The research presented in this thesis represents a body of work which addresses issues in medical imaging, primarily as it applies to breast cancer screening and laparoscopic surgery. The concern here is how computer based methods can aid medical practitioners in these tasks. Thus, research is presented which develops both new techniques of analysing radiologists performance data and also new approaches of examining surgeons visual behaviour when they are undertaking laparoscopic training. Initially a new chest X-Ray self-assessment application is described which has been developed to assess and improve radiologists performance in detecting lung cancer. Then, in breast cancer screening, a method of identifying potential poor performance outliers at an early stage in a national self-assessment scheme is demonstrated. Additionally, a method is presented to optimize whether a radiologist, in using this scheme, has correctly localised and identified an abnormality or made an error. One issue in appropriately measuring radiological performance in breast screening is that both the size of clinical monitors used and the difficulty in linking the medical image to the observer s line of sight hinders suitable eye tracking. Consequently, a new method is presented which links these two items. Laparoscopic surgeons have similar issues to radiologists in interpreting a medical display but with the added complications of hand-eye co-ordination. Work is presented which examines whether visual search feedback of surgeons operations can be useful training aids.

No description available.

Bayesian network (BN) structure learning from data has been an active research area in the machine learning field in recent decades. Much of the research has considered BN structure learning as an optimization problem. However, the finding of optimal BN from data is NP-hard. This fact has driven the use of heuristic algorithms for solving this kind of problem. Amajor recent focus in BN structure learning is on search and score algorithms. In these algorithms, a scoring function is introduced and a heuristic search algorithm is used to evaluate each network with respect to the training data. The optimal network is produced according to the best score evaluated. This thesis investigates a range of search and score algorithms to understand the relationship between technique performance and structure features of the problems. The main contributions of this thesis include (a) Two novel Ant Colony Optimization based search and score algorithms for BN structure learning; (b) Node juxtaposition distribution for studying the relationship between the best node ordering and the optimal BN structure; (c) Fitness landscape analysis for investigating the di erent performances of both chain score function and the CH score function; (d) A classifier method is constructed by utilizing receiver operating characteristic curve with the results on fitness landscape analysis; and finally (e) a selective o -line hyperheuristic algorithm is built for unseen BN structure learning with search and score algorithms. In this thesis, we also construct a new algorithm for producing BN benchmark structures and apply our novel approaches to a range of benchmark problems and real world problem.

Traditional multiple hypothesis testing procedures, such as that of Benjamini and Hochberg, fix an error rate and determine the corresponding rejection region. In 2002 Storey proposed a fixed rejection region procedure and showed numerically that it can gain more power than the fixed error rate procedure of Benjamini and Hochberg while controlling the same false discovery rate (FDR). In this thesis it is proved that when the number of alternatives is small compared to the total number of hypotheses, Storeys method can be less powerful than that of Benjamini and Hochberg. Moreover, the two procedures are compared by setting them to produce the same FDR. The difference in power between Storeys procedure and that of Benjamini and Hochberg is near zero when the distance between the null and alternative distributions is large, but Benjamini and Hochbergs procedure becomes more powerful as the distance decreases. It is shown that modifying the Benjamini and Hochberg procedure to incorporate an estimate of the proportion of true null hypotheses as proposed by Black gives a procedure with superior power.<p> Multiple hypothesis testing can also be applied to regression diagnostics. In this thesis, a Bayesian method is proposed to test multiple hypotheses, of which the i-th null and alternative hypotheses are that the i-th observation is not an outlier versus it is, for i=1,...,m. In the proposed Bayesian model, it is assumed that outliers have a mean shift, where the proportion of outliers and the mean shift respectively follow a Beta prior distribution and a normal prior distribution. It is proved in the thesis that for the proposed model, when there exists more than one outlier, the marginal distributions of the deletion residual of the i-th observation under both null and alternative hypotheses are doubly noncentral t distributions. The outlyingness of the i-th observation is measured by the marginal posterior probability that the i-th observation is an outlier given its deletion residual. An importance sampling method is proposed to calculate this probability. This method requires the computation of the density of the doubly noncentral F distribution and this is approximated using Patnaiks approximation. An algorithm is proposed in this thesis to examine the accuracy of Patnaiks approximation. The comparison of this algorithms output with Patnaiks approximation shows that the latter can save massive computation time without losing much accuracy.<p> The proposed Bayesian multiple outlier identification procedure is applied to some simulated data sets. Various simulation and prior parameters are used to study the sensitivity of the posteriors to the priors. The area under the ROC curves (AUC) is calculated for each combination of parameters. A factorial design analysis on AUC is carried out by choosing various simulation and prior parameters as factors. The resulting AUC values are high for various selected parameters, indicating that the proposed method can identify the majority of outliers within tolerable errors. The results of the factorial design show that the priors do not have much effect on the marginal posterior probability as long as the sample size is not too small.<p> In this thesis, the proposed Bayesian procedure is also applied to a real data set obtained by Kanduc et al. in 2008. The proteomes of thirty viruses examined by Kanduc et al. are found to share a high number of pentapeptide overlaps to the human proteome. In a linear regression analysis of the level of viral overlaps to the human proteome and the length of viral proteome, it is reported by Kanduc et al. that among the thirty viruses, human T-lymphotropic virus 1, Rubella virus, and hepatitis C virus, present relatively higher levels of overlaps with the human proteome than the predicted level of overlaps. The results obtained using the proposed procedure indicate that the four viruses with extremely large sizes (Human herpesvirus 4, Human herpesvirus 6, Variola virus, and Human herpesvirus 5) are more likely to be the outliers than the three reported viruses. The results with thefour extreme viruses deleted confirm the claim of Kanduc et al.

