Search

Made available in DSpace on 2021-06-25T10:44:05Z (GMT). No. of bitstreams: 0 Previous issue date: 2021-05-01 Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) Fundação de Amparo à Pesquisa do Estado de Minas Gerais (FAPEMIG) The analysis of histological images is based on visual assessment of tissues by specialists using an optical microscopy. This task can be time-consuming and challenging, mainly due to the complexity of the structures and diseases under investigation. These facts have motivated the development of computational methods to support specialists in research and decision-making. Despite the different computational strategies available in the literature, the solutions based on genetic algorithm have not been fully explored to provide the best combination of features, selection algorithms and classifiers. In this paper, we describe an approach based on genetic algorithm able to evaluate a significant number of features, selection methods and classifiers in order to provide an acceptable association for the diagnosis and pattern recognition of non-Hodgkin lymphomas and colorectal cancer. The chromosomal structure was represented with four genes. The evaluation and selection of individuals, as well as the crossover and mutation processes, were defined to distinguish the groups under investigation, with the highest AUC value and the smallest number of features. The tests were performed considering 1512 features from histological images, different population sizes and number of iterations. An initial population of 50 individuals and 50 iterations provided the best result (AUC value of 0.984) for the colorectal histological images. For non-Hodgkin lymphoma images, the best result (AUC value of 0.947) was obtained with a population of 500 individuals and 50 iterations. The proposed methodology with detailed information regarding the methods, features and best associations are relevant contributions for the community interested in the study of pattern recognition of colorectal cancer and lymphomas. Department of Computer Science and Statistics (DCCE) São Paulo State University (UNESP), Rua Cristóvão Colombo, 2265 Faculty of Computer Science (FACOM) - Federal University of Uberlândia (UFU), Avenida João Neves de Ávila 2121, Bl.B Center of Mathematics Computing and Cognition Federal University of ABC (UFABC), Avenida dos Estados, 5001 Federal Institute of Triângulo Mineiro (IFTM), Rua Belarmino Vilela Junqueira sn Department of Computer Science and Statistics (DCCE) São Paulo State University (UNESP), Rua Cristóvão Colombo, 2265 CNPq: #304848/2018-2 CNPq: #313365/2018-0 CNPq: #427114/2016-0 CNPq: #430965/2018-4 FAPEMIG: #APQ-00578-18

Made available in DSpace on 2021-06-25T10:44:33Z (GMT). No. of bitstreams: 0 Previous issue date: 2021-05-01 Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) Fundação de Amparo à Pesquisa do Estado de Minas Gerais (FAPEMIG) There are different types of lesions that can be investigated with the hematoxylin–eosin staining protocol. Lymphoma is a type of malignant disease which affects one of the highest white blood cell populations responsible for the immunological defence system. There are lymphoma sub-types that can have similar features, which make their diagnoses a difficult task. In this study, we investigated algorithms based on multiscale and multidimensional fractal geometry with colour models for classification of lymphoma images. Fractal features were extracted from the colour models and separate channels from these models. These features were concatenated to form feature vectors. Finally, we investigated the Hermite polynomial classifier and machine learning algorithms in order to evaluate the performance of the proposed approach. We employed the tenfold cross-validation method and evaluated the lesion sub-types with the binary and multiclass classifications. The separated colour channels obtained from histological images achieved relevant values for the binary and multiclass classifications, with an accuracy rating between 91 and 97%. These results can contribute to the detection and classification of the lesions by supporting specialists in clinical practices. Federal Institute of Triângulo Mineiro (IFTM), Rua Belarmino Vilela Junqueira sn Department of Computer Science and Statistics (DCCE) São Paulo State University (UNESP), Rua Cristóvão Colombo, 2265 Department of Histology and Morphology Institute of Biomedical Science Federal University of Uberlândia Science and Technology Institute Federal University of São Paulo (UNIFESP), Avenida Cesare Mansueto Giulio Lattes, 1201 Faculty of Computer Science (FACOM) Federal University of Uberlândia (UFU), Avenida João Neves de Ávila 2121, Bl.B Department of Computer Science and Statistics (DCCE) São Paulo State University (UNESP), Rua Cristóvão Colombo, 2265 CNPq: (#304848/2018-2) CNPq: (#313365/2018-0) CNPq: (#427114/2016-0) CNPq: (#430965/2018-4) FAPEMIG: (#APQ-00578-18)

