Orientador: Maria Salete Costa Gurgel / Tese (doutorado) - Universidade Estadual de Campinas, Faculdade de Ciências Médicas / Made available in DSpace on 2018-08-16T08:33:14Z (GMT). No. of bitstreams: 1 Marchi_AiltonAugustinho_D.pdf: 9456624 bytes, checksum: 782ef6ab113505e5dd645d40ac6c0d3b (MD5) Previous issue date: 2010 / Resumo: Objetivos: Avaliar a adesão e identificar falhas de aderência das mulheres atendidas em serviços de saúde públicos e privados às recomendações dos programas de rastreamento mamográfico. Sujeitos e Métodos: Estudo prospectivo que acompanhou 460 mulheres na cidade de Taubaté, São Paulo, Brasil, das quais 327 foram atendidas em serviços de saúde públicos e 133 em serviços privados, durante o período de cinco anos após a realização de mamografia-índice. Avaliou-se a adesão ao rastreamento mamográfico através do número de mamografias realizadas nesse período e também pelos intervalos de repetição entre os exames, respectivamente em 18, 24 e 30 meses. Analisou-se a frequência de repetição da mamografia e os fatores associados à adesão ao rastreamento mamográfico vigente. Elegeu-se o intervalo de repetição entre as mamografias superior a 30 meses para definir falha de adesão ao rastreamento mamográfico oportunístico. As associações dos desfechos com as variáveis independentes foram estudadas pela técnica de regressão de Cox, com obtenção das razões de risco (RR) e respectivos intervalos de confiança de 95% (IC95%). Resultados: Apesar de mais de 90% das entrevistadas terem repetido pelo menos uma vez o exame de mamografia, a adesão correta às recomendações do rastreamento mamográfico, com a sua repetição a cada 24 meses, revelou taxas muito baixas, ao redor de 30%, na amostra estudada. As falhas de adesão ocorreram em 51,1% das entrevistadas. O acesso público aos serviços de saúde (RR 1,44; IC95% 1,06-1,96), a ausência de rastreio prévio (RR 1,53; IC95% 1,17-2,00) e a frequência esporádica aos serviços médicos (RR 1,41; IC95% 1,05-1,89) foram os fatores associados às falhas de adesão. Conclusões: Ocorreu baixa adesão às recomendações do rastreamento mamográfico do câncer de mama em ambos os segmentos populacionais estudados. As políticas de rastreamento mamográfico com caráter exclusivamente oportunístico ocasionam falhas de adesão constantes e mais comuns entre as mulheres atendidas nos serviços públicos de saúde / Abstract: Objective: to assess compliance and identify lacks of adherence with the recommendations for breast cancer screening by mammography. Subject and Methods: Prospective study which follow-up 460 women in the city of Taubaté, São Paulo, Brazil, during five years after perform index mammography, 327 of them attended by the public health system and 133 by the private system. The adherence to mammographic screening were assessed through number of underwent mammographies in this period and repeated intervals among the exams at 18, 24 and 30 month, respectively. Prevalence of repeat mammography and predictors associated to adherence to current mammographic screening were analyzed. The repeated interval among mammographies above 30 month was selected to define lack of adherence to opportunistic mammographic screening. The outcomes associations with independent variables were studied by risk ratio (RR) and 95% confidence intervals (95%CI) performed through Cox-regression model. Results: although more than 90% of the studied women repeated the mammography at least once, the rate of correct compliance with the recommendations of mammographic screening, with repetition of the procedure every 24 months, was low, around 30%, in sample studied. The adherence flaws ocurred in about 51.1% of the interviewees and the unequal access to healthcare services, public or private (RR 1.44; 95%CI 1.06-1.96), absence of previous screening (RR 1.53; 95%CI 1.17-2.00), less visiting medical services (RR 1.41; 95%CI 1.05-1.89) were the associated factors to lack of adherence. Conclusion: we concluded that compliance with the recommendations to mammographic screening for breast cancer was low in both studied population segments. The opportunistic model of mammographic screening policies provokes recurrent lack of adherence which is more common among women attended in public healthcare services / Doutorado / Tocoginecologia / Doutor em Tocoginecologia

