In modern society, cancer has become one of the most terrifying diseases because of its high and increasing death rate. The disease's deep impact demands extensive research to detect and eradicate it in all its forms. Breast cancer is one of the most common forms of cancer, and approximately one in nine women in the Western world will develop it over the course of their lives. Screening programmes have been shown to reduce the mortality rate, but they introduce an enormous amount of information that must be processed by radiologists on a daily basis. Computer Aided Diagnosis (CAD) systems aim to assist clinicians in their decision-making process, by acting as a second opinion and helping improve the detection and classification ratios by spotting very difficult and subtle cases. Although the field of cancer detection is rapidly developing and crosses over imaging modalities, X-ray mammography remains the principal tool to detect the first signs of breast cancer in population screening. The advantages and disadvantages of other imaging modalities for breast cancer detection are discussed along with the improvements and difficulties encountered in screening programmes. Remarkable achievements to date in breast CAD are equally presented. This thesis introduces original results for the detection of features from mammographic image analysis to improve the effectiveness of early cancer screening programmes. The detection of early signs of breast cancer is vital in managing such a fast developing disease with poor survival rates. Some of the earliest signs of cancer in the breast are the clusters of microcalcifications. The proposed method is based on image filtering comprising partial differential equations (PDE) for image enhancement. Subsequently, microcalcifications are segmented using characteristics of the human visual system, based on the superior qualities of the human eye to depict localised changes of intensity and appearance in an image. Parameters are set according to the image characteristics, which makes the method fully automated. The detection of breast masses in temporal mammographic pairs is also investigated as part of the development of a complete breast cancer detection tool. The design of this latter algorithm is based on the detection sequence used by radiologists in clinical routine. To support the classification of masses into benign or malignant, novel tumour features are introduced. Image normalisation is another key concept discussed in this thesis along with its benefits for cancer detection.

Made available in DSpace on 2016-04-29T14:16:46Z (GMT). No. of bitstreams: 1 Nathalie Jacinta Rodrigues de Oliveira Py.pdf: 1071074 bytes, checksum: 13862fca79bbb6cfa67df01abeb5b819 (MD5) Previous issue date: 2015-12-02 / Goals: The goal of the study is an analyze of the implantation of health care public polities for mammography access in the Oiapoque river frontier between France and Brazil where there is several social inequalities in health care. Justifications: The interest to this subject has two influences: The work realized at the coordination of the Regional Cancer Network of French Guiana in collaboration with health care professionals, a social worker and a psychologist in the support to patients and their dose relatives. The knowledge of the frontier zone with the richness of the population and the challenges they take up in the everyday life by living far away from the main cities. Hypotheses: Two questions will be analyzed to answer the main problematic: Are the social determinants on health care for the frontier population regarded for the implantation of polities for breast cancer detection access? Which are the strategies of the public powers, institutional actors and the professionals to facilitate the access to mammography for the frontier population? Teorico-metodological aspects: The analyze of the social inequalities on health care influence will be based on the economist Amartya Sen theory on the link between social inequalities and individual freedom. A documental research and interviews of professionals working on the frontier had been realized to understand the specific context of the region, the brazilian and french health care system, the organization of the breast cancer detection for the frontier population. Results: We can conclude that the territorial inequalities has most impact on the access of mammographyfor the women living on frontier. The inequalities needs a coordination of the public action to realized the structural modifications, and also local actions promoting more interaction between professionals and population / Objetivos: Este trabalho tem como objetivo analisar a implementação das políticas publicas de saúde para o acesso à mamografia na região da fronteira fluvial do rio Oiapoque entre a França e o Brasil que apresenta varias situações de desigualdades sociais de saúde. Justificativa: O interesse por essa problemática teve duas influências: O trabalho realizado na coordenação da Rede regional do câncer da Guiana Francesa, em colaboração com os profissionais de saúde, uma assistente social e uma psicóloga no atendimento aos pacientes e familiares. O conhecimento de uma região de fronteira rica pela diversidade de sua população e dos desafios que enfrentam no seu quotidiano pelo distanciamento com as cidades principais. Duas questões foram contempladas para responder à problemática principal: Os determinantes sociais de saúde da população da região fronteiriça estão sendo contemplados na implementação das políticas de acesso à detecção do câncer de mama? Quais são as estratégias propostas pelos poderes públicos, os atores institucionais, os profissionais para facilitar o acesso à mamografia para a população da fronteira? Aspectos teórico-metodológicos: A análise da influência das desigualdades sociais de saúde no acesso a mamografia foi realizada com base na teoria do economista Amartya Sen sobre a relação entre as desigualdades sociais e a liberdade dos indivíduos. Uma pesquisa documental e entrevistas com profissionais da fronteira foram realizadas para entender o contexto específico da região, os sistemas de saúde brasileiros e francês e a organização da detecção do câncer de mama para a população fronteiriça. Resultados obtidos: Pudemos concluir que as desigualdades territoriais são maior impacto na falta de participação ao exame de as que tem detecção do câncer de mama das mulheres de vivem na fronteira. Essas desigualdades requerem uma ação pública coordenada para realizar mudanças estruturais "e de organização dos serviços públicos, mais também ações localizadas, promovendo maior interação entre os profissionais e a população

