|
|
Preprocessing of retinal images aimed at support diagnosis of glaucoma
Holásková, Anna ; Walek, Petr (referee) ; Odstrčilík, Jan (advisor)
Preprocessing of retinal images can serve as a first phase of the further image analysis or the first step preceding diagnosing of various eye diseases. The preprocessing thus represents methods of image adjustments that can improve visual characteristics of fundus images. These methods mainly include the removal of noise generated during data acquisition, contrast and brightness transformations, edge detection and thresholding. This work handles with the basic methods of image preprocessing and specific methods of preprocessing of retinal images. The preprocessing includes global illumination correction, high-pass and homomorphic filtering and adaptive enhancement of the images. Manual methods for fundus image preprocessing that are usually based on the doctor's experience can be used as well. Hence, a procedure for enhancement of retinal images using Adobe Photoshop is mentioned in this work too. Three methods for preprocessing of fundus images were selected and implemented in MATLAB programming software. These methods include homomorphic filtering, CLAHE (Contrast Limited Adaptive Histogram Equalization) and adaptive enhancement. Experimental program functions were created and tested on the available image data. Results of the selected methods are mentioned in the conclusion section. Instructions for use of implemented functions are in appendix.
|
|
|
X-ray computed tomography of mouse embryo
Šejnohová, Marie ; Walek, Petr (referee) ; Kolář, Radim (advisor)
The aim of this semestral thesis is to compare the possibilities of available micro-CT systems. Theoretic part of this thesis there deals with possibilities of staining soft tissues and embryos because of enhancement the contrast of micro-CT images. Here follows a description of sources X-ray and detectors of available micro-CT systems. In practice there was realized the staining of embryo in cooperation with Department of histology and embryology in Brno. Then followed a measuring on FSI in Brno, ČVUT in Prague and synchrotron Elettra in Italy. In semestral thesis are described of the thesis there are compared the micro-CT systems and results of measuring embryos by means of presented systems and results are compared.The best results were obtained on micro-CT in Brno, where X-ray tube and flat panel detector were used. This images were used for a segmentation of cartilage olfactory system by means of 3D region growing. From results they were created 3D models for comparison with a manually segmented model. A less accurate results were obtain with the semi-automatic segmentation but this method isn’t too time-consuming.
|
|
|
Segmentation of airways in CT data
Votoupal, Pavel ; Odstrčilík, Jan (referee) ; Walek, Petr (advisor)
This thesis deals with the segmentation of lung parenchyma and extraction of airways tree from three dimensional CT scans. The external mask of the lungs is created and subsequently used to ease the process of airway segmentation. In this work, some published methods for airways segmentation are described with focus on one, which is described more in detail and also implemented in MATLAB. The proposed approach is based on morphological grayscale reconstruction. Method is tested on the real patient CT scans and finally, the results are discussed.
|
|
|
Blind Image Deconvolution in STEM mode of Electron Microscope
Valterová, Eva ; Walek, Petr (referee) ; Potočňák, Tomáš (advisor)
Slepá dekonvoluce je metoda, při které je rozptylová funkce a skutečný obraz rekonstruován zároveň. Cílem této práce je představit různé metody slepé dekonvoluce a najít optimální metodu rekonstrukce původního obrazu a rozptylové funkce. Jako nejvhodnější metoda slepé dekonvoluce byl zvolen algoritmus střídavé minimalizace, který byl upraven a testován. Vlastnosti navrženého algoritmu byly testovány na uměle degradovaných datech a na reálných datech pořízených skenovacím transmisním elektronovým mikroskopem. Účinnost algoritmu byla hodnocena hned několika hodnotícími kritérii. Byla zjištěna omezení algoritmu a tím specifikováno jeho využití.
|
|
|
Contour Shape Classification for Detection of Mis-Segmented bones in CT Data
Janovič, Tomáš ; Jan, Jiří (referee) ; Walek, Petr (advisor)
The thesis discusses the possibilities of using contour shape classification for detection of mis-segmented bones in computed tomography (CT) data. In the first part there are presented published methods and algorithms which deal with the segmentation of bone structures in CT data. Then segmentation of cortical bones is implemented by a simple thresholding with global threshold. The threshold is determined by the optimized fitting of a selected type probability distribution to the histogram. Subsequently, the thesis describes some important shape descriptors that can quantitatively describe the shapes of objects in the image. Further, the contour extraction is implemented and a suitable shape descriptor, cumulative angular function, is applied. Finally, the points which can potentially indicate mis-segmented bones are detected by using continuous wavelet transform. The proposed technique is tested on the real CT data.
|
|
|
Camera based eye tracking
Otáhal, Miroslav ; Walek, Petr (referee) ; Janoušek, Oto (advisor)
The aim of this master thesis is to understand problematic of eyes movement tracking using webcam. In individual chapters there are introduced basic approaches of eyes movement tracking, based on this method we can get the position of eye pupil and identify where a person looks. The part of this work is program in Matlab, which using the method of infrared detection follow the position of eye pupil and transfer this movements to the movements on the computer screen. Using this program it was tested several volunteers and the results of detection were transferred to the visual form. As part of this program it was created template for assessment of accuracy of used method. At the end of work are discussed achieved results.
|
|
| |
|
| |
|
|
ECG noise generator
Siegel, Jan ; Walek, Petr (referee) ; Smital, Lukáš (advisor)
The signal of ECG is interfered by the noise of different origin.. Most common are powerline interferences, baseline wandering, electromyographic and impuls noises. Such kind of noise is undesirable in signal since they decrease diagnostic yield in ECG. For effective removal of noise, we must detect the type of interference consequently use its theorists properties for specific filtration. The aim of this work is to creat a technical tool - ECG noise generator. ECG noise generator is being used for simulation of signal with defined parameters and type of noise. This noise generator can be employed for the verification of techniques designed for the elimination of interferences or the identification of the noise present in the unknown signal.
|
|
|
Segmentation of hippocampus in MRI data
Kodym, Oldřich ; Chmelík, Jiří (referee) ; Walek, Petr (advisor)
The thesis deals with application of graph-based methods in segmentation of low contrast image data, specifically hippocampus segmentation from magnetic resonance data. Firstly, basics and terminology of graph theory is introduced. Next, minimum graph cut method is explained along with algorithms capable of finding this cut. After that comes the description of its implementation for 2D and 3D image data segmentation. Method was tested on sample data and then implemented as a 3D Slicer software module. Here the method was tested on the hipocampus data of healthy patients as well as patients suffering from Alzheimer’s disease. Most common problems occuring during the segmentation were forshadowed as well as possible ways to solve them.
|
guest ::