Traditional multiple hypothesis testing procedures, such as that of Benjamini and Hochberg, fix an error rate and determine the corresponding rejection region. In 2002 Storey proposed a fixed rejection region procedure and showed numerically that it can gain more power than the fixed error rate procedure of Benjamini and Hochberg while controlling the same false discovery rate (FDR). In this thesis it is proved that when the number of alternatives is small compared to the total number of hypotheses, Storeys method can be less powerful than that of Benjamini and Hochberg. Moreover, the two procedures are compared by setting them to produce the same FDR. The difference in power between Storeys procedure and that of Benjamini and Hochberg is near zero when the distance between the null and alternative distributions is large, but Benjamini and Hochbergs procedure becomes more powerful as the distance decreases. It is shown that modifying the Benjamini and Hochberg procedure to incorporate an estimate of the proportion of true null hypotheses as proposed by Black gives a procedure with superior power.<p> Multiple hypothesis testing can also be applied to regression diagnostics. In this thesis, a Bayesian method is proposed to test multiple hypotheses, of which the i-th null and alternative hypotheses are that the i-th observation is not an outlier versus it is, for i=1,...,m. In the proposed Bayesian model, it is assumed that outliers have a mean shift, where the proportion of outliers and the mean shift respectively follow a Beta prior distribution and a normal prior distribution. It is proved in the thesis that for the proposed model, when there exists more than one outlier, the marginal distributions of the deletion residual of the i-th observation under both null and alternative hypotheses are doubly noncentral t distributions. The outlyingness of the i-th observation is measured by the marginal posterior probability that the i-th observation is an outlier given its deletion residual. An importance sampling method is proposed to calculate this probability. This method requires the computation of the density of the doubly noncentral F distribution and this is approximated using Patnaiks approximation. An algorithm is proposed in this thesis to examine the accuracy of Patnaiks approximation. The comparison of this algorithms output with Patnaiks approximation shows that the latter can save massive computation time without losing much accuracy.<p> The proposed Bayesian multiple outlier identification procedure is applied to some simulated data sets. Various simulation and prior parameters are used to study the sensitivity of the posteriors to the priors. The area under the ROC curves (AUC) is calculated for each combination of parameters. A factorial design analysis on AUC is carried out by choosing various simulation and prior parameters as factors. The resulting AUC values are high for various selected parameters, indicating that the proposed method can identify the majority of outliers within tolerable errors. The results of the factorial design show that the priors do not have much effect on the marginal posterior probability as long as the sample size is not too small.<p> In this thesis, the proposed Bayesian procedure is also applied to a real data set obtained by Kanduc et al. in 2008. The proteomes of thirty viruses examined by Kanduc et al. are found to share a high number of pentapeptide overlaps to the human proteome. In a linear regression analysis of the level of viral overlaps to the human proteome and the length of viral proteome, it is reported by Kanduc et al. that among the thirty viruses, human T-lymphotropic virus 1, Rubella virus, and hepatitis C virus, present relatively higher levels of overlaps with the human proteome than the predicted level of overlaps. The results obtained using the proposed procedure indicate that the four viruses with extremely large sizes (Human herpesvirus 4, Human herpesvirus 6, Variola virus, and Human herpesvirus 5) are more likely to be the outliers than the three reported viruses. The results with thefour extreme viruses deleted confirm the claim of Kanduc et al.