The Support Vector Machine (SVM) classifier seeks to find the separating hyperplane wx=r that maximizes the margin distance 1/||w||2^2. It can be formalized as an optimization problem that minimizes the hinge loss Ʃ[subscript i](1-y[subscript i] f(x[subscript i]))₊ plus the L₂-norm of the weight vector. SVM is now a mainstay method of machine learning. The goal of this dissertation work is to solve different biomedical data analysis problems efficiently using extensions of SVM, in which we augment the standard SVM formulation based on the application requirements. The biomedical applications we explore in this thesis include: cancer diagnosis, biomarker discovery, and energy function learning for protein structure prediction. Ovarian cancer diagnosis is problematic because the disease is typically asymptomatic especially at early stages of progression and/or recurrence. We investigate a sample set consisting of 44 women diagnosed with serous papillary ovarian cancer and 50 healthy women or women with benign conditions. We profile the relative metabolite levels in the patient sera using a high throughput ambient ionization mass spectrometry technique, Direct Analysis in Real Time (DART). We then reduce the diagnostic classification on these metabolic profiles into a functional classification problem and solve it with functional Support Vector Machine (fSVM) method. The assay distinguished between the cancer and control groups with an unprecedented 99\% accuracy (100\% sensitivity, 98\% specificity) under leave-one-out-cross-validation. This approach has significant clinical potential as a cancer diagnostic tool. High throughput technologies provide simultaneous evaluation of thousands of potential biomarkers to distinguish different patient groups. In order to assist biomarker discovery from these low sample size high dimensional cancer data, we first explore a convex relaxation of the L₀-SVM problem and solve it using mixed-integer programming techniques. We further propose a more efficient L₀-SVM approximation, fractional norm SVM, by replacing the L₂-penalty with L[subscript q]-penalty (q in (0,1)) in the optimization formulation. We solve it through Difference of Convex functions (DC) programming technique. Empirical studies on the synthetic data sets as well as the real-world biomedical data sets support the effectiveness of our proposed L₀-SVM approximation methods over other commonly-used sparse SVM methods such as the L₁-SVM method. A critical open problem in emph{ab initio} protein folding is protein energy function design. We reduce the problem of learning energy function for extit{ab initio} folding to a standard machine learning problem, learning-to-rank. Based on the application requirements, we constrain the reduced ranking problem with non-negative weights and develop two efficient algorithms for non-negativity constrained SVM optimization. We conduct the empirical study on an energy data set for random conformations of 171 proteins that falls into the {it ab initio} folding class. We compare our approach with the optimization approach used in protein structure prediction tool, TASSER. Numerical results indicate that our approach was able to learn energy functions with improved rank statistics (evaluated by pairwise agreement) as well as improved correlation between the total energy and structural dissimilarity.

