A análise de textura é uma das mais básicas e famosas áreas de pesquisa em visão computacional. Ela é também de grande importância em muitas outras disciplinas, tais como ciências médicas e biológicas. Por exemplo, uma tarefa comum de análise de textura é a detecção de tecidos não saudáveis em imagens de Ressonância Magnética do pulmão. Nesta dissertação, nós propomos um método novo de caracterização de textura baseado nas medidas de complexidade tais como o expoente de Hurst, o expoente de Lyapunov e a complexidade de Lempel-Ziv. Estas medidas foram aplicadas sobre amostras de imagens no espaço de frequência. Três métodos de amostragem foram propostas, amostragem: radial, circular e por caminhadas determinísticas parcialmente auto- repulsivas (amostragem CDPA). Cada método de amostragem produz um vetor de características por medida de complexidade aplicada. Esse vetor contem um conjunto de descritores que descrevem a imagem processada. Portanto, cada imagem será representada por nove vetores de características (três medidas de complexidade e três métodos de amostragem), os quais serão comparados na tarefa de classificação de texturas. No final, concatenamos cada vetor de características conseguido calculando a complexidade de Lempel-Ziv em amostras radiais e circulares com os descritores obtidos através de técnicas de análise de textura tradicionais, tais como padrões binários locais (LBP), wavelets de Gabor (GW), matrizes de co-ocorrência en níveis de cinza (GLCM) e caminhadas determinísticas parcialmente auto-repulsivas em grafos (CDPAg). Este enfoque foi testado sobre três bancos de imagens: Brodatz, USPtex e UIUC, cada um com seus próprios desafios conhecidos. As taxas de acerto de todos os métodos tradicionais foram incrementadas com a concatenação de relativamente poucos descritores de Lempel-Ziv. Por exemplo, no caso do método LBP, o incremento foi de 84.25% a 89.09% com a concatenação de somente cinco descritores. De fato, simplesmente concatenando cinco descritores são suficientes para ver um incremento na taxa de acerto de todos os métodos tradicionais estudados. Por outro lado, a concatenação de un número excessivo de descritores de Lempel-Ziv (por exemplo mais de 40) geralmente não leva a melhora. Neste sentido, vendo os resultados semelhantes obtidos nos três bancos de imagens analisados, podemos concluir que o método proposto pode ser usado para incrementar as taxas de acerto em outras tarefas que envolvam classificação de texturas. Finalmente, com a amostragem CDPA também se obtém resultados significativos, que podem ser melhorados em trabalhos futuros. / Texture analysis is one of the basic and most popular computer vision research areas. It is also of importance in many other disciplines, such as medical sciences and biology. For example, non-healthy tissue detection in lung Magnetic Resonance images is a common texture analysis task. We proposed a novel method for texture characterization based on complexity measures such as Lyapunov exponent, Hurst exponent and Lempel-Ziv complexity. This measurements were applied over samples taken from images in the frequency domain. Three types of sampling methods were proposed: radial sampling, circular sampling and sampling by using partially self-avoiding deterministic walks (CDPA sampling). Each sampling method produce a feature vector which contains a set of descriptors that characterize the processed image. Then, each image will be represented by nine feature vectors which are means to be compared in texture classification tasks (three complexity measures over samples from three sampling methods). In the end, we combine each Lempel-Ziv feature vector from the circular and radial sampling with descriptors obtained through traditional image analysis techniques, such as Local Binary Patterns (LBP), Gabor Wavelets (GW), Gray Level Co-occurrence Matrix (GLCM) and Self-avoiding Deterministic Walks in graphs (CDPAg). This approach were tested in three datasets: Brodatz, USPtex and UIUC, each one with its own well-known challenges. All traditional methods success rates were increased by adding relatively few Lempel-Ziv descriptors. For example in the LBP case the increment went from 84.25% to 89.09% with the addition of only five descriptors. In fact, just adding five Lempel-Ziv descriptors are enough to see an increment in the success rate of every traditional method. However, adding too many Lempel-Ziv descriptors (for example more than 40) generally doesnt produce better results. In this sense, seeing the similar results we obtain in all three databases, we conclude that this approach may be used to increment the success rate in a lot of others texture classification tasks. Finally, the CDPA sampling also obtain very promising results that we can improve further on future works.