CoordenaÃÃo de AperfeiÃoamento de Pessoal de NÃvel Superior / O cÃncer de mama (CM) à um problema de saÃde pÃblica mundial. Uma em cada oito mulheres terà cÃncer de mama, tornando-se assim a neoplasia mais freqÃente entre as mulheres. O cÃncer de mama està ligado à identidade feminina no tocante a sua potÃncia orgÃstica e a sua sensualidade. Elaborar estratÃgicas cirÃrgicas confiÃveis pouco agressivas e menos multilantes tem sido busca de respostas a muitas pesquisas. Objetivo: O presente estudo visou avaliar a concordÃncia do volume tumoral entre a avaliaÃÃo anatomopatolÃgica e os mÃtodos de diagnÃstico por imagem dedicados a mama: Mamografia (MX), Ultra-som (US) e RessonÃncia magnÃtica (RMM), em mulheres com cÃncer de mama localmente avanÃado, submetidas à quimioterapia neoadjuvante. Pacientes e MÃtodos: Foram analisadas 95 mulheres portadoras de neoplasia mamÃria oriundas dos ambulatÃrios da Maternidade Escola Assis Chateaubriant (MEAC), Centro Regional e Integrado de Oncologia (CRIO) e Instituto do CÃncer do Cearà (ICC), no perÃodo de marÃo de 2003 a marÃo de 2005. Estas pacientes foram divididas em dois grupos. Grupo Tratamento (GT) com n=46 e Grupo Controle (GC) com n=49. Realizou-se anÃlise nÃo paramÃtrica correlacionando as variÃveis estudadas com o padrÃo ouro, ou seja, a anatomia patolÃgica. Os resultados mostraram concordÃncia na anÃlise volumÃtrica dos mÃtodos imaginolÃgicos e o padrÃo-ouro no GT nos seguintes percentuais: RMM: 0,70; US: 0,63 e MX: 0,42. Quando comparado ao grupo controle os valores encontrados foram RMM: 0,72; US: 0,70 e MX: 0,41. ConclusÃo: A RMM deteve os maiores valores de concordÃncia volumÃtrica em percentuais semelhantes nos dois grupos (GT e GC) e a MX, mÃtodo de imagem mais difundido, ofereceu os menores Ãndices de concordÃncia imaginolÃgica quando comparado com a avaliaÃÃo anatomopatolÃgica. A US apresentou valores de concordÃncia volumÃtrica satisfatÃria quando, comparada a RMM, devendo ressaltar que se trata de mÃtodo operador dependente. / The cancer of breast (CB) it is a problem of world public health. One in each eight women will have cancer of breast, becoming like this the most frequent neoplasia among the women. CB it is tied up the feminine identity concerning its potency of orgasm and her sensuality. To elaborate surgical strategic reliable not very aggressive and less mutilate has been search of answers to many researches. Objective: The present study was to evaluate the agreement of the volume of tumor to the evaluation anatomopathological and the diagnosis methods for image dedicated to he/she suckles her: Mammography (MX), Ultra-sound (US) and magnetic Resonance (RMM), in women with cancer of breast locally advanced, submitted to the neoadjuvante chemotherapy. Patient and Methods: 95 women carriers of mammary neoplasia originating from of the national health clinics of the Maternity Escola Assis Chateaubriant (MEAC), Center Regional and Integrated of Oncology (CRIO) and Institute of Cancer of Cearà (ICC) were analyzed at the period of 2003 March to 2005 March. These patient ones were divided in two groups. Treatment Group (TG) with n=46 and Control Group (CG) with n=49. Non parametric analysis correlating the variables was compared with the standard gold, the anatomopathological analysis. Results: The data showed agreement in it analyzes at volumÃtrica of the imaginolÃgicos methods and the pattern-gold in TG in the following percentages: RMM: 0.70; US: 0.63 and MX: 0.42, when compared to the control group, where were found values of RMM: 0.72; US: 0.70 and MX: 0.41. Conclusion: RMM stopped the largest values of agreement volumÃtrica in percentile similar in the two groups (GT and GC) and MX, spread image method, offered the smallest indexes of agreement imaginolÃgica when compared with the evaluation anatomopathological. US presented values of agreement satisfactory volumÃtrica when, compared RMM, should stand out that is method dependent operator.