This thesis presents the research results on the development of a microwave tomography imaging algorithm capable of reconstructing the dielectric properties of the unknown object. Our focus was on the theoretical aspects of the non-linear tomographic image reconstruction problem with particular emphasis on developing efficient numerical and non-linear optimization for solving the inverse scattering problem. A detailed description of a novel microwave tomography method based on frequency dependent finite difference time domain, a numerical method for solving Maxwell's equations and Genetic Algorithm (GA) as a global optimization technique is given. The proposed technique has the ability to deal with the heterogeneous and dispersive object with complex distribution of dielectric properties and to provide a quantitative image of permittivity and conductivity profile of the object. It is shown that the proposed technique is capable of using the multi-frequency, multi-view, and multi-incident planer techniques which provide useful information for the reconstruction of the dielectric properties profile and improve image quality. In addition, we show that when a-priori information about the object under test is known, it can be easily integrated with the inversion process. This provides realistic regularization of the solution and removes or reduces the possibility of non-true solutions. We further introduced application of the GA such as binary-coded GA, real-coded GA, hybrid binary and real coded GA, and neural-network/GA for solving the inverse scattering problem which improved the quality of the images as well as the conversion rate. The implications and possible advantages of each type of optimization are discussed, and synthetic inversion results are presented. The results showed that the proposed algorithm was capable of providing the quantitative images, although more research is still required to improve the image quality. In the proposed technique the computation time for solution convergence varies from a few hours to several days. Therefore, the parallel implementation of the algorithm was carried out to reduce the runtime. The proposed technique was evaluated for application in microwave breast cancer imaging as well as measurement data from university of Manitoba and Institut Frsenel's microwave tomography systems.

This thesis presents the research results on the development of a microwave tomography imaging algorithm capable of reconstructing the dielectric properties of the unknown object. Our focus was on the theoretical aspects of the non-linear tomographic image reconstruction problem with particular emphasis on developing efficient numerical and non-linear optimization for solving the inverse scattering problem. A detailed description of a novel microwave tomography method based on frequency dependent finite difference time domain, a numerical method for solving Maxwell's equations and Genetic Algorithm (GA) as a global optimization technique is given. The proposed technique has the ability to deal with the heterogeneous and dispersive object with complex distribution of dielectric properties and to provide a quantitative image of permittivity and conductivity profile of the object. It is shown that the proposed technique is capable of using the multi-frequency, multi-view, and multi-incident planer techniques which provide useful information for the reconstruction of the dielectric properties profile and improve image quality. In addition, we show that when a-priori information about the object under test is known, it can be easily integrated with the inversion process. This provides realistic regularization of the solution and removes or reduces the possibility of non-true solutions. We further introduced application of the GA such as binary-coded GA, real-coded GA, hybrid binary and real coded GA, and neural-network/GA for solving the inverse scattering problem which improved the quality of the images as well as the conversion rate. The implications and possible advantages of each type of optimization are discussed, and synthetic inversion results are presented. The results showed that the proposed algorithm was capable of providing the quantitative images, although more research is still required to improve the image quality. In the proposed technique the computation time for solution convergence varies from a few hours to several days. Therefore, the parallel implementation of the algorithm was carried out to reduce the runtime. The proposed technique was evaluated for application in microwave breast cancer imaging as well as measurement data from university of Manitoba and Institut Frsenel's microwave tomography systems.

Pilocytic astrocytoma (PA) is the most common brain tumor in children. This tumor is usually benign and has a good prognosis. Total resection is the treatment of choice and will cure the majority of patients. However, often only partial resection is possible due to the location of the tumor. In that case, spontaneous regression, regrowth, or progression to a more aggressive form have been observed. The dependency between the residual tumor size and spontaneous regression is not understood yet. Therefore, the prognosis is largely unpredictable and there is controversy regarding the management of patients for whom complete resection cannot be achieved. Strategies span from pure observation (wait and see) to combinations of surgery, adjuvant chemotherapy, and radiotherapy. Here, we introduce a mathematical model to investigate the growth and progression behavior of PA. In particular, we propose a Markov chain model incorporating cell proliferation and death as well as mutations. Our model analysis shows that the tumor behavior after partial resection is essentially determined by a risk coefficient γ, which can be deduced from epidemiological data about PA. Our results quantitatively predict the regression probability of a partially resected benign PA given the residual tumor size and lead to the hypothesis that this dependency is linear, implying that removing any amount of tumor mass will improve prognosis. This finding stands in contrast to diffuse malignant glioma where an extent of resection threshold has been experimentally shown, below which no benefit for survival is expected. These results have important implications for future therapeutic studies in PA that should include residual tumor volume as a prognostic factor.

