Topics of lessons and practical exercises
1. Basics of the medical image data processing in the SW MATLAB and Simulink, introduction to the imaging process, parameters of the exposition, photometric and radiometric parameters and definition of elementary unit of the 2D and 3D image.
2. Basic techniques for adjustment and representation of the digital image: discretization, mathematical process of the image signal evaluation of the imaging quality, histogram, models of entropy, color modulations and basic models of the image representation.
3. Brightness transformations: basic types and mathematical models for the brightness transformations, and contrast transformations. Application of the brightness transformations for optimization of the brightness characteristics of the medical image objects in a context of the image preprocessing.
4. Geometric transformations: basic types of the transformations, algorithms for rotation and the image translation, affine transformation, algorithms for the image interpolation, RoI, and VoI definition.
5. Spatial image analysis: mathematical description of the image convolution for the image filtration, definition of the average and median filter in the spatial area, application of the filtration procedures in the spatial area on the medical image data.
6. Frequency image analysis: representation of the spatial image frequencies, 2D Fourier transformation, algorithms for the FFT, filter proposal in the frequency domain, and application of the filtration procedures in the frequency domain on the medical image data.
7. Analysis of the image noise: the noise mathematical models, noise parameters, selected implementation of the image noise on the CT and MR data, and analysis of the image noise evaluation.
8. Edge detection: definition of the edge points, image edge boundaries, basic models of the image edge, and basic operators for the edge detection in the medical image data.
9. Detection of object in image: image segmentation based on the histogram thresholding, fuzzy thresholding, and algorithms for the regional image segmentation.
10. Iterative segmentation methods: image boundaries detection on the base of the active contours and level sets, analysis of the basic algorithms and parameters in an application of selected objects in the medical images.
11. Image classification: principles of the data classification, basic models for the medical image data classification, and image features extraction.
12. Methods of the artificial intelligence: model of the neuron, basic neural networks, classification and segmentation of the image on the base of the neural network, and deep learning.
13. Cluster analysis: analysis of the K means and FCM, application of methods for the image segmentation and classification.
14. Basic reconstruction techniques for the CT and MR: the sinogram analysis, back projection, filtered back projection, iterative CT reconstruction, k-space, and MR image signal.
Practival exercises will be done in MATLAB.
1. Basics of the medical image data processing in the SW MATLAB and Simulink, introduction to the imaging process, parameters of the exposition, photometric and radiometric parameters and definition of elementary unit of the 2D and 3D image.
2. Basic techniques for adjustment and representation of the digital image: discretization, mathematical process of the image signal evaluation of the imaging quality, histogram, models of entropy, color modulations and basic models of the image representation.
3. Brightness transformations: basic types and mathematical models for the brightness transformations, and contrast transformations. Application of the brightness transformations for optimization of the brightness characteristics of the medical image objects in a context of the image preprocessing.
4. Geometric transformations: basic types of the transformations, algorithms for rotation and the image translation, affine transformation, algorithms for the image interpolation, RoI, and VoI definition.
5. Spatial image analysis: mathematical description of the image convolution for the image filtration, definition of the average and median filter in the spatial area, application of the filtration procedures in the spatial area on the medical image data.
6. Frequency image analysis: representation of the spatial image frequencies, 2D Fourier transformation, algorithms for the FFT, filter proposal in the frequency domain, and application of the filtration procedures in the frequency domain on the medical image data.
7. Analysis of the image noise: the noise mathematical models, noise parameters, selected implementation of the image noise on the CT and MR data, and analysis of the image noise evaluation.
8. Edge detection: definition of the edge points, image edge boundaries, basic models of the image edge, and basic operators for the edge detection in the medical image data.
9. Detection of object in image: image segmentation based on the histogram thresholding, fuzzy thresholding, and algorithms for the regional image segmentation.
10. Iterative segmentation methods: image boundaries detection on the base of the active contours and level sets, analysis of the basic algorithms and parameters in an application of selected objects in the medical images.
11. Image classification: principles of the data classification, basic models for the medical image data classification, and image features extraction.
12. Methods of the artificial intelligence: model of the neuron, basic neural networks, classification and segmentation of the image on the base of the neural network, and deep learning.
13. Cluster analysis: analysis of the K means and FCM, application of methods for the image segmentation and classification.
14. Basic reconstruction techniques for the CT and MR: the sinogram analysis, back projection, filtered back projection, iterative CT reconstruction, k-space, and MR image signal.
Practival exercises will be done in MATLAB.