O disco intervertebral é uma estrutura cuja função é receber, amortecer e distribuir o impacto das cargas impostas sobre a coluna vertebral. O aumento da idade e a postura adotada pelo indivíduo podem levar à degeneração do disco intervertebral. Atualmente, a Ressonância Magnética (RM) é considerada o melhor e mais sensível método não invasivo de avaliação por imagem do disco intervertebral. Neste trabalho foram desenvolvidos métodos quantitativos computadorizados para auxílio ao diagnóstico da degeneração do disco intervertebral em imagens de ressonância magnética ponderadas em T2 da coluna lombar, de acordo com a escala de Pfirrmann, uma escala semi-quantitativa, com cinco graus de degeneração. Os algoritmos computacionais foram testados em um conjunto de dados que consiste de imagens de 300 discos, obtidos de 102 indivíduos, com diferentes graus de degeneração. Máscaras binárias de discos segmentados manualmente foram utilizadas para calcular seus centroides, visando criar um ponto de referência para possibilitar a extração de atributos. Uma análise de textura foi realizada utilizando a abordagem proposta por Haralick. Para caracterização de forma, também foram calculados os momentos invariantes definidos por Hu e os momentos centrais para cada disco. A classificação do grau de degeneração foi realizada utilizando uma rede neural artificial e o conjunto de atributos extraídos de cada disco. Uma taxa média de acerto na classificação de 87%, com erro padrão de 6,59% e uma área média sob a curva ROC (Receiver Operating Characteristic) de 0,92 indicam o potencial de aplicação dos algoritmos desenvolvidos como ferramenta de apoio ao diagnóstico da degeneração do disco intervertebral. / The intervertebral disc is a structure whose function is to receive, absorb and transmit the impact loads imposed on the spine. Increasing age and the posture adopted by the individual can lead to degeneration of the intervertebral disc. Currently, Magnetic Resonance Imaging (MRI) is considered the best and most sensitive noninvasive method to imaging evaluation of the intervertebral disc. In this work were developed methods for quantitative computer-aided diagnosis of the intervertebral disc degeneration in MRI T2 weighted images of the lumbar column according to Pfirrmann scale, a semi-quantitative scale with five degrees of degeneration. The algorithms were tested on a dataset of 300 images obtained from 102 subjects with varying degrees of degeneration. Binary masks manually segmented of the discs were used to calculate their centroids, to create a reference point to enable extraction of attributes. A texture analysis was performed using the approach proposed by Haralick. For the shape characterization, invariant moments defined by Hu and central moments were also calculated for each disc. The rating of the degree of degeneration was performed using an artificial neural network and the set of extracted attributes of each disk. An average rate of correct classification of 87%, with standard error 6.59% and an average area under the ROC curve (Receiver Operating Characteristic) of 0.92 indicates the potential application of the algorithms developed as a diagnostic support tool to the degeneration of the intervertebral disc.

Le travail présenté dans cette thèse a pour objectif d’évaluer le potentiel de modèles probabilistes multivariés appliqués sur les sous-bandes d’une décomposition en ondelettes pour la classification d’images de télédétection optiques à très haute résolution spatiale. Trois thématiques principales ont été investiguées dans ce travail : la différenciation de classes d’âge de peuplements de pins maritimes, la détection de parcelles viticoles et la détection de parcs ostréicoles. Une contribution originale concerne la proposition d’une chaîne traitement pour une classification supervisée orientée objet se basant sur des mesures de similarité adaptées au contexte de modélisation probabiliste. Celle-ci implique la création d’une base de données de patchs de texture pour l’apprentissage et l’utilisation d’une pré-segmentation de l’image à classifier. Les modèles probabilistes multivariés testés ont tout d’abord été évalués dans une procédure d’indexation d’images. Les modèles les