Image Analysis & Stereology

Ahead of print section

Current issue - Vol 35, No 3 (2016)

  • AN ENSEMBLE TEMPLATE MATCHING AND CONTENT-BASED IMAGE RETRIEVAL SCHEME TOWARDS EARLY STAGE DETECTION OF MELANOMA
    Spiros Kostopoulos, Dimitris Glotsos, Pantelis Asvestas, Christos Konstandinou, George Xenogiannopoulos, Konstantinos Sidiropoulos, Eirini-Konstantina Nikolatou, Konstantinos Perakis, Spyros Mantzouratos, Theophilos Sakkis, George Sakellaropoulos, George Nikiforidis, Dionisis Cavouras
    Malignant melanoma represents the most dangerous type of skin cancer. In this study we present an ensemble classification scheme, employing the mutual information, the cross-correlation and the clustering based on proximity of image features methods, for early stage assessment of melanomas on plain photography images. The proposed scheme performs two main operations. First, it retrieves the most similar, to the unknown case, image samples from an available image database with verified benign moles and malignant melanoma cases. Second, it provides an automated estimation regarding the nature of the unknown image sample based on the majority of the most similar images retrieved from the available database. Clinical material comprised 75 melanoma and 75 benign plain photography images collected from publicly available dermatological atlases. Results showed that the ensemble scheme outperformed all other methods tested in terms of accuracy with 94.9±1.5%, following an external cross-validation evaluation methodology. The proposed scheme may benefit patients by providing a second opinion consultation during the self-skin examination process and the physician by providing a second opinion estimation regarding the nature of suspicious moles that may assist towards decision making especially for ambiguous cases, safeguarding, in this way from potential diagnostic misinterpretations.

  • THE CORRELATION ANALYSIS OF THE SHAPE PARAMETERS FOR ENDOTHELIAL IMAGE CHARACTERISATION
    Karolina Nurzynska, Adam Piorkowski
    Microscopic images of corneal endothelium cells are investigated to deliver information about their medical state. Although this could be achieved automatically, this examination is manual and very time consuming. Two medical parameters for endothelial layer quality description have been introduced and more are planned. Yet, since they will exploit image processing, a thoughtful overview of applicable existing shape parameters is necessary. This work investigates the possibility of exploiting well-known image processing techniques for describing the endothelial layer by calculating information about shape features using spatial moments or topological attributes. The comparison concentrates on finding which shape measures could be combined to improve descriptions, and which cannot due to their high correlation and the fact that they do not contain any new information. The performed experiments revealed a set of 17 non-correlated features and four groups of shape parameters that show some correlation, but one representative can always be selected. Moreover, the investigation proved some correlation between the metrics used in medicine and considered shape features.

  • SHAPE ANALYSIS OF FINE AGGREGATES USED FOR CONCRETE
    Huan He, Luc Courard, Eric Pirard, Frederic Michel
    Fine aggregate is one of the essential components in concrete and significantly influences the material properties. As parts of natures, physical characteristics of fine aggregate are highly relevant to its behaviors in concrete. The most of previous studies are mainly focused on the physical properties of coarse aggregate due to the equipment limitations. In this paper, two typical fine aggregates, i.e. river sand and crushed rock, are selected for shape characterization. The new developed digital image analysis systems are employed as the main approaches for the purpose. Some other technical methods, e.g. sieve test, laser diffraction method are also used for the comparable references. Shape characteristics of fine aggregates with different origins but in similar size ranges are revealed by this study. Compared with coarse aggregate, fine grains of different origins generally have similar shape differences. These differences are more significant in surface texture properties, which can be easily identified by an advanced shape parameter: bluntness. The new image analysis method is then approved to be efficient for the shape characterization of fine aggregate in concrete.

  • ESTIMATING FIBRE DIRECTION DISTRIBUTIONS OF REINFORCED COMPOSITES FROM TOMOGRAPHIC IMAGES
    Oliver Wirjadi, Katja Schladitz, Prakash Easwaran, Joachim Ohser
    Fibre reinforced composites constitute a relevant class of materials used chiefly in lightweight constructions for example in fuselages or car bodies. The spatial arrangement of the fibres and in particular their direction distribution have huge impact on macroscopic properties and, thus, its determination is an important topic of material characterisation. The fibre direction distribution is defined on the unit sphere, and it is therefore preferable to work with fully three-dimensional images of the microstructure as obtained, e.g., by computed micro-tomography. A number of recent image analysis algorithms exploit local grey value variations to estimate a preferred direction in each fibre point. Averaging these local results leads estimates of the volume-weighted fibre direction distribution. We show how the thus derived fibre direction distribution is related to quantities commonly used in engineering applications. Furthermore, we discuss four algorithms for local orientation analysis, namely those based on the response of anisotropic Gaussian filters, moments and axes of inertia derived from directed distance transforms, the structure tensor, or the Hessian matrix. Finally, the feasibility of these algorithms is demonstrated for application examples and some advantages and disadvantages of the underlying methods are pointed out.

  • ASSESSING DISSIMILARITY OF RANDOM SETS THROUGH CONVEX COMPACT APPROXIMATIONS, SUPPORT FUNCTIONS AND ENVELOPE TESTS
    Vesna Gotovac, Kateřina Helisová, Ivo Ugrina
    In recent years random sets were recognized as a valuable tool in modelling different processes from fields like biology, biomedicine or material sciences. Nevertheless, the full potential of applications has not still been reached and one of the main problems in advancement is the usual inability to correctly differentiate between underlying processes generating real world realisations. This paper presents a measure of dissimilarity of stationary and isotropic random sets through a heuristic based on convex compact approximations, support functions and envelope tests. The choice is justified through simulation studies of common random models like Boolean and Quermass-interaction processes.

  • THE USE OF HAAR WAVELETS IN DETECTING AND LOCALIZING TEXTURE DEFECTS
    Gintarė Vaidelienė, Jonas Valantinas
    In this paper, a new Haar wavelet-based approach to the detection and localization of defects in grey-level texture images is presented. This new approach explores space localization properties of the discrete Haar wavelet transform (HT) and generates statistically-based parameterized texture defect detection criteria. The criteria provide the user with a possibility to control the percentage of both the actually defect-free images detected as defective and/or the actually defective images detected as defect-free, in the class of texture images under investigation. The experiment analyses samples of ceramic tiles, glass samples, as well as fabric scraps, taken from real factory environment.