O uso de ferramentas computacionais para avaliação postural tem sido de grande valia na detecção das alterações posturais, porém a utilização destes programas exige estruturas de hardware complexas e implica em custos elevados para pesquisadores da fisioterapia, educação física e da comunidade científica. No ano 2005 foi criado o Software de Avaliação Postural (SAPO) que é uma opção gratuita para os mesmos fins, amplamente utilizada pela comunidade científica e profissional com ótimos resultados documentados. Apesar do sucesso do SAPO na comunidade científica este programa possui limitações. Neste âmbito a proposta do presente trabalho é desenvolver um software denominado ApLoB (Avaliação Postural do Laboratório de Biofísica) para avaliação postural, tendo como parâmetro de desenvolvimento o SAPO, mas tentando colaborar em relação à superação de suas limitações. Para isso, seu desenvolvimento é baseado nas estruturas e metodologias estabelecidas pela engenharia de software que permitam a continuidade do trabalho e melhorias de suas funcionalidades. O software foi desenvolvido utilizando a linguagem de programação Python, suas extensões científicas como NumPy, a biblioteca de processamento de imagem (PIL), a aplicação para interfaces gráficas (PyQt), além da biblioteca de plotagem de dados em 2D e desenvolvimento de aplicações de processamento de sinais (Guiqwt), dentre outros. O protótipo obtido foi testado e comparado em relação às suas funcionalidades com o software SAPO e foram considerados aceitáveis / The use of computational tools for postural evaluation has been very valuable in the detection of postural changes, however the use of these programs requires complex hardware structures and involves high costs for researchers in physiotherapy, physical education and the scientific community. In 2005, the Postural Assessment Software (SAPO) became to be a free option for the same purpose, widely used by the scientific community and professional with excellent documented results. Despite the success of SAPO in the scientific community, this software has limitations. So, the purpose of this study is to develop a software called ApLoB (Postural Assessment Laboratory of Biophysics) for postural assessment, having as parameter the development SAPO, but trying to collaborate on the overcome of its limitations. For this reason, its development is based on the structures and methods established by the software engineering that allow continuity of work and improved functionality. The software was developed using the Python programming language, scientific and NumPy extensions, the library of image processing (PIL), the application for graphical interfaces (PyQt), as well as data plotting library of 2D and application development signal processing (Guiqwt), among others. The prototype obtained was tested and its functionality was found to be acceptable, compared to SAPO

O uso de ferramentas computacionais para avaliação postural tem sido de grande valia na detecção das alterações posturais, porém a utilização destes programas exige estruturas de hardware complexas e implica em custos elevados para pesquisadores da fisioterapia, educação física e da comunidade científica. No ano 2005 foi criado o Software de Avaliação Postural (SAPO) que é uma opção gratuita para os mesmos fins, amplamente utilizada pela comunidade científica e profissional com ótimos resultados documentados. Apesar do sucesso do SAPO na comunidade científica este programa possui limitações. Neste âmbito a proposta do presente trabalho é desenvolver um software denominado ApLoB (Avaliação Postural do Laboratório de Biofísica) para avaliação postural, tendo como parâmetro de desenvolvimento o SAPO, mas tentando colaborar em relação à superação de suas limitações. Para isso, seu desenvolvimento é baseado nas estruturas e metodologias estabelecidas pela engenharia de software que permitam a continuidade do trabalho e melhorias de suas funcionalidades. O software foi desenvolvido utilizando a linguagem de programação Python, suas extensões científicas como NumPy, a biblioteca de processamento de imagem (PIL), a aplicação para interfaces gráficas (PyQt), além da biblioteca de plotagem de dados em 2D e desenvolvimento de aplicações de processamento de sinais (Guiqwt), dentre outros. O protótipo obtido foi testado e comparado em relação às suas funcionalidades com o software SAPO e foram considerados aceitáveis / The use of computational tools for postural evaluation has been very valuable in the detection of postural changes, however the use of these programs requires complex hardware structures and involves high costs for researchers in physiotherapy, physical education and the scientific community. In 2005, the Postural Assessment Software (SAPO) became to be a free option for the same purpose, widely used by the scientific community and professional with excellent documented results. Despite the success of SAPO in the scientific community, this software has limitations. So, the purpose of this study is to develop a software called ApLoB (Postural Assessment Laboratory of Biophysics) for postural assessment, having as parameter the development SAPO, but trying to collaborate on the overcome of its limitations. For this reason, its development is based on the structures and methods established by the software engineering that allow continuity of work and improved functionality. The software was developed using the Python programming language, scientific and NumPy extensions, the library of image processing (PIL), the application for graphical interfaces (PyQt), as well as data plotting library of 2D and application development signal processing (Guiqwt), among others. The prototype obtained was tested and its functionality was found to be acceptable, compared to SAPO

