Elias P. Zafiropoulos

An intelligent system for automated breast cancer diagnosis and prognosis using SVM based classifiers

Abstract In recent years, computational diagnostic tools and artificial intelligence techniques provide automated procedures for objective judgments by making use of quantitative measures and machine learning techniques. In this paper we propose a Support Vector Machines (SVMs) based classifier in comparison with Bayesian classifiers and Artificial Neural Networks for the prognosis and diagnosis of breast cancer disease. The paper provides the implementation details along with the corresponding results for all the assessed classifiers. Several comparative studies have been carried out concerning both the prognosis and diagnosis problem demonstrating the superiority of the proposed SVM algorithm in terms of sensitivity, specificity and accuracy.

Reliability and cost optimization of electronic devices considering the component failure rate uncertainty

Abstract The objective of this paper is to present an efficient computational methodology to obtain the optimal system structure of electronic devices by using either a single or a multiobjective optimization approach, while considering the constraints on reliability and cost. The component failure rate uncertainty is taken under consideration and it is modeled with two alternative probability distribution functions. The Latin hypercube sampling method is used to simulate the probability distributions. An optimization approach was developed using the simulated annealing algorithm because of its flexibility to be applied in various system types with several constraints and its efficiency in computational time. This optimization approach can handle efficiently either the single or the multiobjective optimization modeling of the system design. The developed methodology was applied to a power electronic device and the results were compared with the results of the complete enumeration of the solution space. The stochastic nature of the best solutions for the single objective optimization modeling of the system design was sampled extensively and the robustness of the developed optimization approach was demonstrated.

Characterization of digital medical images utilizing support vector machines

BackgroundIn this paper we discuss an efficient methodology for the image analysis and characterization of digital images containing skin lesions using Support Vector Machines and present the results of a preliminary study.MethodsThe methodology is based on the support vector machines algorithm for data classification and it has been applied to the problem of the recognition of malignant melanoma versus dysplastic naevus. Border and colour based features were extracted from digital images of skin lesions acquired under reproducible conditions, using basic image processing techniques. Two alternative classification methods, the statistical discriminant analysis and the application of neural networks were also applied to the same problem and the results are compared.ResultsThe SVM (Support Vector Machines) algorithm performed quite well achieving 94.1% correct classification, which is better than the performance of the other two classification methodologies. The method of discriminant analysis classified correctly 88% of cases (71% of Malignant Melanoma and 100% of Dysplastic Naevi), while the neural networks performed approximately the same.ConclusionThe use of a computer-based system, like the one described in this paper, is intended to avoid human subjectivity and to perform specific tasks according to a number of criteria. However the presence of an expert dermatologist is considered necessary for the overall visual assessment of the skin lesion and the final diagnosis.

Intelligent segmentation and classification of pigmented skin lesions in dermatological images

During the last years, computer vision-based diagnostic systems have been used in several hospitals and dermatology clinics, aiming mostly at the early detection of malignant melanoma tumor, which is among the most frequent types of skin cancer, versus other types of non-malignant cutaneous diseases. In this paper we discuss intelligent techniques for the segmentation and classification of pigmented skin lesions in such dermatological images. A local thresholding algorithm is proposed for skin lesion separation and border, texture and color based features, are then extracted from the digital images. Extracted features are used to construct a classification module based on Support Vector Machines (SVM) for the recognition of malignant melanoma versus dysplastic nevus.

Methodology for the optimal component selection of electronic devices under reliability and cost constraints

The objective of this paper is to present an efficient computational methodology for the reliability optimization of electronic devices under cost constraints. The system modeling for calculating the reliability indices of the electronic devices is based on Bayesian networks using the fault tree approach, in order to overcome the limitations of the series–parallel topology of the reliability block diagrams. Furthermore, the Bayesian network modeling for the reliability analysis provides greater flexibility for representing multiple failure modes and dependent failure events, and simplifies fault diagnosis and reliability allocation. The optimal selection of components is obtained using the simulated annealing algorithm, which has proved to be highly efficient in complex optimization problems where gradient-based methods can not be applied. The reliability modeling and optimization methodology was implemented into a computer program in Matlab using a Bayesian network toolbox. The methodology was applied for the optimal selection of components for an electrical switch of power installations under reliability and cost constraints. The full enumeration of the solution space was calculated in order to demonstrate the efficiency of the proposed optimization algorithm. The results obtained are excellent since a near optimum solution was found in a small fraction of the time needed for the complete enumeration (3%). All the optimum solutions found during consecutive runs of the optimization algorithm lay in the top 0.3% of the solutions that satisfy the reliability and cost constraints. Copyright

Automated Medical Image Registration Using the Simulated Annealing Algorithm

This paper presents a robust, automated registration algorithm, which may be applied to several types of medical images, including CTs, MRIs, X-rays, Ultrasounds and dermatological images. The proposed algorithm is intended for imaging modalities depicting primarily morphology of objects i.e. tumors, bones, cysts and lesions that are characterized by translation, scaling and rotation. An efficient deterministic algorithm is used in order to decouple these effects by transforming images into the log-polar Fourier domain. Then, the correlation coefficient function criterion is employed and the corresponding values of scaling and rotation are detected. Due to the non-linearity of the correlation coefficient function criterion and the heavy computational effort required for its full enumeration, this optimization problem is solved using an efficient simulated annealing algorithm. After the images alignment in scaling and rotation, the simulated annealing algorithm is employed again, in order to detect the remaining values of the horizontal and vertical shifting. The proposed algorithm was tested using different initialization schemes and resulted in fast convergence to the optimal solutions independently of the initial points.

A Support Vector Machine Approach to Breast Cancer Diagnosis and Prognosis

In recent years, computational diagnostic tools and artificial intelligence techniques provide automated procedures for objective judgments by making use of quantitative measures and machine learning. The paper presents a Support Vector Machine (SVM) approach for the prognosis and diagnosis of breast cancer implemented on the Wisconsin Diagnostic Breast Cancer (WDBC) and the Wisconsin Prognostic Breast Cancer (WPBC) datasets found in literature. The SVM algorithm performs excellently in both problems for the case study datasets, exhibiting high accuracy, sensitivity and specificity indices.

Computing the success factors in consistent acquisition and recognition of objects in color digital images by explicit preconditioning

The paper studies the factors influencing the consistent acquisition and recognition of objects color and border features in digital imaging. The proposed image acquisition process is utilized by a computer supported imaging system implementing the acquisition and analysis of skin lesion images supporting medical diagnosis. In addition the same approach may be used for several problems requiring reliable color measurement and object identification. Two methodologies are adopted: The Bayesian Networks, which provide an efficient way of reasoning under uncertainty and are used to incorporate the expert judgement into the estimation of the probability of successful operation, and a Markov chain approach, which is generally used for the dynamic modeling of the system behavior. The Markov chain model requires asymptotically the solution of sparse linear systems. Explicit preconditioned methods are used for the efficient solution of the derived sparse linear system, and the parallel implementation of the dominant computational part is exploited.