|
|
Segmentation of hippocampus in MRI data
Kodym, Oldřich ; Chmelík, Jiří (referee) ; Walek, Petr (advisor)
The thesis deals with application of graph-based methods in segmentation of low contrast image data, specifically hippocampus segmentation from magnetic resonance data. Firstly, basics and terminology of graph theory is introduced. Next, minimum graph cut method is explained along with algorithms capable of finding this cut. After that comes the description of its implementation for 2D and 3D image data segmentation. Method was tested on sample data and then implemented as a 3D Slicer software module. Here the method was tested on the hipocampus data of healthy patients as well as patients suffering from Alzheimer’s disease. Most common problems occuring during the segmentation were forshadowed as well as possible ways to solve them.
|
|
|
Implementation of Ford-Fulkerson Algorithm
Makovský, Benjamin ; Rychnovský, Lukáš (referee) ; Masopust, Tomáš (advisor)
This work describes the design of the graphic implementation of the Ford-Fulkerson Algorithm for searching the maximum flow and the minimal cut in the network. It contains a brief introduction with the theory of the graphs and the flows in the networks, it describes the principle of the Ford-Fulkerson Algorithm. The object design representing the graph in the program is cited, the drawing of the graph by the program and the creation of the graphic user interface of the application is described. The final program is worked up as a Java applet which is placed at the public internet pages www.ffaplikace.php5.cz.
|
|
|
Segmentation of hippocampus in MRI data
Kodym, Oldřich ; Chmelík, Jiří (referee) ; Walek, Petr (advisor)
The thesis deals with application of graph-based methods in segmentation of low contrast image data, specifically hippocampus segmentation from magnetic resonance data. Firstly, basics and terminology of graph theory is introduced. Next, minimum graph cut method is explained along with algorithms capable of finding this cut. After that comes the description of its implementation for 2D and 3D image data segmentation. Method was tested on sample data and then implemented as a 3D Slicer software module. Here the method was tested on the hipocampus data of healthy patients as well as patients suffering from Alzheimer’s disease. Most common problems occuring during the segmentation were forshadowed as well as possible ways to solve them.
|
|
|
Implementation of Ford-Fulkerson Algorithm
Makovský, Benjamin ; Rychnovský, Lukáš (referee) ; Masopust, Tomáš (advisor)
This work describes the design of the graphic implementation of the Ford-Fulkerson Algorithm for searching the maximum flow and the minimal cut in the network. It contains a brief introduction with the theory of the graphs and the flows in the networks, it describes the principle of the Ford-Fulkerson Algorithm. The object design representing the graph in the program is cited, the drawing of the graph by the program and the creation of the graphic user interface of the application is described. The final program is worked up as a Java applet which is placed at the public internet pages www.ffaplikace.php5.cz.
|
|
|
Optimalization of flows in the network using the linear programming
Doubrava, Jiří ; Kalčevová, Jana (advisor) ; Flusserová, Lenka (referee)
This thesis deals with optimization of flows in a network with focus on solutions based on linear programming. The theoretical part is divided into three main sections: maximal flow, minimal flow and maximal flow with minimal costs. The first part focuses on theoretical basics of maximal flow problem and mainly on these algorithms: Ford-Fulkerson, Dinic/Edmonds-Karp, Three Indians algorithm and Goldberg push-relabel algorithm. These are explained on examples. The other chapters explain the minimal flow and the maximal flow with minimal costs problems with simple algorithms for their solutions, again explained on some examples. The practical part includes software solution of maximal flow problem in application MaxTok, which can be found on attached CD.
|
guest ::