plus performants identifiés par cette procédure ont été ensuite appliqués dans la chaîne de traitement proposée. Dans les trois thématiques explorées, les modèles multivariés ont révélé des capacités remarquables de représentation de la texture et ont permis d’obtenir une qualité de classification supérieure à celle obtenue par la méthode des matrices de co-occurrence. Ces résultats démontrent l’intérêt de la représentation multi-échelles et multi-orientations de la texture dans l’espace transformé en ondelettes et la pertinence de la modélisation multivariée des coefficients d’ondelettes issus de cette décomposition. / The prime objective of this thesis is to evaluate the potential of multivariate probabilistic models applied on wavelet subbands for the classification of very high resolution remote sensing optical data. Three main applications are investigated in this study: the differentiation of age classes of maritime pine forest stands, the detection of vineyards and the detection of oyster fields. One main contribution includes the proposal of an original supervised and object-oriented classification scheme based on similarity measurements adapted to the context of probabilistic modeling. This scheme involves the creation of a database of texture patches for the learning step and a pre-segmentation of the image to classify. The tested multivariate models were first evaluated in an image retrieval framework. The best models identified in this procedure were then applied in the proposed image processing scheme. In the three proposed thematic applications, multivariate models revealed remarkable abilities to represent the texture and reached higher classification accuracies than the method based on co-occurrence matrices. These results confirm the interest of the multi-scale and multi-orientation representation of textures through the wavelet transform, as well as the relevance of the multivariate modeling of wavelet coefficients

Για τις Ευρωπαίες γυναίκες ο καρκίνος του σώματος της μήτρας αποτελεί το τέταρτο συχνότερο νεόπλασμα και την δέκατη σε σειρά αιτία θανάτου από καρκίνο. Ανεξάρτητα από το εάν η διακολπική υπερηχογραφία (TVS) αποτελεί δόκιμο μέσο διαλογής (screening) για την ανίχνευση ενδομητρικού καρκίνου σε ασυμπτωματικές μετεμμηνοπαυσιακές γυναίκες, εντούτοις κυριαρχεί στους διαγνωστικούς αλγόριθμους διερεύνησης κάθε μητρορραγίας προς αποκλεισμό του καρκίνου αυτού. Παράλληλα με τα πιθανά οφέλη από την ενσωμάτωση τεχνικών Υπερηχοϋστερογραφίας (SIS) και Doppler στην ενδομητρική απεικόνιση, η δισδιά- στατη “gray scale” διακολπική υπερηχογραφία οφείλει μεγάλο μέρος της προόδου της στην ώθηση από τις εξελίξεις της τεχνολογίας. Μετά την εισαγωγή των διακολπικών ηχοβολέων πολλαπλών συχνοτήτων (multifrequency) και της “αρμονικής” (harmonic) απεικόνισης, τα σύγχρονα υπερηχογραφικά μηχανήματα διαθέτουν επιλογές λογισμι- κού για ενίσχυση της ανάλυσης της αντίθεσης δομών, λεπτών ρυθμίσεων για εξέταση διαφορετικών τύπων ιστών, πολλαπλού εύρους εστίασης, μετάδοσης της δέσμης σε πλάγια διεύθυνση ως προς το ακουστικό παράθυρο, κ.α. Τα παραπάνω, καθώς και φίλτρα μείωσης του θορύβου βελτιστοποιούν την απεικόνιση του ενδομητρίου διευκολύνοντας την αποτίμησή του, ακόμη και στα χέρια άπειρων εξεταστών. Το πάχος της διπλής ενδομητρικής στιβάδας αποτελεί ιστορικά τον πλέον αδιαμφισβήτητο ποσοτικό δείκτη ενδομητρικού καρκίνου, ειδικά στην παρουσία μετεμμηνοπαυσιακής μητρορραγίας. Η συνδυασμένη μελέτη της ενδομητρικής μορφο- λογίας και πάχους παρέχει περισσότερες πληροφορίες, ειδικά στην αποτίμηση της “γκρίζας ζώνης” των 4-10 χιλιοστών ενδομητρικού πάχους, αν και τα ευρήματα των “μορφολογικών” αυτών μελετών δεν υπήρξαν πάντα σταθερά. Με δεδομένη τη σημασία της μορφολογίας στην αποτίμηση του ενδομητρικού ιστού, και αποσκοπώντας στην υπέρβαση του υποκειμενικού χαρακτήρα της ποιοτικής εκτίμησης της υπερηχογραφικής εικόνας, θα ήταν χρήσιμη η εφαρμογή αυτοματοποιημένων τεχνικών που αξιολογούν αντικειμενικά μορφολογικά χαρακτη- ριστικά, όπως η υποβοηθούμενη από υπολογιστή ανάλυση υφής, (“computerized texture analysis”). Στις ψηφιακές εικόνες, η υφή αντικατοπτρίζει τονικές (ένταση των εικονο- στοιχείων) και δομικές (χωρική κατανομή της έντασης των εικονοστοιχείων) ιδιότητες. Η “ανάλυση υφής” αναφέρεται