Στην εργασία χρησιμοποιούνται σήματα καρδιακού ρυθμού, τα οποία αντιστοιχούν σε φυσιολογικές και οξαιμικές περιπτώσεις.Στην συνέχεια αυτά τα σήματα τα επεξεργαζόμαστε με διάφορες τεχνικές. Στόχος της εργασίας αυτής είναι ο διαχωρισμός των δυο αυτών ομάδων. / In this thesis are used signals of cardiac rythm, that correspond in physiologic and oxidemic cases.Then we processed these signals with various techniques.Target of this thesis is the segregation of this two teams.

Steered Response Power based algorithms are widely used for finding sound source location using microphone array systems. SRCP-PHAT is one such algorithm that has a robust performance under noisy and reverberant conditions. The algorithm creates a likelihood function over the field of view. This thesis employs image processing methods on SRCP-PHAT images, to exploit the difference in power levels and pixel patterns to discriminate between sound source and background pixels. Hough Transform based ellipse detection is used to identify the sound source locations by finding the centers of elliptical edge pixel regions typical of source patterns. Monte Carlo simulations of an eight microphone perimeter array with single and multiple sound sources are used to simulate the test environment and area under receiver operating characteristic (ROCA) curve is used to analyze the algorithm performance. Performance was compared to a simpler algorithm involving Canny edge detection and image averaging and an algorithms based simply on the magnitude of local maxima in the SRCP image. Analysis shows that Canny edge detection based method performed better in the presence of coherent noise sources.

Em vista das mudanças ambientais em nível global, disponibilizar informações ecológicas e buscar uma melhor compreensão dos fatores e processos que moldam a distribuição de espécies, é uma iniciativa importante para o planejamento de ações de conservação. Neste contexto, a importância e carência de informações sobre a distribuição geográficas das espécies nos motivaram a predizer a distribuição potencial de arbustos e árvores das famílias Lauraceae e Myrtaceae na Floresta Atlântica, no sul do Brasil. Modelos lineares generalizados (GLM) foram usados para ajustar modelos preditivos com os registros de ocorrência de 88 espécies em função de variáveis ambientais. As variáveis preditoras foram selecionadas com base no menor critério de informação de Akaike corrigido. Nós avaliamos o desempenho dos modelos usando o método de validação cruzada (10-fold) para calcular a habilidade estatística verdadeira (TSS) e a área sob a curva característica do operador receptor (AUC). Nós usamos GLM para testar a influência da área de ocorrência estimada, do número de registros das espécies e da complexidade dos modelos sobre a TSS e a AUC. Nossos resultados mostraram que as variáveis climáticas governam amplamente a distribuição de espécies, mas as variáveis que captam as variações ambientais locais são relativamente importantes na área de estudo. A TSS foi significativamente influenciada pelo número de registros e complexidade dos modelos, enquanto a AUC sofreu com o efeito de todos os três fatores avaliados. A interação entre estes fatores é uma questão importante e a ser considerada em novas avaliações sobre ambas medidas e com diferentes técnicas de modelagem. Nossos resultados também mostraram que as distribuições de algumas espécies foram superestimadas e outras corresponderam bem com a ocorrência por nós conhecida. Efetivamente nossos resultados têm fundamentos para embasar novos levantamentos de campo, a avaliação de áreas prioritárias e planos de conservação, além de inferências dos efeitos de mudanças ambientais sobre as espécies da Mata Atlântica. / In view of environmental change on a global level, providing ecological information and getting a better understanding of the factors and processes that shape species distribution is an important initiative for planning conservation actions. In this context, the importance and lack of information about the geographical distribution of species motivated us to predict the potential species distribution of shrubs and trees of the family Lauraceae and Myrtaceae, in the Atlantic Forest in southern Brazil. Generalized linear models (GLM) were used to fit predictive models with records of occurrence of 88 species according to environmental variables. Predictor variables were selected based on the lowest corrected Akaike information criterion. We evaluate the performance of the models using the method of cross-validation (10-fold) to calculate the true skill statistic (TSS) and area under the receiver operator characteristic curve (AUC). We used GLM to test the influence of the area of occurrence estimated, the number of records of the species and the complexity of the models on the TSS and AUC. Our results show that climatic variables largely govern the distribution of species, but the variables that capture the local environmental variations are relatively important in the study area. The TSS was significantly influenced by the number of records and complexity of models while the AUC suffered from the effect of all three evaluated factors. The interaction between these factors is an important issue and be considered for new reviews on both measures and with different modeling techniques. Our results also showed that the distributions of some species were overestimated and other corresponded well with the occurrence known to us. Indeed our results have foundations to support new field surveys, assessment of priority areas and conservation plans, and inferences of the effects of environmental change on species of the Atlantic Forest.