京都大学 / 0048 / 新制・課程博士 / 博士(医学) / 甲第21649号 / 医博第4455号 / 新制||医||1034(附属図書館) / 京都大学大学院医学研究科医学専攻 / (主査)教授 宮本 享, 教授 森田 智視, 教授 鈴木 実 / 学位規則第4条第1項該当 / Doctor of Medical Science / Kyoto University / DFAM

INTRODUÇÃO: O ceratocone é uma doença não inflamatória, sem etiologia definida, caracterizada pelo afilamento estromal e protrusão da córnea. Geralmente esta doença torna-se clinicamente evidente na adolescência. Apesar de possuir sinais clínicos bem conhecidos, a detecção do ceratocone em estádios iniciais pode representar uma tarefa de difícil execução, mesmo quando a videoceratografia computadorizada ou outros métodos são utilizados para avaliar a córnea. Anteriormente, diagnosticar o ceratocone apenas após a identificação de sinais clínicos inequívocos era uma conduta aceitável. Com o advento da cirurgia refrativa porém, a identificação precoce do ceratocone tornou-se um procedimento de vital importância para evitar complicações pós-operatórias. O objetivo principal deste estudo é avaliar o uso de máquinas de vetor de suporte e redes neurais artificiais como métodos auxiliares para identificação de ceratocone e suspeita de ceratocone em exames realizados com o Orbscan II. MÉTODOS: Foram avaliados retrospectivamente dados de 344 pacientes. Os exames selecionados foram classificados em 6 categorias: normal (n=172), astigmatismo (n=89), ceratocone (n=46), ceratocone forma frustra (n=10), suspeita de ceratocone (n=16) e cirurgia refrativa (n=11). Para cada paciente 10 atributos foram obtidos ou calculados a partir de dados fornecidos pelo Orbscan II. O método do holdout e da validação cruzada foram utilizados para encontrar a melhor configuração, treinar e testar os classificadores. Além da acurácia, sensibilidade e especificidade, curvas ROC foram obtidas para cada classificador, e as áreas sob as curvas ROC foram calculadas. RESULTADOS: Os dois classificadores selecionados alcançaram um bom desempenho, com áreas sob as curvas ROC de 0,99. Não houve diferença estatística entre as suas performances. O desempenho dos classificadores foi superior ao desempenho de todos os atributos individuais do Orbscan II. (p<0,05). CONCLUSÃO: Os resultados alcançados sugerem que xi x máquinas de vetor de suporte e redes neurais artificiais podem representar técnicas úteis para a detecção de ceratocone em exames realizados com o Orbscan II. / PURPOSE: Keratoconus is a bilateral and non-inflammatory condition characterized by progressive thinning, protrusion and scarring of the córnea. The disease usually becomes clinically evident at puberty, and its etiology remains unknown. Although it has well-described clinical signs, early forms of the disease may be undetected, even when computer-assisted videokeratography techniques or other methods are used to evaluate the cornea. Prior to the development of refractive surgery, it was considered sufficient to diagnose clinically evident keratoconus. However, given the spread of refractive surgery, a careful differentiation between normal and early keratoconus cases is essential to avoid postoperative complications. This study evaluated the performance of support vector machine and multilayer perceptron neural network, as auxiliary tools to identify keratoconus from Orbscan II maps. METHODS: A total of 344 maps were retrospectively selected and classified into six categories: normal (n=172), astigmatism (n=89), keratoconus (n=46), forme fruste keratoconus (n=10), keratoconus suspect (n=16), and photorefractive keratectomy (n=11). For each map 10 attributes were obtained or calculated from data provided by the Orbscan II. Holdout method and ten-fold cross-validation was used to train and test the classifiers. Besides accuracy, sensitivity and specificity, ROC curves for each classifier were generated and the areas under the curves were calculated. RESULTS: The two selected classifiers provided a good performance and there were no differences between their performances. The area under the ROC curve of the support vector machine and multi-layer perceptron were significantly larger than those for all individual Orbscan II attributes evaluated (p<0.05). CONCLUSION: Overall, our results suggest that support vector machine and multi-layer perceptron classifiers, trained on Orbscan II data, could represent useful techniques for keratoconus detection