Made available in DSpace on 2020-12-10T19:39:31Z (GMT). No. of bitstreams: 0 Previous issue date: 2019-10-01 Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) Fundação de Amparo à Pesquisa do Estado de Minas Gerais (FAPEMIG) Histological images stained with hematoxylin-eosin are widely used by pathologists for cancer diagnosis. However, these images can have color variations that highly influence the histological image processing techniques. To deal with this potential limitation, normalization methods are useful for color correction. In this paper, a histological image color normalization is presented by considering the biological and hematoxylin-eosin properties. To this end, the stain representation of a reference image was applied in place of the original images representation, allowing the preservation of histological structures. This proposal was evaluated on histological images with great variations of contrast, and both visual and quantitative analyzes yielded promising results. (C) 2019 Elsevier Ltd. All rights reserved. Fed Univ ABC, Ctr Math Comp & Cognit, Av Estados 5001, BR-09210580 Santo Andre, SP, Brazil Univ Fed Uberlandia, Inst Biomed Sci, Dept Histol & Morphol, Av Amazonas S-N, BR-38405320 Uberlandia, MG, Brazil Univ Uberaba, Sch Dent, Av Nene Sabino 1801, BR-38055500 Uberaba, MG, Brazil Sao Paulo State Univ, Dept Comp Sci & Stat, R Cristovao Colombo 2265, BR-15054000 Sao Jose Do Rio Preto, SP, Brazil Univ Fed Uberlandia, Fac Comp Sci, Av Joao Naves de Avila 2121, BR-38400902 Uberlandia, MG, Brazil Fed Inst Triangulo Mineiro, R Belarmino Vilela Junqueira S-N, BR-38305200 Ituiutaba, MG, Brazil Sao Paulo State Univ, Dept Comp Sci & Stat, R Cristovao Colombo 2265, BR-15054000 Sao Jose Do Rio Preto, SP, Brazil CAPES: 001 CNPq: 427114/2016-0 CNPq: 304848/2018-2 CNPq: 430965/2018-4 CNPq: 313365/2018-0 FAPEMIG: APQ-00578-18 CAPES: 1575210

Made available in DSpace on 2019-10-06T16:07:51Z (GMT). No. of bitstreams: 0 Previous issue date: 2019-04-15 Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) Fundação de Amparo à Pesquisa do Estado de Minas Gerais (FAPEMIG) Colorectal cancer is one of the most common types of cancer according to worldwide incidences statistics. The correct diagnosis of this lesion leads to the indication of the most adequate treatments for cancer-affected patients. The diagnosis is made through the visual analysis of tissue samples by pathologists. However, this analysis is susceptible to intra- and inter-pathologists variability in addition to being a complex and time-consuming task. To deal with these challenges, image processing methods are developed for application on histological images obtained through the digitization of the tissue samples. To do so, feature extraction and classification techniques are investigated to aid pathologists and make it possible a faster and more objective diagnosis definition. Therefore, in this work, we propose a method that associates multidimensional fractal techniques, curvelet transforms and Haralick descriptors for the study and pattern recognition of colorectal cancer, which not yet explored in the Literature. The proposed method considered a feature selection approach and different classification techniques for evaluating associations, such as decision tree, random forest, support vector machine, naive Bayes, k* and a polynomial method. This strategy allowed for more precise interpretations regarding the best associations for the separation of groups concerning histological images of colorectal cancer. The proposal was tested on colorectal images from two distinct datasets commonly investigated in the Literature. The best result was reached with features based mainly on lacunarity and percolation obtained from curvelet sub-images, using a polynomial classifier. The tests were evaluated by applying the 10-fold cross-validation method and the result was 0.994 of AUC, which is a relevant contribution to the Literature of pattern recognition of colorectal cancer. The obtained performance with a detailed analysis involving different types of features and classifiers are important contributions for pathologists, specialists interested in the study of this cancer and histological image processing researchers, which aim to develop the clinically applicable computational techniques. Department of Computer Science and Statistics (DCCE) São Paulo State University (UNESP), Rua Cristóvão Colombo, 2265, São José do Rio Preto Faculty of Computation (FACOM) - Federal University of Uberlândia (UFU), Avenida João Neves de Ávila 2121, Bl.B Federal Institute of Triangulo Mineiro (IFTM), Rua Belarmino Vilela Junqueira S/N Center of Mathematics Computing and Cognition Federal University of ABC (UFABC), Avenida dos Estados, 5001, Santo André Department of Computer Science and Statistics (DCCE) São Paulo State University (UNESP), Rua Cristóvão Colombo, 2265, São José do Rio Preto CAPES: 33004153073P9 CNPq: 427114/2016-0 FAPEMIG: APQ-00578-18

