Thesis (Ph.D.) in Spatial Information Science and Engineering--University of Maine, 2002. / Includes vita. Includes bibliographical references (leaves 151-161 ).

Thesis (M.S.)--Rochester Institute of Technology, 2005. / Typescript. Includes bibliographical references (p. 91-93).

The availability of digital models of real 3D objects is becoming more and more important in many different applications (e-commerce, virtual visits etc). Very often the objects to be represented cannot be modeled by means of the classical 3D modeling tools because of the geometrical complexity or color texture. In these cases, devices for the automatic acquisition of the shape and the color of the objects (3D scanners or range scanners) have to be used. The scanner presented in this work, a Shape from silhouette scanner, is very cheap (it is based on the use of a simple digital camera and a turntable) and easy to use. While maintaining the camera on a tripod and the object on the turntable, the user acquires images with different rotation angles of the table. The fusion of all the acquired views enables the production of a digital 3D representation of the object. Existing Shape from silhouette scanners operate in an indirect way. They subdivide the object definition space in a regular 3D grid and verify that a voxel belongs to the object by verifying that its 2D projection falls inside the silhouette of the corresponding image. Our scanner adopts a direct method: by using a new 3D representation scheme and algorithm, the Marching Intersections data structure, we can directly intersect all the 3D volumes obtained by the silhouettes extracted from the images.

No description available.

X-ray tomography is an imaging technique to inspect objects' internal structures with externally measured data by X-ray radiation non-destructively. However, there are concerns about X-ray radiation damage and tomographic acquisition speed in real-life applications. Strategies with insufficient measurements, such as measurements with insufficient dosage (low-dose) and measurements with insufficient projection angles (sparse-view), have been proposed to relieve these problems but are generally compromising imaging quality. Such a dilemma inspires the development of advanced tomographic imaging techniques, in particular, deep learning algorithms to improve reconstruction results with insufficient measurements. The overall aim of this thesis is to design efficient and robust data-driven algorithms with the help of prior knowledge from physics insights and measurement models. We first introduce a hierarchical synthesis CNN (HSCNN), which is a knowledge-incorporated data-driven tomographic reconstruction method for sparse-view and low-dose tomography with a split-and-synthesis approach. This proposed learning-based method informs the forward model biases based on data-driven learning but with reduced training data. The learning scheme is robust against sampling bias and aberrations introduced in the forward modeling. High-fidelity X-ray tomographic imaging reconstruction results are obtained with a very sparse number of projection angles for both numerical simulated and physics experiments. Comparison with both conventional non-learning-based algorithms and advanced learning-based approaches shows improved accuracy and reduced training data size. As a result of the split-and-synthesis strategy, the trained network could be transferable to new cases. We then present a deep learning-based enhancement method, HDrec (hybrid-dose reconstruction algorithm), for low-dose tomography reconstruction via a hybrid-dose acquisition strategy composed of textit{extremely sparse-view normal-dose measurements} and textit{full-view low-dose measurements}. The training is applied for each individual sample without the need of transferring the trained models for other samples. Evaluation of two experimental datasets under different hybrid-dose acquisition conditions shows significantly improved structural details and reduced noise levels compared to results with traditional analytical and regularization-based iterative reconstruction methods from uniform acquisitions under the same amount of total dosage. Our proposed approach is also more efficient in terms of single projection denoising and single image reconstruction. In addition, we provide a strategy to distribute dosage smartly with improved reconstruction quality. When the total dosage is