INTRODUÇÃO: O ceratocone é uma doença não inflamatória, sem etiologia definida, caracterizada pelo afilamento estromal e protrusão da córnea. Geralmente esta doença torna-se clinicamente evidente na adolescência. Apesar de possuir sinais clínicos bem conhecidos, a detecção do ceratocone em estádios iniciais pode representar uma tarefa de difícil execução, mesmo quando a videoceratografia computadorizada ou outros métodos são utilizados para avaliar a córnea. Anteriormente, diagnosticar o ceratocone apenas após a identificação de sinais clínicos inequívocos era uma conduta aceitável. Com o advento da cirurgia refrativa porém, a identificação precoce do ceratocone tornou-se um procedimento de vital importância para evitar complicações pós-operatórias. O objetivo principal deste estudo é avaliar o uso de máquinas de vetor de suporte e redes neurais artificiais como métodos auxiliares para identificação de ceratocone e suspeita de ceratocone em exames realizados com o Orbscan II. MÉTODOS: Foram avaliados retrospectivamente dados de 344 pacientes. Os exames selecionados foram classificados em 6 categorias: normal (n=172), astigmatismo (n=89), ceratocone (n=46), ceratocone forma frustra (n=10), suspeita de ceratocone (n=16) e cirurgia refrativa (n=11). Para cada paciente 10 atributos foram obtidos ou calculados a partir de dados fornecidos pelo Orbscan II. O método do holdout e da validação cruzada foram utilizados para encontrar a melhor configuração, treinar e testar os classificadores. Além da acurácia, sensibilidade e especificidade, curvas ROC foram obtidas para cada classificador, e as áreas sob as curvas ROC foram calculadas. RESULTADOS: Os dois classificadores selecionados alcançaram um bom desempenho, com áreas sob as curvas ROC de 0,99. Não houve diferença estatística entre as suas performances. O desempenho dos classificadores foi superior ao desempenho de todos os atributos individuais do Orbscan II. (p<0,05). CONCLUSÃO: Os resultados alcançados sugerem que xi x máquinas de vetor de suporte e redes neurais artificiais podem representar técnicas úteis para a detecção de ceratocone em exames realizados com o Orbscan II. / PURPOSE: Keratoconus is a bilateral and non-inflammatory condition characterized by progressive thinning, protrusion and scarring of the córnea. The disease usually becomes clinically evident at puberty, and its etiology remains unknown. Although it has well-described clinical signs, early forms of the disease may be undetected, even when computer-assisted videokeratography techniques or other methods are used to evaluate the cornea. Prior to the development of refractive surgery, it was considered sufficient to diagnose clinically evident keratoconus. However, given the spread of refractive surgery, a careful differentiation between normal and early keratoconus cases is essential to avoid postoperative complications. This study evaluated the performance of support vector machine and multilayer perceptron neural network, as auxiliary tools to identify keratoconus from Orbscan II maps. METHODS: A total of 344 maps were retrospectively selected and classified into six categories: normal (n=172), astigmatism (n=89), keratoconus (n=46), forme fruste keratoconus (n=10), keratoconus suspect (n=16), and photorefractive keratectomy (n=11). For each map 10 attributes were obtained or calculated from data provided by the Orbscan II. Holdout method and ten-fold cross-validation was used to train and test the classifiers. Besides accuracy, sensitivity and specificity, ROC curves for each classifier were generated and the areas under the curves were calculated. RESULTS: The two selected classifiers provided a good performance and there were no differences between their performances. The area under the ROC curve of the support vector machine and multi-layer perceptron were significantly larger than those for all individual Orbscan II attributes evaluated (p<0.05). CONCLUSION: Overall, our results suggest that support vector machine and multi-layer perceptron classifiers, trained on Orbscan II data, could represent useful techniques for keratoconus detection

