|
|
Automatic segmentation of regions of interest in a human vertebra
Novosadová, Michaela ; Jan, Jiří (referee) ; Peter, Roman (advisor)
This bachelor´s thesis describes anatomy of the spine and the most frequent pathologies of the spine with focus on those tumour diseases, that affect more and more people today. The other part of the work describes theory of image registration. The aim of this thesis is to create an algorithm able to do automatic segmentation of regions of interest in human vertebra (body and posterior elements). This segmentation can simplify the classification of tumour diseases of the spine in the future. A solution was designed on the base of theoretical knowledge. This solution is based on registration of segmented models on original vertebrae. The thesis also describes the process of the solution. For easier understanding, the process of solution and the evaluation of results are added with number of graphs, images and tables.
|
|
|
Detection of pathological vertebrae in spinal CTs utilised by machine learning methods
Tyshchenko, Bohdan ; Ronzhina, Marina (referee) ; Chmelík, Jiří (advisor)
This master's thesis focuses on detection of pathological vertebrae in spinal CT utilized by machine learning. Theoretical part describes anatomy of the spine and occurrence of pathologies in CT image data, contains an overview of existing methods intended for automated detection of pathological vertebrae. Practical part devotes to design a computer aided detection systems to identify pathological vertebrae and to classify a type of pathology. Designed classification system is based on using neural network, which performs classification step and on principal component analysis (PCA), which is used to reducing the original number of observation features. For completing this task were used real data. Conclusion contains evaluation of obtained results.
|
|
|
Detection of pathological vertebrae in spinal CTs utilised by machine learning methods
Tyshchenko, Bohdan ; Ronzhina, Marina (referee) ; Chmelík, Jiří (advisor)
This master's thesis focuses on detection of pathological vertebrae in spinal CT utilized by machine learning. Theoretical part describes anatomy of the spine and occurrence of pathologies in CT image data, contains an overview of existing methods intended for automated detection of pathological vertebrae. Practical part devotes to design a computer aided detection systems to identify pathological vertebrae and to classify a type of pathology. Designed classification system is based on using neural network, which performs classification step and on principal component analysis (PCA), which is used to reducing the original number of observation features. For completing this task were used real data. Conclusion contains evaluation of obtained results.
|
|
|
Automatic segmentation of regions of interest in a human vertebra
Novosadová, Michaela ; Jan, Jiří (referee) ; Peter, Roman (advisor)
This bachelor´s thesis describes anatomy of the spine and the most frequent pathologies of the spine with focus on those tumour diseases, that affect more and more people today. The other part of the work describes theory of image registration. The aim of this thesis is to create an algorithm able to do automatic segmentation of regions of interest in human vertebra (body and posterior elements). This segmentation can simplify the classification of tumour diseases of the spine in the future. A solution was designed on the base of theoretical knowledge. This solution is based on registration of segmented models on original vertebrae. The thesis also describes the process of the solution. For easier understanding, the process of solution and the evaluation of results are added with number of graphs, images and tables.
|
guest ::
