Presentation Contents
 Introduction
 Medical Imaging Technologies
 The Role of Imaging in Cancer Care
 Lung cancer Detection Approach
 Work Performed and Results
 Image Enhancement
 Gabor Filter
 Fast Fourier Transform
 Image Segmentation
 Thresholding approach
 Features Extraction


Image processing is one of most growing research area these
days and now it is very much integrated with the medical and
biotechnology field



Cancer is one of the most dangerous disease for which still
proper treatment is not available. World Health Organization
(WHO) mentioned that cancer accounted 13% of all death in
the world in 2004



Cancer is a tumor that grows larger than 2mm in every 3
months and multiplies out of control. It also spreads to other
parts of the body and destroys the healthy tissue.






X-Rays (X-Işınları)
Mammography (Mamografi )
Ultrasound (Ultrason )
Computed Tomography (Bilgisayarlı Tomografi)
Magnetic Resonance Imaging (Manyetik Rezonans
Görüntüleme)
 Nuclear Medicine (Planar and SPECT Gamma Imaging, PET)
(Nükleer Tıp (Planar ve SPECT Gama Görüntüleme, PET)
the role of medical imaging in cancer is
something of an anomaly
On the one hand, imaging plays a vital role in
detecting and treating virtually all types of
cancer
The roles are as follows : Imaging Detects Cancer Early
 Imaging Enables Less-Invasive Cancer Diagnosis
and Treatment
 Imaging Fosters More Effective Management of
Cancer
 Imaging Fosters Efficiencies and Savings in Cancer
Care
 Imaging Keeps Workers Productive
 Lung cancer is the most dangerous and widespread cancer in
the world according to stage of discovery of the cancer cells in
the lungs
 Lung cancer image processing stages as follows
görüntü yakalama

görüntü geliştirme
görüntü bölünme
Özelikler çıkarma
the aim of image enhancement is to improve the
interpretability or perception of information included in the
image for human viewers, or to provide better input for
other automated image processing techniques.

Image enhancement techniques can be divided into two
broad categories:
 Spatial domain methods
 and frequency domain methods.
Image enhancement stage we use the following
three techniques:
 Gabor filter,
 Auto-enhancement
 Fast Fourier transform techniques
A Gabor filter is a linear filter whose impulse
response is defined by a harmonic function
multiplied by a Gaussian function.
The follwoıng Figure shows a) the original image
and (b) the enhanced image using Gabor Filter.
Fast Fourier Transform technique operates on
Fourier transform of a given image.
Fast Fourier Transform is used here in image
filtering (enhancement).
Subject

Auto Enhancement

Gabor Filter

FFT Filter

SUB1

37.95

80.975

27.075

SUB2

47.725

80

36.825

SUB3

36.825

79.5

25.625

SUB4

34.775

81.8

25.175

SUB5

32.85

81.4

22.85

Final Average

38.025

80.735

27.51
Image segmentation is an essential process for most
image analysis subsequent tasks
Segmentation divides the image into its constituent
regions or objects. Segmentation of medical images in
2D
The goal of segmentation is to simplify and/or change
the representation of the image into something that
is more meaningful and easier to analyse.
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
Threshold values based on this method will be
between 0 and 1, after achieving the threshold
value; image will be segmented based on it. Figure
4 shows the result of applying thresholding
technique.
Image features Extraction stage is an important
stage that uses algorithms and techniques to
detect and isolate various desired portions or
shapes (features) of a given image.
To predict the probability of lung cancer
presence, the following two methods are used:
binarization and masking
Binarization approach depends on the fact that
the number of black pixels is much greater than
white pixels in normal lung images,
Masking approach depends on the fact that the
masses(means areas affected by cancer) are
appeared as white connected areas inside ROI
(lungs), as they increase the percent of cancer
presence increase.
The appearance of solid blue colour indicates
normal case while appearance of RGB masses
indicates the presence of cancer
Figure 8 shows normal and abnormal images
resulted by implementing Masking approach using
MATLAB
Combining Binarization and Masking approaches
together will lead us to take a decision whether
the case is normal or abnormal according to the
mentioned assumptions in the previous two
approaches.
Tıp alanında kanserli hücrelerin tespiti  @ hasan abdi
Tıp alanında kanserli hücrelerin tespiti  @ hasan abdi

