948 resultados para Foreground Segmentation
Resumo:
Background: An accurate percutaneous puncture is essential for disintegration and removal of renal stones. Although this procedure has proven to be safe, some organs surrounding the renal target might be accidentally perforated. This work describes a new intraoperative framework where tracked surgical tools are superimposed within 4D ultrasound imaging for security assessment of the percutaneous puncture trajectory (PPT). Methods: A PPT is first generated from the skin puncture site towards an anatomical target, using the information retrieved by electromagnetic motion tracking sensors coupled to surgical tools. Then, 2D ultrasound images acquired with a tracked probe are used to reconstruct a 4D ultrasound around the PPT under GPU processing. Volume hole-filling was performed in different processing time intervals by a tri-linear interpolation method. At spaced time intervals, the volume of the anatomical structures was segmented to ascertain if any vital structure is in between PPT and might compromise the surgical success. To enhance the volume visualization of the reconstructed structures, different render transfer functions were used. Results: Real-time US volume reconstruction and rendering with more than 25 frames/s was only possible when rendering only three orthogonal slice views. When using the whole reconstructed volume one achieved 8-15 frames/s. 3 frames/s were reached when one introduce the segmentation and detection if some structure intersected the PPT. Conclusions: The proposed framework creates a virtual and intuitive platform that can be used to identify and validate a PPT to safely and accurately perform the puncture in percutaneous nephrolithotomy.
Resumo:
Dental implant recognition in patients without available records is a time-consuming and not straightforward task. The traditional method is a complete user-dependent process, where the expert compares a 2D X-ray image of the dental implant with a generic database. Due to the high number of implants available and the similarity between them, automatic/semi-automatic frameworks to aide implant model detection are essential. In this study, a novel computer-aided framework for dental implant recognition is suggested. The proposed method relies on image processing concepts, namely: (i) a segmentation strategy for semi-automatic implant delineation; and (ii) a machine learning approach for implant model recognition. Although the segmentation technique is the main focus of the current study, preliminary details of the machine learning approach are also reported. Two different scenarios are used to validate the framework: (1) comparison of the semi-automatic contours against implant’s manual contours of 125 X-ray images; and (2) classification of 11 known implants using a large reference database of 601 implants. Regarding experiment 1, 0.97±0.01, 2.24±0.85 pixels and 11.12±6 pixels of dice metric, mean absolute distance and Hausdorff distance were obtained, respectively. In experiment 2, 91% of the implants were successfully recognized while reducing the reference database to 5% of its original size. Overall, the segmentation technique achieved accurate implant contours. Although the preliminary classification results prove the concept of the current work, more features and an extended database should be used in a future work.
Resumo:
In daily cardiology practice, assessment of left ventricular (LV) global function using non-invasive imaging remains central for the diagnosis and follow-up of patients with cardiovascular diseases. Despite the different methodologies currently accessible for LV segmentation in cardiac magnetic resonance (CMR) images, a fast and complete LV delineation is still limitedly available for routine use. In this study, a localized anatomically constrained affine optical flow method is proposed for fast and automatic LV tracking throughout the full cardiac cycle in short-axis CMR images. Starting from an automatically delineated LV in the end-diastolic frame, the endocardial and epicardial boundaries are propagated by estimating the motion between adjacent cardiac phases using optical flow. In order to reduce the computational burden, the motion is only estimated in an anatomical region of interest around the tracked boundaries and subsequently integrated into a local affine motion model. Such localized estimation enables to capture complex motion patterns, while still being spatially consistent. The method was validated on 45 CMR datasets taken from the 2009 MICCAI LV segmentation challenge. The proposed approach proved to be robust and efficient, with an average distance error of 2.1 mm and a correlation with reference ejection fraction of 0.98 (1.9 ± 4.5%). Moreover, it showed to be fast, taking 5 seconds for the tracking of a full 4D dataset (30 ms per image). Overall, a novel fast, robust and accurate LV tracking methodology was proposed, enabling accurate assessment of relevant global function cardiac indices, such as volumes and ejection fraction.
Resumo:
RESUMO: O constructo de customer value é aquele que melhor explica o comportamento do consumidor, uma vez que o seu objectivo é o de entender como os consumidores traduzem os atributos e consequências do uso de um produto em valores pessoais relevantes. A metodologia laddering, que tem como base a teoria das cadeias meios-fim, é um elemento teórico que se considera consistente para estabelecer a relação entre os atributos e os valores do consumidor. Esta dissertação pretende demonstrar a exequibilidade da metodologia laddering em estudos sobre o valor para o consumidor, percebendo quais são as vantagens e limitações do seu uso. É conclusivo que este método, através da construção de cadeias A-C-V, proporciona elementos de estudo que permitem a visualização de hierarquia de valores produzida pelos consumidores, função dos critérios de escolha destes durante e após um processo de compra. A aplicabilidade desta metodologia na perspectiva do valor para o cliente, permite a utilização dos seus resultados num conjunto de áreas específicas do marketing, das quais destacamos a segmentação e análise de mercado, a avaliação do posicionamento de produtos e marcas, a avaliação da publicidade e o desenvolvimento de estratégias de comunicação. ABSTRACT: The customer value construct is the one that best explains the consumer behavior, since its purpose is to understand how consumers translate the attributes and consequences of the use of a product in relevant personal values. The laddering methodology, which is based on the theory of means-end chains, is a theoretical element that is considered consistent for establish the relationship between attributes and consumer values. This thesis attempts to demonstrate the feasibility of the laddering methodology in studies about the value for the consumer, knowing what are the advantages and limitations of its use. It is conclusive that this method, by building chains A-C-V, provides elements of study that allows the visualization of the values hierarchy produced by consumers, according to the criteria of their choice during and after a purchase process. The applicability of this methodology from the perspective of customer value, allows the use of their results in a number of specific areas of marketing, which we emphasize the segmentation and market analysis, evaluation of product and branding positioning, evaluation of advertising and development of communication strategies.
