Дисертації з теми "Guide d'images"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-37 дисертацій для дослідження на тему "Guide d'images".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте дисертації для різних дисциплін та оформлюйте правильно вашу бібліографію.
Banville, Frédéric Alexandre. "Amélioration de la résolution latérale en microscopie SPR/MCWG par reconstruction d'images." Mémoire, Université de Sherbrooke, 2014. http://hdl.handle.net/11143/6743.
Повний текст джерелаBismuth, Vincent. "Algorithmes de traitement d'images pour la visualisation d'outils interventionnels dans des séquence de fluoroscopie par rayons X." Phd thesis, Université Paris-Est, 2012. http://tel.archives-ouvertes.fr/tel-00747682.
Повний текст джерелаNassif, Marcel. "Méthode de fabrication additive endoscopique par photopolymérisation pour la réparation in-situ de systèmes en espace contraint." Electronic Thesis or Diss., Compiègne, 2022. http://www.theses.fr/2022COMP2684.
Повний текст джерелаThis thesis concerns the study and the development of a novel endoscopic 3D printing process based on photo-polymerization. The idea behind endoscopic 3D printing is to print 3D objects or to repair damaged parts in a dense mechanical assembly without disassembling it. The thesis aims, once the state of the art is studied, to propose solutions adapted to the endoscopic problem, then to model, design, realize and experimentally validate the two main subsystems (UV photo-polymerization through an image guide, resin spraying through a tubular pipe) which, once synchronized, provide the additive printing. Inspired by the vat polymerization method, the liquid resin is transmitted endoscopically and sprayed onto the printing surface (spraying system). Then, a UV pattern, structured by a DMD (Digital Micromirror Device), is transmitted through the image guide and focused onto the printing surface to polymerize a layer of liquid resin. These two steps are repeated several times in order to print layers on top of each other to obtain a 3D part. An endoscopic actuation system (non-integrated translation actuator) allows maintaining the probe at a distance from the printing surface equal to the focal length of the objective of the instrument. In this thesis, the endoscopic UV projection system was designed, modeled, implemented and tested. The design and performances of the optical system were presented in two international conferences. Multilayer objects were fabricated with a layer thickness of 50 μm on a circular printing area of 9.54 mm in diameter. An optical analysis method based on the use of the modulation transfer functions (MTF) was used to test the performance of the endoscopic optical system and to characterize the lateral resolution of the printed parts. Using the MTF method experimentally, a drop in optical resolution due to the image guide was estimated as high as 16 μm compared to the value obtained in the experimental setup containing the same optical components except for the image guide. The lateral resolution of the printed parts was finally limited by the resin (50 μm) and not by the resolution of the optical system. An endoscopic atomization system was also studied, implemented and tested. An endoscopic spraying system was implemented to allow a remote deposition of the resin onto the printing surface. The choice of an air atomization method was adopted. The design, control and realization of the atomization system are presented. Finally, the spraying system was combined with the UV pattern projection system. Preliminary results of printing objects were obtained and 3D parts with a thickness of 0.65 mm are printed (nine layers). Due to a phenomenon called "overspray" (during the spraying process, the resin reaches the printing area and is pushed to the sides by the air pressure that sprays it), the thickness of the layers is not constant between them, but gradually decreases, so the adjustment of the spraying parameters becomes critical. The spraying system still needs to be optimized in order to eliminate overspray and to be able to print uniform layers with a specific thickness. In addition, we have been working on a 2D visualization system but the lack of light on the printing surface prevents us from being able to visualize and control the system. In the future, we propose to spray a resin mixed with a fluorescent dye to make it possible to distinguish the polymerized zones from the uncured zones in each layer of the part
Hristova, Hristina. "Example-guided image editing." Thesis, Rennes 1, 2017. http://www.theses.fr/2017REN1S119/document.
Повний текст джерелаThis thesis addresses three main topics from the domain of image processing, i.e. color transfer, high-dynamic-range (HDR) imaging and guidance-based image filtering. The first part of this thesis is dedicated to color transfer between input and target images. We adopt cluster-based techniques and apply Gaussian mixture models to carry out a more precise color transfer. In addition, we propose four new mapping policies to robustly portray the target style in terms of two key features: color, and light. Furthermore, we exploit the properties of the multivariate generalized Gaussian distributions (MGGD). in order to transfer an ensemble of features between images simultaneously. The multi-feature transfer is carried out using our novel transformation of the MGGD. Despite the efficiency of the proposed MGGD transformation for multi-feature transfer, our experiments have shown that the bounded Beta distribution provides a much more precise model for the color and light distributions of images. To exploit this property of the Beta distribution, we propose a new color transfer method, where we model the color and light distributions by the Beta distribution and introduce a novel transformation of the Beta distribution. The second part of this thesis focuses on HDR imaging. We introduce a method for automatic creation of HDR images from only two images - flash and non-flash images. We mimic the camera response function by a brightness function and we recover details from the flash image using our new chromatic adaptation transform (CAT), called bi-local CAT. That way, we efficiently recover the dynamic range of the real-world scenes without compromising the quality of the HDR image (as our method is robust to misalignment). In the context of the HDR image creation, the bi-local CAT recovers details from the flash image, removes flash shadows and reflections. In the last part of this thesis, we exploit the potential of the bi-local CAT for various image editing applications such as image de-noising, image de-blurring, texture transfer, etc. We propose a novel guidance-based filter in which we embed the bi-local CAT. The proposed filter performs as good as (and for certain applications even better than) state-of-the art methods
CHARROUX, BENOIT. "Analyse d'images : cooperation d'operateurs de segmentation guidee par l'interpretation." Paris 11, 1996. http://www.theses.fr/1996PA112024.
Повний текст джерелаCatrou, Sylvie. "Étude et mise en œuvre d'un système de décorrélation hybride d'images guidé par apprentissage." Compiègne, 1991. http://www.theses.fr/1991COMPD343.
