No description available.

A perda volumétrica cerebral ou atrofia é um importante índice de destruição tecidual e pode ser usada para apoio ao diagnóstico e para quantificar a progressão de diversas doenças com componente degenerativo, como a esclerose múltipla (EM), por exemplo. Nesta doença ocorre perda tecidual regional, com reflexo no volume cerebral total. Assim, a presença e a progressão da atrofia podem ser usadas como um indexador da progressão da doença. A quantificação do volume cerebral é um procedimento relativamente simples, porém, quando feito manualmente é extremamente trabalhoso, consome grande tempo de trabalho e está sujeito a uma variação muito grande inter e intra-observador. Portanto, para a solução destes problemas há necessidade de um processo automatizado de segmentação do volume encefálico. Porém, o algoritmo computacional a ser utilizado deve ser preciso o suficiente para detectar pequenas diferenças e robusto para permitir medidas reprodutíveis a serem utilizadas em acompanhamentos evolutivos. Neste trabalho foi desenvolvido um algoritmo computacional baseado em Imagens de Ressonância Magnética para medir atrofia cerebral em controles saudáveis e em pacientes com EM, sendo que para a classificação dos tecidos foi utilizada a teoria da entropia generalizada de Tsallis. Foram utilizadas para análise exames de ressonância magnética de 43 pacientes e 10 controles saudáveis pareados quanto ao sexo e idade para validação do algoritmo. Os valores encontrados para o índice entrópico q foram: para o líquido cerebrorraquidiano 0,2; para a substância branca 0,1 e para a substância cinzenta 1,5. Nos resultados da extração do tecido não cerebral, foi possível constatar, visualmente, uma boa segmentação, fato este que foi confirmado através dos valores de volume intracraniano total. Estes valores mostraram-se com variações insignificantes (p>=0,05) ao longo do tempo. Para a classificação dos tecidos encontramos erros de falsos negativos e de falsos positivos, respectivamente, para o líquido cerebrorraquidiano de 15% e 11%, para a substância branca 8% e 14%, e substância cinzenta de 8% e 12%. Com a utilização deste algoritmo foi possível detectar um perda anual para os pacientes de 0,98% o que está de acordo com a literatura. Desta forma, podemos concluir que a entropia de Tsallis acrescenta vantagens ao processo de segmentação de classes de tecido, o que não havia sido demonstrado anteriormente. / The loss of brain volume or atrophy is an important index of tissue destruction and it can be used to diagnosis and to quantify the progression of neurodegenerative diseases, such as multiple sclerosis. In this disease, the regional tissue loss occurs which reflects in the whole brain volume. Similarly, the presence and the progression of the atrophy can be used as an index of the disease progression. The objective of this work was to determine a statistical segmentation parameter for each single class of brain tissue using generalized Tsallis entropy. However, the computer algorithm used should be accurate and robust enough to detect small differences and allow reproducible measurements in following evaluations. In this work we tested a new method for tissue segmentation based on pixel intensity threshold. We compared the performance of this method using different q parameter range. We could find a different optimal q parameter for white matter, gray matter, and cerebrospinal fluid. The results support the conclusion that the differences in structural correlations and scale invariant similarities present in each single tissue class can be accessed by the generalized Tsallis entropy, obtaining the intensity limits for these tissue class separations. Were used for analysis of magnetic resonance imaging examinations of 43 patients and 10 healthy controls matched on the sex and age for validation of the algorithm. The values found for the entropic index q were: for the cerebrospinal fluid 0.2; for the white matter 0.1 and for gray matter 1.5. The results of the extraction of the tissue not brain can be seen, visually, a good target, which was confirmed by the values of total intracranial volume. These figures showed itself with variations insignificant (p >= 0.05) over time. For classification of the tissues find errors of false negatives and false positives, respectively, for cerebrospinal fluid of 15% and 11% for white matter 8% and 14%, and gray matter of 8% and 12%. With the use of this algorithm could detect an annual loss for the patients of 0.98% which is in line with the literature. Thus, we can conclude that the entropy of Tsallis adds advantages to the process of target classes of tissue, which had not been demonstrated previously.