Em vista das mudanças ambientais em nível global, disponibilizar informações ecológicas e buscar uma melhor compreensão dos fatores e processos que moldam a distribuição de espécies, é uma iniciativa importante para o planejamento de ações de conservação. Neste contexto, a importância e carência de informações sobre a distribuição geográficas das espécies nos motivaram a predizer a distribuição potencial de arbustos e árvores das famílias Lauraceae e Myrtaceae na Floresta Atlântica, no sul do Brasil. Modelos lineares generalizados (GLM) foram usados para ajustar modelos preditivos com os registros de ocorrência de 88 espécies em função de variáveis ambientais. As variáveis preditoras foram selecionadas com base no menor critério de informação de Akaike corrigido. Nós avaliamos o desempenho dos modelos usando o método de validação cruzada (10-fold) para calcular a habilidade estatística verdadeira (TSS) e a área sob a curva característica do operador receptor (AUC). Nós usamos GLM para testar a influência da área de ocorrência estimada, do número de registros das espécies e da complexidade dos modelos sobre a TSS e a AUC. Nossos resultados mostraram que as variáveis climáticas governam amplamente a distribuição de espécies, mas as variáveis que captam as variações ambientais locais são relativamente importantes na área de estudo. A TSS foi significativamente influenciada pelo número de registros e complexidade dos modelos, enquanto a AUC sofreu com o efeito de todos os três fatores avaliados. A interação entre estes fatores é uma questão importante e a ser considerada em novas avaliações sobre ambas medidas e com diferentes técnicas de modelagem. Nossos resultados também mostraram que as distribuições de algumas espécies foram superestimadas e outras corresponderam bem com a ocorrência por nós conhecida. Efetivamente nossos resultados têm fundamentos para embasar novos levantamentos de campo, a avaliação de áreas prioritárias e planos de conservação, além de inferências dos efeitos de mudanças ambientais sobre as espécies da Mata Atlântica. / In view of environmental change on a global level, providing ecological information and getting a better understanding of the factors and processes that shape species distribution is an important initiative for planning conservation actions. In this context, the importance and lack of information about the geographical distribution of species motivated us to predict the potential species distribution of shrubs and trees of the family Lauraceae and Myrtaceae, in the Atlantic Forest in southern Brazil. Generalized linear models (GLM) were used to fit predictive models with records of occurrence of 88 species according to environmental variables. Predictor variables were selected based on the lowest corrected Akaike information criterion. We evaluate the performance of the models using the method of cross-validation (10-fold) to calculate the true skill statistic (TSS) and area under the receiver operator characteristic curve (AUC). We used GLM to test the influence of the area of occurrence estimated, the number of records of the species and the complexity of the models on the TSS and AUC. Our results show that climatic variables largely govern the distribution of species, but the variables that capture the local environmental variations are relatively important in the study area. The TSS was significantly influenced by the number of records and complexity of models while the AUC suffered from the effect of all three evaluated factors. The interaction between these factors is an important issue and be considered for new reviews on both measures and with different modeling techniques. Our results also showed that the distributions of some species were overestimated and other corresponded well with the occurrence known to us. Indeed our results have foundations to support new field surveys, assessment of priority areas and conservation plans, and inferences of the effects of environmental change on species of the Atlantic Forest.