Повний текст джерелаOgudo, Kingsley. "Development of edge-emitting Si/SiGe based optical sources operating in the visible and near visible range wavelength for sensing and communication applications." Thesis, Paris Est, 2018. http://www.theses.fr/2018PESC1060/document.
Повний текст джерелаWe propose a low cost full-silicon optical links utilizing 650 – 850 nm propagation wavelengths. The creation of large-scale opto-electronic integrated circuits and optical data “highways” inCMOS integrated circuitry, utilizing Si CMOS compounds, have been envisioned and hold much promise [1] - [3] The latest attempts for realizing optoelectronic systems in CMOS technology have until now mainly been focused on utilizing wavelengths at 1550 nm [4] - [6], mainly because of the ease of design and fabrication of waveguides in this wavelength regime. However, no effective high-speed optical sources and Si detectors are available at this 1550nmwavelength. Today solutions to overcome the problem are mostly focused on the integration of group III-V elements based optical sources on Silicon through molecular bonding [7a] – [7b]. If optical sources, detectors, waveguides, and sensors could be realized on the same Si CMOS chip at, say, 750 nm wavelength, various low power consuming, light and miniature on-chip-based micro-photonic systems can be designed and realized. While Silicon optical sources may not yet be at the required performance level for very-high speed communications, the low cost “all silicon”opto-electronic systems still remain a great grail. These sources could lead as well to new field that could be appropriately named “Si photonic microsystems” opening the route to new sensing applications and products especially for the medical, biomedical optics, optical interconnect and bio-photonics field. These systems also do not require ultrahigh frequency bandwidths to transmit, and the emission powers of our avalanche Si light-emitting diodes(LEDs) may be sufficient to sustain the operation of such systems. This PhD thus deals with low cost SiGe/Si optical links using Microwave-Photonics devices such as, Bipolar integrated SiAvLED, Silicon Nitride and Silicon Oxide optical waveguides, SiGeHPTs, Si and SiGe/Si LEDs. It focuses on the combined integration of micron-scale optical sources, optical waveguides and detectors on the same chip to form a complete communication link for various applications involving short wavelength links (750nm to 950nm). The progress provided by this PhD to previous works could be synthesized as below:• Optical source, waveguide and the detector were all integrated and aligned on the same chip, in an industrial based technology, to form complete on-chip micro-optical links at750nm wavelength, with a SiGe radio frequency (RF) 0.35µm bipolar process.• A series of second generation of on-chip optical communication links of 50µm length, utilizing 650 – 850 nm propagation wavelengths, have been designed and realized inSiGe. Micron dimensioned optical sources, waveguides and detectors were all integrated ion the same chip to form a complete communication on-chip micro-optical links. Avalanche based Si LEDs (Si Av LEDs), Schottky contacting, TEOS densification strategies, Silicon-Nitride based waveguides, and state of the art SiGe bipolar detector technologies were used as key design strategies.• R-soft simulation software (Beam Prop) was used as a mathematical capable simulation tool to model various Silicon-Nitride optical waveguide structures, before the designing, the fabrication, characterization and testing of the device. Various device structures were modeled, simulation iterations were performed on several optical waveguide designed structures before the device design, and the devices were tested experimentally.• Best performances of the designed on-chip optical links show a conversion loss as low as30dB from source to detector with up to 500MHz in cut off frequency. The good alignment and the good efficiency of each device are then clearly achieved. Higher frequency performances are also envisaged from preliminary measurements
Denis, de Senneville Baudouin. "Correction des mouvements pour la thermométrie temps réel guidée par IRM." Bordeaux 1, 2005. http://www.theses.fr/2005BOR13123.
Повний текст джерелаHamdan, Iyas. "Multimodal Image Registration in Image-Guided Prostate Brachytherapy." Thesis, Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2017. http://www.theses.fr/2017IMTA0002/document.
Повний текст джерелаProstate cancer is the most common cancer in men in France and western countries. It is the third leading cause of death from cancer, being responsible for around 10% of deaths. Brachytherapy, a radiotherapy technique, is associated with a better health-related quality of life after the treatment, compared to other treatment techniques. Prostate brachytherapy involves the implantation of radioactive sources inside the prostate to deliver a localized radiation dose to the tumor while sparing the surrounding healthy tissues. Multi-modal imaging is used in order to improve the overall accuracy of the treatment. The pre-operative Computed Tomography (CT) images can be used to calculate a personalized and accurate dose distribution. During the intervention, the surgeon utilizes a real-time guiding system, Trasnrectal Ultrasound (TRUS), to accurately place the radioactive sources in their desired pre-planned positions. Therefore, if the positions of the sources were determined on CT, they need to be transferred to US. However, a robust and direct US/CT registration is hardly possible since they both provide low soft tissue contrast. Magnetic Resonance Imaging (MRI), on the other hand, has a superior contrast and can potentially improve the treatment planning and delivery by providing a better visualization. Thus, these three modalities (MRI, US and CT) need to be accurately registered. To compensate for prostate deformations, caused by changes in size and form between the different acquisitions, non-rigid registration is essential. Fully automatic registration methodology is necessary in order to facilitate its integration in a clinical workflow. At first, we propose a registration between pre-operative MR and CT images based on the maximization of the mutual information in combination with a deformation field parameterized by cubic B-Splines. We propose to constrain the registration to volumes of interest (VOIs) in order to improve the robustness and the computational efficiency. The proposed approach was validated on clinical patient datasets. Quantitative evaluation indicated that the overall registration error was of 1.15±0.20 mm; which satisfies the desired clinical accuracy. Then, we propose a second intra-operative US/MRI registration, where a multi-resolution approach is implemented to reduce the probability of local minima and improve the computational efficiency. A similarity measure, which correlates intensities of the US image with intensities and gradient magnitude of the MRI, is used to determine the transformation that aligns the two images. The proposed methodology was validated on a prostate phantom at first to assess its feasibility. Subsequently, the method was validated on clinical patient datasets and evaluated using qualitative and quantitative criteria, resulting in a registration error of 1.44±0.06 mm. The approach proposed in this work allows going towards a multimodal protocol for image-guided brachytherapy which can improve the overall accuracy of this procedure. Despite such encouraging results, future work will involve further evaluation on a larger number of datasets in order to assess the reliability and the efficiency of this methodology before integrating it in a clinical workflow
Bordes, Ghislaine. "Interprétation d'images aériennes guidée par une base de données cartographiques : application à l'extraction automatique des routes." Université de Marne-la-Vallée, 1997. http://www.theses.fr/1997MARN0012.