Indiana University-Purdue University Indianapolis (IUPUI) / Cancer is still among those diseases that prominently contribute to the numerous deaths that are caused each year. But as technology and research is reaching new zeniths in the present times, cure or early detection of cancer is possible. The detection of rare cells can help understand the origin of many diseases. The current study deals with one such technology that is used for the capture or effective separation of these rare cells called Lab-on-a-chip microchip technology. The isolation and capture of rare cells is a problem uniquely suited to microfluidic devices, in which geometries on the cellular length scale can be engineered and a wide range of chemical functionalizations can be implemented. The performance of such devices is primarily affected by the chemical interaction between the cell and the capture surface and the mechanics of cell-surface collision and adhesion. This study focuses on the fundamental adhesion and transport mechanisms in rare cell-capture microdevices, and explores modern device design strategies in a transport context. The biorheology and engineering parameters of cell adhesion are defined; chip geometries are reviewed. Transport at the microscale, cell-wall interactions that result in cell motion across streamlines, is discussed. We have concentrated majorly on the fluid dynamics design of the chip. A simplified description of the device would be to say that the chip is at micro scale. There are posts arranged on the chip such that the arrangement will lead to a higher capture of rare cells. Blood consisting of rare cells will be passed through the chip and the posts will pose as an obstruction so that the interception and capture efficiency of the rare cells increases. The captured cells can be observed by fluorescence microscopy. As compared to previous studies of using solid microposts, we will be incorporating a new concept of cylindrical shell micropost. This type of micropost consists of a solid inner core and the annulus area is covered with a forest of silicon nanopillars. Utilization of such a design helps in increasing the interception and capture efficiency and reducing the hydrodynamic resistance between the cells and the posts. Computational analysis is done for different designs of the posts. Drag on the microposts due to fluid flow has a great significance on the capture efficiency of the chip. Also, the arrangement of the posts is important to contributing to the increase in the interception efficiency. The effects of these parameters on the efficiency in junction with other factors have been studied and quantified. The study is concluded by discussing design strategies with a focus on leveraging the underlying transport phenomena to maximize device performance.

No description available.

No description available.

Studying the internal characteristics of a network using measurements obtained from endhosts is known as network tomography. The foremost challenge in measurement-based approaches is the large size of a network, where only a subset of measurements can be obtained because of the inaccessibility of the entire network. As the network becomes larger, a question arises as to how rapidly the monitoring resources (number of measurements or number of samples) must grow to obtain a desired monitoring accuracy. Our work studies the scalability of the measurements with respect to the size of the network. We investigate the issues of scalability and performance evaluation in IP networks, specifically focusing on fault and congestion diagnosis. We formulate network monitoring as a machine learning problem using probabilistic graphical models that infer network states using path-based measurements. We consider the theoretical and practical management resources needed to reliably diagnose congested/faulty network elements and provide fundamental limits on the relationships between the number of probe packets, the size of the network, and the ability to accurately diagnose such network elements. We derive lower bounds on the average number of probes per edge using the variational inference technique proposed in the context of graphical models under noisy probe measurements, and then propose an entropy lower (EL) bound by drawing similarities between the coding problem over a binary symmetric channel and the diagnosis problem. Our investigation is supported by simulation results. For the congestion diagnosis case, we propose a solution based on decoding linear error control codes on a binary symmetric channel for various probing experiments. To identify the congested nodes, we construct a graphical model, and infer congestion using the belief propagation algorithm. In the second part of the work, we focus on the development of methods to automatically analyze the information contained in electron tomograms, which is a major challenge since tomograms are extremely noisy. Advances in automated data acquisition in electron tomography have led to an explosion in the amount of data that can be obtained about the spatial architecture of a variety of biologically and medically relevant objects with sizes in the range of 10-1000 nm A fundamental step in the statistical inference of large amounts of data is to segment relevant 3D features in cellular tomograms. Procedures for segmentation must work robustly and rapidly in spite of the low signal-to-noise ratios inherent in biological electron microscopy. This work evaluates various denoising techniques and then extracts relevant features of biological interest in tomograms of HIV-1 in infected human macrophages and Bdellovibrio bacterial tomograms recorded at room and cryogenic temperatures. Our approach represents an important step in automating the efficient extraction of useful information from large datasets in biological tomography and in speeding up the process of reducing gigabyte-sized tomograms to relevant byte-sized data. Next, we investigate automatic techniques for segmentation and quantitative analysis of mitochondria in MNT-1 cells imaged using ion-abrasion scanning electron microscope, and tomograms of Liposomal Doxorubicin formulations (Doxil), an anticancer nanodrug, imaged at cryogenic temperatures. A machine learning approach is formulated that exploits texture features, and joint image block-wise classification and segmentation is performed by histogram matching using a nearest neighbor classifier and chi-squared statistic as a distance measure.