σε αλγόριθμους που ποσοτικοποιούν περιεχόμενο και στοιχεία υφής που πιθανόν, ή όχι, να γίνονται αντιληπτά με το γυμνό μάτι. Δεδομένου ότι στην ιατρική απεικόνιση οι εικόνες περιλαμβάνουν πολλαπλές ιδιότητες των βιολογικών δομών, η ανάλυση υφής των εικόνων αυτών παρέχει ποσοτικές πληροφο- ρίες σχετικές με τα χαρακτηριστικά, τη μορφολογία και τις ιδιότητες των δομών αυτών. Σχήματα ταξινόμησης στηριζόμενα στην υφή έχουν χρησιμοποιηθεί με επιτυχία σε ποικιλία υπερηχογραφικών εφαρμογών. Η βασισμένη σε υπολογιστή αποτίμηση εικόνων του ενδομητρίου έχει βρει κυρίως εφαρμογή στη Υποβοηθούμενη Αναπαραγωγή, αλλά δεν έχει χρησιμοποιηθεί για τη διάγνωση ενδομητρικών κακοηθειών στην δισδιάστατη υπερηχογραφία. Σκοπός της διδακτορικής αυτής διατριβής είναι η αξιολόγηση του εφικτού της υποβοηθούμενης από υπολογιστή ανάλυσης υφής του ενδομητρικού ιστού όπως απεικονίζεται σε δισδιάστατες “gray scale” υπερηχογραφικές εικόνες. Περαιτέρω, διερευνήθηκε το αποτέλεσμα μιας τεχνικής επεξεργασίας βασισμένης σε μετασχη- ματισμό κυματίου (wavelet) στη διαδικασία τμηματοποίησης και χαρακτηρισμού του ενδομητρικού ιστού. / Cancer of the corpus uteri represents the fourth commonest neoplasm among European women and the tenth most common cause of death attributed to cancer. Irrespective whether the use of transvaginal ultrasonography (TVS) as a screening tool for detecting endometrial cancer in asymptomatic postmenopausal women is warranted, TVS dominates most diagnostic algorithms in assessing metrorrhagias to exclude this cancer. Alongside the potential benefits stemming from the integration of Saline Infusion Sonography) and Doppler modalities in endometrial imaging, gray scale TVS showed remarkable advances in the previous decades, largely attributed to the evolution in computer sciences. Following the introduction of multifrequency transvaginal probes and harmonic imaging, modern scanners are equipped with software options that enhance the resolution or the contrast between different structures, fine tune while assessing different types of tissue, implement different depth of focusing, transmit the ultrasonic beam in oblique directions to the acoustic window; all these features, in addition to de-speckle filters optimize the endometrial depiction, facilitating its assessment, even in the hands of moderately skilled operators. Double stripe endometrial thickness has illustrated a remarkable robustness over time as a quantitative indicator of endometrial cancer, especially in the presence of postmenopausal bleeding. The combined consideration of endometrial morphology and thickness has proven particularly beneficial, especially in the assessment of the 4-10 mm endometrial thickness “grey zone”, although the findings of the “morphologic” studies haven’t always been consistent. Given the importance of morphology in assessing endometrial tissue, and aiming to overcome the inherent subjectivity of the qualitative consideration of ultrasonic images, implementation of automated techniques assessing objective morphologic features such as “computerized texture analysis” would be beneficial. In digital images, texture reflects tonal (intensities of image pixels) and structural (spatial distribution of pixel intensities) properties. Texture analysis refers to algorithms that quantify texture content that may, or may not, be visually perceived. Since medical images capture various properties of biological structures, texture analysis of medical images can provide quantitative metrics relevant to structure, morphology and status of biological tissues. Texture based classification schemes have been successfully implemented in a variety of ultrasound applications. Computerized TVS assessment of endometrial morphology, has been applied mainly in assisted reproduction techniques; however, computerized texture analysis has not been implemented for diagnosing endometrial malignancies in grey scale TVS. The aim of this study is to investigate the feasibility of computerized texture analysis in characterizing endometrial tissue as depicted in 2D grey scale TVS images. Furthermore, we assess the effect of a wavelet-based image processing technique in the segmentation and subsequent characterization tasks of endometrial tissue.