Em vista das mudanças ambientais em nível global, disponibilizar informações ecológicas e buscar uma melhor compreensão dos fatores e processos que moldam a distribuição de espécies, é uma iniciativa importante para o planejamento de ações de conservação. Neste contexto, a importância e carência de informações sobre a distribuição geográficas das espécies nos motivaram a predizer a distribuição potencial de arbustos e árvores das famílias Lauraceae e Myrtaceae na Floresta Atlântica, no sul do Brasil. Modelos lineares generalizados (GLM) foram usados para ajustar modelos preditivos com os registros de ocorrência de 88 espécies em função de variáveis ambientais. As variáveis preditoras foram selecionadas com base no menor critério de informação de Akaike corrigido. Nós avaliamos o desempenho dos modelos usando o método de validação cruzada (10-fold) para calcular a habilidade estatística verdadeira (TSS) e a área sob a curva característica do operador receptor (AUC). Nós usamos GLM para testar a influência da área de ocorrência estimada, do número de registros das espécies e da complexidade dos modelos sobre a TSS e a AUC. Nossos resultados mostraram que as variáveis climáticas governam amplamente a distribuição de espécies, mas as variáveis que captam as variações ambientais locais são relativamente importantes na área de estudo. A TSS foi significativamente influenciada pelo número de registros e complexidade dos modelos, enquanto a AUC sofreu com o efeito de todos os três fatores avaliados. A interação entre estes fatores é uma questão importante e a ser considerada em novas avaliações sobre ambas medidas e com diferentes técnicas de modelagem. Nossos resultados também mostraram que as distribuições de algumas espécies foram superestimadas e outras corresponderam bem com a ocorrência por nós conhecida. Efetivamente nossos resultados têm fundamentos para embasar novos levantamentos de campo, a avaliação de áreas prioritárias e planos de conservação, além de inferências dos efeitos de mudanças ambientais sobre as espécies da Mata Atlântica. / In view of environmental change on a global level, providing ecological information and getting a better understanding of the factors and processes that shape species distribution is an important initiative for planning conservation actions. In this context, the importance and lack of information about the geographical distribution of species motivated us to predict the potential species distribution of shrubs and trees of the family Lauraceae and Myrtaceae, in the Atlantic Forest in southern Brazil. Generalized linear models (GLM) were used to fit predictive models with records of occurrence of 88 species according to environmental variables. Predictor variables were selected based on the lowest corrected Akaike information criterion. We evaluate the performance of the models using the method of cross-validation (10-fold) to calculate the true skill statistic (TSS) and area under the receiver operator characteristic curve (AUC). We used GLM to test the influence of the area of occurrence estimated, the number of records of the species and the complexity of the models on the TSS and AUC. Our results show that climatic variables largely govern the distribution of species, but the variables that capture the local environmental variations are relatively important in the study area. The TSS was significantly influenced by the number of records and complexity of models while the AUC suffered from the effect of all three evaluated factors. The interaction between these factors is an important issue and be considered for new reviews on both measures and with different modeling techniques. Our results also showed that the distributions of some species were overestimated and other corresponded well with the occurrence known to us. Indeed our results have foundations to support new field surveys, assessment of priority areas and conservation plans, and inferences of the effects of environmental change on species of the Atlantic Forest.