Marek Kretowski

An Evolutionary Algorithm for Oblique Decision Tree Induction

In the paper, a new evolutionary approach to induction of oblique decision trees is described. In each non-terminal node, the specialized evolutionary algorithm is applied to search for a splitting hyper-plane. The feature selection is embedded into the algorithm, which allows to eliminate redundant and noisy features at each node. The experimental evaluation of the proposed approach is presented on both synthetic and real datasets.

Toward a better understanding of texture in vascular CT scan simulated images

This paper shows the influence of computed tomography slice thickness on textural parameters by simulating realistic images issued from: (1) a 3D model of vascular tree, with structural and functional features and in which angiogenesis is related to the organ growth; (2) a projection/reconstruction process using fast Fourier transform. Texture analysis is performed by means of second-order statistics and gradient based methods.

Multiscale Model of Liver DCE-MRI Towards a Better Understanding of Tumor Complexity

The use of quantitative imaging for the characterization of hepatic tumors in magnetic resonance imaging (MRI) can improve the diagnosis and therefore the treatment of these life-threatening tumors. However, image parameters remain difficult to interpret because they result from a mixture of complex processes related to pathophysiology and to acquisition. These processes occur at variable spatial and temporal scales. We propose a multiscale model of liver dynamic contrast-enhanced (DCE) MRI in order to better understand the tumor complexity in images. Our design couples a model of the organ (tissue and vasculature) with a model of the image acquisition. At the macroscopic scale, vascular trees take a prominent place. Regarding the formation of MRI images, we propose a distributed model of parenchymal biodistribution of extracellular contrast agents. Model parameters can be adapted to simulate the tumor development. The sensitivity of the multiscale model of liver DCE-MRI was studied through observations of the influence of two physiological parameters involved in carcinogenesis (arterial flow and capillary permeability) on its outputs (MRI images at arterial and portal phases). Finally, images were simulated for a set of parameters corresponding to the five stages of hepatocarcinogenesis (from regenerative nodules to poorly differentiated HepatoCellular Carcinoma).

Global learning of decision trees by an evolutionary algorithm

In the paper, an evolutionary algorithm for global induction of decision trees is presented. In contrast to greedy, top-down approaches it searches for the whole tree at the moment. Specialised genetic operators are proposed which allow modifying both tests used in the non-terminal nodes and structure of the tree. The proposed approach was validated on both artificial and real-life datasets. Experimental results show that the proposed algorithm is able to find competitive classifiers in terms of accuracy and especially complexity.

Simulation of Biphasic CT Findings in Hepatic Cellular Carcinoma by a Two-Level Physiological Model

In this paper, we present a two-level physiological model that is able to reflect morphology and function of vascular networks, in clinical images. Our approach results from the combination of a macroscopic model, providing simulation of the growth and pathological modifications of vascular network, and a microvascular model, based on compartmental approach, which simulates blood and contrast medium transfer through capillary walls. The two-level model is applied to generate biphasic computed tomography of hepatocellular carcinoma. A contrast-enhanced sequence of simulated images is acquired, and enhancement curves extracted from normal and tumoral regions are compared to curves obtained from in vivo images. The model offers the potential of finding early indicators of disease in clinical vascular images

Evolutionary learning of linear trees with embedded feature selection

In the paper a new evolutionary algorithm for global induction of linear trees is presented. The learning process consists of searching for both a decision tree structure and hyper-plane weights in all non-terminal nodes. Specialized genetic operators are developed and applied according to the node quality and location. Feature selection aimed at simplification of the splitting hyper-planes is embedded into the algorithm and results in elimination of noisy and redundant features. The proposed approach is verified on both artificial and real-life data and the obtained results are promising.

Induction of Multivariate Decision Trees by Using Dipolar Criteria

A new approach to the induction of multivariate decision trees is proposed. A linear decision function (hyper-plane) is used at each non-terminal node of a binary tree for splitting the data. The search strategy is based on the dipolar criterion functions and exploits the basis exchange algorithm as an optimization procedure. The feature selection is used to eliminate redundant and noisy features at each node. To avoid the problem of over-fitting the tree is pruned back after the growing phase. The results of experiments on some real-life datasets are presented and compared with obtained by state-of-art decision trees.

A memetic algorithm for global induction of decision trees

In the paper, a new memetic algorithm for decision tree learning is presented. The proposed approach consists in extending an existing evolutionary approach for global induction of classification trees. In contrast to the standard top-down methods, it searches for the optimal univariate tree by evolving a population of trees. Specialized genetic operators are selectively applied to modify both tree structures and tests in non-terminal nodes. Additionally, a local greedy search operator is embedded into the algorithm, which focusses and speeds up the evolutionary induction. The problem of over-fitting is mitigated by suitably defined fitness function. The proposed method is experimentally validated and preliminary results show that the proposed approach is able to effectively induce accurate and concise decision trees.

Global Induction of Oblique Decision Trees: An Evolutionary Approach

A new evolutionary algorithm for induction of oblique decision trees is proposed. In contrast to the classical top-down approach, it searches for the whole tree at the moment. Specialized genetic operators are developed, which enable modifying both the tree structure and the splitting hyper-planes in non-terminal nodes. The problem of over-fitting can be avoided thanks to suitably defined fitness function. Experimental results on both synthetical and real-life data are presented and compared with obtained by the state-of-the-art decision tree systems.

Evolutionary Induction of Decision Trees for Misclassification Cost Minimization

In the paper, a new method of decision tree learning for cost-sensitive classification is presented. In contrast to the traditional greedy top-down inducer in the proposed approach optimal trees are searched in a global manner by using an evolutionary algorithm (EA). Specialized genetic operators are applied to modify both the tree structure and tests in non-terminal nodes. A suitably defined fitness function enables the algorithm to minimize the misclassification cost instead of the number of classification errors. The performance of the EA-based method is compared to three well-recognized algorithms on real-life problems with known and randomly generated cost-matrices. Obtained results show that the proposed approach is competitive both in terms of misclassification cost and compactness of the classifier at least for some datasets.