Roll compaction is a continuous process commonly used in the pharmaceutical industry for dry granulation of moisture and heat sensitive powder blends. It is intended to increase bulk density and improve flowability. Roll compaction is a complex process that depends on many factors, such as feed powder properties, processing conditions and system layout. Some of the variability in the process remains unexplained. Accordingly, modeling tools are needed to understand the properties and the interrelations between raw materials, process parameters and the quality of the product. It is important to look at the whole manufacturing chain from raw materials to tablet properties. The main objective of this thesis was to investigate the impact of raw materials, process parameters and system design variations on the quality of intermediate and final roll compaction products, as well as their interrelations. In order to do so, we have conducted a series of systematic experimental studies and utilized chemometric tools, such as design of experiments, latent variable models (i.e. PCA, OPLS and O2PLS) as well as mechanistic models based on the rolling theory of granular solids developed by Johanson (1965). More specifically, we have developed a modeling approach to elucidate the influence of different brittle filler qualities of mannitol and dicalcium phosphate and their physical properties (i.e. flowability, particle size and compactability) on intermediate and final product quality. This approach allows the possibility of introducing new fillers without additional experiments, provided that they are within the previously mapped design space. Additionally, this approach is generic and could be extended beyond fillers. Furthermore, in contrast to many other materials, the results revealed that some qualities of the investigated fillers demonstrated improved compactability following roll compaction. In one study, we identified the design space for a roll compaction process using a risk-based approach. The influence of process parameters (i.e. roll force, roll speed, roll gap and milling screen size) on different ribbon, granule and tablet properties was evaluated. In another study, we demonstrated the significant added value of the combination of near-infrared chemical imaging, texture analysis and multivariate methods in the quality assessment of the intermediate and final roll compaction products. Finally, we have also studied the roll compaction of an intermediate drug load formulation at different scales and using roll compactors with different feed screw mechanisms (i.e. horizontal and vertical). The horizontal feed screw roll compactor was also equipped with an instrumented roll technology allowing the measurement of normal stress on ribbon. Ribbon porosity was primarily found to be a function of normal stress, exhibiting a quadratic relationship. A similar quadratic relationship was also observed between roll force and ribbon porosity of the vertically fed roll compactor. A combination of design of experiments, latent variable and mechanistic models led to a better understanding of the critical process parameters and showed that scale up/transfer between equipment is feasible.

Fúze obrazu je dnes jednou z nejběžnějších avšak stále velmi diskutovanou oblastí v lékařském zobrazování a hraje důležitou roli ve všech oblastech lékařské péče jako je diagnóza, léčba a chirurgie. V této dizertační práci jsou představeny tři projekty, které jsou velmi úzce spojeny s oblastí fúze medicínských dat. První projekt pojednává o 3D CT subtrakční angiografii dolních končetin. V práci je využito kombinace kontrastních a nekontrastních dat pro získání kompletního cévního stromu. Druhý projekt se zabývá fúzí DTI a T1 váhovaných MRI dat mozku. Cílem tohoto projektu je zkombinovat stukturální a funkční informace, které umožňují zlepšit znalosti konektivity v mozkové tkáni. Třetí projekt se zabývá metastázemi v CT časových datech páteře. Tento projekt je zaměřen na studium vývoje metastáz uvnitř obratlů ve fúzované časové řadě snímků. Tato dizertační práce představuje novou metodologii pro klasifikaci těchto metastáz. Všechny projekty zmíněné v této dizertační práci byly řešeny v rámci pracovní skupiny zabývající se analýzou lékařských dat, kterou vedl pan Prof. Jiří Jan. Tato dizertační práce obsahuje registrační část prvního a klasifikační část třetího projektu. Druhý projekt je představen kompletně. Další část prvního a třetího projektu, obsahující specifické předzpracování dat, jsou obsaženy v disertační práci mého kolegy Ing. Romana Petera.