The four-dimensional (4-D) cardiac MR images contain rich information about the static and dynamic properties of the heart, which were not fully utilized in clinical practice for quantitative analysis -- a difficult task for humans, which can be achieved by computer-aided image analysis and diagnosis. In this thesis, the 4-D Active Appearance Model (AAM) was used to achieve highly automated computer segmentation of the left and right ventricles (LV and RV) and the diagnosis of normal and tetralogy of Fallot (TOF) patients. The whole process was implemented in four stages: data construction, model construction, computer segmentation, and computer-aided diagnosis. The data construction stage overcame most inherent limitations of cardiac MR imaging and produced high-quality 4-D ventricular image with isotropic voxels, complete coverage and no respiratory motion artifacts. A manual tracing application was developed to trace the ventricular surfaces in a true 4-D context and produced accurate independent standard for model construction and segmentation validation. In the model construction stage, the 4-D AAMs were constructed using a custom designed automatic landmarking and texture mapping procedure with high efficiency. In the computer segmentation stage, the 4-D AAMs were applied to segment the left and right ventricles of 25 normal and 25 TOF patient scans. The segmentation achieved accurate results measured by signed surface positioning errors. On normal hearts, the average signed errors were 0.3±2.3 mm for LV and 0.1±3.4 mm for RV. On TOF hearts with large shape variability, the errors were -1.5±3.2 mm for LV and -0.9±4.3 mm for RV. Other error metrics such as relative overlapping also indicated good segmentation accuracies. In the computer-aided diagnosis stage, 100% normal/TOF classification was achieved using the novel 4-D ventricular function indices -- the shape modal indices. The longitudinal analysis performed on subjects with multiple annual scans showed that the normal subjects exhibited smaller variances of these 4-D indices than TOF patients, which demonstrated the potential of using them as disease status determinants. In addition, the quantitative 4-D indices provided more information about the dynamic properties of the heart and identified patient-specific features that were not sensed by human expert observers.

The upper airways are a major site of pediatric airway obstruction with its accompanying morbidity and mortality. The simplest approach to provide a stable airway is to perform a tracheotomy but it is a long recovery with its own complications. Other surgical procedures to reconstruct the airway require significant experience. The long-term objectives of this project are to develop a greater understanding of congenital abnormalities of the larynx and trachea. The objective of this thesis is to create a process to automatically segment and measure the pediatric trachea from MR images. Using 3DSlicer and ITK and program was created to perform the measurements. The software tool was optimized to produce similar results to that of CT image measurements from Pulmonary Workstation. The program was tested on a pediatric population and showed a significant correlation between cross-sectional area and age or height of the individual.

This dissertation presents results of a medical image analysis project leading towards development of a comprehensive set of methods and tools for computational image analysis of dynamic contrast-enhanced (DCE) breast magnetic resonance image (MRI), with the aim to aid the physician in interpreting DCE breast MRI examinations. Toward this goal, we developed image analysis methods that would be needed in a breast MRI computer aided diagnosis (CADx) system. A novel contribution of this dissertation is the performance evaluation for each of the major algorithm components developed in this dissertation project. This dissertation begins with reviewing breast imaging techniques, including routinely used modalities in current clinical practice and emerging techniques still in development. We discuss at length the principles of DCE breast MRI, a very sensitive breast imaging modality that has been increasingly used in clinical practice. Then we review the diagnostic guidelines for interpreting DCE breast MRI, and explain the needs and challenges that arise in developing computational image analysis system for breast MRI applications. In this dissertation project, both the morphological and kinetic features of the lesion are automatically extracted for diagnostic purpose. In order to extract morphological features from the segmented lesions, the lesion needs to be accurately segmented