limited, the strategy of combining a very few numbers of normal-dose projections and with not-too-low full-view low-dose measurements greatly outperforms the uniform distribution of the dosage throughout all projections. We finally apply the proposed data-driven X-ray tomographic imaging reconstruction techniques, HSCNN and HDrec, to the dynamic damage/defect characterization applications for the cellular materials and binder jetting additive manufacturing. These proposed algorithms improve data acquisition speeds to record internal dynamic structure changes. A quantitative comprehensive framework is proposed to study the dynamic internal behaviors of cellular structure, which contains four modules: (i) In-situ fast synchrotron X-ray tomography, which enables collection of 3D microstructure in a macroscopic volume; (ii) Automated 3D damage features detection to recognize damage behaviors in different scales; (iii) Quantitative 3D structural analysis of the cellular microstructure, by which key morphological descriptors of the structure are extracted and quantified; (iv) Automated multi-scale damage structure analysis, which provides a quantitative understanding of damage behaviors. In terms of binder jetting materials, we show a pathway toward the efficient acquisition of holistic defect information and robust morphological representation through the integration of (i) fast tomography algorithms, (ii) 3D morphological analysis, and (iii) machine learning-based big data analysis. The applications to two different 4D material characterization demonstrate the advantages of these proposed tomographic imaging techniques and provide quantitative insights into the global evolution of damage/defect beyond qualitative human observation. / Doctor of Philosophy / X-ray tomography is a nondestructive imaging technique to visualize interior structures of non-transparent objects, which has been widely applied to resolve implicit 3D structures, such as human organs and tissues for clinical diagnosis, contents of baggage for security check, internal defect evolution during additive manufacturing, observing fracturing accompanying mechanical tests, and etc. Multiple planar measurements with sufficient X-ray exposure time among different angles are desirable to reconstruct the unique high-quality 3D internal distribution. However, there are practical concerns about X-ray radiation damage to biology samples or long-time acquisition for dynamic experiments in real-life applications. Insufficient measurements by reducing the number of total measurements or the time for each measurement, are proposed to solve this problem but doing so usually leads to the sacrifice of the reconstruction quality. Computational algorithms are developed for tomographic imaging under these insufficient measurement conditions to obtain reconstructions with improved quality. Deep learning has been successfully applied to numerous areas, such as in recognizing speech, translating languages, detecting objects, and etc. It has also been applied to X-ray tomographic imaging to improve the reconstruction results by learning the features through thousands to millions of corrupted and ideal reconstruction pairs. The aim of this thesis to design efficient deep learning-based algorithms with the help of physical and measurement priors to reduce the number of training datasets. We propose two different deep learning-based tomographic imaging techniques to improve reconstruction results with reduced training data under different insufficient measurement conditions. One way is to incorporate prior knowledge of the physics models to reduce the required amount of ground truth data, from thousands to hundreds. The training data requirement is further simplified with another hybrid measurement strategy, which could be implemented on each individual sample with only several high-quality measurements. In the end, we apply these two proposed algorithms to different dynamic damage/defect behavior characterization applications. Our methods achieve improved reconstruction results with greatly enhanced experimental speeds, which become suitable for dynamic 3D recording. Final results demonstrate the advantages of the proposed tomographic imaging techniques and provide quantitative insights into the global dynamic evolution inside the material. This quantitative analysis also provides a much more comprehensive understanding than qualitative human observation.