Повний текст джерелаBoichis, Nicolas. "Extraction automatique des carrefours routiers par interpretation d'images aeriennes guidee par une base de donnees cartographiques." Cergy-Pontoise, 2000. http://www.theses.fr/2000CERG0089.
Повний текст джерелаCoupé, Pierrick. "Méthode de compensation des déformations cérébrales par imagerie ultrasonore intraopératoire pour la neurochirurgie guidée par l'image." Phd thesis, Université Rennes 1, 2008. http://tel.archives-ouvertes.fr/tel-00328179.
Повний текст джерелаMaclair, Grégory. "Développement d'algorithmes temps réel de traitement de séquences d'images animées biomédicales pour la thermothérapie guidée par IRM." Thesis, Bordeaux 1, 2008. http://www.theses.fr/2008BOR13720/document.
Повний текст джерелаDuring the last years MR-guided lo cal hyp erthermia has b een develop edfor the clinical practice. Hyp erthermia is based on the destruction of tumorcells due to an increased temp erature over a sufficient amount of time. The si-multaneous acquisition of MR images during the heating pro cess allows on-linemonitoring of the temp erature and a control of the tissue destruction inducedby the hyp erthermia treatment. The on-line calculation of the temp erature isnot a trivial problem. This is b ecause the physical and physiological pheno-mena like the respiration disturb the temp erature measurement. Hence, it isnecessary to develop strategies for real-time correction in order to deliver pre-cise temp erature maps. In this work, we prop ose several algorithms for imagetreatment enabling the correction of artefacts related to motion and magneticsusceptibility effects. These corrections will provide a reliable estimation of theefficiency of the hyp erthermia treatment
Sdiri, Bilel. "2D/3D Endoscopic image enhancement and analysis for video guided surgery." Thesis, Sorbonne Paris Cité, 2018. http://www.theses.fr/2018USPCD030.
Повний текст джерелаMinimally invasive surgery has made remarkable progress in the last decades and became a very popular diagnosis and treatment tool, especially with the rapid medical and technological advances leading to innovative new tools such as robotic surgical systems and wireless capsule endoscopy. Due to the intrinsic characteristics of the endoscopic environment including dynamic illumination conditions and moist tissues with high reflectance, endoscopic images suffer often from several degradations such as large dark regions,with low contrast and sharpness, and many artifacts such as specular reflections and blur. These challenges together with the introduction of three dimensional(3D) imaging surgical systems have prompted the question of endoscopic images quality, which needs to be enhanced. The latter process aims either to provide the surgeons/doctors with a better visual feedback or improve the outcomes of some subsequent tasks such as features extraction for 3D organ reconstruction and registration. This thesis addresses the problem of endoscopic image quality enhancement by proposing novel enhancement techniques for both two-dimensional (2D) and stereo (i.e. 3D)endoscopic images.In the context of automatic tissue abnormality detection and classification for gastro-intestinal tract disease diagnosis, we proposed a pre-processing enhancement method for 2D endoscopic images and wireless capsule endoscopy improving both local and global contrast. The proposed method expose inner subtle structures and tissues details, which improves the features detection process and the automatic classification rate of neoplastic,non-neoplastic and inflammatory tissues. Inspired by binocular vision attention features of the human visual system, we proposed in another workan adaptive enhancement technique for stereo endoscopic images combining depth and edginess information. The adaptability of the proposed method consists in adjusting the enhancement to both local image activity and depth level within the scene while controlling the interview difference using abinocular perception model. A subjective experiment was conducted to evaluate the performance of the proposed algorithm in terms of visual qualityby both expert and non-expert observers whose scores demonstrated the efficiency of our 3D contrast enhancement technique. In the same scope, we resort in another recent stereo endoscopic image enhancement work to the wavelet domain to target the enhancement towards specific image components using the multiscale representation and the efficient space-frequency localization property. The proposed joint enhancement methods rely on cross-view processing and depth information, for both the wavelet decomposition and the enhancement steps, to exploit the inter-view redundancies together with perceptual human visual system properties related to contrast sensitivity and binocular combination and rivalry. The visual qualityof the processed images and objective assessment metrics demonstrate the efficiency of our joint stereo enhancement in adjusting the image illuminationin both dark and saturated regions and emphasizing local image details such as fine veins and micro vessels, compared to other endoscopic enhancement techniques for 2D and 3D images
Nassef, Mohamed. "Monitoring de dose pour la radiothérapie du cancer de la prostate." Thesis, Rennes 1, 2016. http://www.theses.fr/2016REN1S033/document.
Повний текст джерелаThis thesis concerns the compensation of the anatomical variations, mainly the organs at risk (rectum, bladder) deformations, which occur during intensity modulated radiotherapy of the prostate cancer. These variations can lead to significant dose drift compared to the initially planned dose, increasing the risk of toxicity. Thanks to the evolution of imaging devices and of image processing methods, dose accumulation processes, allowing to estimate the cumulated dose during the treatment, have been recently proposed. Nevertheless those strategies suffer of a lack of evaluation and their integration into an adaptive radiotherapy raises many questions. Thus, in the first part of this work, a dose accumulation method recently developed at the LTSI was evaluated using a numerical phantom. The results obtained showed that the dosimetric uncertainties related to the cumulated dose process remain low compared to the dose drifts observed for patients. The second part of this work aimed to develop a dose guided adaptive radiotherapy process and to evaluate its dosimetrical benefit using three patients showing a dose drift. The principle of this method is to detect a potential drift between the planned and actually delivered doses and, if necessary, to compensate them thanks to one or more replanning(s). The results have shown that this approach has reduced the dose drift to the organs at risk, while increasing the dose to the prostate compared to standard IGRT treatment, with a limited number of replannings (one or two), enabling to consider a clinical implementation
André, Barbara. "Atlas intelligent pour guider le diagnostic en endomicroscopie : une application clinique de la reconnaissance d'images par le contenu." Phd thesis, École Nationale Supérieure des Mines de Paris, 2011. http://pastel.archives-ouvertes.fr/pastel-00640899.