out from its surrounding tissues. We utilized a probabilistic method to obtain an optimal segmentation map based on several algorithmic segmentation outputs. In evaluating the performance of segmentation algorithms, we compared the algorithmic segmentation results against manually segmented lesions, and further assessed the segmentation impact on subsequent classification stage. In order to extract accurate kinetic information, the motion needs to be compensated across image volumes acquired sequentially. In this dissertation, we comparatively assessed the similarity metric in registering DCE breast MR images. The performance of cross correlation(CC) coefficient, and mutual information (MI) were studied in both rigid and non-rigid registration schemes. Numerical results and statistical properties were reported. The resultant image quality after registration is discussed both qualitatively and quantitatively. In this dissertation we implemented a classification system based upon quantitative morphological and kinetic features in improving the specificity of breast MRI. Morphological and kinetic features of the lesion were extracted automatically, and then the feature selection step was utilized to select the most relevant features to maximize the classifier performance. In our study, the area under the receiver operating curve (AUC) is used as the performance metric of the classifier, and our results are competitive with those of previous studies. The dissertation concludes by summarizing the contribution of this project and suggesting the future directions of quantitative and highly automated approaches to breast MR image analysis. / text

Orientador: Edmundo Medici Filho. / Banca: Luiz Cesar de Moraes / Banca: Marcos Vinícius Queiroz de Paula / Banca: Henrique Nogueira Reis / Banca: Estevão Tomomitsu Kimpara / Resumo: O objetivo neste estudo foi investigar a reproducibilidade dos resultados (confiabilidade) e a validade dos testes utilizando exames de imagem por ressonância magnética no diagnóstico da posição do disco articular e no diagnóstico das alterações ósseas do côndilo mandibular da articulação temporomandibular. Para tanto, foram avaliados 90 exames de IRM (180 ATM) realizados num equipamento de ressonância magnética de 1,0 Tesla, em próton-densidade (PD), planos coronal e sagital, usando bobina de superfície. Todas as imagens foram analisadas, individualmente, por um médico e por três cirurgiões-dentistas, especialistas em radiologia, sem conhecimento dos diagnósticos dos demais examinadores e das informações clínicas dos indivíduos (duplo-cego). Os examinadores receberam um guia para orientação e treinamento com imagens impressas a respeito dos quatro diagnósticos pré-definidos para a posição do disco (posição normal, descolamento anterior do disco com redução, deslocamento anterior do disco sem redução ou deslocamento posterior do disco articular) e quatro critérios para as alterações do côndilo mandibular (osso normal, presença de osteófito, erosão condilar ou defeito/aplainamento). A partir da metodologia aplicada, os resultados para confiabilidade interexaminadores foram: concordância variando de moderada à alta para a posição do disco e, de fraca à moderada, para as alterações ósseas do côndilo mandibular. A confiabilidade intraexaminador oscilou de alta à excelente para a posição do disco e, de fraca à moderada, para as alterações ósseas do côndilo mandibular. Para a validade da IRM, comparando os cirurgiões-dentistas com o padrãoouro (médico), obteve-se para a posição do disco articular valores acima de 75,0% para sensibilidade, acima 73,1% para especificidade, acima de 70,4% para VPP, acima de 83,0% para VPN e acima... (Resumo completo, clicar acesso eletrônico abaixo) / Abstract: The aim of this study was to investigate the reproducibility of results (reliability) and validity of magnetic resonance image examinations (MRI) on diagnosis of disk position and osseous alterations of the mandibular condyle of temporomandibular joint (TMJ). Ninety (90) MRI examinations (180 TMJ) were taken on 1,0 Tesla equipment, on proton-density (DP), coronal and sagittal planes, using surface coil. All images were analyzed by a physician e by three surgeon dentists, specialists in radiology, independently, without the knowledge of others examiners diagnosis or subjects clinical information (double-blind). The examiners received a guide for orientation, training and diagnosing according to the four previous defined possibilities for the disk (normal position, anterior disc displacement with reduction, anterior disc displacement without reduction or posterior disc displacement) and four possibilities for the alterations