Les images angiographiques sont utilisés pour différentes tâches comme le diagnostique, le suivie de pathologies et la planification d'interventions chirurgicales. Toutefois, en raison du faible ratio signal sur bruit et le contenu complexe des données (informations clairsemées), l'analyse des images angiographiques est une tâche fastidieuse et source d'erreurs. Ces différentes considérations ont motivé le développement de nombreuses techniques d'analyse.Les travaux de cette thèse s'organisent autour de deux axes de recherches : d'une part la segmentation des images angiographiques, et d'autre part la modélisation des réseaux vasculaires cérébraux. En segmentation, l'automatisation induit généralement un coût de calcul élevé, alors que les méthodes interactives sont difficiles à utiliser en raison de la dimension et de la complexité des images. Ces travaux présentent un compromis entre les deux approches, en utilisant le concept de segmentation à base d'exemple. Cette stratégie qui utilise les arbres de coupes de façon non standard,conduit à des résultats satisfaisant, lorsqu'elle est appliqué sur des données d'ARM cérébrales 3D. Les approches existantes, en modélisation, reposent exclusivement sur des informations relatives aux vaisseaux. Ces travaux ont exploré une nouvelle voie, consistant à utiliser à la fois les informations vasculaires et morphologiques ( c-à-d structures cérébrales) pour améliorer la précision et la pertinence des atlas obtenus. Les expériences soulignent des améliorations dans les principales étapes du processus de création de l'atlas impacté par l'utilisation de l'information morphologique. Un exemple d'atlas cérébraux a été réalisé. / Angiographie images are useful data for several tasks, e.g., diagnosis, pathology follow-up or surgery planning. However, due to low SNR (noise,artifacts), and complex semantic content (sparseness), angiographie image analysis is a time consurning and error prone task. These consideration have motivated the development of numerous vesse! filtering, segmentation, or modeling techinques.This thesis is organized around two research areas : the segmentation anù the moùeling. Segmentation of cerebral vascular networks from 3D angiographie data remains a challenge. Automation generally induces a high computational cost and possible errors, white interactive methods are hard to use due to the dimension and the complexity of images. This thesis presents a compromise between both approaches by using the concept of example-based segmentation. This strategy, which uses component-trees in a non-standard fashion, leads to promising results, when applied on cerebral MR angiographie data. The generation of cerebrovascular atlases remains a complex and infrequently considered issue. The existing approaches rely on information exclusively related to the vessels. This thesis investigate a new way, consisting of using both vascular and morphological information (i.e. Cerebral structures) to improve the accuracy and relevance of the obtaines vascular atlases. Experiments emphasize improvments in the main steps of the atlas generation process impacted by the use of the morphological information. An example of cerebrovascular atlas obtained from a dataset of MRAs acquired form different acquisition devices has been provided.

Segmentation of vessel structure is an important phase in analysis of retinal images. The resulting vessel system description may be important for diagnostic of many eye and cardiovascular diseases. A method for automatic segmentation of the vessel structure in colour retinal images is presented in the thesis. The method utilises 2D matched filtering to detect presence of short linear vessel sections of a particular thickness and orientation. The approach correlates the local image areas with a 2D masks based on a typical brightness profile perpendicular to vessels of a particular width. Three different approximated profiles are used and corresponding matched filters are designed for: thin, medium and thick vessels. The evaluation of typical vessel profiles and filter design are described in chapter 3 and chapter 4. The parametric images obtained by convolution of the image with the masks are then thresholded in order to obtain binary representation of vessel structure. The three binary representations are consequently combined to provide the best available rough vessel map, which is finalised by complementing the obviously missing vessel sections and cleaning the disconnected fractional artefacts. The thresholding algorithm and final steps of processing are mentioned in chapter 5 and chapter 6. The method has been implemented by computer and the program for automatic vessel segmentation has been developed using database of real retinal images. The efficiency of the method has been finally evaluated on images from the standard database DRIVE.

This thesis deals with method of blood vessels segmentation from retinal images acquired by fundus camera. There is explored possibility of using wavelet transform as fast outline segmentation. The thesis includes study problems of preprocessing input image and decomposition of image using 2D DWT. Furthermore there is explored possibility of parametrical images thresholding that ensue from application of 2D DWT. There are designed algorithms for cleaning off artifacts from rough vessel map of blood vessel structures. The realization of algorithm was solved in programming environment MATLAB. There was created a user control interface in graphic application GUIDE, for easy control of whole segmentation process. In conclusion of thesis is proceeded the discussion of segmentation results for images from DBME database and quantitative evaluation of results for DRIVE database images.

