|
|
Automatic detection of brain tumors in MR images
Dvořák, P. ; Kropatsch, W.G. ; Bartušek, Karel
This paper deals with automatic brain tumor detection in magnetic resonance images. The goal is to determine whether the MR image of a brain contains a tumor. The proposed method works with T2-weighted magnetic resonance images, where the head is vertically aligned. The detection is based on checking the left-right symmetry of the brain, which is the assumption for healthy brain. The algorithm was tested by fivefold cross-validation technique on 72 images of brain containing tumors and 131 images of healthy brain. The proposed method reaches the true positive rate of 91.16% and the true negative rate of 94.68%.
|
|
|
Statistics-based classification on tissues in the mandibular region
Marcon, P. ; Bartušek, Karel ; Mikulka, J. ; Gescheidtová, E.
The authors present a statistical evaluation of T1-weighted and T2-weighted images of healthy and diseased human tissues. In each patient, the statistical data were evaluated from several tissues, namely the bone, bone marrow, muscle, fat, white matter and gray matter tissue types. Based on the acquired statistical data, we compiled new statistics. In the given tissue samples, we evaluated the following statistical quantities: standard deviation (s.d.), skewness, and kurtosis. The box plots and a small statistical database were created. This database is currently used to determine the tissues.
|
|
|
Multiparametric Data Collection of Animal Tissues in Magnetic Resonance Imaging
Marcon, P. ; Bartušek, Karel
In this article a magnetic resonance multiparametric data collection is described. The spin echo and the gradient echo sequences for magnetic resonance measurement were used. Images obtained by a nuclear magnetic resonance tomographare proton density, longitudinal relaxation time T-1, transversal relaxation time T-2 and magnetic susceptibility weighted. As a measured sample chicken wing was used. Several parameters as a maximal value, minimal value, mean value and standard deviation were evaluated in skin, fat, muscle, bone and bone marrow tissues. Obtained data could be used for multiparametric analysis and for image segmentation.
|
guest ::