O leite condensado é um produto amplamente estudado, sendo que os problemas de cristalização ao longo do processo constituem um dos aspectos de interesse quando se considera a produção em escala industrial. No entanto, não foram encontrados estudos que padronizassem técnicas de medida de tamanho de cristais e determinação da cristalinidade total em leite condensado. Este trabalho visa adaptar/desenvolver uma técnica especifica para análise de tamanho de cristais de lactose em leite condensado utilizando de microscopia juntamente com processamento e análise de imagem (software ImageJ). Além disso, acredita-se que o grau de cristalinidade possa se tornar um parâmetro de controle de qualidade em leites condensados, de modo que se propõe o estudo da viabilidade do uso de calorimetria exploratória diferencial para a determinação deste parâmetro. A técnica de processamento e análise de imagem mostrou-se confiável e permitiu realizar comparativo eficiente entre três marcas comerciais de leite condensado. Foi possível, mediante análise estatística, otimizar a metologia existente de preparação de lâminas visando reduzir o tempo e esforço da aplicação da técnica de acompanhamento de tamanho de cristais em ambiente industrial. Para o estudo da viabilidade do uso de analises térmicas para a determinação do grau de cristalinidade em leite condensado foram realizados estudos em térmicos simultâneos (DSC-TGA) e estudos de calorimetria exploratória diferencial em DSC e TMDSC em lactose p.a., sacarose p.a., misturas dos dois açúcares e em leite condensado. Na comparação das técnicas, observou-se que as três apresentam mesmo nível de precisão, porém exatidão distintas. A técnica de DSC foi a que permitiu obter maior definição dos picos identificados ao longo do termograma. Por outro lado, na técnica de MDSC, utilizando porta-amostras com furo, foi possível obter boa repetibilidade também com relação aos processos reversíveis e irreversíveis. A análise quantitativa de cristalinidade a partir de dados de calorimetria para misturas de sacarose e lactose é dificultada pela sobreposição dos picos dos diferentes processos térmicos sofridos pelos dois açúcares e pelo fato que foram encontrados indicativos de efeito sinergético na resposta térmica dos dois carboidratos quando em mistura. Assim como para as misturas de açúcares estudadas, não foi possível determinar o grau de cristalinidade em amostras de leite condensado. / Condensed milk is a widely studied product, given that the crystallization problems throughout the production process constitute one of the aspects of interest as far as the industrial scale production is concerned. However, studies that might enable standardized crystal size measurement techniques and crystallinity determination in condensed milk have not been found yet. This work aims at adapting/developing a specific technique for the analysis of lactose crystals size in condensed milk by using microscopy along with image analysis and processing (ImageJ software). Besides, it is believed that degree of crystallinity may become a quality control parameter in condensed milks, in such a way that it is proposed a viability study of the use of differential exploratory calorimetry for its determination. Processing technique and image analysis have demonstrated to be reliable and allowed to carry out efficient comparison between the three commercially available brands of condensed milk. It was possible, by means of statistical analysis, to optimize the existing thin plate preparation methodology with the aim of reducing time and strain of crystal size monitoring in industrial environment. In view of studying thermal analyses aiming at determining degree of crystallinity in condensed milk, studies in simultaneous thermal instruments (DSC-TGA) along with differential exploratory calorimetry in DSC and TMDSC were carried out in analytical grade sucrose and lactose, mixtures of both sugars and condensed milk. When comparing the techniques, one can observe that all three presented the same level of precision, but different accuracies. DSC technique was the one that allowed higher definition of identified peaks along the thermogram. On the other hand, in MDSC technique, using pierced sample holder, it was possible to obtain good repeatability even in regard to reversible and irreversible processes. Cristallinity quantitative analysis from calorimetry data for sucrose and lactose mixtures is hindered by the superposition of peaks from different thermal processes undergone by both sugars and by the fact that indicatives of synergistic effect were found in the thermal response of the above mentioned carbohydrates when mixed together. As it had occurred for the sugar mixtures studied, it was not possible to determine the degree of crystallinity in condensed milk samples.