Повний текст джерелаSauvaget, Catherine. "De la synthèse d'images expressive aux effets bande déssinée : vers un outil d'aide à la création artistique." Paris 8, 2011. http://www.theses.fr/2011PA083398.
Повний текст джерелаWe present a tool for assisting artistic creation which produce a wide variety of image stylizations with “comics” effects. The system gives to the user an important role in the control of stylization. Starting from an artistic analysis, we propose a system based on the most important criteria in the artistic process of picture creation. We present models coming up to artists expectations. First, we present a model semi-automatically generating a depth map to stylize images while avoiding depth problems. It can also produce atmospheres used by artists to induce specific psychological effects to the observer. Then, we propose two models showing the interest of harmonizing images and using the contrast of quantity defined by Johannes Itten. The first one ensures this harmony in images like photographs or illustrations; based on the same harmony, the second one offers, by extension, a coloring aid for sketches to obtain harmonious images at the early stages of creation. Our last model deals with the effects of light contained in the images. It allows to stylize different kinds of lighting effects by moving, reshaping or giving them a style developed from well-known artistic movements. We conclude with our tool contributions and we present possible improvements as well as our plans for the future
Nicolau, Stéphane. "Un système de réalité augmentée pour guider les opérations du foie en radiologie interventionnelle." Nice, 2004. http://www.theses.fr/2004NICE4066.
Повний текст джерелаIn the interventional radiology field, the medical expert needs several CT-scan acquisitions (2D slices) to reach the target during a percutaneous puncture in the abdominal area. We aim at designing a guidance system to reduce the number of CT acquisition and thus, the intervention duration. We propose an augmented reality system that superimposes preoperative 3D reconstructions of the patient abdominal structures in external video images of his/her body. This system will not only have to be accurate, quick and reliable, but will also have to be easily introduced in the operative room. In our case, the patient is intubated and the breathing is controlled. Therefore, we can neglect breathing motion: a rigid 3D/2D registration of radio-opaque markers is sufficient to obtain the necessary accuracy. Since statistical assumptions of existing 3D/2D registration criteria do not fit our application, we derived a new criterion generalizing classical methods. A rigorous evaluation of the performances showed the superiority of our approach in terms of accuracy and robustness. To reach real-time processing in the operative room, we developed and validated several algorithms to automatically extract and match radio-opaque markers. Since the system accuracy depends on numerous factors (camera position, marker number. . . ), it is not possible to calculate it beforehand. To provide a reliable system, we propose a technique of covariance propagation that enables to estimate the superimposition error of reconstructed models. A rigorous validation step on synthetic and real data showed that our prediction is correct in our conditions. All the different parts of the system being validated, we perform an evaluation of the whole system on an abdominal phantom. Results proved the feasibility and the interest of the system: four surgeons managed to reach emboddied targets with an average accuracy under 2 mm. Moreover, the time needed for the needle positioning was ten times under classical interventional duration. Finally, several clinical experiments on patients showed that our system can be used in the operating room and suggest that this system could be used routinely in a near future
Derivaux, Sébastien. "Construction et classification d'objets à partir d'images de télédétection par une approche itérative guidée par des connaissance du domaine." Strasbourg, 2009. http://www.theses.fr/2009STRA6145.
Повний текст джерелаCazoulat, Guillaume. "Radiothérapie guidée par l'image du cancer de la prostate : vers l'intégration des déformations anatomiques." Phd thesis, Université Rennes 1, 2013. http://tel.archives-ouvertes.fr/tel-00992354.
Повний текст джерелаRigaud, Bastien. "Radiothérapie adaptative guidée par l’imagerie anatomique." Thesis, Rennes 1, 2018. https://ged.univ-rennes1.fr/nuxeo/site/esupversions/718ad2cd-1afa-4219-8c54-640c6bf5f6b6.
Повний текст джерелаThe reference treatment for locally advanced cervical carcinomas relies on chemoradiotherapy and brachytherapy (BT). The radiotherapy (RT) is based on a planning made on a single scanner and on the delivery of the treatment. During the treatment, the clinical target volume (CTV) position may change and hamper the precision of the dose delivery, thus, increasing the risk of recurrence and toxicity. The aim of the thesis is the development of new adaptive radiation therapy (ART) strategies in order to take in account the per-treatment anatomical deformations. These approches will have to rely on image processing tools such as deformable image registration (DIR) and data mining to extract the information from the images acquired at the planning and during the treatment. The work of this thesis has led to the definition of two new ART strategies: (1) an evolutive planning library that can be enriched by new per-treatment anatomies; (2) a modeled library based on a population analysis at the time of planning. Finally, in the context of delivered dose estimation, a biomechanical based DIR method is proposed to map the anatomy of the BT, with applicator, toward the anatomy of RT, without applicator. This method is compared to open access and commercially available DIR methods. The geometrical evaluation, show that the proposed adaptive strategies allow to insure a good coverage of the CTV for all the patients while limiting the irradiation of the healthy organs. Such strategies may improve the clinical outcome of the patients
Belarte, Bruno. "Extraction, analyse et utilisation de relations spatiales entre objets d'intérêt pour une analyse d'images de télédétection guidée par des connaissances du domaine." Thesis, Strasbourg, 2014. http://www.theses.fr/2014STRAD011/document.
