The ability to visualise hidden structures in detail using 3-D volume data has become a valuable resource in medical imaging applications (Maintz & Viergever, 1998). Importantly, the alignment of volumes enables the combination of different structural and functional information for diagnosis and planning purposes (Pluim, Maintz, & Viergever, 2003). Transform optimisation, resampling, and similarity calculation form the basic stages of a registration process (Zitova & Flusser, 2003): During transform optimisation, translation and rotation parameters which geometrically map points in the reference (fixed) image/volume to points in the sensed (moving) image/volume are estimated. Once estimated, pixel/voxel intensities which are mapped into nondiscrete coordinates are interpolated during the resampling stage. After resampling, a metric is used for similarity calculation in which the degree of likeness between corresponding volumes is evaluated (Tait & Schaefer, 2008). Optimisation of the similarity measure is the goal of the registration process and is achieved by seeking the best transform. All possible transform parameters therefore define the search space. Due to the iterative nature of registration algorithms, similarity calculation represents a considerable performance bottleneck which limits the speed of time critical clinical applications.Request access from your librarian to read this chapter's full text.

Many problems can be formulated as optimisation problems. Among the many classes of algorithms for solving such problems, one interesting, biologically inspired group is that of evolutionary optimisation techniques. In this tutorial paper we provide an overview of such techniques, in particular of Genetic Algorithms and Genetic Programming and its related subtasks of selection, cross-over, mutation, and coding. We then also explore Ant Colony Optimisation and Particle Swarm Optimisation techniques.

Accurate color information in dermoscopy images is very important for melanoma diagnosis since inappropriate white balance or brightness in the images adversely affects the diagnostic performance. In this paper, we present an automated color normalization method for dermoscopy images of skin lesions. We develop color normalization filters based on a total of 319 images which normalize color of images using the HSV color system. We determined that the color characteristics of the peripheral part of the tumors significantly influence the color normalization and confirmed that the developed normalization filter achieved satisfactory normalization performance as evaluated by a cross-validation test.

In this paper, we present a classification method of dermoscopy images between melanocytic skin lesions (MSLs) and non-melanocytic skin lesions (NoMSLs). The motivation of this research is to develop a pre-processor of an automated melanoma screening system. Since NoMSLs have a wide variety of shapes and their border is often ambiguous, we developed a new tumor area extraction algorithm to account for these difficulties. We confirmed that this algorithm is capable of handling different dermoscopy images not only those of NoMSLs but also MSLs as well. We determined the tumor area from the image using this new algorithm, calculated a total 428 features from each image, and built a linear classifier. We found only two image features, “the skewness of bright region in the tumor along its major axis” and “the difference between the average intensity in the peripheral part of the tumor and that in the normal skin area using the blue channel” were very efficient at classifying NoMSLs and MSLs. The detection accuracy of MSLs by our classifier using only the above mentioned image feature has a sensitivity of 98.0% and a specificity of 86.6% in a set of 107 non-melanocytic and 548 melanocytic dermoscopy images using a cross-validation test.

Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Due to the difficulty and subjectivity of human interpretation, automated analysis of dermoscopy images has become an important research area. Border detection is often the first step in this analysis. In many cases, the lesion can be roughly separated from the background skin using a thresholding method applied to the blue channel. However, no single thresholding method appears to be robust enough to successfully handle a wide variety of dermoscopic images. In this paper, we present an automated method for detecting lesion borders in dermoscopy images using a fusion of several thresholding methods. Experiments on a difficult set of 90 images demonstrate that the proposed method achieves both fast and accurate results when compared to six state-of-the-art methods.

The aim of colour quantisation is to reduce the number of distinct colour in images while preserving a high colour fidelity as compared to the original images. The choice of a good colour palette is crucial as it directly determines the quality of the resulting image. Colour quantisation can also be seen as a clustering problem where the task is to identify those clusters that best represent the colours in an image. In this paper we investigate the performance of various fuzzy c-means clustering algorithms for colour quantisation of images. In particular, we use conventional fuzzy c-means as well as some more efficient variants thereof, namely fast fuzzy c-means with random sampling, fast generalised fuzzy c-means, and a recently introduced anisotropic mean shift based fuzzy c-means algorithm. Experimental results show that fuzzy c-means performs significantly better than other, purpose built colour quantisation algorithms, and also confirm that the fast fuzzy clustering algorithms provide similar quantisation results to the full conventional fuzzy c-means approach.

