|
|
Thrombi detection in main brain arteries in CT image data
Líška, Martin ; Nemček, Jakub (referee) ; Chmelík, Jiří (advisor)
The master’s thesis deals with automatic preprocessing, segmentation and consecutive analysis of volume data of anonymized patient CTA acquisitions with an indication of stroke. Preprocessing of volume data is an essential step for proper vascular tree segmentation and analysis. The region growing method was used to segment the vascular tree of the brain. After extracting the vascular tree, the labeling of individual branches was applied in the algorithm and the appropriate features were extracted. The analysis examined the features of vessel lengths, their diameter and local brightness profiles, which are important indicators of possible stenosis or occlusion of the main vessels of the brain. The output of the algorithm are various modalities of diagnostic, assisted visualizations of the segmented vascular tree. The segmentation and analysis algorithm of cerebrovascular system was created in the MATLAB programming environment.
|
|
|
Ultrasound Image Sequence Segmentation
Gallo, Vladimír ; Walek, Petr (referee) ; Mézl, Martin (advisor)
This paper presents basic principles of ultrasonography, review of different modes of medical ultrasound imaging, principle of contrast-enhanced ultrasonography and review of basic techniques of image segmentation. The individual methods based on edge detection and region growing were implemented in Matlab. The performance of algorithms were tested in each category using synthetic and phantom image data.
|
|
|
Image segmentation of ultrasound images
Schwarzerová, Jana ; Odstrčilík, Jan (referee) ; Mézl, Martin (advisor)
This bachelor’s thesis deals with basic description of ultrasonography, principles of contrast-enhanced imaging and application of segmentation methods in ultrasound problematics. Some individual methods were implemented in Matlab, version R2015b. Algorithms were tested on synthetic images data, on ultrasound phantom images data and on real ultrasound images. Then the thesis was extended by ultrasound sequences segmentation.
|
|
|
Thrombi detection in main brain arteries in CT image data
Líška, Martin ; Nemček, Jakub (referee) ; Chmelík, Jiří (advisor)
The master’s thesis deals with automatic preprocessing, segmentation and consecutive analysis of volume data of anonymized patient CTA acquisitions with an indication of stroke. Preprocessing of volume data is an essential step for proper vascular tree segmentation and analysis. The region growing method was used to segment the vascular tree of the brain. After extracting the vascular tree, the labeling of individual branches was applied in the algorithm and the appropriate features were extracted. The analysis examined the features of vessel lengths, their diameter and local brightness profiles, which are important indicators of possible stenosis or occlusion of the main vessels of the brain. The output of the algorithm are various modalities of diagnostic, assisted visualizations of the segmented vascular tree. The segmentation and analysis algorithm of cerebrovascular system was created in the MATLAB programming environment.
|
|
|
Image segmentation of ultrasound images
Schwarzerová, Jana ; Odstrčilík, Jan (referee) ; Mézl, Martin (advisor)
This bachelor’s thesis deals with basic description of ultrasonography, principles of contrast-enhanced imaging and application of segmentation methods in ultrasound problematics. Some individual methods were implemented in Matlab, version R2015b. Algorithms were tested on synthetic images data, on ultrasound phantom images data and on real ultrasound images. Then the thesis was extended by ultrasound sequences segmentation.
|
|
|
Ultrasound Image Sequence Segmentation
Gallo, Vladimír ; Walek, Petr (referee) ; Mézl, Martin (advisor)
This paper presents basic principles of ultrasonography, review of different modes of medical ultrasound imaging, principle of contrast-enhanced ultrasonography and review of basic techniques of image segmentation. The individual methods based on edge detection and region growing were implemented in Matlab. The performance of algorithms were tested in each category using synthetic and phantom image data.
|
guest ::