A análise de textura é uma das mais básicas e famosas áreas de pesquisa em visão computacional. Ela é também de grande importância em muitas outras disciplinas, tais como ciências médicas e biológicas. Por exemplo, uma tarefa comum de análise de textura é a detecção de tecidos não saudáveis em imagens de Ressonância Magnética do pulmão. Nesta dissertação, nós propomos um método novo de caracterização de textura baseado nas medidas de complexidade tais como o expoente de Hurst, o expoente de Lyapunov e a complexidade de Lempel-Ziv. Estas medidas foram aplicadas sobre amostras de imagens no espaço de frequência. Três métodos de amostragem foram propostas, amostragem: radial, circular e por caminhadas determinísticas parcialmente auto- repulsivas (amostragem CDPA). Cada método de amostragem produz um vetor de características por medida de complexidade aplicada. Esse vetor contem um conjunto de descritores que descrevem a imagem processada. Portanto, cada imagem será representada por nove vetores de características (três medidas de complexidade e três métodos de amostragem), os quais serão comparados na tarefa de classificação de texturas. No final, concatenamos cada vetor de características conseguido calculando a complexidade de Lempel-Ziv em amostras radiais e circulares com os descritores obtidos através de técnicas de análise de textura tradicionais, tais como padrões binários locais (LBP), wavelets de Gabor (GW), matrizes de co-ocorrência en níveis de cinza (GLCM) e caminhadas determinísticas parcialmente auto-repulsivas em grafos (CDPAg). Este enfoque foi testado sobre três bancos de imagens: Brodatz, USPtex e UIUC, cada um com seus próprios desafios conhecidos. As taxas de acerto de todos os métodos tradicionais foram incrementadas com a concatenação de relativamente poucos descritores de Lempel-Ziv. Por exemplo, no caso do método LBP, o incremento foi de 84.25% a 89.09% com a concatenação de somente cinco descritores. De fato, simplesmente concatenando cinco descritores são suficientes para ver um incremento na taxa de acerto de todos os métodos tradicionais estudados. Por outro lado, a concatenação de un número excessivo de descritores de Lempel-Ziv (por exemplo mais de 40) geralmente não leva a melhora. Neste sentido, vendo os resultados semelhantes obtidos nos três bancos de imagens analisados, podemos concluir que o método proposto pode ser usado para incrementar as taxas de acerto em outras tarefas que envolvam classificação de texturas. Finalmente, com a amostragem CDPA também se obtém resultados significativos, que podem ser melhorados em trabalhos futuros. / Texture analysis is one of the basic and most popular computer vision research areas. It is also of importance in many other disciplines, such as medical sciences and biology. For example, non-healthy tissue detection in lung Magnetic Resonance images is a common texture analysis task. We proposed a novel method for texture characterization based on complexity measures such as Lyapunov exponent, Hurst exponent and Lempel-Ziv complexity. This measurements were applied over samples taken from images in the frequency domain. Three types of sampling methods were proposed: radial sampling, circular sampling and sampling by using partially self-avoiding deterministic walks (CDPA sampling). Each sampling method produce a feature vector which contains a set of descriptors that characterize the processed image. Then, each image will be represented by nine feature vectors which are means to be compared in texture classification tasks (three complexity measures over samples from three sampling methods). In the end, we combine each Lempel-Ziv feature vector from the circular and radial sampling with descriptors obtained through traditional image analysis techniques, such as Local Binary Patterns (LBP), Gabor Wavelets (GW), Gray Level Co-occurrence Matrix (GLCM) and Self-avoiding Deterministic Walks in graphs (CDPAg). This approach were tested in three datasets: Brodatz, USPtex and UIUC, each one with its own well-known challenges. All traditional methods success rates were increased by adding relatively few Lempel-Ziv descriptors. For example in the LBP case the increment went from 84.25% to 89.09% with the addition of only five descriptors. In fact, just adding five Lempel-Ziv descriptors are enough to see an increment in the success rate of every traditional method. However, adding too many Lempel-Ziv descriptors (for example more than 40) generally doesnt produce better results. In this sense, seeing the similar results we obtain in all three databases, we conclude that this approach may be used to increment the success rate in a lot of others texture classification tasks. Finally, the CDPA sampling also obtain very promising results that we can improve further on future works.

