Navegando por Autor "Rezende, Mariana Trevisan"
Agora exibindo 1 - 12 de 12
Resultados por página
Opções de Ordenação
Item Avaliação dos serviços de saúde e dos recursos materiais para rastreio do câncer cervical em Ouro Preto - MG.(2022) Oliveira, Renata Rocha e Rezende; Rezende, Giselle Aparecida de Souza; Silva, Bruna Viana; Lage, Ana Luiza; Martins, Bruna Aparecida; Veloso, Marco Antônio; Geöcze, Bruna Albuquerque; Abreu, Ronan David Souza; Rezende, Mariana Trevisan; Carneiro, Cláudia MartinsA realização periódica do exame de Papanicolaou é o método convencional no Brasil para o rastreio do Câncer do Colo do Útero (CCU). As estratégias de serviço e os recursos materiais nas Unidades Básicas de Saúde (UBS) são aspectos fundamentais que refletem na qualidade do programa de rastreamento. Objetivo: Analisar quatro UBS do município de Ouro Preto, Minas Gerais e verificar o contexto local de rastreio do CCU. Métodos: Foi realizado estudo qualitativo, baseado em entrevistas semiestruturadas com enfermeiros e agentes comunitários de saúde (ACS) das UBS selecionadas. Resultados: Observou-se que apenas uma UBS apresentava planta física e recursos materiais adequados à realização do exame. Em geral, as ACS realizavam busca ativa não sistematizada das pacientes para realização do exame de Papanicolau. A conduta para informar os resultados alterados às pacientes era semelhante entre as UBS, porém, não havia padronização para realizar o seguimento dos casos alterados. Além disso, as atividades educativas eram escassas para a comunidade e para a equipe de trabalho. Conclusão: Percebe-se que uma estrutura física de qualidade associada a uma equipe de saúde da família (ESF) treinada favorece o estabelecimento de programas de rastreio exitosos. Por não se tratar de uma realidade de todas as UBS locais, é necessário lançar princípios de organização para sistematizar as estratégias de busca ativa, registro e acompanhamento das pacientes, sendo os ACS fundamentais neste processo, devido à proximidade com a população.Item Cervical cancer : automation of Pap test screening.(2021) Rezende, Mariana Trevisan; Bianchi, Andrea Gomes Campos; Carneiro, Cláudia MartinsBackground: Cervical cancer progresses slowly, increasing the chance of early detection of pre-neoplastic lesions via Pap exam test and subsequently preventing deaths. However, the exam presents both false-negatives and false-positives results. Therefore, automatic methods (AMs) of reading the Pap test have been used to improve the quality control of the exam. We performed a literature review to evaluate the feasibility of implementing AMs in laboratories. Methods: This work reviewed scientific publications regarding automated cytology from the last 15 years. The terms used were “Papanicolaou test” and “Automated cytology screening” in Portuguese, English, and Spanish, in the three scientific databases (SCIELO, PUBMED, MEDLINE). Results: Of the resulting 787 articles, 34 were selected for a complete review, including three AMs: ThinPrep Imaging System, FocalPoint GS Imaging System and CytoProcessor. In total, 1 317 148 cytopathological slides were evaluated automatically, with 1 308 028 (99.3%) liquid-based cytology slides and 9120 (0.7%) conventional cytology smears. The AM diagnostic performances were statistically equal to or better than those of the manual method. AM use increased the detection of cellular abnormalities and reduced false-negatives. The average sample rejection rate was ≤3.5%. Conclusion: AMs are relevant in quality control during the analytical phase of cervical cancer screening. This technology eliminates slide-handling steps and reduces the sample space, allowing professionals to focus on diagnostic interpretation while maintaining high-level care, which can reduce false-negatives. Further studies with conventional cytology are needed. The use of AM is still not so widespread in cytopathology laboratories.Item Cervical cancer : automation of Pap test screening.(2021) Rezende, Mariana Trevisan; Bianchi, Andrea Gomes Campos; Carneiro, Cláudia MartinsBackground: Cervical cancer progresses slowly, increasing the chance of early detection of pre-neoplastic lesions via Pap exam test and subsequently preventing deaths. However, the exam presents both false-negatives and false-positives results. Therefore, automatic methods (AMs) of reading the Pap test have been used to improve the quality control of the exam. We performed a literature review to evaluate the feasibility of implementing AMs in laboratories. Methods: This work reviewed scientific publications regarding automated cytology from the last 15 years. The terms used were “Papanicolaou test” and “Automated cytology screening” in