Background/purposeLocalised scleroderma (LS) is the most common form of scleroderma seen in children, and usually presents unilaterally. Infrared thermography (IRT) and laser Doppler (LD) have both been reported to be useful in assessing the active, inflammatory stage of LS. We developed and validated a protocol using these techniques for the assessment of unilateral LS activity in children.MethodWe investigated the spatial variability and repeatability of LD measurements from adult control forearm skin, and the inter- and intra-operator reproducibility of both LD blood flow trace analysis and IRT skin temperature analysis. Software was developed to produce overlay images of thermograms onto digital photographs of skin sites. In a group of seven adult control subjects, we established the normal range for skin temperature and LD blood flow at six standardised sites (forehead, cheek, abdomen, back, arm and leg), and measured contralateral differences in readings. In a group of 34 children with LS, we investigated the skin temperature and LD blood flow in unaffected skin at the same six sites.ResultsIn adults, physiological variability in LD blood flow and skin temperature between the two sides of the body was found to be greater than the uncertainty introduced into the measurements by (inter alia) limited intra- or inter-operator reproducibility. The cheek displayed the highest mean asymmetry in both skin temperature (0.5 degrees C) and LD blood flow (40%).ConclusionOur protocol combines IRT, LD and photography for LS assessment in children, and establishes a normal range of readings in line with other authors.

While many digital image libraries allow access to large repositories of images, unfortunately, often the provided free-text search returns unsatisfactory retrieval results. The reason for this is that search techniques typically rely solely on statistical analysis of keyword recurrences in image annotations. In this chapter we show that through the employment of a semantic framework for image annotation, vastly improved retrieval can be accomplished. We present a semantically-enabled annotation and retrieval engine which relies on methodically structured ontologies for image annotation, and demonstrate how it provides more accurate retrieval results as well as a richer set of alternatives matchmaking the original query.

Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Due to the difficulty and subjectivity of human interpretation, automated analysis of dermoscopy images has become an important research area. Border detection is often the first step in this analysis. In this article, we present an approximate lesion localization method that serves as a preprocessing step for detecting borders in dermoscopy images. In this method, first the black frame around the image is removed using an iterative algorithm. The approximate location of the lesion is then determined using an ensemble of thresholding algorithms. Experiments on a large set of images demonstrate that the presented method achieves both fast and accurate localization of lesions in dermoscopy images.

Breast cancer is the most; commonly diagnosed form of cancer in women accounting for about 30% of all cases. Medical thermography has been shown to be well suited for the task of detecting breast cancer, in particular when the tumour is in its early stages or in dense tissue. In this paper we perform breast cancer analysis based on thermography. We employ a series of statistical features extracted from the thermograms which describe bilateral differences between left and right; breast areas. These features then form the basis of a. hybrid fuzzy rule-based classification system for diagnosis. The rule base of the classifier is optimised through the application of a genetic algorithm which ensures a. small set of rules coupled with high classification performance. Experimental results on a large dataset of nearly 150 cases confirm the efficacy of our approach.

Retrieval of images based on features derived directly from the images provides a useful way of accessing medical imagery. While most of these techniques operate in the pixel domain, a more efficient approach is to perform retrieval directly in the compressed domain of images. In this paper we look at two different methods for such compressed-domain retrieval of medical images. Both algorithms are based on wavelet image compression such as the one used in the JPEG2000 standard. We compare the effectiveness of the two techniques based on a database of 400 medical infrared images.

Thermography captures the temperature distribution of the human skin and is employed in various medical applications. Techniques for automaticaly retrieving medical images based on their content have shown to be useful and are highly sought after. In this paper we show that efficient and effective content-based retrieval of medical thermograms can be performed directly in the compressed domain of wavelet compressed images. Experimental results on a large dataset of medical infrared images confirm the usefulness of our presented approach.