O leite condensado é um produto amplamente estudado, sendo que os problemas de cristalização ao longo do processo constituem um dos aspectos de interesse quando se considera a produção em escala industrial. No entanto, não foram encontrados estudos que padronizassem técnicas de medida de tamanho de cristais e determinação da cristalinidade total em leite condensado. Este trabalho visa adaptar/desenvolver uma técnica especifica para análise de tamanho de cristais de lactose em leite condensado utilizando de microscopia juntamente com processamento e análise de imagem (software ImageJ). Além disso, acredita-se que o grau de cristalinidade possa se tornar um parâmetro de controle de qualidade em leites condensados, de modo que se propõe o estudo da viabilidade do uso de calorimetria exploratória diferencial para a determinação deste parâmetro. A técnica de processamento e análise de imagem mostrou-se confiável e permitiu realizar comparativo eficiente entre três marcas comerciais de leite condensado. Foi possível, mediante análise estatística, otimizar a metologia existente de preparação de lâminas visando reduzir o tempo e esforço da aplicação da técnica de acompanhamento de tamanho de cristais em ambiente industrial. Para o estudo da viabilidade do uso de analises térmicas para a determinação do grau de cristalinidade em leite condensado foram realizados estudos em térmicos simultâneos (DSC-TGA) e estudos de calorimetria exploratória diferencial em DSC e TMDSC em lactose p.a., sacarose p.a., misturas dos dois açúcares e em leite condensado. Na comparação das técnicas, observou-se que as três apresentam mesmo nível de precisão, porém exatidão distintas. A técnica de DSC foi a que permitiu obter maior definição dos picos identificados ao longo do termograma. Por outro lado, na técnica de MDSC, utilizando porta-amostras com furo, foi possível obter boa repetibilidade também com relação aos processos reversíveis e irreversíveis. A análise quantitativa de cristalinidade a partir de dados de calorimetria para misturas de sacarose e lactose é dificultada pela sobreposição dos picos dos diferentes processos térmicos sofridos pelos dois açúcares e pelo fato que foram encontrados indicativos de efeito sinergético na resposta térmica dos dois carboidratos quando em mistura. Assim como para as misturas de açúcares estudadas, não foi possível determinar o grau de cristalinidade em amostras de leite condensado. / Condensed milk is a widely studied product, given that the crystallization problems throughout the production process constitute one of the aspects of interest as far as the industrial scale production is concerned. However, studies that might enable standardized crystal size measurement techniques and crystallinity determination in condensed milk have not been found yet. This work aims at adapting/developing a specific technique for the analysis of lactose crystals size in condensed milk by using microscopy along with image analysis and processing (ImageJ software). Besides, it is believed that degree of crystallinity may become a quality control parameter in condensed milks, in such a way that it is proposed a viability study of the use of differential exploratory calorimetry for its determination. Processing technique and image analysis have demonstrated to be reliable and allowed to carry out efficient comparison between the three commercially available brands of condensed milk. It was possible, by means of statistical analysis, to optimize the existing thin plate preparation methodology with the aim of reducing time and strain of crystal size monitoring in industrial environment. In view of studying thermal analyses aiming at determining degree of crystallinity in condensed milk, studies in simultaneous thermal instruments (DSC-TGA) along with differential exploratory calorimetry in DSC and TMDSC were carried out in analytical grade sucrose and lactose, mixtures of both sugars and condensed milk. When comparing the techniques, one can observe that all three presented the same level of precision, but different accuracies. DSC technique was the one that allowed higher definition of identified peaks along the thermogram. On the other hand, in MDSC technique, using pierced sample holder, it was possible to obtain good repeatability even in regard to reversible and irreversible processes. Cristallinity quantitative analysis from calorimetry data for sucrose and lactose mixtures is hindered by the superposition of peaks from different thermal processes undergone by both sugars and by the fact that indicatives of synergistic effect were found in the thermal response of the above mentioned carbohydrates when mixed together. As it had occurred for the sugar mixtures studied, it was not possible to determine the degree of crystallinity in condensed milk samples.

