Articles catalogue

Machine Learning Methods for Knowledge Discovery in Medical Data on Atherosclerosis
Low-dimensional Multimodal Deformable Registration of MRI Brain Images in Stereotaxic Space
A Prediction of Blood Flow through a Bypass Graft Using Statistical Methods

Machine Learning Methods for Knowledge Discovery in Medical Data on Atherosclerosis
José Ignacio Serrano¹, Marie Tomečková², Jana Zvárová²
1. Instituto de Automática Industrial, CSIC, Madrid, Spain, 2. Department of Medical Informatics, Institute of Computer Science AS CR, Prague, Czech Republic
15.08.2006 Summary Machine learning techniques are methods that given a training set of examples infer a model for the categories of the data, so that new (unknown) examples could be assigned to one or more categories by pattern matching within the model. The data from follow-up studies with repeated collection of the same type of data are very suitable for this analysis. Machine learning algorithms belonging to a variety of paradigms have been applied to knowledge discovery on medical data. All the used algorithms belong to the supervised learning paradigm. Several algorithms have been tested, trying to cover most of the kinds of supervised learning. Two kinds of experiments have been carried out. The first is intended to discover associations between attributes. The second kind is intended to test prediction of future disorders. For the experiments in this paper the data used was from the twenty years lasting primary preventive longitudinal study of the risk factors (RF) of atherosclerosis in middle aged men. Study is named STULONG (LONGitudinal STUdy). The results show that some methods predict some disorders better than others, so it is interesting to use all the algorithms at a time and consider the result confidence based upon the known tendency of each method. The machine learning algorithms have been also used in the prediction of death cause, obtaining poor results in this case, maybe due to the small amount of information (entries) of this type in the dataset. Keywords: knowledge discovery, supervised machine learning, biomedical data mining, risk factors of atherosclerosis full article Česky Español

Low-dimensional Multimodal Deformable Registration of MRI Brain Images in Stereotaxic Space
Daniel Schwarz¹, Ivo Provazník²
1. Institute of Biostatistics and Analyses, Masaryk University, Czech Republic, 2. Department of Biomedical Engineering, Brno University of Technology, Czech Republic
15.08.2006 Summary Deformable image registration is a fundamental technique in computational neuroanatomy. An iterative multilevel block matching technique with the use of several recent inventions is proposed here. A symmetric multimodal similarity measure allows to register subject images to an arbitrary digital brain atlas. Smooth deformations produced by scattered data interpolation based on compactly supported radial basis functions suppress gross inter-subject differences and preserve the localized anatomical variability which may be further studied with selected automated morphometry methods. Four similarity measures are tested in an experiment with image data obtained from the Simulated Brain Database and a quantitative evaluation of the algorithm is presented. Keywords: image processing, image registration, MRI images, computational neuroanatomy, radial basis functions full article Česky

A Prediction of Blood Flow through a Bypass Graft Using Statistical Methods
Jana Vrbková¹, Vilém Bruk²
1. Department of Mathematical Analysis and Applications of Mathematics, Faculty of Natural Sciences, Palacky University Olomouc, Czech Republic, 2. Clinic of Cardiosurgery, Faculty Hospital Olomouc, Czech Republic
15.08.2006 Summary Myocardial revascularization belongs among the most frequent cardiosurgery operations. Perioperative and longterm survival depend on the patency of the graft used and the anastomotic quality. Haemodynamical characteristics measured during a coronary artery bypass graft (CABG) surgery help verify anastomotic quality and also affect longterm graft patency. During CABG surgery (on a heart bypass machine with extracorporal circulation), a surgeon measures blood flow through the bypass at the time the cross clamp is applied to the ascending aorta (blood is not flowing through coronary vessels, rather through the bypass) and later at the same place after removal of the cross clamp. The aim of this article is to find a statistical model for prediction of blood flow through the bypass after removal of the cross clamp based on the blood flow value when the cross clamp is placed on the aorta. When this prediction is good, we will be able to decrease a number of measurements with keeping whole information about an object. Keywords: myocardial revascularization, prediction of blood flow and blood pressure, multiple regression, nonlinear regression model, linearization, linear regression model with constraints, outlier, leverage full article Česky