Made available in DSpace on 2016-08-16T18:18:41Z (GMT). No. of bitstreams: 1 Tese Daniel Duarte Costa.pdf: 3067192 bytes, checksum: b9a8d78583596a2e1dff6298c4a89014 (MD5) Previous issue date: 2012-12-06 / Conselho Nacional de Desenvolvimento Científico e Tecnológico / Breast cancer is the leading cause of cancer death among women in Western countries. To improve the accuracy of diagnosis by radiologists and doing it so early, new computer vision systems have been developed and improved with the passage of time. Some methods of the detection and classification of lesions in mammography images for computer systems diagnostic (CAD) were developed using different statistical techniques. In this thesis, we present methodologies of CADs systems to detect and classify mass regions in mammographic images, from two image databases: DDSM and MIAS. The results show that it is possible by these methods to obtain a detection rate of up to 96% of mass regions, using efficient coding technique and K-means clustering algorithm. To classify regions in mass or non-mass correctly, was obtained a success rate up to 90% using the independent component analysis (ICA) and linear discriminant analysis (LDA). From these results generated a web application, called SADIM (Sistema de Auxílio a Diagnóstico de Imagem Mamográfica), which can be used by any registered professional. / O câncer de mama é a principal causa de morte por câncer na população feminina dos países ocidentais. Para melhorar a precisão do diagnóstico por radiologistas e fazê-lo de forma precoce, novos sistemas de visão computacional têm sido criados e melhorados com o decorrer do tempo. Alguns métodos de detecção e classificação da lesão em imagens radiológicas, por sistemas de diagnósticos por computador (CAD), foram desenvolvidos utilizando diferentes técnicas estatísticas. Neste trabalho, apresentam-se metodologias de sistemas CADs para detectar e classificar regiões de massa em imagens mamográficas, oriundas de duas bases de imagens: DDSM e MIAS. Os resultados mostram que é possível, através destas metodologias, obter uma taxa de detecção de até 96% das regiões de massa, utilizando a técnica de codificação eficiente com o algoritmo de agrupamento k-means, e classificar corretamente as regiões de massa em até 90% utilizando-se das técnicas de análise de componentes independentes (ICA) e análise discriminante linear (LDA). A partir destes resultados gerou-se uma aplicação web, denominada SADIM (Sistema de Auxílio a Diagnóstico de Imagem Mamográfica), que pode ser utilizado por qualquer profissional cadastrado. Palavras-chave: processamento de imagens médicas; diagnóstico auxiliado por computador; mamografias análise de imagens; codificação eficiente.

