|
|
Segmentation of brain tumours in MRI images using deep learning
Ustsinau, Usevalad ; Odstrčilík, Jan (oponent) ; Chmelík, Jiří (vedoucí práce)
The following master's thesis paper equipped with a short description of CT scans and MR images and the main differences between them, explanation of the structure of convolutional neural networks and how they implemented into biomedical image analysis, besides it was taken a popular modification of U-Net and tested on two loss-functions. As far as segmentation quality plays a highly important role for doctors, in experiment part it was paid significant attention to training quality and prediction results of the model. The experiment has shown the effectiveness of the provided algorithm and performed 100 training cases with the following analysis through the similarity. The proposed outcome gives us certain ideas for future improving the quality of image segmentation via deep learning techniques.
|
|
|
Interaktivní segmentace medicínských obrazových dat
Olša, Martin ; Kršek, Přemysl (oponent) ; Španěl, Michal (vedoucí práce)
Tato práce se zabývá segmentací anatomických struktur v medicínských objemových datech pomocí metody fast level-set. Zvolená metoda reprezentuje uzavřený 3D povrch postupující v čase z počáteční pozice. Hlavním zaměřením této práce je implementace metody level-set a vytvoření interaktivního nástroje určeného na segmentaci 3D medicínských objemových dat využitím této metody. Nástroj je schopný interaktivně měnit parametry vývoje povrchu během samotného procesu segmentace. Díky povaze metody level-set, může být proces vývoje povrchu pozastaven v jakémkoli momentě, nebo sledovaný několik kroků vedoucích zpět a z této pozice může být restartován s úplně jinou konfigurací.
|
|
| |
|
|
Airway analysis of prematurely born babies based on X-ray CT and MRI scans
Lázňovský, Jakub ; Harabiš, Vratislav (oponent) ; Chmelík, Jiří (vedoucí práce)
The proposed Master’s thesis deals with the analysis and creation of airway models of premature babies. Firstly, the theoretical basis is discussed in the field of development of the respiratory system and the creation of airway models. Then the used imaging modalities are introduced, and methods for working with image data are described. The practical part of the thesis deals with the creation of airway models of three newborns. All of these models are based on clinical CT and MRI data of neonates born at 30 weeks of gestational age. In these created models, selected parameters related to the anatomical structure of the airways are further analysed. Based on the analysis of these parameters, a representative model corresponding to the airways of a newborn of a given gestational age was subsequently proposed.
|
|
|
Brain Tumor Detection and Segmentation in Multisequence MRI
Dvořák, Pavel ; Přibil, Jiří (oponent) ; Šprláková-Puková,, Andrea (oponent) ; Smékal, Zdeněk (vedoucí práce)
This work deals with the brain tumor detection and segmentation in multisequence MR images with particular focus on high- and low-grade gliomas. Three methods are propose for this purpose. The first method deals with the presence detection of brain tumor structures in axial and coronal slices. This method is based on multi-resolution symmetry analysis and it was tested for T1, T2, T1C and FLAIR images. The second method deals with extraction of the whole brain tumor region, including tumor core and edema, in FLAIR and T2 images and is suitable to extract the whole brain tumor region from both 2D and 3D. It also uses the symmetry analysis approach which is followed by automatic determination of the intensity threshold from the most asymmetric parts. The third method is based on local structure prediction and it is able to segment the whole tumor region as well as tumor core and active tumor. This method takes the advantage of a fact that most medical images feature a high similarity in intensities of nearby pixels and a strong correlation of intensity profiles across different image modalities. One way of dealing with -- and even exploiting -- this correlation is the use of local image patches. In the same way, there is a high correlation between nearby labels in image annotation, a feature that has been used in the ``local structure prediction'' of local label patches. Convolutional neural network is chosen as a learning algorithm, as it is known to be suited for dealing with correlation between features. All three methods were evaluated on a public data set of 254 multisequence MR volumes being able to reach comparable results to state-of-the-art methods in much shorter computing time (order of seconds running on CPU) providing means, for example, to do online updates when aiming at an interactive segmentation.
|
|
| |
|
| |
|
|
Image Super-Resolution Using Deep Learning
Bublavý, Martin ; Juránková, Markéta (oponent) ; Španěl, Michal (vedoucí práce)
The ability to identify and treat a variety of medical diseases is made possible by medical imaging, which is an essential component of contemporary healthcare. Yet, elements like noise and low resolution can have a negative impact on the quality of medical photographs. In this thesis, how to enhance the resolution and quality of medical images was investigated using MedSRGAN, a deep learning model built on generative adversarial networks (GANs). MedSRGAN was implemented and then applied to computed tomography (CT), one of the most utilized medical imaging methods.
|
|
|
Podpůrné zpracování tomografických dat pro 3D Slicer
Dašek, Filip ; Harabiš, Vratislav (oponent) ; Čmiel, Vratislav (vedoucí práce)
Diplomová práce shrnuje dostupné programy pro vizualizaci a segmentaci biomedicínských dat. Hlavní zaměření je na open source software 3D Slicer, u kterého jsou popsány všechny hlavní moduly a dostupné nástroje pro zpracování a segmentaci 3D obrazů. Čtenář je také seznámen s možností vytváření nových modulů a funkcí ve Sliceru za použití programování v Pythnu. V praktické části je vytvořen modul pro rychlou a efektivní segmentaci srdce a jeho částí pomocí metody Watershed. Modul obsahuje nástroje pro předzpracování CT snímků a automatický post-processing vysegmentovaných čátí srdce. Grafické rozhraní bylo vytvořené pomocí QT designeru. V testovací části jsou prezentovány výsledky segmentací. Při stejných vstupech dosahuje segmentace pomocí vytvořeného modulu lepších výsledků, než nabízená možnost ve 3D sliceru.
|
|
|
Creation Of Prematurely Born Infant Airways Model Based On X-Ray Ct And Mri Scans
Lázňovský, Jakub
Proposed contribution deals with the creation of infants’ airway model, based on available clinical MRI and CT scans of newborns. For this purpose, an algorithm which extracts the airway geometry was developed. Resulting geometry is consequently transformed to the airway model in stereolithography format, suitable for further analysis. The algorithm was tested on the data which correspond to an infant born in 30 weeks of gestation and scanned 14 days after birth. Thus, the model corresponds to the 32 weeks old infant.
|
host ::
RSS.