Повний текст джерелаThe new remote sensors allow the acquisition of very high spatial resolution images at high speeds, thus producing alarge volume of data. Manual processing of these data has become impossible, new tools are needed to process them automatically. Effective segmentation algorithms are required to extract objects of interest of these images. However, the produced segments do not match to objects of interest, making it difficult to use expert knowledge.In this thesis we propose to change the level of interpretation of an image in order to see the objects of interest of the expert as objects composed of segments. For this purpose, we have implemented a multi-level learning process in order to learn composition rules. Such a composition rule can then be used to extract corresponding objects of interest.In a second step, we propose to use the composition rules learning algorithm as a first step of a bottom-up top-down approach. This processing chain aims at improving the classification from contextual knowledge and expert information.Composed objects of higher semantic level are extracted from learned rules or rules provided by the expert, and this new information is used to update the classification of objects at lower levels.The proposed method has been tested and validated on Pléiades images representing the city of Strasbourg. The results show the effectiveness of the composition rules learning algorithm to make the link between expert knowledge and segmentation, as well as the interest of the use of contextual information in the analysis of remotely sensed very high spatial resolution images
Cotteret, Gilles. "Extraction d'éléments curvilignes guidée par des mécanismes attentionnels pour des images de télédétection. Approche par fusion de données." Thesis, Université Laval, 2006. http://www.theses.ulaval.ca/2006/23332/23332.pdf.
Повний текст джерелаThe extraction of curvilinear elements from remote sensing images, especially when noisy or near the limit of resolution constitutes a significant challenge for data-processing algorithms. In this work a method is presented for linear feature extraction in remote sensing (RS) images. An original model (ELECA) is introduced allowing out of date geographical information system (GIS) data to be updated though the use of a visual search method that mimics human eye movements. The ELECA model is composed of three parts : (1) a visual search module using virtual gaze to avoid processing the entire image ; (2) a simple and fast method for local information extraction by a clever adaptation of connected-component labeling ; and (3) an original method for the fusion of local information to construct a global representation at the scale of the image based on qualitative spatial reasoning techniques. The ELECA model avoids several problems characteristic of current methods. In particular, the proposed technique can be applied to low resolution or partially occluded images for which currently only human interpreters can successfully process the image. The technique is also designed to be very fast and efficient when a quick GIS update is needed. The last part of this project is devoted to the design of software which supports the ELECA model. The proposed software architecture is adaptive and allows the integration of future model developments. Finally it is shown how the ELECA model could be implemented.
La extracción de elementos curvilíneos de las imágenes de teledetección, sobre todo en proximidad del límite de resolución o en presencia de ruido, representa siempre un reto importante para los algoritmos informáticos, mientras que para los intérpretes humanos es una tarea inmediata. Este trabajo presenta un método nuevo para guiar la extracción de elementos curvilíneos (carreteras, ríos, etc.) de imágenes de teledetección. El objetivo del método consiste en actualizar un sistema de información geográfica (SIG) gracias a un modelo inédito (ELECA) constituído de tres partes. El modelo ELECA desarrolla dos ideas principales. El modelo puede utilizar las imágenes de teledetección y los datos del SIG que están desactualizados. El modelo se basa asimismo en resultados recientes de la investigación en ciencias psico-cognitivas, dado que imita parcialmente el movimiento de los ojos durante una búsqueda visual. Las tres partes del modelo ELECA son: (1) un método de búsqueda de la información local que utiliza un ojo virtual par focalizarse únicamente donde se encuentra la información probable, evitando un tratamiento global de la imagen; (2) un método simple y rápido de extracción de la información local, que utiliza una adaptación astuciosa de un análisis en componentes conexos; y (3) un método original de fusión de informaciones locales que se apoya sobre trabajos de reconstrucción del espacio global por razonamiento espacial cualitativo. El modelo ELECA evita así algunas trampas en las que caen a menudo los métodos clásicos. En particular, la técnica propuesta puede ser utilizada para imágenes parcialmente enmascaradas o de baja resolución, que sólo pueden ser tratadas actualmente por intérpretes humanos. El método ha sido elaborado para ser eficiente en la actualización rápida de un SIG si es necesario. La última parte de este trabajo presenta una solución informática elaborada para soportar el modelo ELECA. Una arquitectura de programa flexible y adaptable es presentada, permitiendo la integración de desarrollos ulteriores del modelo. Finalmente, un aspecto algorítmico muestra concretamente que las soluciones del modelo ELECA. se pueden implantar en términos informáticos.
Garnier, Carole. "Segmentation de la prostate pour la thérapie par Ultrasons Haute Intensité guidée par l’Image." Rennes 1, 2009. https://tel.archives-ouvertes.fr/tel-00498035.
Повний текст джерелаThis work deals with the segmentation of echographic prostate images acquired intra-operatively simultaneously to the application of high intensity ultrasound (HIFU) for the destruction of tumor. The objective is to precisely delineate the target in order to concentrate the heating induced by ultrasound and to reduce as much as possible their impact on the neighboring structures. After a brief presentation of the clinical and the technical context, in particular the dosimetry, a state-of-the-art is carried out: it shows that although all the most recent and effective methods have been explored, only partial solutions have been obtained due to a large variability of situations to deal with and the relatively poor quality of the images in HIFU devices. Several solutions are then proposed based on discrete deformable contours, improved by the search of gradient based landmark points, coupled or not with optimal search detection. These solutions are tested on about thirty datasets and qualitatively and quantitatively analysed by comparison with expert-defined contours. A preliminary study is also performed for texture characterization using different types of moments (Zernike, Legendre, etc. ). The results show that an overall good behaviour is obtained fulfilling the time computation constraints
Girum, Kibrom Berihu. "Artificial intelligence for image-guided prostate brachytherapy procedures." Thesis, Bourgogne Franche-Comté, 2020. http://www.theses.fr/2020UBFCI012.