Made available in DSpace on 2016-08-17T14:53:15Z (GMT). No. of bitstreams: 1 Daniel Rodrigues Ericeira.pdf: 2002346 bytes, checksum: df76ac081a5d0e5816a81b5699935561 (MD5) Previous issue date: 2011-03-17 / Mammography is the exam of the breast, used as breast cancer prevention and also as a diagnostic method. This exam, which consists in an X-Ray of the breast, allows cancer detection. The purpose of this work is to use image processing techniques and computer vision to help specialists in detecting suspect regions and masses in digital mammographies. The first stage of the methodology consists in pre-processing the images to make them more suitable to registration, through noise reduction, image segmentation and re-scale. The next stage presents bilateral left and right breast image pairs registration. In order to correct position and compression differences that occur during the exams, rigid registration (followed by optic flow deformable registration) was applied in each image pair. Corresponding pairs of regions were related and their mutual variations were measured through cross-variogram spatial description. On the next stage, a training model for a Support Vector Machine (SVM) was created using as characteristics the cross-variogram values of each pair of regions of 180 cases. This SVM was tested for 100 new cases. The region pairs that contained lesions were classified as suspect regions , and the other regions as non-suspect regions . From the suspect regions, variogram characteristics were extracted as tissue texture descriptors. The regions that contained masses were classified as mass regions and the other regions as non-mass regions . Stepwise linear discriminant analysis was applied to select the most significant characteristics to train the second SVM. Tests with 30 new cases were performed for the trained SVM final classification in mass or non-mass . The best case presented on the final classification: 96% accuracy, 100% sensitivity and 95,34% specificity. The worst case presented: 70% accuracy, 100% sensitivity and 67,56% specificity. On average, the 30 cases presented: 90% accuracy, 100% sensitivity and 85% specificity. / A mamografia é um exame de mama, utilizado de forma preventiva ao câncer de mama e também como método diagnóstico. Este exame, que consiste em uma radiografia das mamas, permite a detecção do câncer. O objetivo deste trabalho é utilizar técnicas de processamento de imagens e visão computacional para auxiliar especialistas na detecção de regiões suspeitas e detecção de massas mamárias em mamografias digitais. A primeira etapa da metodologia consiste em pré-processar as imagens de forma a torná-las mais apropriadas ao registro, através de redução de ruído, segmentação e re-dimensionamento. A etapa seguinte apresenta o registro bilateral de pares de mamas esquerda e direita. Para corrigir as diferenças de posicionamento e compressão ocorridas no momento do exame, o método de registro rígido foi aplicado (seguido do método de registro deformável com fluxo óptico) para cada par de imagens. Pares de regiões correspondentes foram relacionados e suas variações foram medidas através do descritor espacial variograma cruzado. Na etapa seguinte, foi criado um modelo para treinamento de uma Máquina de Vetores de Suporte (MVS) utilizando como características os valores de variograma cruzado de cada par de janelas de 180 casos. Esta MVS foi testada em 100 novos casos. Os pares que continham lesões foram classificados como regiões suspeitas ; as demais, como regiões não-suspeitas . Destas regiões suspeitas, foram extraídas características de variograma como descritores de textura de tecido. As regiões que continham massas foram classificadas como regiões de massa e as demais como regiões de não-massa . Análise linear discriminante stepwise foi aplicada para selecionar as características mais significativas para treinamento de uma segunda MVS. Foram realizados testes com 30 novos casos para a classificação final pela MVS treinada em massa e nãomassa . O melhor resultado apresentou na classificação final: 96% de acurácia, 100% de sensibilidade e 95,34% de especificidade. O pior caso apresentou: 70% de acurácia, 100% de sensibilidade e 67,56% de especificidade. Em média, os 30 casos apresentaram: 90% de acurácia, 100% de sensibilidade e 85% de especificidade.

