Martin Tabakov

Learn More
During recent years a number of medical diagnosis support systems have been presented. Such systems are important from medical point of view, because they aid physicians in their daily work. Some of those systems, like Computed tomography support systems (CT) rely on image data analysis, making it an interesting research topic from pattern recognition point(More)
In this paper a decision making support system based on fuzzy logic is considered. The examined decision problem is related to the problem of recognition of histopathology images with respect to the degree of HER2/neu receptor overexpression. We used fuzzy decision trees, defined over different sets of image features, as separate image classifiers. Then,(More)
The Human Epidermal Growth Factor Receptor 2 (HER2/neu) is a biomarker, recognized as a valuable prognostic and predictive factor for breast cancer. In approximately 20% of primary breast cancers, the HER2/neu protein is over-expressed. By recent clinical research, a treatment procedure, with corresponding monoclonal antibodies specifically designed to(More)
The human epidermal growth factor receptor 2 (HER-2/neu) is a bi-omarker, recognized as a valuable prognostic and predictive factor for breast cancer. In approximately 20% of primary breast cancers, the HER2/neu protein is over-expressed. The effect of this over-expression is an increase in receptor mediated intracellular signalling, directing the cancer(More)
In this paper we introduce a method for calculating the volume of spontaneous intracerebral hematomas from a sequence of tomographic scans. The described approach is a modification of a gold standard method called step-section planimetry. It uses image interpolation techniques to increase the accuracy of the obtained volume and employs semi-automatic(More)
In this paper a decision making support system dedicated to histopathology image recognition is considered. The proposed system supports the classification process of histopathology preparations through microscopy image information analysis, with respect to the degree of HER2/neu receptor overexpression. The system combines the output information of(More)
In this article, a method of histopathology image recognition, based on image similarity is presented. The image similarity is interpreted in terms of fuzzy rough sets. Approximations of fuzzy sets are used for investigation how close (in terms of fuzzy rough sets) is a considered histopathology image to a reference image information, which enables HER2(More)
  • 1