Resumo:
The use of iris recognition for human authentication has been spreading in the past years. Daugman has proposed a method for iris recognition, composed by four stages: segmentation, normalization, feature extraction, and matching. In this paper we propose some modifications and extensions to Daugman's method to cope with noisy images. These modifications are proposed after a study of images of CASIA and UBIRIS databases. The major modification is on the computationally demanding segmentation stage, for which we propose a faster and equally accurate template matching approach. The extensions on the algorithm address the important issue of pre-processing that depends on the image database, being mandatory when we have a non infra-red camera, like a typical WebCam. For this scenario, we propose methods for reflection removal and pupil enhancement and isolation. The tests, carried out by our C# application on grayscale CASIA and UBIRIS images show that the template matching segmentation method is more accurate and faster than the previous one, for noisy images. The proposed algorithms are found to be efficient and necessary when we deal with non infra-red images and non uniform illumination.
Resumo:
Mortality from asthma has shown important variations over time in several countries. In Brazil, a mortality study performed in the 60s, covering the cities of S.Paulo and Ribeirão Preto, and other ten cities showed that S.Paulo presented the lowest death rate from asthma among of them all. It was decided to study the time trends of deaths from asthma and from the whole set of respiratory diseases from 1970 to 1992, in the population aged 15-34 yrs. old in the State of S.Paulo, as well as to compare them with those of other countries. Asthma mortality rates during the 23 years of observation since 1975, showed an oscillatory declining pattern with a peak of deaths in the initial years. The linearization of the curve allows the calculation of Pearson's correlation coefficient that was significantly negative, suggesting a decline in the mortality over this period, mainly in the 5-9 yrs. old and 30-34 yrs. old strata. The segmentation of data between the period of ICD-9, 1970 to 1978, and of ICD-9, 1979 and subsequent years, shows that there is stability within each period, in all age-groups, except for that of 5-9 yr. olds between 1970-1978. Comparing the rates of the population aged 15-34 yrs. old for the State of S. Paulo, Brazil, with trends observed in 14 other countries, an intermediate pattern for the first triennial period (1970-1972) as well as for the subsequent triennial periods, emerges. A prevalence study of asthma, a follow up program meant for using emergency rooms and a surveillance of deaths due to all respiratory diseases and specifically to asthma are strongly recommended.
Resumo:
Dissertação apresentada ao Instituto Superior de Contabilidade para a obtenção do Grau de Mestre em Empreendedorismo e Internacionalização Orientada por Professor Doutor José Freitas Santos
Resumo:
OBJECTIVE: To identify the effects of decentralization on health financing and governance policies in Mexico from the perspective of users and providers. METHODS: A cross-sectional study was carried out in four states that were selected according to geopolitical and administrative criteria. Four indicators were assessed: changes and effects on governance, financing sources and funds, the final destination of resources, and fund allocation mechanisms. Data collection was performed using in-depth interviews with health system key personnel and community leaders, consensus techniques and document analyses. The interviews were transcribed and analyzed by thematic segmentation. RESULTS: The results show different effectiveness levels for the four states regarding changes in financing policies and community participation. Effects on health financing after decentralization were identified in each state, including: greater participation of municipal and state governments in health expenditure, increased financial participation of households, greater community participation in low-income states, duality and confusion in the new mechanisms for coordination among the three government levels, absence of an accountability system, lack of human resources and technical skills to implement, monitor and evaluate changes in financing. CONCLUSIONS: In general, positive and negative effects of decentralization on health financing and governance were identified. The effects mentioned by health service providers and users were related to a diversification of financing sources, a greater margin for decisions around the use and final destination of financial resources and normative development for the use of resources. At the community level, direct financial contributions were mentioned, as well as in-kind contributions, particularly in the form of community work.
Resumo:
Mestrado em Engenharia Informática
Resumo:
Dissertação de Mestrado, Estudos Integrados dos Oceanos, 26 de Fevereiro de 2014, Universidade dos Açores.
Resumo:
Resumo: Este artigo analisa a relação entre o nível de consciência fonológica, conhecimento das letra e as estratégias utilizadas para ler e escrever, em crianças de cinco anos, ensinadas em catalão. Participaram 69 crianças de três classes diferentes. Cada um dos seus professores utilizava um método diferente de ensino: analítico, sintético ou analítico-sintético. As crianças foram avaliadas no início e no final do ano letivo em: Reconhecimento de letras, segmentação palavra oral, leitura de palavras, leitura de um texto curto e um ditado. Foram realizadas análises de granulação fina em nas respostas das crianças, para identificar estratégias e padrões específicos. A análise qualitativa indica que a capacidade de segmentar uma palavra em sílabas por via oral parece ser suficiente para as crianças começarem a ler de uma forma convencional. Além disso, a consciência fonológica e o conhecimento das letras são usados em formas relativamente diferentes, dependendo do tipo de texto a ser lido. As abordagens de ensino dos professores parecem ter uma influência nos resultados das crianças.
Resumo:
Dissertação apresentada à Escola Superior de Educação de Lisboa para obtenção de grau de mestre em Ciências da Educação Especialidade Intervenção Precoce
Resumo:
Dissertação de Mestrado em Ciências Económicas e Empresariais.
Resumo:
Dissertação apresentada à Escola Superior de Educação de Lisboa para obtenção de grau de Mestre em Ciências da Educação - Especialização em Educação Especial
Resumo:
Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia Civil na Área de Especialização de Vias de Comunicação e Transportes