Made available in DSpace on 2016-08-17T14:53:21Z (GMT). No. of bitstreams: 1 Peterson.pdf: 1362910 bytes, checksum: 963fec328036941a0790b198cc0d6187 (MD5) Previous issue date: 2012-04-20 / FUNDAÇÃO DE AMPARO À PESQUISA E AO DESENVOLVIMENTO CIENTIFICO E TECNOLÓGICO DO MARANHÃO / Breast cancer is the second most common in the world and which more affects women. In recent years, several Computer Aided Detection/Diagnosis Systems has been developed in order to assist health specialists in the detection and diagnosis of cancer, serving as a second opinion. The aim of this paper is to present a methodology for discrimination and classification of regions extracted from mammograms in mass and non-mass. In this study, Digital Database for Screening Mammography (DDSM) is used. To describe the texture of the region of interest is applied McIntosh Diversity Index, commonly used in ecology. The calculation of this index is proposed in four approaches: through the Histogram, through the Gray Level Co-occurrence Matrix, through the Gray Level Run Length Matrix and through the Gray Level Gap Length Matrix. For the classification of regions in mass and non-mass, is used the supervised classificator Support Vector Machine (SVM). The methodology shows promising results for the classification of masses and non-masses, reaching an accuracy of 93,68%. / O câncer de mama é o segundo tipo de câncer mais frequente no mundo e o que mais acomete as mulheres. Nos últimos anos, vários Sistemas de Detecção e Diagnóstico auxiliados por Computador (Computer Aided Detection/Diagnosis) têm sido desenvolvidos no intuito de auxiliar especialistas da área da saúde na detecção e diagnóstico de câncer, servindo como uma segunda opnião. O objetivo deste trabalho é apresentar uma metodologia de discriminação e classificação de regiões extraídas de mamografias em massa e não massa. Neste estudo, o Digital Database for Screening Mammography (DDSM) é usado. Para descrever a textura da região de interesse é aplicado o Índice de Diversidade de McIntosh, comumente usado em ecologia. O cálculo deste índice é proposto em quatro abordagens: através do Histograma, da Matriz de Co-ocorrência de Níveis de Cinza, da Matriz de Comprimentos de Corrida de Cinza e da Matriz de Comprimentos de Lacuna de Cinza. Para classificação das regiões em massa e não massa, é utilizado o classificador supervisionado Support Vector Machine (SVM). A metodologia apresenta resultados promissores para a classificação de massas e não massas, alcançando uma acurácia de 93,68%.

Contexte : Les inégalités sociales de santé représentent un problème de santé publique considérable. Dans le cadre du cancer du sein, la précarité est associée au pronostic. En effet, une relation entre précarité géographique et stade au diagnostic a été établie dans la littérature. Cependant, à ce jour, aucune étude n'a encore analysé l'association de ce dernier à la précarité individuelle.Objectifs : Les objectifs de ce travail de recherche sont (1) d'estimer le risque de cancer du sein de stade avancé associé à la précarité individuelle, (2) d'étudier l'impact des facteurs pouvant modifier ce risque, (3) d'évaluer la robustesse de l'association face au choix de la mesure de précarité.Population et méthode : Les données sont issues d'une étude cas-témoins. Les Cas et les Témoins de l'étude ont été recrutés parmi les patientes de l'Hérault atteintes de cancers du sein invasifs diagnostiqués entre 2011 et 2012. Les Cas correspondent aux patientes présentant un cancer du sein de mauvais pronostic (taille de tumeur supérieure à 5cm, ou atteinte ganglionnaire ou atteinte métastatique) et les Témoins aux patientes présentant des cancers de bon pronostic (taille de tumeur inférieure à 5cm et aucune atteinte ganglionnaire et aucune atteinte métastatique). Au total 604 patientes ont été incluses : 173 Cas et 431 Témoins. L'exposition à la précarité a été recueillie par un questionnaire standardisé.Résultats : Les patientes précaires ont, toutes variables égales par ailleurs, 2 fois plus de risque d'avoir un cancer de stade avancé comparée aux patientes non précaires. La précarité n'est associée à aucun autre facteur biologique (grade SBR, types histologique et moléculaire). Chez les patientes asymptomatiques (diagnostiquées suite à un dépistage) les patientes précaires ont plus de risque d'avoir des cancers de stade avancé. Chez les femmes avec un antécédent familial de cancer du sein tout comme chez les femmes vivant dans une zone géographique favorisée, les patientes précaires et non-précaires ont le même risque de cancer de stade avancé. Comparé aux autres mesures de l'environnement socio-économique (classe sociale, précarité géographique…), le score EPICES semble la méthode de mesure la plus adaptée pour étudier l'association entre précarité et stade au diagnostic.Conclusion : Nos résultats suggèrent que les écarts observés entre les patientes précaires et les patientes non-précaire semblent être plutôt liés à retard au diagnostic plutôt qu'à des différences biologiques entre les tumeurs. Ce retard au diagnostic semble dépendre de composantes individuelles mais aussi collectives. De plus, une meilleure connaissance du cancer du sein pourrait permettre de réduire les barrières supplémentaires vécues par les précaires. / Context: Socio-economic inequalities in health represent a significant public health problem. In the breast cancer context, socio-economic deprivation is associated with prognosis. Indeed, a relationship between area-based deprivation