Download presentation
Presentation is loading. Please wait.
1
Medical Imaging Mohammad Dawood Department of Computer Science University of Münster Germany
2
2 Medical Imaging, SS-2010 Mohammad Dawood What is medical imaging? Medical imaging is the process of acquiring images without or with minimal invasion for the purpose of detecting, diagnosing, quantifying or treating a disease. Techniques and methods from image processing are used to assist the clinicians.
3
3 Medical Imaging, SS-2010 Mohammad Dawood Structure of the Course 1. Basics of Image processing 2. Medical Image modalities 3. Reconstruction 4. Registration 5. Segmentation 6. Enhancement
4
4 Medical Imaging, SS-2010 Mohammad Dawood Image processing Signal processing with an image as an input and an image or a set of features as output. Definitions Image Domain In the discrete case
5
5 Medical Imaging, SS-2010 Mohammad Dawood Classical methods of image processing include Grayscale transformations Color spaces Filtering Edge detection Morphological operations
6
6 Medical Imaging, SS-2010 Mohammad Dawood Grayscale transformations The human eye can distinguish between different colors with estimates ranging from 100,000 to 10 million!
7
7 Medical Imaging, SS-2010 Mohammad Dawood Michelson contrast : Weber contrast:
8
8 Medical Imaging, SS-2010 Mohammad Dawood Grayscale Transforms
9
9 Medical Imaging, SS-2010 Mohammad Dawood Grayscale transformations Three of the most common grayscale transforms are: 1.Linear 2.Logarithmic 3.Power law Point operations
10
10 Medical Imaging, SS-2010 Mohammad Dawood Linear color domain transform X-Ray Mammogram
11
11 Medical Imaging, SS-2010 Mohammad Dawood Power law MRI of Spinal cord
12
12 Medical Imaging, SS-2010 Mohammad Dawood Power law CT of Head
13
13 Medical Imaging, SS-2010 Mohammad Dawood Histogram Histogram function: Probability function: Cumulative histogram:
14
14 Medical Imaging, SS-2010 Mohammad Dawood Histogram Equalization MRI of Spinal cord
15
15 Medical Imaging, SS-2010 Mohammad Dawood Histogram equalization Mammograms
16
16 Medical Imaging, SS-2010 Mohammad Dawood Adaptive/Local Histogram Equalization
17
17 Medical Imaging, SS-2010 Mohammad Dawood Local Histogram Equalization
18
18 Medical Imaging, SS-2010 Mohammad Dawood Use of color spaces
19
19 Medical Imaging, SS-2010 Mohammad Dawood Use of different color spaces The continuous spectrum visible to human eyes
20
20 Medical Imaging, SS-2010 Mohammad Dawood Use of different color spaces RGB (Red, Green, Blue)
21
21 Medical Imaging, SS-2010 Mohammad Dawood Use of different color spaces RGB (Red Green Blue) Cardiac PET
22
22 Medical Imaging, SS-2010 Mohammad Dawood Use of different color spaces HSV (Hue, Saturation, Value)
23
23 Medical Imaging, SS-2010 Mohammad Dawood Use of different color spaces HSV (Hue, Saturation, Value) S=1, V=1 V=1 S=1 Cardiac PET
24
24 Medical Imaging, SS-2010 Mohammad Dawood Using different spectrums Cardiac PET
25
25 Medical Imaging, SS-2010 Mohammad Dawood Fourier Transform Euler’s formula: Fourier transform: Inverse Fourier transform:
26
26 Medical Imaging, SS-2010 Mohammad Dawood Fourier Transform Respiratory signal
27
27 Medical Imaging, SS-2010 Mohammad Dawood
28
28 Medical Imaging, SS-2010 Mohammad Dawood Fourier Transform Convolution theorm
29
29 Medical Imaging, SS-2010 Mohammad Dawood Spatial filtering
30
30 Medical Imaging, SS-2010 Mohammad Dawood Spatial connectivity 2D - 4 connectivity - 8 connectivity 3D - 6 connectivity - 18 connectivity - 26 connectivity
31
31 Medical Imaging, SS-2010 Mohammad Dawood Spatial filtering (local operators) Filters are used in image processing for various purposes e.g. noise reduction, edge detection, pattern recognition. 111 111 111 073-23 835-6 40374 01-50-3 7146-8 f h f* (0*1+7*1+3*1-1*1+8*1+3*1+4*1+0*1+3)*1/9 = 3 073-23 335-6 40374 01-50-3 7146-8 * 1/9 Applied only to red cell
32
32 Medical Imaging, SS-2010 Mohammad Dawood Noise reduction Averaging filter * *1/9= 33330 35330 33330 00000 00000 111 111 111 33330 33.2330 33330 0110.70 00000 Cardiac PET, averaging with 5x5 Applied only to red cells
33
33 Medical Imaging, SS-2010 Mohammad Dawood Median filter Median = Middle value of the set Example - givenS = {1, 5, 2, 0, -3, 8, 0} - sort S = {-3, 0, 0, 1, 2, 5, 8} median(S)= 1 What happens if |s| is even? - givenS = {1, 5, 2, 0, -3, 8, 0, -5} - sort S = {-3, -5, 0, 0, 1, 2, 5, 8} median(S)= 0.5
34
34 Medical Imaging, SS-2010 Mohammad Dawood Noise reduction Median filter * median filter = 33330 35330 33330 00000 00000 33330 33330 33330 00000 00000 Applied only to red cells
35
35 Medical Imaging, SS-2010 Mohammad Dawood Noise reduction Gaussian filter Gauss function is defined as:
36
36 Medical Imaging, SS-2010 Mohammad Dawood OriginalAveraging (5x5) Median(5x5) Gaussian (5x5) Noise reduction Comparison
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.