Portuguese, English, and Spanish, in the three scientific databases (SCIELO, PUBMED, MEDLINE). Results: Of the resulting 787 articles, 34 were selected for a complete review, including three AMs: ThinPrep Imaging System, FocalPoint GS Imaging System and CytoProcessor. In total, 1 317 148 cytopathological slides were evaluated automatically, with 1 308 028 (99.3%) liquid-based cytology slides and 9120 (0.7%) conventional cytology smears. The AM diagnostic performances were statistically equal to or better than those of the manual method. AM use increased the detection of cellular abnormalities and reduced false-negatives. The average sample rejection rate was ≤3.5%. Conclusion: AMs are relevant in quality control during the analytical phase of cervical cancer screening. This technology eliminates slide-handling steps and reduces the sample space, allowing professionals to focus on diagnostic interpretation while maintaining high-level care, which can reduce false-negatives. Further studies with conventional cytology are needed. The use of AM is still not so widespread in cytopathology laboratories.Item Clinical, hematological and biochemical alterations in hamster (Mesocricetus auratus) experimentally infected with Leishmania infantum through different routes of inoculation.(2016) Moreira, Nádia das Dores; Souza, Juliana Vitoriano de; Roatt, Bruno Mendes; Vieira, Paula Melo de Abreu; Vital, Wendel Coura; Cardoso, Jamille Mirelle de Oliveira; Rezende, Mariana Trevisan; Ker, Henrique Gama; Giunchetti, Rodolfo Cordeiro; Carneiro, Cláudia Martins; Reis, Alexandre BarbosaBackground: Leishmaniasis remains among the most important parasitic diseases in the developing world and visceral leishmaniasis (VL) is the most fatal. The hamster Mesocricetus auratus is a susceptible model for the characterization of the disease, since infection of hamsters with L. infantum reproduces the clinical and pathological features of human VL. In this context, it provides a unique opportunity to study VL in its active form. The main goal of this study was to evaluate the clinical, biochemical, and hematological changes in male hamsters infected through different routes and strains of L. infantum. Methods: In the current study, hamsters (Mesocricetus auratus) were infected with the L. infantum strains (WHO/MHOM/BR/74/PP75 and MCAN/BR/2008/OP46) by intradermal, intraperitoneal and intracardiac routes. The animals were monitored for a nine month follow-up period. Results: The hamsters showed clinical signs similar to those observed in classical canine and human symptomatic VL, including splenomegaly, severe weight loss, anemia, and leucopenia. Therefore the OP46 strain was more infective, clinical signs were more frequent and more exacerbated in IC group with 80 to 100 % of the animals showing splenomegaly, in the last month infection. Additionally, desquamation, hair loss and external mucocutaneous lesions and ulcers localized in the snout, accompanied by swelling of the paws in all animals, were observed. Consequently, the animals presented severe weight loss/cachexia, hunched posture, an inability to eat or drink, and non-responsiveness to external stimuli. Furthermore, regardless of strain, route of inoculum and time assessed, the animals showed renal and hepatic alterations, with increased serum levels of urea and creatinine as well as elevated serum levels of aspartate aminotransferase and alanine aminotransferase. Conclusions: These results strongly suggest that the inoculation through the intracardiac route resulted in a higher severity among infections, especially in the sixth and ninth month after infection via intracardiac, exhibited clinical manifestations and biochemical/hematological findings similar to human visceral leishmaniasis. Therefore, we suggest that this route must be preferentially used in experimental infections for pathogenesis studies of VL in the hamster model.Item Comparação dos exames citopatológicos do colo do útero do município de Ouro Preto-MG, submetidos ao monitoramento externo da qualidade.(2017) Rezende, Mariana Trevisan; Carneiro, Cláudia Martins; Tobias, Alessandra Hermógenes Gomes; Carneiro, Cláudia Martins; Amaral, Rita Goreti; Vieira, Paula Melo de AbreuItem A cytopathologist eye assistant for cell screening.