and diagnostic stages was already described in the international literature. However, the association between individual deprivation and diagnostic stages was not study so far.Objectives: Our aim was to (1) estimate the risk of advanced breast cancer associated with individual socio-economic deprivation, (2) study the impact of modifying factors, (3) evaluate the strength of this association according to the method used to measure deprivation.Population and methods: Data were collected from a Case-Control study. Cases and Controls were recruited among invasive breast cancer patients diagnosed between 2011 and 2012 in the Hérault. Cases were defined as patients with poor prognosis breast cancer (with tumor size over 5cm, or with lymph node involvement, or with metastasis). Controls were defined as patients with good prognosis breast cancer (with tumor size under 5cm, and without lymph node involvement, and without metastasis). A total number of 604 patients were included: 173 Cases and 431 Controls. The exposition to deprivation was measured by a standardized questionnaire.Results: Deprived patients, with all other variables remaining constant, have a two-fold risk of having advanced breast cancer compared to non-deprived patients. Deprivation was not associated with the other biological factors (SBR grade, histologic and molecular type). Among asymptomatic patients (diagnosed after a mammographic screening), deprived patients have a higher risk of advanced breast cancer. Among women with family history of breast cancer so as women living in affluent geographic areas, deprived and non-deprived patients have the same risk of advanced breast cancer. Compared to other measures of socio-economic environment (social class, area-based deprivation…), EPICES score seems to be the most adapted method to study the association between deprivation and breast cancer diagnostic stages.Conclusion: Our results suggest that the gap observed between deprived and non-deprived patients seem to be associated with delayed diagnosis more than biological differences between tumors. This delayed diagnosis seems depend on individual and geographic components. Moreover, a better knowledge of breast cancer could allow a reduction of the barrier experienced by deprived women.

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Breast cancer is the type of cancer that affects more women worldwide. Its early detection is key to achieve its treatment and, consequently, reduce its mortality rate. Mammography is considered the most suitable technique for this detection, which is based on the visualization of small structures and patterns that may represent cancerous lesions. But for visualization of these structures, the quality control of mammographic images and the training of residents and radiologists is required. With this in mind, this study aimed the development and confection of three breast simulators (phantoms) that serve these purposes. The materials used in this construction were analyzed and their attenuation coefficients were compared to simulated breast tissues. The phantoms were prepared in polymethylmethacrylate molds and plates, known as acrylic, and the test structures used were microcalcifications, simulated by limestone, and fibers, simulated by nylon. The phantoms I-a and I-b are intended to perform quality control and has its test structures placed in a mixture of paraffin gel and acrylic powder and dental wax, respectively. The phantom II is intended to conduct the training of residents and radiologists and has its test structures placed in dental wax. The detectability of the test structures was variable with the thickness of phantoms. After analysis and comparison of results between the phantoms made and the marketable phantom recommended by the national standard, made phantoms were validated. / O câncer de mama é o tipo de câncer que mais atinge mulheres em todo o mundo. Sua detecção precoce é fundamental para realização do seu tratamento e, consequentemente, a redução da sua taxa de mortalidade. A mamografia é considerada a técnica mais adequada para esta detecção, que se baseia na visualização de pequenas estruturas e padrões que podem representar lesões cancerígenas. Porém, para visualização destas estruturas, o controle da qualidade das imagens mamográficas e o treinamento de residentes e radiologistas é necessário. Tendo isto em vista, este trabalho teve como objetivo o desenvolvimento e a confecção de três simuladores de mama (phantoms) que servem a estes propósitos. Os materiais utilizados nesta construção foram analisados e seus coeficientes de atenuação foram comparados aos tecidos mamários que simulam. Os phantoms foram confeccionados em moldes e placas de polimetilmetacrilato, conhecido como acrílico, e as estruturas de teste utilizadas foram as microcalcificações, simuladas por calcário, e as fibras, simuladas por nylon. Os phantoms I-a e I-b têm o propósito de realizar o controle de qualidade e possuem suas estruturas de teste inseridas em uma mistura de parafina em gel e acrílico em pó e cera, respectivamente. O phantom II tem o propósito de realizar o treinamento de residentes e radiologistas e possui suas estruturas de teste inseridas em cera de uso odontológico. A detectabilidade das estruturas de teste se mostrou variável com as espessuras dos phantoms. Após análise e comparação dos resultados entre os phantoms confeccionados e o phantom comercial recomendado pela norma nacional, os phantoms confeccionados foram validados.