Orientador: Konradin Metze / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Ciencias Medicas / Made available in DSpace on 2018-08-10T11:27:03Z (GMT). No. of bitstreams: 1 Valladao_MariaLuizadeCastroRamos_M.pdf: 884922 bytes, checksum: 2e058daa788641932fbfccd1408d3d69 (MD5) Previous issue date: 2007 / Resumo: O Tumor Venéreo Transmissível Canino (TVTC) é uma neoplasia muito comum em caninos com livre acesso as ruas. O TVTC pode provocar metástases que levam o animal à morte. A presente tese realizou estudo exploratório e prospectivo em 100 caninos portadores de TVTC de ocorrência natural. Foram anotados dados clínicos como raça, sexo, idade, peso corporal e escore na Escala de Desempenho Karnofsky Adaptada (EDKA), bem como amostras citológicas. O objetivo do estudo foi elaborar fatores prognósticos relacionados à sobrevida e fatores preditivos da resposta da monoterapia com vincristina. Os resultados demonstraram que o a idade, o peso corporal do cão e o escore na EDKA são fatores independentes prognósticos da sobrevida durante o tratamento. Cães com escore na EDKA abaixo de 50 tiveram um péssimo prognóstico de sobrevida. O tempo de interrupção do tratamento, época do ano em que se iniciou o tratamento, área do núcleo e a "rugosidade" da cromatina em preparações citológicas mostraram ser fatores independentes preditivos do sucesso da terapia. A sobrevida durante a terapia depende do estado clínico do animal, enquanto a resposta terapêutica depende tanto de características da neoplasia como de fatores ambientais externos que modificam o estado clínico do animal / Abstract: The veneral transmissible tumor of dogs (CTVT) is a common neoplasia in free roaming dogs. Since this tumor may metastasize it is a possible tread for the animals. In a prospective exploratory study based on 100 dogs with naturally occuring CTVT we collected data on breed, sex, age, weight, tumor size and the score on a modified Karnofsky Performance Scale, as well cytologic smears. The objective of the investigation was study to elaborate prognostic factors related to survival and predicitive factors related to the response to vincristine monochemotherapy. Age, sex and the Karnofsky score showed to be independent prognostic factors for survival during chemotherapy. A score below 50 indicated poor survival. Time of interruption of the treatment, season of the year, nuclear area and "roughness" of the cromatin in cytologic preparations showed to be independent prognostic factors for the success of therapy. Thus survival during therapy depends on the performance status of the dog, whereas therapy success depends both on tumor characteristics and external factors modificating the animals performance / Mestrado / Biologia Estrutural, Celular, Molecular e do Desenvolvimento / Mestre em Fisiopatologia

Ce travail de thèse propose une nouvelle approche ponctuelle pour l'analyse de texture dans l'imagerie de télédétection à très haute résolution (THR). Cette approche ne prend en compte que des points caractéristiques, et non pas tous les pixels dans l'image, pour représenter et caractériser la texture. Avec l'augmentation de la résolution spatiale des capteurs satellitaires, les images THR ne vérifient que faiblement l'hypothèse de stationnarité. Une telle approche devient donc pertinente étant donné que seuls l'interaction et les caractéristiques des points-clés sont exploitées. De plus, puisque notre approche ne considère pas tous les pixels dans l'image comme le font la plupart des méthodes denses de la littérature, elle est plus à-même de traiter des images de grande taille acquises par des capteurs THR. Dans ce travail, la méthode ponctuelle est appliquée en utilisant des pixels de maxima locaux et minima locaux (en intensité) extraits à partir de l'image. Elle est intégrée dans plusieurs chaînes de traitement en se fondant sur différentes techniques existantes telles la théorie des graphes, la notion de covariance, la mesure de distance géométrique, etc. En conséquence, de nombreuses applications basées sur la texture sont abordées en utilisant des données de télédétection (images optiques et radar), telles l'indexation d'images, la segmentation, la classification et la détection de changement, etc. En effectuant des expériences dédiées à chaque application thématique, la pertinence et l'efficacité du cadre méthodologique proposé sont confirmées et validées. / This thesis work proposes a novel pointwise approach for texture analysis in the scope of very high resolution (VHR) remote sensing imagery. This approach takes into consideration only characteristic pixels, not all pixels of the image, to represent and characterize textural features. Due to the fact that increasing the spatial resolution of satellite sensors leads to the lack of stationarity hypothesis in the acquired images, such an approach becomes relevant since only the interaction and characteristics of keypoints are exploited. Moreover, as this technique does not need to consider all pixels inside the image like classical dense approaches, it is more capable to deal with large-size image data offered by VHR remote sensing acquisition systems. In this work, our pointwise strategy is performed by exploiting the local maximum and local minimum pixels (in terms of intensity) extracted from the image. It is integrated into several texture analysis frameworks with the help of different techniques and methods such as the graph theory, the covariance-based approach, the geometric distance measurement, etc. As a result, a variety of texture-based applications using remote sensing data (both VHR optical and radar images) are tackled such as image retrieval, segmentation, classification, and change detection, etc. By performing dedicated experiments to each thematic application, the effectiveness and relevance of the proposed approach are confirmed and validated.