Tıp alanında kanserli hücrelerin tespiti @ hasan abdi

  • 2.
    Presentation Contents  Introduction Medical Imaging Technologies  The Role of Imaging in Cancer Care  Lung cancer Detection Approach  Work Performed and Results  Image Enhancement  Gabor Filter  Fast Fourier Transform  Image Segmentation  Thresholding approach  Features Extraction
  • 3.
     Image processing isone of most growing research area these days and now it is very much integrated with the medical and biotechnology field  Cancer is one of the most dangerous disease for which still proper treatment is not available. World Health Organization (WHO) mentioned that cancer accounted 13% of all death in the world in 2004  Cancer is a tumor that grows larger than 2mm in every 3 months and multiplies out of control. It also spreads to other parts of the body and destroys the healthy tissue.
  • 4.
         X-Rays (X-Işınları) Mammography (Mamografi) Ultrasound (Ultrason ) Computed Tomography (Bilgisayarlı Tomografi) Magnetic Resonance Imaging (Manyetik Rezonans Görüntüleme)  Nuclear Medicine (Planar and SPECT Gamma Imaging, PET) (Nükleer Tıp (Planar ve SPECT Gama Görüntüleme, PET)
  • 5.
    the role ofmedical imaging in cancer is something of an anomaly On the one hand, imaging plays a vital role in detecting and treating virtually all types of cancer
  • 6.
    The roles areas follows : Imaging Detects Cancer Early  Imaging Enables Less-Invasive Cancer Diagnosis and Treatment  Imaging Fosters More Effective Management of Cancer  Imaging Fosters Efficiencies and Savings in Cancer Care  Imaging Keeps Workers Productive
  • 7.
     Lung canceris the most dangerous and widespread cancer in the world according to stage of discovery of the cancer cells in the lungs  Lung cancer image processing stages as follows görüntü yakalama görüntü geliştirme görüntü bölünme Özelikler çıkarma
  • 8.
    the aim ofimage enhancement is to improve the interpretability or perception of information included in the image for human viewers, or to provide better input for other automated image processing techniques. Image enhancement techniques can be divided into two broad categories:  Spatial domain methods  and frequency domain methods.
  • 9.
    Image enhancement stagewe use the following three techniques:  Gabor filter,  Auto-enhancement  Fast Fourier transform techniques
  • 10.
    A Gabor filteris a linear filter whose impulse response is defined by a harmonic function multiplied by a Gaussian function. The follwoıng Figure shows a) the original image and (b) the enhanced image using Gabor Filter.
  • 11.
    Fast Fourier Transformtechnique operates on Fourier transform of a given image. Fast Fourier Transform is used here in image filtering (enhancement).
  • 12.
    Subject Auto Enhancement Gabor Filter FFTFilter SUB1 37.95 80.975 27.075 SUB2 47.725 80 36.825 SUB3 36.825 79.5 25.625 SUB4 34.775 81.8 25.175 SUB5 32.85 81.4 22.85 Final Average 38.025 80.735 27.51
  • 13.
    Image segmentation isan essential process for most image analysis subsequent tasks Segmentation divides the image into its constituent regions or objects. Segmentation of medical images in 2D The goal of segmentation is to simplify and/or change the representation of the image into something that is more meaningful and easier to analyse.
  • 14.
    Thresholding is anon-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
  • 15.
    Threshold values basedon this method will be between 0 and 1, after achieving the threshold value; image will be segmented based on it. Figure 4 shows the result of applying thresholding technique.
  • 16.
    Image features Extractionstage is an important stage that uses algorithms and techniques to detect and isolate various desired portions or shapes (features) of a given image. To predict the probability of lung cancer presence, the following two methods are used: binarization and masking
  • 17.
    Binarization approach dependson the fact that the number of black pixels is much greater than white pixels in normal lung images,
  • 18.
    Masking approach dependson the fact that the masses(means areas affected by cancer) are appeared as white connected areas inside ROI (lungs), as they increase the percent of cancer presence increase. The appearance of solid blue colour indicates normal case while appearance of RGB masses indicates the presence of cancer
  • 19.
    Figure 8 showsnormal and abnormal images resulted by implementing Masking approach using MATLAB
  • 20.
    Combining Binarization andMasking approaches together will lead us to take a decision whether the case is normal or abnormal according to the mentioned assumptions in the previous two approaches.