COVID-19 is a highly contagious and virulent disease caused by the severe acute respiratory syndrome-coronavirus-2 (SARS-CoV-2). COVID-19 disease induces lung changes observed in lung computerized tomography (CT) and the percentage of those diseased areas on the CT correlates with the severity of the disease. Therefore, segmentation of CT images to delineate the diseased or lesioned areas is a logical first step to quantify disease severity, which will help physicians predict disease prognosis and guide early treatments to deliver more positive patient outcomes. It is crucial to develop an automated analysis of CT images to save their time and efforts. This dissertation proposes CoviNet, a deep three-dimensional convolutional neural network (3D-CNN) to diagnose COVID-19 in CT images. It also proposes CoviNet Enhanced, a hybrid approach with 3D-CNN and support vector machines. It also proposes CoviSegNet and CoviSegNet Enhanced, which are enhanced U-Net models to segment ground-glass opacities and consolidations observed in computerized tomography (CT) images of COVID-19 patients. We trained and tested the proposed approaches using several public datasets of CT images. The experimental results show the proposed methods are highly effective for COVID-19 detection and segmentation and exhibit better accuracy, precision, sensitivity, specificity, F-1 score, Matthew's correlation coefficient (MCC), dice score, and Jaccard index in comparison with recently published studies.

CoordenaÃÃo de AperfeiÃoamento de Pessoal de NÃvel Superior / O incremento na incidÃncia da fluorose dentÃria ocorrido nos Ãltimos tempos, à motivo de preocupaÃÃo dos epidemiologistas em nÃvel nacional e internacional. A diferenciaÃÃo entre as alteraÃÃes do esmalte fluorÃtico e nÃo fluorÃtico leva a importantes decisÃes em epidemiologia e saÃde pÃblica bucal. O objetivo deste estudo à investigar a capacidade dos cirurgiÃes-dentistas do serviÃo pÃblico de saÃde no municÃpio de Fortaleza, em diagnosticar a fluorose dentÃria, frente Ãs diversas afecÃÃes do esmalte dentÃrio, seus graus de severidade e a conduta terapÃutica apropriada a cada caso. Utilizou-se para isso um questionÃrio com questÃes semi-estruturadas, o qual foi aplicado a 200 cirurgiÃes-dentistas, de um universo de 527 profissionais do serviÃo pÃblico de saÃde de Fortaleza. O questionÃrio foi aplicado no local de trabalho dos participantes, cujas respostas se basearam na apresentaÃÃo de 20 fotografias digitalizadas de dentes com alteraÃÃes prÃprias do esmalte. A presenÃa ou ausÃncia de fluorose dentÃria e seus graus de severidade foram determinados pelo Ãndice de Dean. NÃo foram detectadas diferenÃas significativas no nÃvel de acerto do grau de fluorose, quando os respondentes foram classificados segundo a instituiÃÃo de graduaÃÃo (p>0,05). No entanto, aqueles profissionais menos experientes apresentaram melhor desempenho (p<0,05), tanto no diagnÃstico de fluorose, quanto na conduta mas nÃo no grau de severidade da doenÃa. Os profissionais gerenciados pela Secretaria Municipal de SaÃde obtiveram desempenho superior aos gerenciados pelo Estado, em todas as percepÃÃes do teste. Quanto ao agrupamento da amostra por especialidades, nenhuma diferenÃa significativa (p>0,05) foi encontrada entre os Grupos. A mÃdia de acertos no diagnÃstico diferencial da fluorose dentÃria foi de 7,70  0,15. Valores inferiores a 30% de acertos foram obtidos no diagnÃstico do grau de severidade da fluorose, destacando-se as formas mais graves como de maior percentual de acerto. A maioria (90%) dos respondentes admitiram ter sentido dificuldades no diagnÃstico da fluorose, apesar de 75% ter recebido informaÃÃo acerca do assunto no curso de graduaÃÃo, porÃm consideraram escassa e deficiente (79,5%). A mÃdia de acertos da conduta clÃnica foi considerada muito baixa (2,71  0,76). Cerca de 70% dos inquiridos solicitaram curso de capacitaÃÃo acerca do diagnÃstico diferencial da fluorose dentÃria. A partir desses resultados, conclui-se que os cirurgiÃes-dentistas que atuam no serviÃo pÃblico de saÃde de Fortaleza apresentaram um baixo nÃvel de conhecimento e falta de preparo adequado para o diagnÃstico da fluorose dentÃria, a percepÃÃo dos seus graus de severidade e definiÃÃo da conduta clÃnica apropriada. Sugere-se que estudos mais abrangentes sejam conduzidos a fim de identificar as carÃncias do setor pÃblico de saÃde, em todos os nÃveis de atenÃÃo / Increasing levels of dental fluorosis are a major concern to public health authorities. The ability to discriminate fluorosis from other enamel modifications is an important factor to support decision makers in epidemiology and oral health. The main objective of this research is to investigate the ability of the odontologists working for the public health services in Fortaleza, to discriminate fluorosis from other enamel alterations, the severity of the disease and the correct clinical approach. Two hundred dentists out of 527 professionals of the public health services answered a semi-structured survey, based on the evaluation of 20 digitalized pictures showing enamel modifications. The presence or absence of fluorosis, as well as the severity of the disease were determined according to the Deanâs index. We were unable to detect an effect of the school of graduation (p>0.05) on the ability to diagnose fluorosis. However, the youngest, less experienced dentists performed better (p<0.05) for both fluorosis diagnosis and to determine to adequate clinical approach for each case. Also, odontologists working in the city health services were more likely to get higher scores compared to the ones working for the state services, with an average of correct answers for differential diagnosis of 7.70  0.15. Although a few subjects achieved less than 30% of correct answers, pictures displaying more severe cases of fluorosis were more likely to result in correctly answered questions. The vast majority (90%) of the subjects reported to have a poor ability do diagnose fluorosis, although 75% had received information about that disease during undergraduation. The odontologists also displayed a very poor performance (2,71  0,76) in defining the best clinical approach, and about 70% of them asked for specific training for correctly diagnose dental fluorosis. Based on the above results, we conclude that most dental surgeons working for the public health services in Fortaleza displayed a poor knowledge about dental fluorosis and lack an adequate training to diagnose and treat that disease. Similar researchs in other regions of Ceara should be performed in order to better identify the deficiencies of the public health services, at different levels