Introdução: Diferenciais socioeconômicos, raciais e de acesso a medidas de prevenção, diagnóstico e tratamento precoce tem aumentado a mortalidade por câncer de próstata. Objetivo: Descrever a mortalidade por câncer de próstata no Estado do Maranhão, segundo variáveis socioeconômicas e demográficas. Métodos: Estudo descritivo com 4.238 óbitos por câncer de próstata, CID 10 - C61, ocorridos de 2000 a 2017 entre homens ≥40 anos. Foram estimadas as frequências absolutas e relativas. Elaboraram-se curvas etárias de mortalidade proporcional por cor/raça e idade, e box-plot para a idade de morte por cor/raça. Resultados: O câncer de próstata representou 20,0% dos óbitos por neoplasia. Predominaram entre pardos, >80 anos, com baixa escolaridade, com morte domiciliar e na região fora da capital São Luís. Observou-se pior estrutura de mortalidade para pardos e pretos em todos os anos, com a mediana de idade de morte menor do que nos brancos. Conclusões: Observou-se um perfil de características individuais e contextuais associadas aos óbitos, apontando a necessidade de ações mais amplas de prevenção, diagnóstico e tratamento dessa neoplasia.

This study aims at identifying ocular findings in infants with microcephaly associated with presumed intrauterine infection by ZIKV. A cross-sectional study included 62 outpatient infants with congenital microcephaly, presumably secondary to maternal ZIKV infection. The included infants had head circumference below −2 standard deviations, with negative maternal serology for toxoplasmosis, rubella, cytomegalovirus, syphilis, and HIV. Assessment of ocular alterations was performed through review of their medical records. Forty two (67.7%) of the children analyzed presented some degree of ocular alteration. Findings in the posterior segment occurred in 29 (46.8%) patients, including atrophy of the retinal pigmentary epithelium in 15 (24.2%) patients, chorioretinal scars in 14 (22.6%) patients, retinal coloboma in 6 (9.7%) patients, and punctate retinal hemorrhage in 1 (1.6%) patient. Other ocular alterations were seen in 15 (24.2%) patients, including pathological strabismus in 11 (17.7%) patients, congenital cataracts in 2 (3.2%) patients, and nystagmus in 2 (3.2%) patients. Functional alterations were seen in four (6.5%) children. More than one change occurred in 11 (17.7%) children, eight of whom had head circumferences below −3 standard deviations. Changes in both the eyes occurred in 22 (35.5%) children, while 20 (32.3%) children had unilateral involvement. Among the 42 children with any ocular alteration, 27 (64.3%) children presented with severe microcephaly (head circumference with standard deviation lower than −3). The majority of children with microcephaly, presumably secondary to maternal ZIKV infection, present ocular alterations, with a higher frequency of involvement in the fundus. Severe ocular alterations are related to severe microcephaly.

Made available in DSpace on 2018-12-11T17:15:47Z (GMT). No. of bitstreams: 0 Previous issue date: 2017-12-01 Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) Fundação de Amparo à Pesquisa do Estado de Minas Gerais (FAPEMIG) Non-Hodgkin lymphomas are a health problem that affects over 70,000 people per year in the United States alone. The early diagnosis and the identification of this lymphoma are essential for an effective treatment. The classification of non-Hodgkin lymphomas is a task that continues to rank as one of the main challenges faced by hematologists, pathologists, as well as in the producing of computer vision methods due to its inherent complexity. In this paper, we present a new method to quantify and classify tissue samples of non-Hodgkin lymphomas based on the percolation theory. The method consists of associating multiscale and multidimensional approaches in order to divide the image into smaller regions and then verifying color similarity between pixels. A cluster labeling algorithm was applied to each region of interest to obtain the values for the number of clusters, occurrence of percolation and coverage ratio of the largest cluster. The method was tested on different classifiers aiming to differentiate three different groups of non-Hodgkin lymphomas. The obtained results (AUC rates between 0.940 and 0.993) were compared to those provided by methods consolidated in the Literature, which indicates that the percolation theory is a suitable approach for identifying these three classes of non-Hodgkin lymphomas, those being: mantle cell lymphoma, follicular lymphoma and chronic lymphocytic leukemia. Department of Computer Science and Statistics (DCCE) São Paulo State University (UNESP), R. Cristóvão Colombo, 2265 Faculty of Computation (FACOM) - Federal University of Uberlândia (UFU), Av. João Neves de Ávila 2121, Bl.B Center of Mathematics Computing and Cognition Federal University of ABC (UFABC), Av. dos Estados, 5001 Federal Institute of Triangulo Mineiro (IFTM), R. Belarmino Vilela Junqueira S/N Department of Histology and Morphology Institute of Biomedical Science Federal University of Uberlândia (UFU), Av. Amazonas, S/N Department of Computer Science and Statistics (DCCE) São Paulo State University (UNESP), R. Cristóvão Colombo, 2265 CAPES: 33004153073P9 FAPEMIG: APQ-02885-15