Повний текст джерелаRadiotherapy procedures aim at exposing cancer cells to ionizing radiation. Permanently implanting radioactive sources near to the cancer cells is a typical technique to cure early-stage prostate cancer. It involves image acquisition of the patient, delineating the target volumes and organs at risk on different medical images, treatment planning, image-guided radioactive seed delivery, and post-implant evaluation. Artificial intelligence-based medical image analysis can benefit radiotherapy procedures. It can help to facilitate and improve the efficiency of the procedures by automatically segmenting target organs and extrapolating clinically relevant information. However, manual delineation of target volumes is still the standard routine for most clinical centers, which is time-consuming, challenging, and not immune to intra- and inter-observer variations. In this thesis, we aim to develop medical image processing solutions to automate various components of the current image-guided prostate brachytherapy procedures, including radioactive seeds identification from CT images and clinical target volume segmentation from different medical images. In the first application, we developed and evaluated a new technique for detecting and identifying implanted radioactive seeds on post-implant CT scans of prostate brachytherapy. This allows experts to evaluate the quality of the image-guided radioactive seed delivery by computing the delivered dosimetric parameters, specifically to compute the post-implant dosimetry of salvage prostate brachytherapy performed years after primary brachytherapy in the treatment of relapsed prostate cancer. The second application involved the development of deep learning methods to delineate clinical target volumes automatically. We evaluated the proposed methods on a clinical database of intraoperative transrectal ultrasound and post-implant CT images of image-guided prostate brachytherapy. The evaluation is then extended to other medical image analysis applications. Our methods yielded promising results and opening important perspectives towards efficient and accurate medical image analysis tasks. They can be applied to automate the management of image-guided prostate brachytherapy procedures
Haouchine, Nazim. "Image-guided simulation for augmented reality during hepatic surgery." Thesis, Lille 1, 2015. http://www.theses.fr/2015LIL10009/document.
Повний текст джерелаThe main objective of this thesis is to provide surgeons with tools for pre and intra-operative decision support during minimally invasive hepatic surgery. These interventions are usually based on laparoscopic techniques or, more recently, flexible endoscopy. During such operations, the surgeon tries to remove a significant number of liver tumors while preserving the functional role of the liver. This involves defining an optimal hepatectomy, i.e. ensuring that the volume of post-operative liver is at least at 55% of the original liver and the preserving at hepatic vasculature. Although intervention planning can now be considered on the basis of preoperative patient-specific, significant movements of the liver and its deformations during surgery data make this very difficult to use planning in practice. The work proposed in this thesis aims to provide augmented reality tools to be used in intra-operative conditions in order to visualize the position of tumors and hepatic vascular networks at any time
Boydev, Christine. "Segmentation automatique des images de tomographie conique pour la radiothérapie de la prostate." Thesis, Valenciennes, 2015. http://www.theses.fr/2015VALE0030/document.
Повний текст джерелаThe use of CBCT imaging for image-guided radiation therapy (IGRT), and beyond that, image-guided adaptive radiation therapy (IGART), in the context of prostate cancer is challenging due to the poor contrast and high noise in pelvic CBCT images. The principal aim of the thesis is to provide methodological contributions for automatic intra-patient image registration between the planning CT scan and the treatment CBCT scan. The first part of our contributions concerns the development of a CBCT-based prostate setup correction strategy using CT-to-CBCT rigid registration (RR). We established a comparison between different RR algorithms: (a) global RR, (b) bony RR, and (c) bony RR refined by a local RR using the prostate CTV in the CT scan expanded with 1- to-20-mm varying margins. A comprehensive statistical analysis of the quantitative and qualitative results was carried out using the whole dataset composed of 115 daily CBCT scans and 10 planning CT scans from 10 prostate cancer patients. We also defined a novel practical method to automatically estimate rectal distension occurred in the vicinity of the prostate between the CT and the CBCT scans. Using our measure of rectal distension, we evaluated the impact of rectal distension on the quality of local RR and we provided a way to predict registration failure. On this basis, we derived recommendations for clinical practice for the use of automatic RR for prostate localization on CBCT scans. The second part of the thesis provides a methodological development of a new joint segmentation and deformable registration framework. To deal with the poor contrast-to-noise ratio in CBCT images likely to misguide registration, we conceived a new metric (or enery) which included two terms: a global similarity term (the normalized cross correlation (NCC) was used, but any other one could be used instead) and a segmentation term based on a localized adaptation of the piecewise-constant region-based model of Chan-Vese using an evolving contour in the CBCT image. Our principal aim was to improve the accuracy of the registration compared with an ordinary NCC metric. Our registration algorithm is fully automatic and takes as inputs (1) the planning CT image, (2) the daily CBCT image and (3) the binary image associated with the CT image and corresponding to the organ of interest we want to segment in the CBCT image in the course of the registration process
Curticapean, Dan Silviu. "Méthode pour l'ajustement précis de fibres optiques à géométrie définie avec imprécision, application à l'optimisation d'une épissure de fibres optiques." Université Louis Pasteur (Strasbourg) (1971-2008), 2002. http://www.theses.fr/2002STR13019.
Повний текст джерелаThe goal of this work is to propose and realise a new control system for a splicer. The new investigations and analyses are based on digital image processing and in-situ measurements. They offer new control possibilities for the splice process. In addition to this, new technological implementations are investigated and discussed. They can be used in future splicers. In the first part, a feasibility study to measure the core eccentricity using the scattering pattern method, was presented and discussed. After modelling of the thermal behaviour of the splice process and the loss analyses considerations the developed splice investigation and analyse system is presented
Fanchon, Louise. "Autoradiographie quantitative d'échantillons prélevés par biopsie guidée par TEP/TDM : méthode et applications cliniques." Thesis, Brest, 2016. http://www.theses.fr/2016BRES0018.