The 'in situ' investigation of different biological, chemical, physical, and environmental processes often requires the knowledge of these sample characteristics with high - (sub)micro-meter - resolution as a valuable complement to the average bulk information. Different microprobe techniques can meet these requirements and their possible combinations would offer the opportunity of thorough study of a given sample or a scientific problem.Although some of the existing software packages allow for multivariate statistical treatment of data-sets obtained by a given experimental technique, none of them permits a simultaneous statistical treatment of datasets obtained by different experimental techniques, e.g. by simultaneous scanning mu-XRF (X-ray fluorescence) and mu-XRD (X-ray diffraction), or measured at several set-ups/beamlines/synchrotrons/laboratories (e.g. combined mu-IR and mu-XRF spectroscopy). The goal of this paper is to describe in detail a sequence of operations which can be applied to multi-technique datasets for obtaining a complete set of sample characteristics and to show that at present this can be realised automatically.

This paper discusses the use of genetic algorithms and genetic programming within the simulation soccer domain. Genetic algorithms (GAs) are based on the Darwinian theory of evolution and provide techniques to execute an effective search on a large range of potential solutions to a specific problem. Genetic Programming (GP) uses GA concepts to evolve a computer program. We show how GAs and GP have been applied to the challenging real-time and noisy domain of RoboCup simulation soccer. Among others, genetic approaches can be used to find appropriate actions for a soccer agent during a game, to improve different aspects of team strategy as well as to strengthen the ability of a player or a team in training exercises.

This paper surveys cost-sensitive fuzzy rule-based systems for pattern classification. Weighted training patterns are used to construct cost-sensitive fuzzy rule-based systems. A fuzzy classification system is constructed from a given set of training patterns. It is assumed that a weight is assigned to each training pattern a priori. The weight of training patterns can be determined based on their distribution. We show an example of weight assignment for a two-dimensional problem.

Microarray expression studies measure, through a hybridisation process, the levels of genes expressed in biological samples. Knowledge gained from these studies is deemed increasingly important due to its potential of contributing to the understanding of fundamental questions in biology and clinical medicine. One important aspect of microarray expression analysis is the classification of the recorded samples which poses many challenges due to the vast number of recorded expression levels compared to the relatively small numbers of analysed samples. In this paper we show how fuzzy rule-based classification can be applied successfully to analyse gene expression data. The generated classifier consists of an ensemble of fuzzy if-then rules which together provide a reliable and accurate classification of the underlying data. Experimental results on several standard microarray datasets confirm the efficacy of the approach.

Advances in camera technologies and reduced equipment costs have lead to an increased interest in the application of thermography in the medical fields. Thermography is of particular interest for detection of breast cancer as it has been shown that it is capable of detecting the cancer earlier and is also allows diagnosis of fatty breast tissue. In this paper we perform breast cancer detection based on thermography, using a series of statistical features extracted from the thermograms coupled with a fuzzy rule-based classification system for diagnosis. The features stem from a comparison of left and right breast areas and quantify the bilateral differences encountered. Following this asymmetry analysis the features are fed to a fuzzy classification system. This classifier is used to extract fuzzy if-then rules based on a training set of known cases. Experimental results on a set of nearly 150 cases show the proposed system to work well accurately classifying about 80% of cases, a performance that is comparable to other imaging modalities such as mammography.

Many image processing applications involve a pattern classification stage. In this paper we propose a classifier based on fuzzy if–then rules that allows the incorporation of weighted training patterns which can be used to adjust the sensitivity of the classification with respect to certain classes. The antecedent part of fuzzy if–then rules are specified by partitioning each attributes into fuzzy sets while the consequent class and the degree of certainty are determined from the compatibility and weights of training patterns. We also introduce a learning method which adjusts the degree of certainty in order to provide improved classification performance and reduced costs. Experimental results on several image processing tasks demonstrate the efficacy of the proposed method.