[EN] The World Health Organization estimates that in 2010 there were 285 million people visually impaired in the world. It is calculated that the 80\% of these cases are preventable or treatable. In addition, aging population and chronic disease increase are two factors that predict a higher number of blindness cases in the future. Hypertension, diabetic retinopathy (DR), age-related macular degeneration (AMD) and glaucoma are the most common pathologies in the current society that provoke retinal damage and can be directly related to blindness and vision loss. The early diagnosis of these diseases allows, through appropriate treatment, to reduce costs generated when they are in advanced states and may become chronic. This fact justifies screening campaigns. However, a screening campaign requires a heavy workload for trained experts in the analysis of anomalous patterns of each disease, which in addition to the increase of population at risk, makes these campaigns economically unfeasible. Therefore, the need of automatic screening system developments is highlighted. The final goal of this thesis is the implementation of novel methods that allow the analysis and processing of fundus images to implement an automatic screening of four of the most important diseases that affect world population. In particular, the main objective of the thesis is to build up algorithms for the characterization of the retinal structures and the retina background in order to assist in the discrimination between a ``normal" and pathological retina. Mathematical morphology along with other operators are used for the detection of the retinal vessels and the optic disk. The proposed methods work properly on databases with a large degree of variability. Not only have the main structures been segmented, but significant features have also been extracted from them to be used in a computer aided diagnosis software for hypertensive risk determination. The texture of the retina background is also analyzed in this work by means of local binary patterns with the aim of identifying DR and AMD and avoiding the need of segmentation of the characteristic retinal lesions of each disease. The results are promising above all for AMD diagnosis. / [ES] La Organización Mundial de la Salud estima que en 2010 había 285 millones de personas con alguna discapacidad visual en el mundo. Se calcula que el 80\% de estos casos son evitables o tratables. Además, el envejecimiento de la población y el aumento de las enfermedades crónicas son dos factores que hacen prever un número todavía mayor de casos de ceguera en el futuro. La hipertensión, la retinopatía diabética (RD), la degeneración macular asociada a la edad (DMAE) y el glaucoma son las enfermedades más comunes que provocan daños en la retina y, por tanto, están directamente relacionadas con la ceguera y con la pérdida de visión. El diagnóstico de estas enfermedades en estadios tempranos permite, mediante el tratamiento adecuado, reducir los costes que generan en estados ya avanzados y que en la mayoría de los casos acaban convirtiéndose en crónicas, lo que justifica la realización de campañas de cribado. Sin embargo, una campaña de cribado exige una gran carga de trabajo de personal experto entrenado en el análisis de los patrones anómalos propios de cada enfermedad, lo que sumado al aumento de la población de riesgo, hace que estas campañas sean inviables económicamente. Por lo tanto, se evidencia la necesidad del desarrollo de sistemas de cribado automáticos. El objetivo final del presente trabajo es la implementación de métodos novedosos de análisis de imágenes de fondo de ojo para usarlos en un sistema de cribado de cuatro de las enfermedades más importantes que afectan a la población actual. En concreto, el objetivo principal de la tesis es el desarrollo de algoritmos para la caracterización de las estructuras y del fondo retiniano, los cuales servirán de ayuda para discriminar una retina ``normal" de otra patológica. Para la detección de los vasos retinianos y del disco óptico, se ha usado morfología matemática además de otros operadores. Se ha demostrado que los métodos propuestos para este fin funcionan adecuadamente en bases de datos con un alto grado de variabilidad. No sólo se han segmentado las principales estructuras retinianas, sino que, además, se han extraído sus características más significativas para determinar el riesgo hipertensivo. En este trabajo, también se han analizado las texturas presentes en el fondo de la retina por medio de la teoría de los patrones binarios locales con el objetivo de identificar la RD y la DMAE a la vez que se evita la necesidad de la segmentación de las lesiones específicas de cada enfermedad. Los resultados son prometedores, sobre todo, para la detección de la DMAE. / [CAT] L'Organització Mundial de la Salut estima que en 2010 havia 285 milions de persones amb alguna discapacitat visual en el món. Es calcula que el 80\% d'aquests casos són evitables o tractables. A més, l'envelliment de la població i l'augment de les malalties cròniques són dos factors que fan preveure un número encara major de casos de ceguera en el futur. La hipertensió, la retinopatia diabètica (RD), la degeneració macular associada a l'edat (DMAE) i el glaucoma són les malalties més comuns que provoquen danys en la retina i, per tant, estan directament relacionades amb la ceguera i amb la pèrdua de visió. El diagnòstic d'aquestes malalties en estadis primerencs permet, per mitjà del tractament adequat, reduir els costos que generen en estats ja avançats i que en la majoria dels casos acaben convertint-se en cròniques, la qual cosa justifica la realització de campanyes de garbellament. No obstant això, una campanya de garbellament exigix una gran càrrega de treball de personal expert entrenat en l'anàlisi dels patrons anòmals propis de cada malaltia, que si es suma a l'augment de la població de risc, fa que aquestes campanyes siguen inviables econòmicament. Per tant, s'evidencia la necessitat del desenrotllament de sistemes de garbellament automàtics. L'objectiu final del present treball és la implementació de mètodes nous d'anàlisi d'imatges de fons d'ull per a usar-los en un sistema de garbellament de quatre de les malalties més importants que afecten la població actual. En concret, l'objectiu principal de la tesi és el desenvolupament d'algoritmes per a la caracterització de les estructures i del fons retinià, els quals serviran d'ajuda per a discriminar una retina ``normal" d'una altra patològica. Per a la detecció dels vasos retinians i del disc òptic, s'ha usat morfologia matemàtica a més d'altres operadors. S'ha demostrat que els mètodes proposats per a aquest fi funcionen adequadament en bases de dades amb un alt grau de variabilitat. No sols s'han segmentat les principals estructures retinianes, sinó que, a més, s'han extret les seues característiques més significatives per a determinar el risc hipertensiu. En aquest treball, també s'han analitzat les textures presents en el fons de la retina per mitjà de la teoria dels patrons binaris locals amb l'objectiu d'identificar la RD i la DMAE al mateix temps que s'evita la necessitat de la segmentació de les lesions específiques de cada malaltia. Els resultats són prometedors, sobretot, per a la detecció de la DMAE. / Morales Martínez, S. (2015). Fundus characterization for automatic disease screening through retinal image processing [Tesis doctoral]. Editorial Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/53933 / TESIS

