Clinical diagnosis of chronic disease is a vital and challenging research problem which requires intensive clinical practice guidelines in order to ensure consistent and efficient patient care. Conventional medical diagnosis systems inculcate certain limitations, like complex diagnosis processes, lack of expertise, lack of well described procedures for conducting diagnoses, low computing skills, and so on. Automated clinical decision support system (CDSS) can help physicians and radiologists to overcome these challenges by combining the competency of radiologists and physicians with the capabilities of computers. CDSS depend on many techniques from the fields of image acquisition, image processing, pattern recognition, machine learning as well as optimization for medical data analysis to produce efficient diagnoses. In this dissertation, we discuss the current challenges in designing an efficient CDSS as well as a number of the latest techniques (while identifying best practices for each stage of the framework) to meet these challenges by finding informative patterns in the medical dataset, analysing them and building a descriptive model of the object of interest and thus aiding in medical diagnosis. To meet these challenges, we propose an extension of conventional clinical decision support system framework, by incorporating artificial immune network (AIN) based hyper-parameter optimization as integral part of it. We applied the conventional as well as optimized CDSS on four case studies (most of them comprise medical images) for efficient medical diagnosis and compared the results. The first key contribution is the novel application of a local energy-based shape histogram (LESH) as the feature set for the recognition of abnormalities in mammograms. We investigated the implication of this technique for the mammogram datasets of the Mammographic Image Analysis Society and INbreast. In the evaluation, regions of interest were extracted from the mammograms, their LESH features were calculated, and they were fed to support vector machine (SVM) and echo state network (ESN) classifiers. In addition, the impact of selecting a subset of LESH features based on the classification performance was also observed and benchmarked against a state-of-the-art wavelet based feature extraction method. The second key contribution is to apply the LESH technique to detect lung cancer. The JSRT Digital Image Database of chest radiographs was selected for research experimentation. Prior to LESH feature extraction, we enhanced the radiograph images using a contrast limited adaptive histogram equalization (CLAHE) approach. Selected state-of-the-art cognitive machine learning classifiers, namely the extreme learning machine (ELM), SVM and ESN, were then applied using the LESH extracted features to enable the efficient diagnosis of a correct medical state (the existence of benign or malignant cancer) in the x-ray images. Comparative simulation results, evaluated using the classification accuracy performance measure, were further benchmarked against state-of-the-art wavelet based features, and authenticated the distinct capability of our proposed framework for enhancing the diagnosis outcome. As the third contribution, this thesis presents a novel technique for detecting breast cancer in volumetric medical images based on a three-dimensional (3D) LESH model. It is a hybrid approach, and combines the 3D LESH feature extraction technique with machine learning classifiers to detect breast cancer from MRI images. The proposed system applies CLAHE to the MRI images before extracting the 3D LESH features. Furthermore, a selected subset of features is fed to a machine learning classifier, namely the SVM, ELM or ESN, to detect abnormalities and to distinguish between different stages of abnormality. The results indicate the high performance of the proposed system. When compared with the wavelet-based feature extraction technique, statistical analysis testifies to the significance of our proposed algorithm. The fourth contribution is a novel application of the (AIN) for optimizing machine learning classification algorithms as part of CDSS. We employed our proposed technique in conjunction with selected machine learning classifiers, namely the ELM, SVM and ESN, and validated it using the benchmark medical datasets of PIMA India diabetes and BUPA liver disorders, two-dimensional (2D) medical images, namely MIAS and INbreast and JSRT chest radiographs, as well as on the three-dimensional TCGA-BRCA breast MRI dataset. The results were investigated using the classification accuracy measure and the learning time. We also compared our methodology with the benchmarked multi-objective genetic algorithm (ES)-based optimization technique. The results authenticate the potential of the AIN optimised CDSS.

Made available in DSpace on 2016-03-15T19:38:14Z (GMT). No. of bitstreams: 1 Ederson Borges.pdf: 626219 bytes, checksum: d83887c1b3e2287f434525ac9701f0c7 (MD5) Previous issue date: 2010-01-27 / Clustering is an important data mining task from the field of Knowledge Discovery in Databases. There are several algorithms capable of performing clustering tasks, and the most popular ones involve the calculation of a similarity or distance measure among objects from the database. Many algorithms can perform clustering in a simple and efficient manner, but have drawbacks as a way to get the optimal number of partitions and the possibility of getting stuck in local optima solutions. To try and reduce these drawbacks this dissertation proposes a new clustering algorithm based on Artificial Immune Systems. This algorithm is characterized by the generation of multiple simultaneous high quality solutions in terms of the number of partitions (clusters) for the database and the use of a cost function that explicitly evaluates the quality of partitions, minimizing the inconvenience of getting stuck in local optima. The algorithm was tested using four databases known in the literature and obtained satisfactory results in terms of the diversity of solutions, but has a high computational cost compared to other algorithms tested. / Agrupamento de dados é uma importante tarefa da mineração de dados e descoberta de conhecimentos em bases de dados. Existem diversos algoritmos capazes de realizar a tarefa de agrupamento de dados, sendo que os mais populares envolvem o cálculo de similaridade ou distância entre objetos da base de dados. Boa parte dos algoritmos pode agrupar os dados de forma simples e eficiente, mas possui inconvenientes como a forma de obter o número ótimo de partições e a possibilidade de ficar preso em ótimos locais. Para tentar diminuir estes inconvenientes essa dissertação propõe um novo Algoritmo Imunológico para Agrupamento de Dados baseado em Sistemas Imunológicos Artificiais. Esse algoritmo é caracterizado pela geração de múltiplas soluções simultâneas de boa qualidade no que tange o número de partições (grupos) para a base de dados e uma função de custo que avalia explicitamente a qualidade dessas partições, minimizando o inconveniente de ficar preso em ótimos locais. O algoritmo foi testado utilizando quatro bases de dados conhecidas na literatura e obteve resultados satisfatórios no que tange a diversidade das soluções encontradas, mas apresentou um custo computacional elevado em relação a outros algoritmos testados.