(2022) Diniz, Débora Nasser; Keller, Breno Nunes de Sena; Rezende, Mariana Trevisan; Bianchi, Andrea Gomes Campos; Carneiro, Cláudia Martins; Oliveira, Renata Rocha e Rezende; Luz, Eduardo José da Silva; Ushizima, Daniela Mayumi; Medeiros, Fátima Nelsizeuma Sombra de; Souza, Marcone Jamilson FreitasScreening of Pap smear images continues to depend upon cytopathologists’ manual scrutiny, and the results are highly influenced by professional experience, leading to varying degrees of cell classification inaccuracies. In order to improve the quality of the Pap smear results, several efforts have been made to create software to automate and standardize the processing of medical images. In this work, we developed the CEA (Cytopathologist Eye Assistant), an easy-to-use tool to aid cytopathologists in performing their daily activities. In addition, the tool was tested by a group of cytopathologists, whose feedback indicates that CEA could be a valuable tool to be integrated into Pap smear image analysis routines. For the construction of the tool, we evaluate different YOLO configurations and classification approaches. The best combination of algorithms uses YOLOv5s as a detection algorithm and an ensemble of EfficientNets as a classification algorithm. This configuration achieved 0.726 precision, 0.906 recall, and 0.805 F1-score when considering individual cells. We also made an analysis to classify the image as a whole, in which case, the best configuration was the YOLOv5s to perform the detection and classification tasks, and it achieved 0.975 precision, 0.992 recall, 0.970 accuracy, and 0.983 F1-score.Item Deep learning for cell image segmentation and ranking.(2019) Araujo, Flavio Henrique Duarte de; Silva, Romuere Rodrigues Veloso e; Ushizima, Daniela Mayumi; Rezende, Mariana Trevisan; Carneiro, Cláudia Martins; Bianchi, Andrea Gomes Campos; Medeiros, Fátima Nelsizeuma Sombra deNinety years after its invention, the Pap test continues to be the most used method for the early identification of cervical precancerous lesions. In this test, the cytopathologists look for microscopic abnormalities in and around the cells, which is a time-consuming and prone to human error task. This paper introduces computational tools for cytological analysis that incorporate cell segmentation deep learning techniques. These techniques are capable of processing both free-lying and clumps of abnormal cells with a high overlapping rate from digitized images of conventional Pap smears. Our methodology employs a preprocessing step that discards images with a low probability of containing abnormal cells without prior segmentation and, therefore, performs faster when compared with the existing methods. Also, it ranks outputs based on the likelihood of the images to contain abnormal cells. We evaluate our methodology on an image database of conventional Pap smears from real scenarios, with 108 fields-of-view containing at least one abnormal cell and 86 containing only normal cells, corresponding to millions of cells. Our results show that the proposed approach achieves accurate results (MAP = 0.936), runs faster than existing methods, and it is robust to the presence of white blood cells, and other contaminants.Item Desenvolvimento e validação de ferramentas computacionais de apoio ao diagnóstico citopatológico do câncer do colo do útero.(2021) Rezende, Mariana Trevisan; Carneiro, Cláudia Martins; Bianchi, Andrea Gomes Campos; Carneiro, Cláudia Martins; Consolaro, Márcia Edilaine Lopes; Claro, Itamar Bento; Travençolo, Bruno Augusto Nassif; Vieira, Paula Melo de AbreuUma das causas dos resultados falso-negativos e falso-positivos do exame de Papanicolaou são fatores subjetivos atrelados a análise microscópica realizada por citopatologistas. A visão computacional tornou-se uma importante estratégia de melhoria da qualidade do exame, permitindo a construção, validação e implementação de ferramentas computacionais para auxiliar o diagnóstico selecionando áreas do esfregaço prováveis de apresentar alterações citopatológicas. Apesar do aprendizado de máquina se mostrar promissor para minimizar as deficiências do exame, até o momento, a visão computacional não é tão aplicada à citologia convencional. Principalmente devido ao custo dos métodos semi-automáticos disponíveis e ao uso mais difundido da citologia em meio líquido em países de alta renda. Entretanto, diversos países no mundo ainda usam a citologia convencional e não há previsão para substituição. Assim, depara-se com ausência de estudos e de base de dados de citologia convencional, que impedem avanços no desenvolvimento de algoritmos de segmentação e classificação. Nesse contexto, o primeiro objetivo específico desse trabalho foi identificar a viabilidade de implementação de métodos semi-automáticos disponíveis para triagem de lâminas cervicais por meio de uma revisão integrativa da literatura; o segundo objetivo foi desenvolver uma plataforma web e uma coleção de dados de imagens de citologia convencional; o terceiro objetivo foi desenvolver e validar algoritmos de classificação de células cervicais. A revisão integrativa mostrou que os