O leite condensado é um produto amplamente estudado, sendo que os problemas de cristalização ao longo do processo constituem um dos aspectos de interesse quando se considera a produção em escala industrial. No entanto, não foram encontrados estudos que padronizassem técnicas de medida de tamanho de cristais e determinação da cristalinidade total em leite condensado. Este trabalho visa adaptar/desenvolver uma técnica especifica para análise de tamanho de cristais de lactose em leite condensado utilizando de microscopia juntamente com processamento e análise de imagem (software ImageJ). Além disso, acredita-se que o grau de cristalinidade possa se tornar um parâmetro de controle de qualidade em leites condensados, de modo que se propõe o estudo da viabilidade do uso de calorimetria exploratória diferencial para a determinação deste parâmetro. A técnica de processamento e análise de imagem mostrou-se confiável e permitiu realizar comparativo eficiente entre três marcas comerciais de leite condensado. Foi possível, mediante análise estatística, otimizar a metologia existente de preparação de lâminas visando reduzir o tempo e esforço da aplicação da técnica de acompanhamento de tamanho de cristais em ambiente industrial. Para o estudo da viabilidade do uso de analises térmicas para a determinação do grau de cristalinidade em leite condensado foram realizados estudos em térmicos simultâneos (DSC-TGA) e estudos de calorimetria exploratória diferencial em DSC e TMDSC em lactose p.a., sacarose p.a., misturas dos dois açúcares e em leite condensado. Na comparação das técnicas, observou-se que as três apresentam mesmo nível de precisão, porém exatidão distintas. A técnica de DSC foi a que permitiu obter maior definição dos picos identificados ao longo do termograma. Por outro lado, na técnica de MDSC, utilizando porta-amostras com furo, foi possível obter boa repetibilidade também com relação aos processos reversíveis e irreversíveis. A análise quantitativa de cristalinidade a partir de dados de calorimetria para misturas de sacarose e lactose é dificultada pela sobreposição dos picos dos diferentes processos térmicos sofridos pelos dois açúcares e pelo fato que foram encontrados indicativos de efeito sinergético na resposta térmica dos dois carboidratos quando em mistura. Assim como para as misturas de açúcares estudadas, não foi possível determinar o grau de cristalinidade em amostras de leite condensado. / Condensed milk is a widely studied product, given that the crystallization problems throughout the production process constitute one of the aspects of interest as far as the industrial scale production is concerned. However, studies that might enable standardized crystal size measurement techniques and crystallinity determination in condensed milk have not been found yet. This work aims at adapting/developing a specific technique for the analysis of lactose crystals size in condensed milk by using microscopy along with image analysis and processing (ImageJ software). Besides, it is believed that degree of crystallinity may become a quality control parameter in condensed milks, in such a way that it is proposed a viability study of the use of differential exploratory calorimetry for its determination. Processing technique and image analysis have demonstrated to be reliable and allowed to carry out efficient comparison between the three commercially available brands of condensed milk. It was possible, by means of statistical analysis, to optimize the existing thin plate preparation methodology with the aim of reducing time and strain of crystal size monitoring in industrial environment. In view of studying thermal analyses aiming at determining degree of crystallinity in condensed milk, studies in simultaneous thermal instruments (DSC-TGA) along with differential exploratory calorimetry in DSC and TMDSC were carried out in analytical grade sucrose and lactose, mixtures of both sugars and condensed milk. When comparing the techniques, one can observe that all three presented the same level of precision, but different accuracies. DSC technique was the one that allowed higher definition of identified peaks along the thermogram. On the other hand, in MDSC technique, using pierced sample holder, it was possible to obtain good repeatability even in regard to reversible and irreversible processes. Cristallinity quantitative analysis from calorimetry data for sucrose and lactose mixtures is hindered by the superposition of peaks from different thermal processes undergone by both sugars and by the fact that indicatives of synergistic effect were found in the thermal response of the above mentioned carbohydrates when mixed together. As it had occurred for the sugar mixtures studied, it was not possible to determine the degree of crystallinity in condensed milk samples.

