|
|
Classification of the vascular tree in fundus images
Tebenkova, Iuliia ; Kolář, Radim (referee) ; Odstrčilík, Jan (advisor)
Retinal image analysis plays a very important role, as human gets around 90% of environment information with the help of eyes. Automation of process of retinal image analysis promotes to improve the efficiency of retinal medical examinations. The following thesis is dedicated to automatic classification methods of retinal vascular system images obtained from a digital fundus camera. Vessel classification method using classifier on the base of neural networks, which is trained and then tested on the retinal vessel segments, is investigated and implemented. In this thesis anatomical retinal survey, properties of image data from digital fundus camera and retinal image classification methods are briefly described. The last chapter is devoted to the evaluation of efficiency of retinal vessel classification with automatic methods.
|
|
|
Analysis of Retinal Image Data to Support Glaucoma Diagnosis
Odstrčilík, Jan ; Kybic, Jan (referee) ; Matula,, Petr (referee) ; Kolář, Radim (advisor)
Fundus kamera je široce dostupné zobrazovací zařízení, které umožňuje relativně rychlé a nenákladné vyšetření zadního segmentu oka – sítnice. Z těchto důvodů se mnoho výzkumných pracovišť zaměřuje právě na vývoj automatických metod diagnostiky nemocí sítnice s využitím fundus fotografií. Tato dizertační práce analyzuje současný stav vědeckého poznání v oblasti diagnostiky glaukomu s využitím fundus kamery a navrhuje novou metodiku hodnocení vrstvy nervových vláken (VNV) na sítnici pomocí texturní analýzy. Spolu s touto metodikou je navržena metoda segmentace cévního řečiště sítnice, jakožto další hodnotný příspěvek k současnému stavu řešené problematiky. Segmentace cévního řečiště rovněž slouží jako nezbytný krok předcházející analýzu VNV. Vedle toho práce publikuje novou volně dostupnou databázi snímků sítnice se zlatými standardy pro účely hodnocení automatických metod segmentace cévního řečiště.
|
|
|
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.
|
|
|
Analysis of fundus images aimed to localize pathological areas
Hartlová, Marie ; Kolář, Radim (referee) ; Odstrčilík, Jan (advisor)
Diabetic retinopathy is a serious eye complication of diabetes mellitus and one of the major causes of blindness in the world. This thesis deals with detection of neovascularizations, which is the first manifestation of diabetic retinopathy in the retina. In summary, in this thesis describe the properties image data from digital fundus camera, image segmentation methods, methods for automatic blood vessels segmentation and detection of neovaskularizations. This information are used to create own method to detect neovaskularization.
|
|
|
Blood vessel segmentation in fundus images using classification methods
Šťastný, Pavel ; Štohanzlová, Petra (referee) ; Odstrčilík, Jan (advisor)
Segmentation blood vessel the local images of retinal is very important for evaluation and for diagnostics eye’s disease, especially diabetic retinopathy and glaucoma. This bachelor’s thesis is deal with segmentation blood vessel by classification methods. I used simple neural network as a classifier. First of all I taught her by delta rule and then I used matched filtering on the prepare image. At the end I compared all information with gold standard. Average va-lues from score for healthy images were sensitivity 0,7717, specificity 0,9571 and accuracy score 0,9225.
|
|
|
Analysis of Colour Retinal Images Aimed at Segmentation of Vessel Structures
Odstrčilík, Jan ; Jiřík, Radovan (referee) ; Jan, Jiří (advisor)
Segmentation of vessel structure is an important phase in analysis of retinal images. The resulting vessel system description may be important for diagnostic of many eye and cardiovascular diseases. A method for automatic segmentation of the vessel structure in colour retinal images is presented in the thesis. The method utilises 2D matched filtering to detect presence of short linear vessel sections of a particular thickness and orientation. The approach correlates the local image areas with a 2D masks based on a typical brightness profile perpendicular to vessels of a particular width. Three different approximated profiles are used and corresponding matched filters are designed for: thin, medium and thick vessels. The evaluation of typical vessel profiles and filter design are described in chapter 3 and chapter 4. The parametric images obtained by convolution of the image with the masks are then thresholded in order to obtain binary representation of vessel structure. The three binary representations are consequently combined to provide the best available rough vessel map, which is finalised by complementing the obviously missing vessel sections and cleaning the disconnected fractional artefacts. The thresholding algorithm and final steps of processing are mentioned in chapter 5 and chapter 6. The method has been implemented by computer and the program for automatic vessel segmentation has been developed using database of real retinal images. The efficiency of the method has been finally evaluated on images from the standard database DRIVE.
|
|
|
Blood vessel segmentation in fundus images using mathematical morphology
Stonawski, Stanislav ; Jan, Jiří (referee) ; Odstrčilík, Jan (advisor)
Segmentation of retinal blood vessel is an important step in the fundus image analysis. The resulting image can be used to diagnose ophthalmic or cardiovascular diseases. The aim of this thesis is to search for possibilities of high resolution eye fundus image processing while using mathematical morphology methods. This should lead to the creation of an algorithm capable of blood vessel segmentation. The thesis provides information on fundus camera, image, blood vessel properties and mathematical morphology filtering methods. The created algorithms and the proposed method based on them are presented, including their performance analysis based on the HRF database processing.
|
|
|
Retinal images in biometry
Bujnošková, Eva ; Drahanský, Martin (referee) ; Kolář, Radim (advisor)
Retinal recognition is very efficient and almost non-fallible tool for persons' identification, thanks its advantages it can be used in cases when high security is needed. Process of the identification comes from successful vessel extraction and the transfer to binary image. After that this is used to look for the vessel bifurcations with help of skeletonization which is one of the operations of mathematical morphology. The parameter of the detection of bifurcations isn't enough therefore there are other information completed - thickness and the direction of vessel in the surroundings of known crossing. The best correlation between the parameters and the images in database is searched, than alignment is made, and with the certain probability the closest image is chosen to be proclaimed as the match. The solution uses also the second method to image processing - the method using image translation and evaluation of minimal distances between found bifurcations.
|
|
|
Arteries and veins segmentation in retinal images
Šumberová, Dagmara ; Odstrčilík, Jan (referee) ; Kolář, Radim (advisor)
This thesis deals with the necessity of vascular segmentation in digital image analysis of the retina and thein subsequent classification.It briefly describes the segmentation of vessels using matched filtering. Next part of this thesis is focused on processing of the retinal images, their manual segmentation and subsequent testing to determine the best discriminating parameters for classification. Finally there is an evaluation of measured parameters and the propřed extension of this method.
|
|
|
Evaluation of Automatic Vessel Tree Segmentation Algorithms
Svoboda, Ondřej ; Jan, Jiří (referee) ; Odstrčilík, Jan (advisor)
Segmentation of the vasculature is an important step in the process of the retinal image analysis. The results of the analysis can be used to diagnose several eye and cardiovascular diseases. This work deals with the creation of gold standard database of high resolution retinal images and their use in evaluating the success of vascular automatic segmentation methods. The aim is to create the application, which will online evaluate the success of the automatic vessel segmentation methods. In brief, this work describes the characteristics of image data from digital fundus camera, the method of image segmentation and automatic segmentation methods of blood vessels. Furthermore, this work describes the gold standard, the databases of gold standards and ultimately the properties of the new database and the reason for HRF (High Resolution Fundus Images). The last chapter deals with methods of evaluating the success of vascular automatic detection methods and application development for this assessment.
|
guest ::