of mandibular condyle (normal, presence of osteophyte, erosion condyle or deformed/flattening). Based on this methodology, the results of interexaminers reliability were: concordance varying from moderate to high for disc position and, from fair to moderate for osseous alterations of mandibular condyle. For validity of MRI, comparing surgeon dentists to gold-standard (physician), for articular disc posicion values obtained were over 75,0% sensibility, over 73,1% specificity, over 70,4% VPP, over 83,0% VPN and over 78,9% accuracy. For morphology of mandibular condyle values obtained were over 85,0% sensibility, over 83,1% specificity, over 41,3% VPP, over 98,0% VPN and over 84,4% accuracy. It was possible to conclude that examiners (physician and surgeon dentists) were able to evaluate, with reliability and accuracy, the position disk and osseous alterations of mandibular condyle by MRI examination / Doutor

Orientadores: Alexandre Xavier Falcão, Guido Costa Souza de Araujo / Tese (doutorado) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-15T05:47:56Z (GMT). No. of bitstreams: 1 Cappabianco_FabioAugustoMenocci_D.pdf: 2671052 bytes, checksum: 751e1d22cedbe679c7440e3163af54d6 (MD5) Previous issue date: 2010 / Resumo: A segmentação de tecidos cerebrais se tornou fundamental para a neurologia no tratamento e diagnose de pacientes. Muitas contribuições tem aprimorado as metodologias de segmentaçao mas, ainda ha muito a ser feito. De fato, ruídos provenientes da aquisiçao da imagem, a enorme quantidade de dados, variações anatômicas decorrentes de doenças, diferença de idade e sexo, alem de incisoes cirúrgicas sao alguns dos desafios enfrentados. Alem disso, e muito difícil gerar padroes ouro dos tecidos cerebrais contidos nas imagens de ressonancia magnetica e tambem escolher metricas apropriadas para avaliar uma determinada metodologia de segmentaçao de tecidos. Neste contexto, apresentamos uma revisao das operações de pre-processamento mais populares da literatura, bem como das diversas metodologias propostas para a segmentaçao de tecidos. Tambem apresentamos uma metodologia inovadora para a se gmentaçao dos tecidos de substancia branca, substancia cinzenta e líquido cerebro espinhal baseada no algoritmo de agrupamento de dados por floresta de caminhos otimos, com as seguintes características desejaveis: baixo tempo de processamento, robustez, alta acuracia, ajuste intuitivo de parametros, adaptabilidade a imagens de diferentes protocolos e a variaçoes anatomicas, e efetividade ao corrigir o efeito de heterogeneidade de campo magnetico. Avaliamos a metodologia quantitativamente e qualitativamente, comparando-a com dois metodos populares da literatura sobre cinco bases de dados de modalidades e anatomias diferentes. A avaliaçao quantitativa leva em conta o intervalo de operaçao das metodologias, e a avaliaçao qualitativa leva em conta o ponto de vista de especialistas com respeito a acuracia das segmentaçoes. Assim, acreditamos que a metodologia de segmentaçao de tecidos cerebrais agrega importantes contribuições ao estado da arte. Ja a metodologia de avaliaçao proposta evidencia a importancia da escolha de metricas apropriadas na analise de imagens medicas / Abstract: Segmentation of brain tissues from MR-images has become crucial to advance research, diagnosis and treatment in Neurology. Despite the large number of contributions, brain tissue segmentation is still a challenge, due to problems in image acquisition, large data sets, and anatomical variations caused by surgery, pathologies and differences in sex and age. Another difficulty is to create reliable ground truths for evaluation, which also requires suitable metrics. In this work, we review the most important pre-processing operations, as well as the most popular brain tissues segmentation methods. We also propose a new approach based on optimum-path forest clustering, which improves previous works on various aspects: speed, robustness, accuracy, intuitive tuning of parameters and adaptability to different imaging modalities and anatomies. The effectiveness of the approach can be noticed in both inhomogeneity correction and in white matter, gray matter and cerebral-spinal fluid segmentation. The method is evaluated quantitatively and qualitatively by taking into account two other popular methods, five datasets from diferent modalities, an operational range of parameters for each method and scores from distinct specialists. The results reveal a signiicant contribution to the state-of-the-art and emphasize the importance of suitable evaluation metrics in medical image analysis / Doutorado / Processamento e Analise de Imagens / Doutor em Ciência da Computação

