|
|
Automatic detection of neural fibers losses
Václavek, Martin ; Jiřík, Radovan (referee) ; Kolář, Radim (advisor)
This work is focused on detection of loss in nerve fibre layer on colour pictures of retina, witch are makes by fundus camera. It describe every simple objects of retina, optic nerve head, macula lutea and vascular bed. It detect optic nerve head and his near area, witch is general for detection of breakdownds. It use several metodes of picture adjusting for picture elaboration and objects detection (segmentation, thresholding, enhancement, hough transformation ). The detection of loss in nerve fibre layer is based on comparing of statistic parameters ( average, standart deviation, skewness coefficient and kurtosis coefficient histogram, entropy ) in choosed areas with and withou destruction of nerve layers. Vascular bed have badwatsh on results, cause of this we using hand choosing of essay.
|
|
| |
|
| |
|
|
Advanced processing of ophthalmologic videosequences of retinal images
Říha, Pavel ; Odstrčilík, Jan (referee) ; Jan, Jiří (advisor)
The diploma thesis deals with registration and analysis of images from the experimental low-cost fundus camera that reaches a low SNR (around 10 dB) and low temporal and spatial resolution. The aim of the diploma tesis is to explore the possibilities of digital processing leading to the creation of a videosequence that has real benefits for medical diagnostics. The well-known program elastix is used for registration. Preprocessing filters and interpolation are implemented in Matlab. The program provides a wide range of setting options, out of which many combinations were tested and evaluated. To assess the accuracy achieved, spatial variations in the detected motion of blood-vessels are evaluated. Best results with a precision below 0.3 px were achieved by using a band-pass filter, a~suitably sized mask, rigid registration and a metric of the mutual information. Test sequences were registered precisely enough both for visual assessment and basic computational analysis. Registered sequences and the developed application that both can be used in the further development of the experimental camera are the main contributions of the diploma thesis.
|
|
|
Penetration tests and network device vulnerability scanning
Gregr, Filip ; Martinásek, Zdeněk (referee) ; Hajný, Jan (advisor)
This thesis is dealing with penetration tests and network device vulnerability assessment. Theoretical part includes analysis of this issue and description of general methodology of performing penetration tests. Thesis provides basic overview of requirements of international norms ISO 27000 and PCI DSS. In another part the software for Nessus vulnerability scanning and Linux Kali distrubution is introduced. Practical part of thesis includes several aims. The first is a comparsion of five vulnerability scanners in a created test network. Chosen tools for this purpose are Nessus, OpenVAS, Retina Community, Nexpose Community and GFI LanGuard. Network scan is performed with each of~these tools. Penetration test using the tools available in Kali Linux is then executed in this network. Procedure of exploiting two selected vulnerabilities is created as a laboratory exercise. The last aim of thesis is testing the web server protection against flood attacks SYN flood, UDP flood and slow attack Slowloris. Scripts for flooding were written in Python language.
|
|
|
Optic disc segmentation in retinal images
Vymazal, Bronislav ; Odstrčilík, Jan (referee) ; Kolář, Radim (advisor)
Cílem této práce bylo vytvořit kompaktní algoritmus sloužící k lokalizaci, segmentaci a sledování optického disku v sekvencích obrazů sítnice. Pro účely lokalizace byla použita nová metoda založena na „fast radial transform“. Segmentace optického disku je založena na klasické metodě Chan-Vese, která byla rozšířena o další prvky a implementována v lokalizované podobě, která umožňuje lépe segmentovat obrazy s vysokou mírou nehomogenity. Pro sledování optického disku v sekvencích obrazů byl využit optický tok založený na Lucas-Kanade algoritmu. Všechny metody byly vyhodnoceny na dvou databázích obrazů s odlišnými charakteristikami. První databází je klasická databáze s vysokým rozlišením. Druhou je pak databáze s nízkým rozlišením a vysokou mírou šumu. Všechny výsledky jsou pak porovnány s referenčními hodnotami a vyhodnoceny.
|
|
|
Analysis of retinal vessel pulsation
Holásková, Anna ; Mézl, Martin (referee) ; Odstrčilík, Jan (advisor)
The content of this work is the analysis of retinal vessels pulsation of video sequences acquired by experimental fundus camera based on measuring the brightness profile of the vessel. The first level of analysis in this work is the segmentation of blood vessels and diameter measurement of blood vessels during the sequence. The work contains research methods dealing with the diameter measurement and evaluation of pulsation and analysis segmentation methods using for analysing the vasculature of the retina. From these methods, a vessel tracking method was selected. In segmented video sequences is on the ground of intensity profiles analysed vessel pulsation. Analysis is also made on original dataset and results are discussed considering the frequency characteristic.
|
|
|
A Classification Methods for Retinal Nerve Fibre Layer Analysis
Zapletal, Petr ; Kolář, Radim (referee) ; Odstrčilík, Jan (advisor)
This thesis is deal with classification for retinal nerve fibre layer. Texture features from six texture analysis methods are used for classification. All methods calculate feature vector from inputs images. This feature vector is characterized for every cluster (class). Classification is realized by three supervised learning algorithms and one unsupervised learning algorithm. The first testing algorithm is called Ho-Kashyap. The next is Bayess classifier NDDF (Normal Density Discriminant Function). The third is the Nearest Neighbor algorithm k-NN and the last tested classifier is algorithm K-means, which belongs to clustering. For better compactness of this thesis, three methods for selection of training patterns in supervised learning algorithms are implemented. The methods are based on Repeated Random Subsampling Cross Validation, K-Fold Cross Validation and Leave One Out Cross Validation algorithms. All algorithms are quantitatively compared in the sense of classication error evaluation.
|
|
|
Texture Analysis of Ophthalmologic Images
Kaňka, Jan ; Odstrčilík, Jan (referee) ; Jan, Jiří (advisor)
This thesis is concerned with creating of software for textural analysis of retinal images by statistic method called co-occurrence matrices as possible alternative method to detection of lesion of retina by the glaucoma diseases. The Glaucoma diseases without well-timed diagnostics and consequential treatment leads to blindness. The retinal images captured by fundus camera are common, easily processable and modern devices are able to make images of 10 Mpix resolution and bigger, what specifies outputs of analytic software. Method of co-occurrence analysis is simple and effective statistic. But computing demandingness, showing up with growing objective quality, comming up as disadvantage.
|
|
|
Classification of arteries and veins in retinal image data
Černohorská, Lucie ; Jakubíček, Roman (referee) ; Kolář, Radim (advisor)
This master's thesis deals with the classification of the retinal blood vessels in retinal image data. The thesis contains a description of anatomy of the human eye with focus on the blood circulation, and imaging and diagnostic methods of the retina are briefly mentioned further. The thesis also summarizes methods of the blood circulation classification with emphasis on the deep learning. The practical section was implemented in Python programming language and describes the pre-processing of the data with determination of AV ratio. Based on a literature search, the U-net architecture was chosen for the classification of the retinal blood vessels. The architecture was modified using the open-source Keras library and tested on images from the experimental video-ophthalmoscope. The modified architecture was initially used for classification of vessels into the corresponding classes and because of unsatisfying results was modified another architecture segmenting retinal vessels, arteries or veins and a proposition of a method of the blood vessels classification.
|
guest ::