Medical imagery is increasingly evolving towards higher resolution and throughput. The increasing volume of data and the usage of multiple and often novel imaging modalities necessitates the use of mathematical and computational techniques for quicker, more accurate and more robust analysis of medical imagery. The fields of computer vision and machine learning provide a rich set of techniques that are useful in medical image analysis, in tasks ranging from segmentation to classification and population analysis, notably by integrating the qualitative knowledge of experts in anatomy and the pathologies of various disorders and making it applicable to the analysis of medical imagery going forward. The object of the proposed research is exactly to explore various computer vision and machine learning methods with a view to the improved analysis of multiple modalities of brain and cardiac imagery, towards enabling the clinical goals of studying schizophrenia, brain tumors (meningiomas and gliomas in particular) and cardiovascular disorders. In the first project, a framework is proposed for the segmentation of tubular, branched anatomical structures. The framework uses the tubular surface model which yields computational advantages and further incorporates a novel automatic branch detection algorithm. It is successfully applied to the segmentation of neural fiber bundles and blood vessels. In the second project, a novel population analysis framework is built using the shape model proposed as part of the first project. This framework is applied to the analysis of neural fiber bundles towards the detection and understanding of schizophrenia. In the third and final project, the use of mass spectrometry imaging for the analysis of brain tumors is motivated on two fronts, towards the offline classification analysis of the data, as well as the end application of intraoperative detection of tumor boundaries. SVMs are applied for the classification of gliomas into one of four subtypes towards application in building appropriate treatment plans, and multiple statistical measures are studied with a view to feature extraction (or biomarker detection). The problem of intraoperative tumor boundary detection is formulated as a detection of local minima of the spatial map of tumor cell concentration which in turn is modeled as a function of the mass spectra, via regression techniques.

