Organ segmentation is often a first step in medical diagnostic. In this paper a fully automatic three-dimensional method for liver segmentation is presented. It is based on voxel density analysis with use of automated grow cut method. Obtained segmentation is then refined by active contours model.
—We use a collection of Python programs for numerical simulation of liver perfusion. We have an application for semi-automatic generation of a finite element mesh of the human liver from computed tomography scans and for reconstruction of the liver vascular structure. When the real vascular trees can not be obtained from the CT data we generate artificial… (More)
This paper provides summary of our experiments with automatic segmentation of liver parenchyma. It presents methods and classifiers that we used on computer tomography medicine data. In introduction there are a description of our motivation to do this research. Second part contains information about our approach, list of methods and classifiers. In part… (More)
Quantitative analysis of histology slides can bring unique knowledge about the investigated sample. Unfortunately this is time consuming procedure. In this paper we suggest method to overcome this disadvantage. However, everything has its price. Semi-automatic evaluation cannot beat human operator by its precision, but it is able to process big amount of… (More)
PURPOSE Quantitative description of hepatic microvascular bed could contribute to understanding perfusion CT imaging. Micro-CT is a useful method for the visualization and quantification of capillary-passable vascular corrosion casts. Our aim was to develop and validate open-source software for the statistical description of the vascular networks in… (More)
An organ segmentation is usually first step of liver treatment. We introduce a semi-automatic method for liver segmentation based on Graph-Cuts. Our experiments compare expert segmentation with our algorithm. We compare two different sets of parameters. Our software implementation is freely available
This paper describes a method for texture based segmentation. Texture features are extracted by applying a bank of Gabor filters using two-sided convolution strategy. Probability texture model is represented by Gaussian mixture that is trained with the Expectation-maximization algorithm. Texture similarity, obtained this way, is used like the input of a… (More)