Automatic segmentation and classification of human intestinal parasites from microscopy images

Human intestinal parasites constitute a problem in most tropical countries, causing death or physical and mental disorders. Their diagnosis usually relies on the visual analysis of microscopy images, with error rates that may range from moderate to high. The problem has been addressed via computational image analysis, but only for a few species and images free of fecal impurities. In routine, fecal impurities are a real challenge for automatic image analysis. We have circumvented this problem by a method that can segment and classify, from bright field microscopy images with fecal impurities, the 15 most common species of protozoan cysts, helminth eggs, and larvae in Brazil. Our approach exploits ellipse matching and image foresting transform for image segmentation, multiple object descriptors and their optimum combination by genetic programming for object representation, and the optimum-path forest classifier for object recognition. The results indicate that our method is a promising approach toward the fully automation of the enteroparasitosis diagnosis. © 2012 IEEE.

Structural analysis of the Pimelodus maculatus (Lacépède, 1803) embryogenesis (Siluriformes: Pimelodidae)

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Eficácia do programa de remediação metafonológica e de leitura para escolares com dificuldades de aprendizagem

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Distribuição intragástrica de refeições com 60 ml e 180 ml: três segmentações proximal-distal empregando a cintilografia

Pós-graduação em Biologia Geral e Aplicada - IBB

Estratégias de construção textual do chat escrito em espanhol com língua estrangeira

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Análise das transformações técnicas produtivas da avicultura de corte em Moçambique: do estado estruturante ao liberalismo econômico

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Mudanças na produção do espaço urbano de Londrina (PR), São José do Rio Preto (SP) e Uberlândia (MG): análise comparativa da dinâmica imobiliária recente

Pós-graduação em Geografia - FCT

Segmentação de imagens e reconstrução de modelos aplicada a estruturas ósseas

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Análise do desenvolvimento embrionário de espécimes provenientes dos cruzamentos interespecíficos entre Pseudoplatystoma corruscans e leiarius marmoratus

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Rank Aggregation for Pattern Classifier Selection in Remote Sensing Images

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Transgressões de grafia em produções textuais de escolares do programa educacional de resistência às drogas e à violência (PROERD)

Presence of the orthographic mistakes on the writting of the students with or without learning difficulties still is a concern. The focus of these study is the classification of orthographic mistakes on the writting of the students who had participated of the Educational Program of Resistance to the Drugs and the Violence (Proerd). Sixty four grade children from a public school were individually analyzed in this study. The aim of this study was to verify the frequency and characterization of the orthographic mistakes on the texts production these students. We had as base for this analysis the studies of Zorzi (1998). The most frequent mistakes made by students were: irregular phonographemic relation (24%), letters omission (18%), similar letters (13%) and hypo-segmentation and hyper-segmentation (11,0%), amongst others. The characterization of the mistakes writing makes possible the planning of the interventions, as well as, the use of the prevention strategies.

Classificação e quantificação de tecidos Biológicos para construção de fantomas pediátricos

Paediatric diagnostic radiology can be considered as a separate specialty and with distinct characteristics of the radiology applied in adult patients. This in reason of the variability in the anatomical structures size and bigger sensitivity of tissues. The literature present in its majority methodologies for segmentation and tissue classification in adult patients, and works on tissue quantification are rare. This work had for objective the development of a biological tissue classifier and quantifier algorithm, from histograms, and that converts the quantified average thickness of these tissues for its respective simulator materials. The results will be used in the optimization process of paediatrics images, in future works, since these patients are frequently over exposed to the radiation in the repeated attempts of if getting considered good quality radiographic images. The developed algorithm was capable to read and store the name of all the archives, in the operational system, to filter artifacs, to count and quantify each biological tissues from the histogram of the examination, to obtain the biological tissues average thicknesses and to convert this value into its respective simulator material. The results show that it is possible to distinguish bone, soft, fat and pulmonary tissues from histograms of tomographic examinations of thorax. The quantification of the constituent materials of anthropomorphic phantom made by the algorithm, compared with the data of literature shows that the biggest difference was of 21,6% for bone. However, the literature shows that variations of up to 30% in bone thickness do not influence of significant form in the radiographic image quality. The average thicknesses of biological tissues, quantified for paediatrics patients, show that one phantom can simulate patients with distinct DAP ranges, since variations... (Complete abstract click electronic access below)

Structural analysis of embryogenesis of Leiarius marmoratus (Siluriformes: Pimelodidae)

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

As lógicas espacias do setor bancário nas cidades de Presidente Prudente e São José do Rio Preto: da estrutura espacial concentrada à multicentralidade seletiva

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Effects of meal size and proximal-distal segmentation on gastric activity

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)