Ce travail a pour objectif de générer des modèles vasculaires et de simuler des écoulements sanguins réalistes à l'intérieur de ces modèles. La première étape consiste à segmenter/reconstruire le volume 3D du réseau vasculaire. Une fois de tels volumes vasculaires segmentés et maillés, il est alors possible de simuler des écoulements sanguins à l'intérieur de ceux-ci. Pour la segmentation, nous utilisons une approche variationnelle. Nous proposons un premier modèle qui inclut un a priori de tubularité dans les modèles de débruitage ROF et TV-L1. Néanmoins, bien que ces modèles permettent de réhausser les vaisseaux, ils ne permettent pas de les segmenter. C'est pourquoi nous proposons un deuxième modèle amélioré qui inclut à la fois un a priori de tubularité et de direction dans le modèle de segmentation de Chan-Vese. Les résultats sont présentés sur des images synthétiques 2D, ainsi que sur des images rétiniennes. En ce qui concerne la simulation, nous nous intéressons d'abord au réseau veineux cérébral, encore peu étudié. Les équations de la dynamique des fluides qui régissent les écoulements sanguins dans notre géométrie sont alors les équations de Navier-Stokes. Pour résoudre ces équations, la méthode classique des caractéristiques est comparée avec un schéma d'ordre plus élevé. Ces deux schémas sont validés sur des solutions analytiques avant d'être appliqués aux cas réalistes du réseau veineux cérébral premièrement, puis du polygone artériel de Willis. / The aim of this work is to generate vascular models and simulate blood flows inside these models. A first step consists of segmenting/reconstructing the 3D volume of the vascular network. Once such volumes are segmented and meshed, it is then possible to simulate blood flows. For segmentation purposes, we use a variational approach. We first propose a model that embeds a vesselness prior in the denoising models ROF and TV-L1. Although these models can enhance vessels, they are not designed for segmentation. Then, we propose a second, improved model that includes both vesselness and direction priors in the Chan-Vese segmentation model. The results are presented on 2D synthetic images, as well as retinal images. In the second part, devoted to simulation, we first focus on the cerebral venous network, that has not been intensively studied. The equations governing blood flows inside our geometry are the Navier-Stokes equations. For their resolution, the classical method of characteristics is compared with a high-order scheme. Both schemes are validated on analytical solutions before their application on the realistic cases of the cerebral venous network, and the arterial polygon of Willis.

Segmentation of vasculature tree is an important step of the process of image processing. There are many methods of automatic blood vessel segmentation. These methods are based on matched filters, pattern recognition or image classification. Use of automatic retinal image processing greatly simplifies and accelerates retinal images diagnosis. The aim of the automatic image segmentation algorithms is thresholding. This work primarily deals with retinal image thresholding. We discuss a few works using local and global image thresholding and supervised image classification to segmentation of blood tree from retinal images. Subsequently is to set of results from two different methods used image classification and discuss effectiveness of the vessel segmentation. Use image classification instead of global thresholding changed statistics of first method on healthy part of HRF. Sensitivity and accuracy decreased to 62,32 %, respectively 94,99 %. Specificity increased to 95,75 %. Second method achieved sensitivity 69.24 %, specificity 98.86% and 95.29 % accuracy. Combining the results of both methods achieved sensitivity up to72.48%, specificity to 98.59% and the accuracy to 95.75%. This confirmed the assumption that the classifier will achieve better results. At the same time, was shown that extend the feature vector combining the results from both methods have increased sensitivity, specificity and accuracy.

No description available.

Los derrames cerebrales son una de las causas principales de morbilidad y mortalidad en los países desarrollados. Esto ha motivado una búsqueda de configuraciones del sistema vascular que se cree que están asociadas con el desarrollo de enfermedades vasculares. En la primera contribución se ha mejorado un método de segmentación vascular para lograr robustez en la segmentación de imágenes procedentes de diferentes modalidades y centros clínicos, con una validación exhaustiva. Una vez que el sistema vascular está correctamente segmentado, en la segunda contribución se ha propuesto una metodología para caracterizar ampliamente la geometría de la arteria carótida interna (ACI). Esto ha incluido el desarrollo de un método para identificar automáticamente la ACI a partir del árbol vascular segmentado. Finalmente, en la tercera contribución, esta identificación automática se ha generalizado a una colección de arterias incluyendo su conectividad y sus relaciones topológicas. Finalmente, la identificación de las arterias en un conjunto de individuos puede permitir la comparación geométrica de sus árboles arteriales utilizando la metodología introducida para la caracterización de la ACI. / Stroke is among the leading causes of morbidity and mortality in the developed countries. This motivated a search for the configurations of vasculature that is assumed to be associated with the development of vascular diseases. In the first contribution we improve a vascular segmentation method to achieve robustness in segmenting images coming from different imaging modalities and clinical centers and we provide exhaustive segmentation validation. Once the vasculature is successfully segmented, in the second contribution we propose a methodology to extensively characterize the geometry of the internal carotid artery (ICA). This includes the development of a method to automatically identify the ICA from the segmented vascular tree. Finally in the third contribution, this automatic identification is generalized to a collection of vessels including their connectivity and topological relationships. Identifying the corresponding vessels in a population enables comparison of their geometry using the methodology introduced for the characterization of the ICA.