A perda volumétrica cerebral ou atrofia é um importante índice de destruição tecidual e pode ser usada para apoio ao diagnóstico e para quantificar a progressão de diversas doenças com componente degenerativo, como a esclerose múltipla (EM), por exemplo. Nesta doença ocorre perda tecidual regional, com reflexo no volume cerebral total. Assim, a presença e a progressão da atrofia podem ser usadas como um indexador da progressão da doença. A quantificação do volume cerebral é um procedimento relativamente simples, porém, quando feito manualmente é extremamente trabalhoso, consome grande tempo de trabalho e está sujeito a uma variação muito grande inter e intra-observador. Portanto, para a solução destes problemas há necessidade de um processo automatizado de segmentação do volume encefálico. Porém, o algoritmo computacional a ser utilizado deve ser preciso o suficiente para detectar pequenas diferenças e robusto para permitir medidas reprodutíveis a serem utilizadas em acompanhamentos evolutivos. Neste trabalho foi desenvolvido um algoritmo computacional baseado em Imagens de Ressonância Magnética para medir atrofia cerebral em controles saudáveis e em pacientes com EM, sendo que para a classificação dos tecidos foi utilizada a teoria da entropia generalizada de Tsallis. Foram utilizadas para análise exames de ressonância magnética de 43 pacientes e 10 controles saudáveis pareados quanto ao sexo e idade para validação do algoritmo. Os valores encontrados para o índice entrópico q foram: para o líquido cerebrorraquidiano 0,2; para a substância branca 0,1 e para a substância cinzenta 1,5. Nos resultados da extração do tecido não cerebral, foi possível constatar, visualmente, uma boa segmentação, fato este que foi confirmado através dos valores de volume intracraniano total. Estes valores mostraram-se com variações insignificantes (p>=0,05) ao longo do tempo. Para a classificação dos tecidos encontramos erros de falsos negativos e de falsos positivos, respectivamente, para o líquido cerebrorraquidiano de 15% e 11%, para a substância branca 8% e 14%, e substância cinzenta de 8% e 12%. Com a utilização deste algoritmo foi possível detectar um perda anual para os pacientes de 0,98% o que está de acordo com a literatura. Desta forma, podemos concluir que a entropia de Tsallis acrescenta vantagens ao processo de segmentação de classes de tecido, o que não havia sido demonstrado anteriormente. / The loss of brain volume or atrophy is an important index of tissue destruction and it can be used to diagnosis and to quantify the progression of neurodegenerative diseases, such as multiple sclerosis. In this disease, the regional tissue loss occurs which reflects in the whole brain volume. Similarly, the presence and the progression of the atrophy can be used as an index of the disease progression. The objective of this work was to determine a statistical segmentation parameter for each single class of brain tissue using generalized Tsallis entropy. However, the computer algorithm used should be accurate and robust enough to detect small differences and allow reproducible measurements in following evaluations. In this work we tested a new method for tissue segmentation based on pixel intensity threshold. We compared the performance of this method using different q parameter range. We could find a different optimal q parameter for white matter, gray matter, and cerebrospinal fluid. The results support the conclusion that the differences in structural correlations and scale invariant similarities present in each single tissue class can be accessed by the generalized Tsallis entropy, obtaining the intensity limits for these tissue class separations. Were used for analysis of magnetic resonance imaging examinations of 43 patients and 10 healthy controls matched on the sex and age for validation of the algorithm. The values found for the entropic index q were: for the cerebrospinal fluid 0.2; for the white matter 0.1 and for gray matter 1.5. The results of the extraction of the tissue not brain can be seen, visually, a good target, which was confirmed by the values of total intracranial volume. These figures showed itself with variations insignificant (p >= 0.05) over time. For classification of the tissues find errors of false negatives and false positives, respectively, for cerebrospinal fluid of 15% and 11% for white matter 8% and 14%, and gray matter of 8% and 12%. With the use of this algorithm could detect an annual loss for the patients of 0.98% which is in line with the literature. Thus, we can conclude that the entropy of Tsallis adds advantages to the process of target classes of tissue, which had not been demonstrated previously.