La formalisation des données cliniques est réalisée et adoptée dans plusieurs domaines de la santé comme la prévention des erreurs médicales, la standardisation, les guides de bonnes pratiques et de recommandations. Cependant, la communauté n'arrive pas encore à tirer pleinement profit de la valeur de ces données. Le problème majeur reste la difficulté à intégrer ces données et des services sémantiques associés au profit de la qualité de soins. Objectif L'objectif méthodologique de ce travail consiste à formaliser, traiter et intégrer les connaissances d'histopathologie et d'imagerie basées sur des protocoles standardisés, des référentiels et en utilisant les langages du web sémantique. L'objectif applicatif est de valoriser ces connaissances dans une plateforme pour faciliter l'exploration des lames virtuelles (LV), améliorer la collaboration entre pathologistes et fiabiliser les systèmes d'aide à la décision dans le cadre spécifique du diagnostic du cancer du sein. Il est important de préciser que notre but n'est pas de remplacer le clinicien, mais plutôt de l'accompagner et de faciliter ses lourdes tâches quotidiennes : le dernier mot reste aux pathologistes. Approche Nous avons adopté une approche transversale pour la représentation formelle des connaissances d'histopathologie et d'imagerie dans le processus de gradation du cancer. Cette formalisation s'appuie sur les technologies du web sémantique. / Semantic modelling of a histopathology image exploration and analysis tool. Recently, anatomic pathology (AP) has seen the introduction of several tools such as high-resolution histopathological slide scanners, efficient software viewers for large-scale histopathological images and virtual slide technologies. These initiatives created the conditions for a broader adoption of computer-aided diagnosis based on whole slide images (WSI) with the hope of a possible contribution to decreasing inter-observer variability. Beside this, automatic image analysis algorithms represent a very promising solution to support pathologist’s laborious tasks during the diagnosis process. Similarly, in order to reduce inter-observer variability between AP reports of malignant tumours, the College of American Pathologists edited 67 organ-specific Cancer Checklists and associated Protocols (CAP-CC&P). Each checklist includes a set of AP observations that are relevant in the context of a given organ-specific cancer and have to be reported by the pathologist. The associated protocol includes interpretation guidelines for most of the required observations. All these changes and initiatives bring up a number of scientific challenges such as the sustainable management of the available semantic resources associated to the diagnostic interpretation of AP images by both humans and computers. In this context, reference vocabularies and formalization of the associated knowledge are especially needed to annotate histopathology images with labels complying with semantic standards. In this research work, we present our contribution in this direction. We propose a sustainable way to bridge the content, features, performance and usability gaps between histopathology and WSI analysis.

There are approximately 1.8 million diagnoses of colorectal cancer, 1 million diagnoses of stomach cancer, and 0.6 million diagnoses of esophageal cancer each year globally. An automatic computer-assisted diagnostic (CAD) tool to rapidly detect colorectal and esophagogastric cancer tissue in optical images would be hugely valuable to a surgeon during an intervention. Based on a colon dataset with 12 patients and an esophagogastric dataset of 10 patients, several state-of-the-art machine learning methods have been trained to detect cancer tissue using hyperspectral imaging (HSI), including Support Vector Machines (SVM) with radial basis function kernels, Multi-Layer Perceptrons (MLP) and 3D Convolutional Neural Networks (3DCNN). A leave-one-patient-out cross-validation (LOPOCV) with and without combining these sets was performed. The ROC-AUC score of the 3DCNN was slightly higher than the MLP and SVM with a difference of 0.04 AUC. The best performance was achieved with the 3DCNN for colon cancer and esophagogastric cancer detection with a high ROC-AUC of 0.93. The 3DCNN also achieved the best DICE scores of 0.49 and 0.41 on the colon and esophagogastric datasets, respectively. These scores were significantly improved using a patient-specific decision threshold to 0.58 and 0.51, respectively. This indicates that, in practical use, an HSI-based CAD system using an interactive decision threshold is likely to be valuable. Experiments were also performed to measure the benefits of combining the colorectal and esophagogastric datasets (22 patients), and this yielded significantly better results with the MLP and SVM models.

No description available.

