Gert Van de Wouwer’s research while affiliated with University of Antwerp and other places

The embryonic stem cell test (EST) is an ECVAM-validated assay to detect embryotoxicity. The output of the assay is the effect of test compounds on the differentiation of murine-derived embryonic stem cells (D3 cells), recorded by visual analysis of contracting cardiomyocyte-like cells. Incorporation of a system to assess the contractility in an automated manner is proposed, to increase the throughput in the EST independent of observer bias. The automated system is based on image recording of each well, resulting in the area (pixels) and frequency of contractility (Hz). Four test compounds were assessed for their embryotoxic potency in the 96-well version of the EST, with both manual and automated analysis: 6-Aminonicotinamide, Valproic Acid, Boric Acid, and Penicillin G. There was no statistically significant difference in the outcome of both methods in the fraction of contractility (p < 0.05), resulting in the same rank-order of Relative Embryotoxic Potency (REP) values: 6-aminonicotinamide (1) > valproic acid (0.007–0.013) > Boric Acid (0.002–0.005) > Penicillin G (0.00001). The automated image recording of contractile cardiomyocyte-like cells in the EST allows for an unbiased high throughput method to assess the embryotoxic potency of test compounds, resulting in an outcome comparable to manual analysis.

We introduce an assay for the semi-automated quantification of nerve regeneration by image analysis. Digital images of histological sections of regenerated nerves are recorded using an automated inverted microscope and merged into high-resolution mosaic images representing the entire nerve. These are analysed by a dedicated image-processing package that computes nerve-specific features (e.g. nerve area, fibre count, myelinated area) and fibre-specific features (area, perimeter, myelin sheet thickness). The assay's performance and correlation of the automatically computed data with visually obtained data are determined on a set of 140 semithin sections from the distal part of a rat tibial nerve from four different experimental treatment groups (control, sham, sutured, cut) taken at seven different time points after surgery. Results show a high correlation between the manually and automatically derived data, and a high discriminative power towards treatment. Extra value is added by the large feature set. In conclusion, the assay is fast and offers data that currently can be obtained only by a combination of laborious and time-consuming tests.

A system for quantification of neurite outgrowth in in-vitro experiments is described. The system is developed for routine use in a high-throughput setting and is therefore needs fast, cheap, and robust. It relies on automated digital microscopical imaging of microtiter plates. Image analysis is applied to extract features for characterisation of neurite outgrowth. The system is tested in a dose-response experiment on PC12 cells + Taxol. The performance of the system and its ability to measure changes on neuronal morphology is studied.

ffl Cluster Size Diversity, Percolation and Phase Transition . I.R. Tsang and I.J. Tsang. Presented at Statistical Physics and Probabilistic Methods in Computer Science and NP-hardness and Phase Transitions, ICTP Trieste, 1999. ffl Entropy and Diversity on Percolation Systems. I.R. Tsang and I.J. Tsang. Presented at Gordon Research Conference on Modern Developments in Thermodynamics, IL Ciocco, 1999.

The discrete wavelet transform maps an image on a series of wavelet detail coefficients, which constitute a multiscale representation of the image. We conjecture that texture can be characterized by the statistics of these coefficients and introduce 2 feature sets for this purpose: the wavelet histogram signatures and the wavelet cooccurrence signatures. Using a model based approach, we show that all first order statistics of the wavelet detail coefficients can be captured in the wavelet histogram signatures. Further improvement in texture characterization can be obtained from the coefficients second order statistics, which are reflected in the wavelet cooccurrence signatures. We verify experimentally the validity of the model for the detail histogram and compare the introduced feature sets to the traditionally used energy signatures in a classification experiment. Best classification performance is shown to be achieved by combining histogram and cooccurrence signatures. 4.1

Non-separable wavelet transforms are applied to generate rotation-invariant texture features. Theoretical arguments are given to explain why they are to be preferred above separable transforms. An advantage of using non-separable transforms is a more flexible filter design, which shall be exploited to build rotation-invariant features using either isotropic or anisotropic wavelets. The features are used to perform supervised (classification) as well as unsupervised (segmentation) image processing tasks on textured images. In an extensive experimental study, the performance with respect to rotation-invariance is discussed. We show that isotropic as well as anisotropic wavelets generate rotation-invariant features with excellent performance on classification and segmentation.

To evaluate the performance of karyometry and histometry in the prediction of survival, recurrence and response of early-stage invasive cervical carcinoma. Nuclear morphometry, chromatin texture and tissue architecture (characterized by syntactic structure analysis) were measured using a semiautomated image analysis system on 46 cases of Feulgen-stained tissue sections. The performance of the features was compared to that of clinical features, reported to be the best prognosticators until now, such as age, lympho-vascular permeation, histologic type, stage and grade. A K nearest neighbor classifier was used for classification. In the prediction of three-year survival, recurrence and response, syntactic structure analysis proved to be the best performer. Classification rates were, respectively, 100%, 94.4% and 94.5%. In all classifications, karyometric and histometric features outperformed clinical features. In general, the best performing features described differences in second-order population statistics (standard deviations). The results show that a quantitative analysis based on nuclear morphology, chromatin texture and histology can be considered an excellent aid in the prognosis of invasive cervical carcinoma. The measurements are not hampered by the need to undertake complete resections and are suited to daily practice when implemented in a semiautomated image analysis system.

. In the last decade, multiscale techniques for gray-level texture analysis have been intensively studied. In this paper, we aim on extending these techniques to color images. We introduce wavelet energycorrelation signatures and we derive the transformation of these signatures upon linear color space transformations. Classification experiments demonstrate that the wavelet correlation features contain more information than the intensity or the energy features of each color plane separately. The influence of image representation in color space is evaluated. 1 Introduction For image analysis, color and texture are two of the most important properties, especially when one is dealing with real world images. Classical image analysis schemes only take into account the pixel gray-levels, which represents the total amount of visible light at the pixels position. The performance of such schemes can be improved by adding color information [1]. The color of a pixel is typically represent...

This report gives an introduction to the application of wavelet based multiscale image analysis methods to texture analysis. It outlines the basic methods and comments on design issues. It also points to the literature and connections with related methods. The un#nishedness of the research in this area becomes clear from the discussion of some extra issues and from a short list of practical applications. #latest revision 30#06#97# I. Introduction Texture is an important cue for the analysis of many types of images. The term is used to pointtointrinsic properties of surfaces, especially those that don't havea smoothly varying intensity. It includes intuitive properties like roughness, granulation and regularity. Some example textures from the Brodatz album #3# are shown in Fig. 1. Texture can be de#ned as the set of local neighbourhood properties of the gray levels of an image region.Texture analysis is considered a challenging task. The abilityto e#ectively classify and segment im...

In this paper, texture analysis based on wavelet transformations is elaborated. The paper is meant as a practical guideline through some aspects of a wavelet-based texture analysis task. The following aspects of the problem are discussed: discrete and continuous wavelet decompositions, texture features for grey-level textures, extensions to colour texture and rotation-invariant features, and classi#cation, including supervised image classi#cation and unsupervised texture segmentation tasks. For these di#erent aspects, a theoretical and practical survey is given, experiments and real-world applications of the literature are reviewed and some small-scale demonstration experiments are included. I. Introduction Texture is an important cue for the analysis of manytypes of images. The term is used to point to intrinsic properties of surfaces, especially those that don't have a smoothly varying intensity.It includes intuitive properties like roughness, granulation and regularity. More form...