<p>Rak dojke je trenutno po incidenciji vodeća maligna bolest kod žena kako u razvijenim tako i u zemljama u razvoju. Osnovni cilj istraživanja bio je da se defini&scaron;u faktori rizika u populaciji žena uzrasta 50-69 godina koje su obuhvaćene Nacionalnim skrining programom ranog otkrivanja raka dojke mamografijom na teritoriji Autonomne Pokrajine Vojvodine (APV). U istraživanju je kori&scaron;ćena retrospektivno-prospektivna studija. Za potrebe istraživanja formirana je grupa obolelih žena i kontrolna grupa žena na teritoriji APV. Istraživanje je obuhvatilo 510 žena sa teritorije AP Vojvodine, uzrasta od 50 do 69 godina. Rezultati istraživanja pokazali su da su se kao značajni prediktori raka dojke u na&scaron;em istraživanju izdvojili: 1. Hormonska terapija &ndash; one osobe koje su uzimale hormonsku terapiju značajno imaju veću verovatnoću da imaju rak dojke i obrnuto. 2. Prethodna maligna bolest &ndash; osobe koje su prethodno imale neku drugu malignu bolest imaju manju &scaron;ansu da imaju rak dojke&nbsp; 3. One žene koje vr&scaron;e samokontrolu dojke če&scaron;će su u nekliničkom uzorku. 4. Žene koje su u grupi starijih su če&scaron;će u kliničkom uzorku. 5. One osobe koje imaju u porodici nekog ko je oboleo od raka dojke če&scaron;će i same oboljevaju. Ovo je prvo istraživanje o faktorima rizika za rak dojke na populaciji žena AP Vojvodine u okviru Nacionalnog programa ranog otkrivanja raka dojke. Rezultati istraživanja daju osnove za buduća istraživanja iz ove oblasti, takođe mogu da utiču na podizanje svesti žena o značaju redovnih pregleda i ranom otkrivanju raka dojke kao i pružanje podr&scaron;ke programu skrininga.</p> / <p>Breast cancer is currently theleading malignant disease in women both in developed and developing countries. The main goal of the research was to define risk factors in the population of women aged 50-69 years, covered by the National Screening Program for Early Detection of Breast Cancer by Mammography on the territory of the Autonomous Province of Vojvodina. The researchwasconducted asretrospective-prospective study. For the purpose of the research,were formed a group of diseased women and a control group of women in the territory of AP Vojvodina . The research involved 510 women with the territory of AP Vojvodina, aged 50 to 69 years. The results of the study showed that as significant predictors ofbreast cancer in our study. 1.Hormone Therapy -Those who have taken hormone therapy are significantly more likely to have breast cancer and vice versa. 2. Pre-existing malignant disease -people who previously had any other malignant disease have a lowerchance of having breast cancer 3. Women who perform self-control of their breasts are more often in a non-clinical sampl.e 4. Women in the elderly group are more often in the clinical sample. 5. Those who have a family member who has breast cancer are more likely to suffer from their own illness. This is the first study on the risk factors for breast cancer in the population of AP Vojvodina women within the National Breast Cancer Screening Program. The results of the research provide the basics for future research in this area, they can also help raise women&#39;s awareness of the importance of regular screening and early detection of breast cancer, as well as supporting the screening program</p>