Les travaux de cette thèse sont consacrés à la détection et le diagnostic des lésions vasculaires, particulièrement dans le cas la maladie coronaire. La maladie coronaire continue à être la première cause de mortalité dans les pays industrialisés. En général, l'identification des lésions vasculaires est abordée en essayant de modéliser les anormalités (lésions). Le principal inconvénient de cette approche est que les lésions sont très hétérogènes, ce qui rend difficile la détection de nouvelles lésions qui n'ont pas été prises en compte par le modèle. Dans cette thèse, nous proposons de ne pas modéliser directement les lésions, mais de supposer que les lésions sont des événements anormaux qui se manifestent comme points avec une faible densité de probabilité. Nous proposons l'utilisation de deux méthodes de classification basées sur les Machines à Vecteurs de Support (SVM) pour résoudre le problème de détection du niveau de densité. Le principal avantage de ces deux méthodes est que la phase d'apprentissage ne requiert pas de données étiquetées représentant les lésions. La première méthode est complètement non supervisée, alors que la seconde exige des étiquettes seulement pour les cas qu'on appelle sains ou normaux. L'utilisation des algorithmes de classification sélectionnés nécessite des descripteurs tels que les anomalies soient représentées comme des points avec une densité de probabilité faible. A cette fin, nous avons développé une métrique basée sur l'intensité de l'image, que nous avons appelée concentric rings. Cette métrique est sensible à la quasi-symétrie des profils d'intensité des vaisseaux sains, mais aussi aux écarts par rapport à cette symétrie, observés dans des cas pathologiques. De plus, nous avons sélectionné plusieurs autres descripteurs candidats à utiliser comme entrée pour les classifieurs. Des expériences sur des données synthétiques et des données de CT cardiaques démontrent que notre métrique a une bonne performance dans la détection d'anomalies, lorsqu'elle est utilisée avec les classifeurs retenus. Une combinaison de plusieurs descripteurs candidats avec la métrique concentric rings peut améliorer la performance de la détection. Nous avons défini un schéma non supervisé de sélection de descripteurs qui permet de déterminer un sous-ensemble optimal de descripteurs. Nous avons confronté les résultats de détection réalisée en utilisant le sous-ensemble de descripteurs sélectionné par notre méthode avec les performances obtenues avec des sous-ensembles sélectionnés par des méthodes supervisées existantes. Ces expériences montrent qu'une combinaison de descripteurs bien choisis améliore effectivement les performances des classifieurs et que les meilleurs résultats s'obtiennent avec le sous-ensemble sélectionné par notre méthode, en association avec les algorithmes de détection retenus. Finalement, nous proposons de réaliser un recalage local entre deux images représentant différentes phases du cycle cardiaque, afin de confronter les résultats de détection dans ces images (phases). L'objectif ici est non seulement d'attirer l'attention du praticien sur les anomalies détectées comme lésions potentielles, mais aussi de l'aider à conforter son diagnostic en visualisant automatiquement la même région reconstruite à différents instants du cycle cardiaque / This thesis presents a framework for the detection and diagnosis of vascular lesions with a special emphasis on coronary heart disease. Coronary heart disease remains to be the first cause of mortality worldwide. Typically, the problem of vascular lesion identification has been solved by trying to model the abnormalities (lesions). The main drawback of this approach is that lesions are highly heterogeneous, which makes the detection of previously unseen abnormalities difficult. We have selected not to model lesions directly, but to treat them as anomalies which are seen as low probability density points. We propose the use of two classification frameworks based on support vector machines (SVM) for the density level detection problem. The main advantage of these two methods is that the learning stage does not require labeled data representing lesions, which is always difficult to obtain. The first method is completely unsupervised, whereas the second one only requires a limited number of labels for normality. The use of these anomaly detection algorithms requires the use of features such that anomalies are represented as points with low probability density. For this purpose, we developed an intensity based metric, denoted concentric rings, designed to capture the nearly symmetric intensity profiles of healthy vessels, as well as discrepancies with respect to the normal behavior. Moreover, we have selected a large set of alternative candidate features to use as input for the classifiers. Experiments on synthetic data and cardiac CT data demonstrated that our metric has a good performance in the detection of anomalies, when used with the selected classifiers. Combination of other features with the concentric rings metric has potential to improve the classification performance. We defined an unsupervised feature selection scheme that allows the definition of an optimal subset of features. We compared it with existent supervised feature selection methods. These experiments showed that, in general, the combination of features improves the classifiers performance, and that the best results are achieved with the combination selected by our scheme, associated with the proposed anomaly detection algorithms. Finally, we propose to use image registration in order to compare the classification results at different cardiac phases. The objective here is to match the regions detected as anomalous in different time-frames. In this way, more than attract the physician's attention to the anomaly detected as potential lesion, we want to aid in validating the diagnosis by automatically displaying the same suspected region reconstructed in different time-frames

No description available.