métodos semi-automáticos mais usados foram o ThinPrep Imaging System e o BD FocalPoint GS Imaging System. Apontou ainda que os métodos semi-automáticos são relevantes no monitoramento da qualidade em citopatologia cervical, porém existem lacunas relacionadas ao custo, logística dos equipamentos e uso da citologia convencional. Neste sentido, foi desenvolvido a CRIC Searchable Image Database, plataforma web de dados de imagens e a CRIC Cervix, coleção de dados de imagens do exame de Papanicolaou convencional, com 11.534 células classificadas, até o momento, é a maior base de dados de células cervicais. Esses dois produtos, publicamente disponíveis, já suportam pesquisas reprodutíveis em visão computacional. O primeiro algoritmo baseado em intensidade e área nuclear mostrou ótimo desempenho nas imagens sintéticas com precisão mais alta que outros trabalhos, ou seja, obteve-se menos resultados falso-positivos. Entretanto, o desempenho foi razoável nas imagens convencionais. O segundo algoritmo baseado em atributos não geométricos extraídos dos núcleos teve precisão de 89,7% e de 85,1% para a classificação em duas classes (células normais e alteradas) e três classes (normal, alteração de baixo grau e de alto grau), com falso-negativos de 3,41% e 1,87%, respectivamente. Os resultados foram satisfatórios, visto que os falso-negativos na rotina laboratorial podem chegar a 62%. A especificidade foi de 83,3% e de 77,8%, para duas e três classes, apontando que os falso-positivos não foram significativos, ainda mais que, posteriormente, esses campos serão avaliados pelo especialista. Os resultados dos algoritmos mostram que é importante basear a extração dos atributos computacionais nos critérios citomorfológicos utilizados pelos citopatologistas para obtenção de resultados mais assertivos. As soluções geradas abrem possibilidades concretas para avançar esforços no desenvolvimento de métodos computacionais de apoio a análise microscópica clássica do exame de Papanicolaou convencional.Item Emotionally subjective reactivity to cervical cytology pictures is modulated by expertise.(2022) Oliveira, Jacqueline Alfenas de; Souza, Miriam de Cássia; Cunha, Laila Fernandes da; Mota, Bruna Eugênia Ferreira; Rezende, Mariana Trevisan; Carneiro, Cláudia Martins; Pereira, Mirtes Garcia; Mocaiber, Izabela; Souza, Gabriela Guerra Leal deOur aims were to create a catalog of cytological pictures and to evaluate the valence (level of pleasantness/ unpleasantness) and arousal (level of calm/excitement) of these pictures in individuals with different occupations. The sample consisted of medical and law college students and cytopathologists. Valence and arousal score for general pictures were not modulated by expertise in cytology. However, students judged the cytological pictures to be lower in valence and in arousal than the cytopathologists. The cytopathologists classified cytological pictures with lesions as lower in valence and higher in arousal than cytological pictures without lesions.Item A hierarchical feature-based methodology to perform cervical cancer classification.(2021) Diniz, Débora Nasser; Rezende, Mariana Trevisan; Bianchi, Andrea Gomes Campos; Carneiro, Cláudia Martins; Ushizima, Daniela Mayumi; Medeiros, Fátima Neusizeuma Sombra de; Souza, Marcone Jamilson FreitasPrevention of cervical cancer could be performed using Pap smear image analysis. This test screens pre-neoplastic changes in the cervical epithelial cells; accurate screening can reduce deaths caused by the disease. Pap smear test analysis is exhaustive and repetitive work performed visually by a cytopathologist. This article proposes a workload-reducing algorithm for cervical cancer detection based on analysis of cell nuclei features within Pap smear images. We investigate eight traditional machine learning methods to perform a hierarchical classification. We propose a hierarchical classification methodology for computer-aided screening of cell lesions, which can recommend fields of view from the microscopy image based on the nuclei detection of cervical cells. We evaluate the performance of several algorithms against the Herlev and CRIC databases, using a varying number of classes during image classification. Results indicate that the hierarchical classification performed best when using Random Forest as the key classifier, particularly when compared with decision trees, k-NN, and the Ridge methods.Item Performance of rapid prescreening and 100% rapid review as internal quality control methods for cervical cytopathology.