|
|
Analysis of retinal nerve fiber layer for diagnosis of glaucoma
Vodáková, Martina ; Malínský, Miloš (referee) ; Odstrčilík, Jan (advisor)
The master thesis is focused on creating a methodology for quantification of the nerve fiber layer on photographs of the retina. The introductory part of the text presents a medical motivation of the thesis and mentions several studies dealing with this issue. Furthermore, the work describes available textural features and compares their ability to quantify the thickness of the nerve fiber layer. Based on the described knowledge, the methodology to make different regression models enabling prediction of the retinal nerve fiber layer thickness was developed. Then, the methodology was tested on the available image dataset. The results showed, that the outputs of regression models achieve a high correlation between the predicted output and the retinal nerve fiber layer thickness measured by optical coherence tomography. The conclusion discusses an usability of the applied solution.
|
|
|
Advanced retinal vessel segmentation methods in colour fundus images
Svoboda, Ondřej ; Jan, Jiří (referee) ; Odstrčilík, Jan (advisor)
Segmentation of vasculature tree is an important step of the process of image processing. There are many methods of automatic blood vessel segmentation. These methods are based on matched filters, pattern recognition or image classification. Use of automatic retinal image processing greatly simplifies and accelerates retinal images diagnosis. The aim of the automatic image segmentation algorithms is thresholding. This work primarily deals with retinal image thresholding. We discuss a few works using local and global image thresholding and supervised image classification to segmentation of blood tree from retinal images. Subsequently is to set of results from two different methods used image classification and discuss effectiveness of the vessel segmentation. Use image classification instead of global thresholding changed statistics of first method on healthy part of HRF. Sensitivity and accuracy decreased to 62,32 %, respectively 94,99 %. Specificity increased to 95,75 %. Second method achieved sensitivity 69.24 %, specificity 98.86% and 95.29 % accuracy. Combining the results of both methods achieved sensitivity up to72.48%, specificity to 98.59% and the accuracy to 95.75%. This confirmed the assumption that the classifier will achieve better results. At the same time, was shown that extend the feature vector combining the results from both methods have increased sensitivity, specificity and accuracy.
|
|
|
Optic disc detection in retinal images
Jalůvková, Lenka ; Odstrčilík, Jan (referee) ; Kolář, Radim (advisor)
The bachelor thesis is focused on a detection of optic disc in the retinal images in order to propose and compare several existing methods. The detection is implemented as the Gaussian filter, matched filter and is done by vascular structure information. The DIARETDB1 database is used for testing. The best results have been achieved using Gaussian filter and detection by vascular structure information with success rate 81%. The description and comparison of all the algorithms can be found in this thesis.
|
|
|
Extraction of texture features aimed to detect glaucoma defects
Daněk, Daniel ; Kolář, Radim (referee) ; Odstrčilík, Jan (advisor)
The thesis deals with an automatic method of texture analysis using Markov random fields texture modeling. The main aim of this work is to find out relevant textural features, which can be used for appropriate classification of the degree of retinal nerve fiber layer loss. The model of Markovian statistic uses a circular symmetric neighborhood structure and a least square error estimation of the model's parameter. Obtained textural features were quantitatively evaluated using correlation analysis. The results show, that there is a significant correlation between proposed textural features and RNFL thickness measured by OCT. Thus, the features can potentially serve for glaucoma diagnosis.
|
|
|
Analysis of Ophthalmological Images Aimed to Diagnosis of Glaucoma
Vodáková, Martina ; Kolář, Radim (referee) ; Odstrčilík, Jan (advisor)
Bachelor thesis is focused on fundamental texture analysis of high-resolution fundus images aimed to subjectively and quantitatively describe properties of texture formed by the retinal nerve fiber layer. An area of interest was predefined in the form of ten sectors on each fundus image. The correlation between results of subjective and quantitative evaluation of the texture was monitored in each sector. The results show that proposed fundamental texture features are closely related to the subjective textural properties obtained from visual appearance of the retinal nerve fiber layer. The last step compares results from fundamental texture analysis with quantitative measurement of the retinal nerve fiber layer thickness provided by Optical Coherence Tomography.
|
|
|
Blood vessel segmentation in retinal image data
Vančurová, Johana ; Mézl, Martin (referee) ; Odstrčilík, Jan (advisor)
This master´s thesis deals with blood vessel segmentation in retinal image data. The theoretical part is focused on the basic description of anatomy and physiology of the eye and methods of observing the back of the eye. This thesis also describes the principles of classical and convolutional neural networks and segmentation techniques that are used to segment blood vessel in retinal images. In the practical part, a segmentation method using convolutional neural network U-net is implemented. This neural network is trained on the three datasets. Two datasets include images from experimental video ophthalmoscope. Because it impossible to compare the results of these two datasets with any other methods of retinal blood vessel segmentation, U-net is trained on other dataset that is HRF database. This dataset includes fundus images. The results of testing on this dataset serves for comparing results with other methods of retinal blood vessel segmentation.
|
|
|
Blood vessel segmentation in retinal image data
Vančurová, Johana ; Mézl, Martin (referee) ; Odstrčilík, Jan (advisor)
This master´s thesis deals with blood vessel segmentation in retinal image data. The theoretical part is focused on the basic description of anatomy and physiology of the eye and methods of observing the back of the eye. This thesis also describes the principles of classical and convolutional neural networks and segmentation techniques that are used to segment blood vessel in retinal images. In the practical part, a segmentation method using convolutional neural network U-net is implemented. This neural network is trained on the three datasets. Two datasets include images from experimental video ophthalmoscope. Because it impossible to compare the results of these two datasets with any other methods of retinal blood vessel segmentation, U-net is trained on other dataset that is HRF database. This dataset includes fundus images. The results of testing on this dataset serves for comparing results with other methods of retinal blood vessel segmentation.
|
|
|
Optic disc detection in video-sequences from experimental fundus camera
Daněk, Daniel ; Štohanzlová, Petra (referee) ; Odstrčilík, Jan (advisor)
This bachelor thesis deals with the analysis of images from experimental fundus camera, especially with structure of optic disc. The theoretical part describes major features of the human eye and principles of examination, especially examinations of fundus camera. This thesis discusses some methods of analysis and segmentation fundus images. The main work content is based on Hough transform and edge detection for optic disc localization. In the practical part of bachelor thesis we created Hough transform algorithm. Fundus images were tested with this algorithm method.
|
|
|
Extraction of texture features aimed to detect glaucoma defects
Daněk, Daniel ; Kolář, Radim (referee) ; Odstrčilík, Jan (advisor)
The thesis deals with an automatic method of texture analysis using Markov random fields texture modeling. The main aim of this work is to find out relevant textural features, which can be used for appropriate classification of the degree of retinal nerve fiber layer loss. The model of Markovian statistic uses a circular symmetric neighborhood structure and a least square error estimation of the model's parameter. Obtained textural features were quantitatively evaluated using correlation analysis. The results show, that there is a significant correlation between proposed textural features and RNFL thickness measured by OCT. Thus, the features can potentially serve for glaucoma diagnosis.
|
|
|
Optic disc detection in retinal images
Jalůvková, Lenka ; Odstrčilík, Jan (referee) ; Kolář, Radim (advisor)
The bachelor thesis is focused on a detection of optic disc in the retinal images in order to propose and compare several existing methods. The detection is implemented as the Gaussian filter, matched filter and is done by vascular structure information. The DIARETDB1 database is used for testing. The best results have been achieved using Gaussian filter and detection by vascular structure information with success rate 81%. The description and comparison of all the algorithms can be found in this thesis.
|
guest ::