Diese Arbeit befasst sich mit der automatisierten Analyse der Ausrichtungen von Neuronenfasern in Mikroskopiebildern des menschlichen Gehirns. Für eine solche Analyse wurden vom Paul-Flechsig-Institut für Hirnforschung Leipzig (PFI) Fluoreszenzbilddaten zur Verfügung gestellt. Um für diese Daten Faserausrichtungen zu ermitteln, werden drei Schritte durchgeführt: Neuronenfasern werden hervorgehoben, bzw. freigestellt, es werden Orientierungen zu diesen zugeordnet und die hierdurch ermittelten Ergebnisse werden visualisiert. Es werden für jeden dieser Schritte mehrere Verfahren der klassischen Bildverarbeitung vorgestellt und die Auswirkung verschiedener Parameter auf deren Ergebnisse untersucht. Betrachtet werden Verfahren zur Kontrasterhöhung, Gauß-Filter, auf Hessematrizen basierende Filter, Berechnung von Phasenübereinstimmung und eine Wavelet-Transformation. Alle während dieser Arbeit vorgenommenen Implementierungen stehen als Python-Skripte auf GitHub (https://github.com/saphyll/fiber-orientation) zur Verfügung.:Einleitung 1. Grundlagen 1.1 Datengrundlage 1.2 Architektur 1.3 Grundlagen der Bildverarbeitung 1.3.1 Histogramme 1.3.2 Konvolution 1.3.3 Gaußkernel 1.3.4 Hessematrix und Eigenvektoren 1.4.5 Fourier-Transformation 2. Faseranalyse in 2D 2.1 Hervorhebung von Fasern 2.1.1 Histogram Equalization 2.1.2 Gauß-Filter 2.1.3 Hessematrix-basierte Filter 2.1.4 Phase Congruency 2.1.5 Isotropic Undecimated Wavelet Transform 2.2 Analyse und Visualisierung von Faserrichtungen 2.2.1 Richtungshistogramme 2.2.2 Kacheln 2.2.3 Direkte Ergebnisbilder 3. Zusammenfassung und Ausblick / This thesis covers the automated analysis of fiber orientations in microscopic images of the human brain in regard to data provided by the Paul Flechsig Institute of Brain Research Leipzig (PFI). For the retrieval of information about fiber orientations, three steps are used: An enhancement of fiber visibility and definition, an assignment of orientations to those fibers and a visualisation of fibers and their orientations. Multiple methods from classical image processing are presented for each of these steps and are evaluated according to the available data. These methods include contrast enhancement, gaussian filters, hessian filters, calculation of phase congruency and a wavelet transformation. All implementations resulting from this thesis are available as Python scripts on GitHub (https://github.com/saphyll/fiber-orientation).:Einleitung 1. Grundlagen 1.1 Datengrundlage 1.2 Architektur 1.3 Grundlagen der Bildverarbeitung 1.3.1 Histogramme 1.3.2 Konvolution 1.3.3 Gaußkernel 1.3.4 Hessematrix und Eigenvektoren 1.4.5 Fourier-Transformation 2. Faseranalyse in 2D 2.1 Hervorhebung von Fasern 2.1.1 Histogram Equalization 2.1.2 Gauß-Filter 2.1.3 Hessematrix-basierte Filter 2.1.4 Phase Congruency 2.1.5 Isotropic Undecimated Wavelet Transform 2.2 Analyse und Visualisierung von Faserrichtungen 2.2.1 Richtungshistogramme 2.2.2 Kacheln 2.2.3 Direkte Ergebnisbilder 3. Zusammenfassung und Ausblick

Η διαχείριση της πληροφορίας που προέρχεται από εικόνες ιστοπαθολογίας μικροσκοπίου (βιοψίες) αποτελεί διεργασία υψηλής πολυπλοκότητας που αξιοποιείται για την εξαγωγή διαγνωστικών και προγνωστικών συμπερασμάτων από τον ιστοπαθολόγο. Η πολυπλοκότητα αυτή πηγάζει από τον τεράστιο όγκο βιολογικών οντοτήτων που περιέχονται στο δείγμα βιοψίας αλλά και στις μεταξύ τους πολυσύνθετες αλληλεπιδράσεις. Οι πιο σύγχρονες μέθοδοι τεχνητής νοημοσύνης προτείνουν εναλλακτικές προσεγγίσεις για την επίλυση των προβλημάτων υψηλής πολυπλοκότητας αυτού του τύπου. Ανάμεσα όμως στην είσοδο (δεδομένα) και έξοδο (αποτέλεσμα) των ‘έξυπνων’ υπολογιστικών συστημάτων, κρύβεται η μεθοδολογία και στρατηγική επεξεργασίας και ανάλυσης της διαθέσιμης πληροφορίας. Κατά το στάδιο αυτό οι παράμετροι ελέγχου διαχωρίζονται και συσχετίζονται μεταξύ τους ΄τυφλά’ (π.