Повний текст джерелаDuring the last decade, positron emission tomography (PET) has been finding broader application in oncology. Some tumors that are non-visible in standard anatomic imaging like computerized tomography (CT) or ultrasounds, can be detected by measuring in 3D the metabolic activity of the body, using PET imaging. PET images can also be used to deliver localized therapy like radiation therapy or ablation. In order to deliver localized therapy, the tumor border has to be delineated with very high accuracy. However, the poor spatial resolution of PET images makes the segmentation challenging. Studies have shown that manual segmentation introduces a large inter- and intra- variability, and is very time consuming. For these reasons, many automatic segmentation algorithms have been developed. However, few datasets with histopathological information are available to test and validate these algorithms since it is experimentally difficult to produce them. The aim of the method developed was to evaluate PET segmentation algorithms against the underlying histopathology. This method consists in acquiring quantitative autoradiography of biopsy specimen extracted under PET/CT guidance. The autoradiography allows imaging the radiotracer distribution in the biopsy specimen with a very high spatial accuracy. Histopathological sections of the specimen can then obtained and observed under the microscope. The autoradiography and the micrograph of the histological sections can then be registered with the PET image, by aligning them first with the biopsy needle seen on the CT image and then transferring them onto the PET image. The next step was to use this dataset to test two PET automatic segmentation algorithms: the Fuzzy Locally Adaptive Bayesian (FLAB) developed at the Laboratory of Medical Information Processing (LaTIM) in Brest, France, as well as a fix threshold segmentation method. However, the reliability of the dataset produced depends on the accuracy of the registration of the PET, autoradiography and micrograph images. The main source of uncertainty in the registration of these images comes from the registration between the CT and the PET. In order to evaluate the accuracy of the registration, a method was developed. The results obtained with this method showed that the registration error ranges from 1.1 to 10.9mm. Based on those results, the dataset obtained from 4 patients was judged satisfying to test the segmentation algorithms. The comparison of the contours obtained with FLAB and with the fixed threshold method shows that at the point of biopsy, the FLAB contour is closer than that to the histopathology contour. However, the two segmentation methods give similar contours, because the lesions were homogeneous
Ciofolo, Cybèle. "Segmentation de formes guidée par des modèles en neuro-imagerie : intégration de la commande floue dans une méthode de segmentation par ensembles de niveau." Rennes 1, 2005. http://www.theses.fr/2005REN1S150.
Повний текст джерелаNicolau, Stephane. "Un système de réalité augmentée pour guider les opérations du foie en radiologie interventionnelle." Phd thesis, Université de Nice Sophia-Antipolis, 2004. http://tel.archives-ouvertes.fr/tel-00000006.
Повний текст джерелаDans notre cas, le patient est intubé et sa ventilation contrôlée, nous pouvons donc négliger les effets de la respiration : un recalage rigide 3D/2D de marqueurs radio-opaques collés sur la peau est suffisant pour atteindre la précision requise. Les hypothèses statistiques des critères classiques n'étant pas adéquates pour notre application, nous avons dérivé un nouveau critère généralisant les approches standard. Une évaluation rigoureuse des performances démontre la supériorité de notre méthode en terme de précision et de robustesse.
Pour atteindre le temps réel en salle d'opération, nous avons ensuite développé un ensemble d'algorithmes d'extraction et de mise en correspondance des marqueurs radio-opaques dont nous avons validé la robustesse sur de nombreuses images réelles. La précision du système dépendant de nombreux paramètres (nombre de marqueurs radio-opaques, position des caméras...), elle ne peut pas être établie préalablement de manière définitive. Afin de fournir un système fiable, nous proposons donc une technique de propagation des covariances qui permet d'estimer dynamiquement l'erreur de repositionnement des modèles reconstruits. Une phase de validation méticuleuse, sur des données synthétiques et réelles, démontre que notre prédiction est fiable dans les conditions de notre application.
Après cette validation de chacun des modules, nous montrons la faisabilité et l'intérêt de notre système complet en menant une évaluation sur un mannequin : quatre chirurgiens ont réussi à atteindre des cibles en des temps dix fois inférieurs à ceux usuellement nécessaires pour ce type d'intervention et avec une précision supérieure. Finalement, plusieurs expériences cliniques sur des patients démontrent que notre système est utilisable en salle d'opération et suggèrent son utilisation en routine dans un futur proche.
Dupont, Erwan. "Méthode de mesure tridimensionnelle active appliquée au contexte de l’analyse endoscopique ou coloscopique." Thesis, Compiègne, 2015. http://www.theses.fr/2015COMP2198/document.
Повний текст джерелаThis thesis aims at developing a tri-dimensional measurement endoscopic device in a double context: the first one is industrial with endoscopic inspection of mechanical pieces (tubular inspection, for example) at micrometric resolution. The second context is medical with tri-dimensional shape detection during colonoscopy to help the surgeon diagnosis. In this study, flexible endoscopy is made possible by using image guides and the tri-dimensional reconstruction method is based on active stereovision where a digital micro-mirror device is used to spatially structure the incoming light. After developing the state of the art, an optical conception and evaluation method, applied to stereovision for flexible endoscopic devices is described. The instrumental realization is then detailed and metrologically evaluated. An innovative method that allows to switch dynamically between active and passive stereovision is then detailed. Finally, 3D reconstruction algorithms adapted to this endoscopic instrument are proposed. The scientific contributions of this study are multiple. Firstly, an optical analysis method based on the modulation transfer function to design an endoscopic stereovision system is proposed. An image processing method for robust calibration in a defocused optical environment and a new phase-shifting algorithm for 3D reconstruction are proposed. Finally, a realization principle for 3D measurement in flexible endoscopy was extracted from the combination of all these methods
Sandoval, Niño Zulma. "Planning and guidance of ultrasound guided High Intensity Focused Ultrasound cardiac arrhythmia therapy." Thesis, Rennes 1, 2015. http://www.theses.fr/2015REN1S044/document.
Повний текст джерелаThe work presented in this document aims at developing new image-processing methods to improve the planning and guidance of transesophageal HIFU atrial fibrillation therapy. This document is divided into two parts, namely therapy planning and therapy guidance. We first propose novel therapy planning methods that exploit high-resolution pre-operative CT or MRI information to extract patient-specific anatomical details and to define future therapeutic procedures. Our specific methodological contributions concern the following: an automatically-refined atlas-based segmentation approach to extract the left atrium and pulmonary veins; the delineation of the lesion lines on the original or segmented volume; and the reconstruction of a volume adapted to future intraoperative transesophageal navigation. Secondly, our proposal of a novel registration approach for use in therapy guidance aligns intraoperative 2D ultrasound with preoperative 3D CT information. This approach first carries out a systematic statistical evaluation to select the best similarity measure for our application and then takes advantage of the geometrical constraints of the transesophageal HIFU probe to simplify the registration process. Our proposed methods have been evaluated on digital and/or physical phantoms and on real clinical data
Hadjerci, Oussama. "Détection automatique du nerf dans les images échographiques." Thesis, Orléans, 2017. http://www.theses.fr/2017ORLE2006/document.