(2018) Tobias, Alessandra Hermógenes Gomes; Vitalino, Aline Costa; Rezende, Mariana Trevisan; Oliveira, Renata Rocha e Rezende; Vital, Wendel Coura; Amaral, Rita Goreti; Carneiro, Cláudia MartinsBackground An objective of quality control for cervical cytopathology is reducing high rates of false‐negative results of laboratory tests. Therefore, methods to review smears such as rapid prescreening and 100% rapid review, which have shown better performance detecting false‐negative results, have been widely used. The performance of rapid prescreening and the performance of 100% rapid review as internal quality control methods for cervical cytology examinations were evaluated. Methods For 24 months, 9318 conventional cervical cytology smears underwent rapid prescreening and routine screening. The 100% rapid review method was performed for 8244 smears classified as negative during routine screening. Any discordant results underwent detailed review to define the final diagnosis. This was considered the gold standard for evaluating the performance of rapid prescreening and 100% rapid review. Results Routine screening showed increases of 13.3% and 11.5% in the detection of abnormal smears with rapid prescreening and 100% rapid review, respectively. The relative percentage variation showed a 38.1% increase in the diagnosis of atypical squamous cells of undetermined significance with routine screening and rapid prescreening and a 12.5% increase in the diagnosis of atypical squamous cells, cannot exclude high‐grade squamous intraepithelial lesion with both rapid prescreening and 100% rapid review. Sensitivity rates of rapid prescreening and routine screening were 48.2% and 83.2%, respectively. Sensitivity rates of rapid prescreening and 100% rapid review were 65.7% and 57.8%, respectively, for detecting false‐negative results. Conclusions Inclusion of rapid prescreening and/or 100% rapid review improved the diagnostic sensitivity of the cervical cytology examination and reduced false‐negative results of routine screening and can provide good quality control.Item Saliency-driven system models for cell analysis with deep learning.(2019) Ferreira, Daniel Silva; Ramalho, Geraldo Luis Bezerra; Torres, Débora; Tobias, Alessandra Hermógenes Gomes; Rezende, Mariana Trevisan; Medeiros, Fátima Nelsizeuma Sombra de; Bianchi, Andrea Gomes Campos; Carneiro, Cláudia Martins; Ushizima, Daniela MayumiBackground and objectives: Saliency refers to the visual perception quality that makes objects in a scene to stand out from others and attract attention. While computational saliency models can simulate the expert’s visual attention, there is little evidence about how these models perform when used to predict the cytopathologist’s eye fixations. Saliency models may be the key to instrumenting fast object detection on large Pap smear slides under real noisy conditions, artifacts, and cell occlusions. This paper describes how our computational schemes retrieve regions of interest (ROI) of clinical relevance using visual attention models. We also compare the performance of different computed saliency models as part of cell screening tasks, aiming to design a computer-aided diagnosis systems that supports cytopathologists. Method: We record eye fixation maps from cytopathologists at work, and compare with 13 different saliency prediction algorithms, including deep learning. We develop cell-specific convolutional neural networks (CNN) to investigate the impact of bottom-up and top-down factors on saliency prediction from real routine exams. By combining the eye tracking data from pathologists with computed saliency models, we assess algorithms reliability in identifying clinically relevant cells. Results: The proposed cell-specific CNN model outperforms all other saliency prediction methods, particularly regarding the number of false positives. Our algorithm also detects the most clinically relevant cells, which are among the three top salient regions, with accuracy above 98% for all diseases, except carcinoma (87%). Bottom-up methods performed satisfactorily, with saliency maps that enabled ROI detection above 75% for carcinoma and 86% for other pathologies. Conclusions: ROIs extraction using our saliency prediction methods enabled ranking the most relevant clinical areas within the image, a viable data reduction strategy to guide automatic analyses of Pap smear slides. Top-down factors for saliency prediction on cell images increases the accuracy of the estimated maps while bottom-up algorithms proved to be useful for predicting the cytopathologist’s eye fixations depending on parameters, such as the number of false positive and negative. Our contributions are: comparison among 13 state-of-the-art saliency models to cytopathologists’ visual attention and deliver a method that the associate the most conspicuous regions to clinically relevant cells.