|
|
Computer-aided data quality monitoring and assessment in clinical research
Šiška, Branislav ; Kolářová, Jana (referee) ; Schwarz, Daniel (advisor)
The diploma thesis deals with the monitoring and evaluation of data in clinical research. Usual methods to identify incorrect data are one-dimensional statistical methods per each variable in the register. Proposed method enters directly into database and finds out outliers in data using machine learning combined with multidimensional statistical methods that transform all column variables of clinical register to one, representing one record of patient in the register. Algorithm of proposed method is written in Matlab.
|
|
|
Pre-registration of CT pulmonary volumetric image data
Šiška, Branislav ; Walek, Petr (referee) ; Chmelík, Jiří (advisor)
This bachelor thesis is dealing with pre-registration of CT pulmonary volumetric image data. Pre-registration is solved by phase correlation method, which decomposes 3D images into 2D slices arranged in a row. It further describes the geometric transformations, interpolation, calculations of similarity criteria, optimization of registration of images and the image registration process itself. The pre-registration software runs in MATLAB^®, which works with 3D images of real CT image data with an emphasis on process speed.
|
|
|
Multidimensional Detection Of Outliers
In Clinical Registers
Šiška, Branislav
Incorrect data in clinical registers can lead to inaccurate or wrong results. This project is aimed at monitoring and evaluation of data in clinical registers. Usual methods to identify incorrect data are one-dimensional statistical methods per each variable in the register. Proposed method finds outliers in data using machine learning combined with multidimensional statistical methods that transform all column variables of clinical register to one, representing one record of a patient in the register.
|
|
|
Computer-aided data quality monitoring and assessment in clinical research
Šiška, Branislav ; Kolářová, Jana (referee) ; Schwarz, Daniel (advisor)
The diploma thesis deals with the monitoring and evaluation of data in clinical research. Usual methods to identify incorrect data are one-dimensional statistical methods per each variable in the register. Proposed method enters directly into database and finds out outliers in data using machine learning combined with multidimensional statistical methods that transform all column variables of clinical register to one, representing one record of patient in the register. Algorithm of proposed method is written in Matlab.
|
|
|
Pre-registration of CT pulmonary volumetric image data
Šiška, Branislav ; Walek, Petr (referee) ; Chmelík, Jiří (advisor)
This bachelor thesis is dealing with pre-registration of CT pulmonary volumetric image data. Pre-registration is solved by phase correlation method, which decomposes 3D images into 2D slices arranged in a row. It further describes the geometric transformations, interpolation, calculations of similarity criteria, optimization of registration of images and the image registration process itself. The pre-registration software runs in MATLAB^®, which works with 3D images of real CT image data with an emphasis on process speed.
|
guest ::