Повний текст джерелаRegional anesthesia presents an interesting alternative or complementary act to general anesthesia in many surgical procedures. It reduces pain scores, improves postoperative mobility and facilitates earlier hospital discharge. Ultrasound-Guided Regional Anesthesia (UGRA) has been gaining importance in the last few years, offering numerous advantages over alternative methods of nerve localization (neurostimulation or paraesthesia). However, nerve detection is one of the most difficult tasks that anesthetists can encounter in the UGRA procedure. The context of the present work is to provide practitioners with a method to facilitate and secure the practice of UGRA. However, automatic detection and segmentation in ultrasound images is still a challenging problem in many medical applications. This work addresses two main issues. The first one, we propose an algorithm for nerve detection and segmentation in ultrasound images, this method is composed of a pre-processing, texture analysis and machine learning steps. In this part of work, we explore two new approaches ; one to characterize the nerve and the second for selecting the minimum redundant and maximum relevant features. The second one, we studied the nerve detection in consecutive ultrasound frames. We have demonstrated that the development of an algorithm based on the temporal coherence of the position, the shape and the confidence measure of the classification, allows to generate a robust segmentation. In this work, we also propose a new model of shape based on a set of intervals landmarks able to adapt to the nerve shape under a morphological variations
Hou, Yingfan. "Apport de la combinaison de méthodes de mesure de formes tridimensionnelles dans le contexte de l'endoscopie flexible." Thesis, Compiègne, 2016. http://www.theses.fr/2016COMP2255/document.
Повний текст джерелаThe techniques of three dimensional shapes reconstruction are widely used in many fields, particularly in the industrial or medical field. And in these areas, non-contact measurement techniques are particularly studied, mainly because they don't damage the measured object. This work therefore falls within this context and in particular in the case of endoscopic devices of surface coordinate measuring by optical methods. ln the medical field, this type of instrument can be applied to 3D colonoscopy or minimally invasive surgery to the surface in the form of biological tissues. In this thesis, methods based on active or passive stereo vision are the principle, which will be studied and integrated into a miniaturized device. Different measurement modes will be incorporated simultaneously into a single miniaturized instrument to help increase measurement performance: the instrument can adjust its measurement principle to the texture of the object or also to the orientation of measured surfaces more generally to the context of the measurement. This thesis is based on an algorithmic study and instrumental integration of these different measurement modes into a single miniaturized endoscopic instrument. The study of the measurement modes stereovision was conducted in three phases. First, it is the influence of the orientation of the measured objects' surface in a case of active stereovision being analyzed. And a technique of switching between the projection and acquisition in an active stereovision system by bistable actuation is proposed, which allows to adapt the measurement to the orientation of the measured surfaces. Finally, the study is oriented towards the ability to switch from one active stereovision mode to one passive stereovision mode, always by bistable actuator operation, the passive stereovision mode is particularly suitable for highly textured objects. Thus, three measurement modes are made in the new system: two modes of active stereovision (reversing capture and projection channels) and a mode of passive stereovision. To achieve three-dimensional reconstruction, two active methods (phase shift and Fourier Transform) and a passive method are studied. Different performance measurements are obtained according to methods selected: a more accurate measuring result is obtained by the phase shift methods; a high measurement speed is obtained by the Fourier transform methods or by passive methods. The instrumental development is also described in this thesis. After optical modeling and mechanical design of the measuring system, a prototype of the endoscopic instrument is manufactured with various specific devices such as a DMD (Digital Micromirror Deviee),images guides and bistable electromagnetic actuators. The experimental validation of the three-dimensional measurement is performed mainly on mechanical objects (such as details measurement on a coin), both active and passive method methods are well tested and compared. Finally, an artificial colon is measured by this system to be placed in a medical application context
Wu, Ke. "3D segmentation and registration for minimal invasive prostate cancer therapy." Phd thesis, Université Rennes 1, 2014. http://tel.archives-ouvertes.fr/tel-00962028.
Повний текст джерелаRani, Kaddour. "Stratégies d’optimisation des protocoles en scanographie pédiatrique." Thesis, Université de Lorraine, 2015. http://www.theses.fr/2015LORR0282/document.
Повний текст джерелаFor the last 10-years, computed tomography (CT) procedures and their increased use have been a major source for concern in the scientific community. This concern has been the starting point for several studies aiming to optimize the dose while maintaining a diagnostic image quality. In addition, it is important to pay special attention to dose levels for children (age range considered to be from a newborn baby to a 16-y-old patient). Indeed, children are more sensitive to ionizing radiations, and they have a longer life expectancy. Optimizing the CT protocols is a very difficult process due to the complexity of the acquisition parameters, starting with the individual patient characteristics, taking into account the available CT device and the required diagnostic image quality. This PhD project is contributing to the advancement of knowledge by: (1) Developing a new approach that can minimize the number of testing CT scans examinations while developing a predictive mathematical model allowing radiologists to prospectively anticipate how changes in protocols will affect the image quality and the delivered dose for four models of CT scan. (2) Setting-up a Generic Optimized Protocol (based on the size of the phantom CATPAHN 600) for four models of CT scan. (3) Developing a methodology to adapt the GOP to five sizes of pediatric patient using Size Specific Dose Estimate calculation (SSDE). (4) Evaluating subjective and objective image quality between size-based optimised CT protocol and age-based CT protocols. (5) Developing a CT protocol optimization tool and a tutorial helping the radiologists in the process of optimization