Le travail présenté dans cette thèse s’inscrit dans le cadre de la modélisation d’images texturées à l’aide des représentations multi-échelles et multi-orientations. Partant des résultats d’études en neurosciences assimilant le mécanisme de la perception humaine à un schéma sélectif spatio-fréquentiel, nous proposons de caractériser les images texturées par des modèles probabilistes associés aux coefficients des sous-bandes. Nos contributions dans ce contexte concernent dans un premier temps la proposition de différents modèles probabilistes permettant de prendre en compte le caractère leptokurtique ainsi que l’éventuelle asymétrie des distributions marginales associées à un contenu texturée. Premièrement, afin de modéliser analytiquement les statistiques marginales des sous-bandes, nous introduisons le modèle Gaussien généralisé asymétrique. Deuxièmement, nous proposons deux familles de modèles multivariés afin de prendre en compte les dépendances entre coefficients des sous-bandes. La première famille regroupe les processus à invariance sphérique pour laquelle nous montrons qu’il est pertinent d’associer une distribution caractéristique de type Weibull. Concernant la seconde famille, il s’agit des lois multivariées à copules. Après détermination de la copule caractérisant la structure de la dépendance adaptée à la texture, nous proposons une extension multivariée de la distribution Gaussienne généralisée asymétrique à l’aide de la copule Gaussienne. L’ensemble des modèles proposés est comparé quantitativement en terme de qualité d’ajustement à l’aide de tests statistiques d’adéquation dans un cadre univarié et multivarié. Enfin, une dernière partie de notre étude concerne la validation expérimentale des performances de nos modèles à travers une application de recherche d’images par le contenu textural. Pour ce faire, nous dérivons des expressions analytiques de métriques probabilistes mesurant la similarité entre les modèles introduits, ce qui constitue selon nous une troisième contribution de ce travail. Finalement, une étude comparative est menée visant à confronter les modèles probabilistes proposés à ceux de l’état de l’art. / In this thesis we study the statistical modeling of textured images using multi-scale and multi-orientation representations. Based on the results of studies in neuroscience assimilating the human perception mechanism to a selective spatial frequency scheme, we propose to characterize textures by probabilistic models of subband coefficients.Our contributions in this context consist firstly in the proposition of probabilistic models taking into account the leptokurtic nature and the asymmetry of the marginal distributions associated with a textured content. First, to model analytically the marginal statistics of subbands, we introduce the asymmetric generalized Gaussian model. Second, we propose two families of multivariate models to take into account the dependencies between subbands coefficients. The first family includes the spherically invariant processes that we characterize using Weibull distribution. The second family is this of copula based multivariate models. After determination of the copula characterizing the dependence structure adapted to the texture, we propose a multivariate extension of the asymmetric generalized Gaussian distribution using Gaussian copula. All proposed models are compared quantitatively using both univariate and multivariate statistical goodness of fit tests. Finally, the last part of our study concerns the experimental validation of the performance of proposed models through texture based image retrieval. To do this, we derive closed-form metrics measuring the similarity between probabilistic models introduced, which we believe is the third contribution of this work. A comparative study is conducted to compare the proposed probabilistic models to those of the state-of-the-art.