Inledning: Mammografi är en vanlig bröstundersökning där kvinnor mellan 40–74 år erbjuds screening av bröst med regelbundna intervaller. Kvinnor som upplever mammografi-undersökningen som smärtsam och obehaglig återkommer ibland inte till sina kontroll-undersökningar. Uteblivna kontroller kan leda till högre mortalitet i bröstcancer. Syfte: Studiens syfte var att kartlägga kunskap om faktorer som påverkar kvinnors smärtupplevelse i samband med screeningmammografi. Metod: Studien är en allmän litteraturöversikt som genomförts via databaserna, Cinahl och PubMed. I huvudsak kvantitativa artiklar har analyserats och kvalitetsgranskats. Resultatet från de granskade artiklarna har ordnats systematisk som underlag för analysen. Resultat: Studiens resultat var att den största delen av smärta och obehag uppkom under bröstkompression. Röntgensjuksköterskans kunskap om möjliga åtgärder som bemötande, information före och efter undersökningen samt individuell anpassning av undersökningen har betydelse. Detta kan göra skillnad för kvinnors upplevelse och bidra till en positiv upplevelse vid mammografiundersökningen. Slutsats: Studiens resultat visar att orsaker till kvinnors smärta vid screeningmammografi är komplexa. Tekniken för mammografi har utvecklats över tid, däremot upplever kvinnorna fortfarande obehag och smärta. Samband kan finnas med tekniken, röntgensjuksköterskans bemötande och brist på information till kvinnorna men forskningen ger inget säkert stöd för slutsatser annat än att bemötandet och patientkommunikation spelar stor roll. Det behövs mer forskning kring olika metoder för de åtgärder en röntgensjuksköterska kan använda för att lindra kvinnors smärtupplevelse vid screeningmammografi. / Introduction: Mammography is a common breast examination where women between the ages of 40–74 are offered breast screening at regular intervals. Women who experience the mammography examination as painful and uncomfortable sometimes do not return to their check-ups. Lack of control can lead to higher mortality in breast cancer. Aim: The purpose of the study was to chart knowledge about factors affecting women´s experience of pain during screening mammography. Method: The study is a general literature review conducted via the databases, Cinahl and PubMed. Mainly quantitative articles have been analyzed and quality reviewed. The results from the reviewed articles have been arranged systematically as a basis for the analysis. Results: The results of the study were that most of the pain and discomfort arose during breast compression. Radiographer's knowledge of enabling measures such as treatment, information before and after the examination and individual adaptation of the examination is important. This can make a difference to women's experience and contribute to a positive atmosphere at the mammography examination. Conclusion: The results of the study show that the causes of women's pain during screening mammography are complex. The technique of mammography has evolved over time; however, women still experience discomfort and pain. There may be a connection with the technology, the radiographer's treatment and lack of information for the women, but the research does not provide definite support for conclusions other than that the treatment and patient communication play a major role. More research is needed on different methods for the measures a radiographer's can use to relieve women's pain experience during the screeningmammography.

In this thesis, a comparison of three different pre-processing methods for imbalanced classification data, is conducted. Variational Autoencoder, Random Under-Sampling Boosting and a hybrid approach of the two, are applied to three imbalanced classification data sets with different class imbalances. A logistic regression (LR) model is fitted to each pre-processed data set and based on its classification performance, the pre-processing methods are evaluated. All three methods shows indications of different advantages when handling class imbalances. For each pre-processed data, the LR-model has is better at correctly classifying minority class observations, compared to a LR-model fitted to the original class imbalanced data sets. Evaluating the overall classification performance, both VAE and RUSBoost shows improving classification results while the hybrid method performs worse for the moderate class imbalanced data and best for the highly imbalanced data.