Neste trabalho, nos apresentaremos tecnicas de aproximacoes numericas do sis- tema de equacoes que governam o escoamento miscivel incompressivel, em meios porosos heterogeneos. As aproximacoes da equacao eliptica e da equacao de conveccao-difusao serao obtidas atraves do metodo dos elementos finitos mistos e hibridos, utilizando espacos de Raviart-Thomas de mais baixa ordem. O estudo sera realizado para o caso unidimensional. Porem, os metodos desenvolvidos podem ser aplicados, sem grandes alteracoes, em problemas que envolvam duas ou mais dimensoes. Esse tipo de tecnica de aproximacao e bastante empregada para a obtencao da velocidade de Darcy e da pressao em meios porosos heterogeneos. Nesse caso, a solucao do sistema de equacoes possui baixa regularidade. Isso ocorre, por exemplo, por conta da descontinuidade da permeabilidade, que e o parametro que caracteriza a incerteza inerente a formacao geologica caotica do meio. As formulacoes fracas da equacao de conveccao-difusao e da equacao da velocidade de fluxo de concentracao darao origem a um problema de valor inicial (PVI), que dependera da velocidade de Darcy. Tal PVI sera representado por uma equacao diferencial ordinaria na variavel que fornece os valores de concentracao, em um dado intervalo de tempo, [tinicial , tf inal ]. O PVI sera resolvido por uma adaptacao no metodo de Adams-Moulton de ordem 2. A velocidade de Darcy sera calculada no tempo tinicial . Nos demais instantes de tempo, pertencentes ao intervalo dado, os valores da velocidade serao obtidos por extrapolacao linear.

Made available in DSpace on 2018-12-11T17:01:51Z (GMT). No. of bitstreams: 0 Previous issue date: 2016-08-15 In computer-aided diagnosis one of the crucial steps to classify suspicious lesions is the extraction of features. Texture analysis methods have been used in the analysis and interpretation of medical images. In this work we present a method based on the association among curvelet transform, local binary patterns, feature selection by statistical analysis and distinct classification methods, in order to support the development of computer aided diagnosis system. The similar features were removed by the statistical analysis of variance (ANOVA). The understanding of the features was evaluated by applying the decision tree, random forest, support vector machine and polynomial (PL) classifiers, considering the metrics accuracy (AC) and area under the ROC curve (AUC): the rates were calculated on images of breast tissues with different physical properties (commonly observed in clinical practice). The datasets were the Digital Database for Screening Mammography, Breast Cancer Digital Repository and UCSB biosegmentation benchmark. The investigated groups were normal-abnormal and benign-malignant. The association of curvelet transform, local binary pattern and ANOVA with the PL classifier achieved higher AUC and AC values for all cases: the obtained rates were among 91% and 100%. These results are relevant, specially when we consider the difficulties of clinical practice in distinguishing the studied groups. The proposed association is useful as an automated protocol for the diagnosis of breast tissues and may contribute to the diagnosis of breast tissues (mammographic and histopathological images). UFABC - CMCC, av. dos Estados 5001, Bl.B UFU - FACOM, av. João Neves de Ávila 2121, Bl.B UNIVASF - CENEL, av. Antoˆnio C. Magalhães 510 UNESP - DCCE, r. Cristóvão Colombo 2265 IFTM, r. Belarmino Vilela Junqueira S/N UNESP - DCCE, r. Cristóvão Colombo 2265