χ. με νευρωνικά δίκτυα, ασαφή λογική) σύμφωνα με συγκεκριμένα μαθηματικά κριτήρια (π.χ. πιθανοκρατικά, ελάχιστων τετραγώνων κ.α.) χωρίς όμως να λαμβάνουν υπόψη την ‘ευρετική’ (heuristic) του ειδικού με αποτέλεσμα να παρουσιάζουν πεπερασμένη ακρίβεια, μεγάλο χρόνο υλοποίησης, αδυναμία γενίκευσης. Έτσι, η απόδοση των συστημάτων αυτών εξαρτάται από το μέγεθος και ποιότητα (θορυβώδη, ελλιπή δεδομένα κ.α.) των δεδομένων, το πλήθος των συνδυασμών των ποσοτικών χαρακτηριστικών που περιγράφουν τα δεδομένα, τον καθορισμό των πλούσιων σε πληροφορία χαρακτηριστικών, την σημαντικότητα των επιμέρους χαρακτηριστικών και των μαθηματικών κριτηρίων ταξινόμησης. Για παράδειγμα πολλά χαρακτηριστικά περιγράφουν καλύτερα την υπό μελέτη διεργασία αλλά η εξαγωγή των πλούσιων σε προγνωστική πληροφορία χαρακτηριστικών απαιτεί πολλούς συνδυασμούς και μεγάλη υπολογιστική ισχύ. Επίσης πολλά χαρακτηριστικά σημαίνει εξειδίκευση του συστήματος στα δεδομένα εκπαίδευσης και αδυναμία εφαρμογής σε άγνωστα δεδομένα. Η παρούσα διατριβή διαπραγματεύεται τον σχεδιασμό, ανάπτυξη και υλοποίηση νέων μεθόδων επεξεργασίας και ανάλυσης ιατρικών εικόνων, επικεντρώνοντας ειδικότερα στην εφαρμογή των μεθόδων αυτών σε υπολογιστικό σύστημα μικροσκοπίας για την διάγνωση όγκων εγκεφάλου τύπου αστροκυττώματος. / Even though histological diagnosis is fundamentally important for patient's management, the potential of diagnostic errors in astrocytomas grading still remains substantially high, ranging from 25% to 40% in routine conditions. Diagnostic errors originate mainly from the lack of experience of experts; rare cancers low prevalence and their biological complexity hinder the establishment of concrete criteria able to predict tumours' behaviour, and, thus, to administrate proper treatments. The latter might explain the fact that a/ although promising treatments have been proposed, death rates have not been yet reduced and b/ the cost of rare cancers management still remains one of the highest healthcare economic burdens in Europe and worldwide. The aim of this thesis was to design, develop and implement new computerized methods to improve manual and computer-assisted malignancy grading of astrocytomas. Scientific objectives comprised: a/ develop a reliable and accurate segmentation algorithm for nuclei detection in routinely stained with H&E histopathological images of astrocytomas, b/ investigate and quantify modifications in nuclei morphology and texture with respect to the degree of tumour abnormality of astrocytic tumours, c/ evaluate whether quantitative analysis of cell nuclei by computer-assisted image analysis could assist the routinely performed malignancy grading of astrocytomas using conventional means, d/ investigate potential modifications in chromatin distribution, which might be used to improve the diagnostic evaluation of cases that histopathologists have difficulty in reaching definite diagnosis (i.e. 'intermediate' grade tumours), e/ support more reliable separation of high grade tumours into clinically meaningful subgroups of patients with grade III and grade IV tumours. For realizing the above objectives, a computer-assisted microscopy system was designed, built and implemented. The system was developed using novel methodologies that integrated state-of-art pattern recognition algorithms for microscopy image segmentation and classification. In addition, new classification techniques have been introduced. The usefulness of the proposed methods has been validated experimentally.