Orientadores: Roberto de Alencar Lotufo, Letícia Rittner / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Elétrica e de Computação / Made available in DSpace on 2018-08-22T11:40:53Z (GMT). No. of bitstreams: 1 Bento_MarianaPinheiro_M.pdf: 1641774 bytes, checksum: d858472eabb82055f830588e8df12b77 (MD5) Previous issue date: 2013 / Resumo: Essa dissertação de mestrado propõe um método de análise de lesões na substância branca do cérebro afim de distinguir as regiões de interesse entre substância branca normal ou não-normal, tarefa denominada identificação de lesões, assim como distinguir diferentes tipos de lesões de acordo com sua etiologia: desmielinizante ou isquêmica, tarefa denominada classificação de lesões. O método combina a análise de textura com o uso de classificadores, como o Máquinas de vetores suporte (SVM), K-vizinhos mais próximos (kNN), Floresta de Caminhos Ótimos (OPF) e Análise Discriminante Linear (LDA). Experimentos realizados em dados reais de ressonância magnética do cérebro mostraram que o método proposto _e adequado para identificação e classificação de lesões no cérebro / Abstract: This dissertation proposes a method for brain white matter lesions analysis in order to distinguish regions of interest between normal and non-normal brain white matter, called lesion identification task, and also to distinguish different types of lesions based on their etiology: demyelinating or ischemic, called lesion classification task. The method combines texture analysis with the use of classifiers such as Support Vector Machine (SVM), k-Nearst Neighboor (kNN), Optimum Path Forest (OPF) and Linear Discriminant Analysis (LDA). Experiments using real brain MRI data have shown that the proposed method is suitable to identify and classify the brain lesions / Mestrado / Engenharia de Computação / Mestra em Engenharia Elétrica

>Magister Scientiae - MSc / Odontogenic myxoma (OM) is one of the rare odontogenic tumours that affect the maxilo-facial regions. Skeletal myxomas are more common than soft tissue types in the facial regions. Odontogenic myxomas (OM) are non metastasizing tumours and therefore are considered benign. These lesions are known for their distinctive infiltrative nature which makes complete surgical removal a challenging task.Since the tumour occurs inside the bone and can reach a considerable size with little or no clinical manifestation, the radiologic examination remains the main method to determine the size and the extension of the tumour preoperatively.Aim of the study To assess the different imaging techniques which are currently in use for the diagnosis of the odontogenic myxomas.Materials and methods The images were retrieved from the library of the Department of Diagnostics and Radiology at the Tygerberg Oral Health Centre.Initially each of the imaging modalities was assessed independently to describe the imaging features of odontogenic myxoma on conventional radiograph,Computed Tomography (CT) and Magnetic Resonance Image (MRI). Secondly the imaging features of the three techniques were correlated and contrasted to determine the most valuable imaging modality in the diagnosis of the tumour.Results In this study we found that MRI was superior to other modalities in the ability to show and determine the true extension of the tumours. Therefore, MRI distinguished the tumour tissue from the surrounding structures and soft tissues.Myxomas were found to display characteristic patterns of growth on MRI. These patterns include lobulations and/or budding, nodulation and crevices formation.Moreover T2 weighted images deduced the contents of the tumour by emitting different signal intensities from the various components of the tumours.Additionally, characteristic pattern of contrast uptake differentiated the myxomatous, collagenous parts and presumed the nature of the trabeculae whether it is bony or fibrous.CT also showed the tumour and determined the subtle extension of the tumour into the adjacent structures and bone. Expansion and status of the cortical margin were reliably detected on CT. It also determined the pattern of growth in all tumours whether it is lobulation and/or budding, crevices formation or combination of them. In the present study this feature seemed to be a characteristic finding for all the tumours on CT. Moreover CT was able to compare densities of the tumours to surrounding muscles.Conventional radiography (CR) showed great limitations with regard to diagnostic abilities. Although it displayed the existence of the abnormality in all cases,conventional radiograph failed to detect margins and extension in most of the lesions. Therefore conventional radiograph is not reliable for presurgical assessment of the tumour or in differentiation the tumour from other benign and some malignant tumour. Conclusion In spite of the many limitations and shortcomings, conventional radiography remains the preliminary step in the diagnosis process. However digital imaging techniques provide images of great diagnostic value which is especially helpful in the diagnosis of odontogenic myxoma.