I) is to 1 only for circular and it is <1 for any other shape. Here it is assumed that, more circularity of the object.

   4. Classification

      Lung nodule are smallest growths in the lung that measure between 5mm to 25mm in size. Malignant nodules tend to be bigger in size >25mm, and have a faster growth rate. In the normal images nodule size is less than 25mm. And in the abnormal images its size is greator than 25mm. In the segmentation that nodule is detected and than we use feature extraction to extract the featuers from that segmented image by which we can identify the stages of lung cancer. Lung nodule show up as round, white opacities on chest x-rays and computed tomography scans.

      Previous scan x-ray or scan and the current x-ray and ct- scan is used to determine if there is any change in shape, size, or appearance of the nodules. If the nodule do not grow larger after monitoring for a 2 year period, no further treatment is necessary.

4. STAGING OF LUNG CANCER

   The stage of a cancer is a measure of the extent to which a cancer has spread in the body. Staging involves evaluation of a cancer's size and its penetration into surrounding tissue as well as the presence or absence of metastases in the lymph nodes or other organs. Staging is important for determining how a particular cancer should be treated, since lung-cancer therapies are geared toward specific stages.

   Staging of a cancer also is critical in estimating the prognosis of a given patient, with higher-stage cancers generally having a worse prognosis than lower-stage cancers.

   Stages from I to IV in order of severity:

   • In stage I, the cancer is confined to the lung.

   • In stages II and III, the cancer is confined to the chest (with larger and more invasive tumors classified as stage III).

   • Stage IV cancer has spread from the chest to other parts of the body.

5. CONCLUSION

Lung cancer is the most dangerous and widespread in the world according to stage the discovery of the cancer cells in the lungs, this gives us the indication that the process of detection this disease plays a very important and essential role to avoid serious stages and to reduce its percentage distribution in the world. To obtain more accurate results we divided our work into three stages:

Image Enhancement stage, Image Segmentation stage and Feature Extraction stage.

Lung Nodule Detection in CT Scans is an active area of research which is continuously emerging and there are many enhancements that can be included to make more efficient.

REFERENCES

1. American Cancer Society, Cancer Statistics, 2005, CA: A Cancer Journal for Clinicians, 55: 10- 30,2005,http://caonline.amcancersoc.org/cgi/content/full/55/1/10 .

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

3. A. El-Baz, A. A. Farag, PH.D., R. Falk, M.D. and R. L. Rocco, M.D., detection, visualization, and identification of lung abnormalities in chest spiral CT scans: phase I, Information Conference on Biomedical Engineering, Egypt (2002).

4. B.V. Ginneken, B. M. Romeny and M. A. Viergever, Computer- aided diagnosis in chest radiography: a survey, IEEE, transactions on medical imaging, vol. 20, no. 12 (2001).

5. 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

6. 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.

7. Suzuki K., et al., False-positive Reduction in Computer-aided Diagnostic Scheme for Detecting Nodules in Chest Radiographs by Means of Massive Training Artificial Neural Network, Academic Radiology, 12, No 2,February 2005, pp. 191-201.