Dissertations / Theses on the topic 'Endoscopic image'
To see the other types of publications on this topic, follow the link: Endoscopic image.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Endoscopic image.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Lotfy, M. Y. "Stereoscopic image feature matching during endoscopic procedure." Thesis, Boston, USA, 2020. http://openarchive.nure.ua/handle/document/11836.
Full textAbstract:
This research work describes of the developed software of endoscopic images processing. Calculating pairs of corresponding points, which in the future can be used for three-dimensional reconstruction, was conducted. The number of points for each frame is not large enough, so the 3D reconstruction should use the entire video stream. To increase the number of points should also conduct a study on setting the parameters of the detector. The study tested the stage of finding matches on stereo pairs of endoscopic images.
2
Sdiri, Bilel. "2D/3D Endoscopic image enhancement and analysis for video guided surgery." Thesis, Sorbonne Paris Cité, 2018. http://www.theses.fr/2018USPCD030.
Full textAbstract:
Grâce à l’évolution des procédés de diagnostiques médicaux et les développements technologiques, la chirurgie mini-invasive a fait des progrès remarquables au cours des dernières décennies surtout avec l’innovation de nouveaux outils médicaux tels que les systèmes chirurgicaux robotisés et les caméras endoscopiques sans fil. Cependant, ces techniques souffrent de quelques limitations liées essentiellement l’environnement endoscopique telles que la non uniformité de l’éclairage, les réflexions spéculaires des tissus humides, le faible contraste/netteté et le flou dû aux mouvements du chirurgien et du patient (i.e. la respiration). La correction de ces dégradations repose sur des critères de qualité d’image subjective et objective dans le contexte médical. Il est primordial de développer des solutions d’amélioration de la qualité perceptuelle des images acquises par endoscopie 3D. Ces solutions peuvent servir plus particulièrement dans l’étape d’extraction de points d’intérêts pour la reconstruction 3D des organes, qui sert à la planification de certaines opérations chirurgicales. C’est dans cette optique que cette thèse aborde le problème de la qualité des images endoscopiques en proposant de nouvelles méthodes d’analyse et de rehaussement de contraste des images endoscopiques 2D et 3D.Pour la détection et la classification automatique des anomalies tissulaires pour le diagnostic des maladies du tractus gastro-intestinal, nous avons proposé une méthode de rehaussement de contraste local et global des images endoscopiques 2D classiques et pour l’endoscopie capsulaire sans fil.La méthode proposée améliore la visibilité des structures locales fines et des détails de tissus. Ce prétraitement a permis de faciliter le processus de détection des points caractéristiques et d’améliorer le taux de classification automatique des tissus néoplasiques et tumeurs bénignes. Les méthodes développées exploitent également la propriété d’attention visuelle et de perception de relief en stéréovision. Dans ce contexte, nous avons proposé une technique adaptative d’amélioration de la qualité des images stéréo endoscopiques combinant l’information de profondeur et les contours des tissues. Pour rendre la méthode plus efficace et adaptée aux images 3Dl e rehaussement de contraste est ajusté en fonction des caractéristiques locales de l’image et du niveau de profondeur dans la scène tout en contrôlant le traitement inter-vues par un modèle de perception binoculaire.Un test subjectif a été mené pour évaluer la performance de l’algorithme proposé en termes de qualité visuelle des images générées par des observateurs experts et non experts dont les scores ont démontré l’efficacité de notre technique 3D d’amélioration du contraste. Dans cette même optique,nous avons développé une autre technique de rehaussement du contraste des images endoscopiques stéréo basée sur la décomposition en ondelettes.Ce qui offre la possibilité d’effectuer un traitement multi-échelle et d’opérer une traitement sélectif. Le schéma proposé repose sur un traitement stéréo qui exploite à la fois l’informations de profondeur et les redondances intervues,ainsi que certaines propriétés du système visuel humain, notamment la sensibilité au contraste et à la rivalité/combinaison binoculaire. La qualité visuelle des images traitées et les mesures de qualité objective démontrent l’efficacité de notre méthode qui ajuste l’éclairage des images dans les régions sombres et saturées et accentue la visibilité des détails liés aux vaisseaux sanguins et les textures de tissuesMinimally 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
3
Erian, Mark. "Contributions to the practice of endoscopic surgery in gynaecology : based on personal published work 1990-2005 /." [St. Lucia, Qld.], 2006. http://www.library.uq.edu.au/pdfserve.php?image=thesisabs/absthe19784.pdf.
Full text
4
Welge, Weston A., and Jennifer K. Barton. "In vivo endoscopic Doppler optical coherence tomography imaging of the colon." WILEY, 2017. http://hdl.handle.net/10150/623988.
Full textAbstract:
Background and ObjectiveColorectal cancer (CRC) remains the second deadliest cancer in the United States. Several screening methods exist; however, detection of small polyps remains a challenge. Optical coherence tomography (OCT) has been demonstrated to be capable of detecting lesions as small as 1mm in the mouse colon, but detection is based on measuring a doubling of the mucosa thickness. The colon microvasculature may be an attractive biomarker of early tumor development because tumor vessels are characterized by irregular structure and dysfunction. Our goal was to develop an endoscopic method of detecting and segmenting colon vessels using Doppler OCT to enable future studies for improving early detection and development of novel chemopreventive agents. MethodWe conducted in vivo colon imaging in an azoxymethane (AOM)-treated mouse model of colorectal cancer using a miniature endoscope and a swept-source OCT system at 1,040nm with a 16kHz sweep rate. We applied the Kasai autocorrelation algorithm to laterally oversampled OCT B-scans to resolve vascular flow in the mucosa and submucosa. Vessels were segmented by applying a series of image processing steps: (i) intensity thresholding; (ii) two-dimensional matched filtering; and (iii) histogram segmentation. ResultsWe observed differences in the vessels sizes and spatial distribution in a mature adenoma compared to surrounding undiseased tissue and compared the results with histology. We also imaged flow in four young mice (two AOM-treated and two control) showing no significant differences, which is expected so early after carcinogen exposure. We also present flow images of adenoma in a living mouse and a euthanized mouse to demonstrate that no flow is detected after euthanasia. ConclusionWe present, to the best of our knowledge, the first Doppler OCT images of in vivo mouse colon collected with a fiber-based endoscope. We also describe a fast and robust image processing method for segmenting vessels in the colon. These results suggest that Doppler OCT is a promising imaging modality for vascular imaging in the colon that requires no exogenous contrast agents.
5
Chen, Min Si. "Calibration and registration of an image enhanced surgical navigation system for endoscopic sinus surgery." Thesis, University of East Anglia, 2007. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.439900.
Full text
6
Phan, Tan Binh. "On the 3D hollow organ cartography using 2D endoscopic images." Electronic Thesis or Diss., Université de Lorraine, 2020. http://www.theses.fr/2020LORR0135.
Full textAbstract:
Les algorithmes de « Structure from motion » (SfM, structure reconstituée à l’aide du mouvement) représentent un moyen efficace de construction de surfaces 3D étendues à partir des images d'une scène acquise sous différents points de vue. Ces algorithmes déterminent simultanément le mouvement de la caméra et un nuage de points 3D se trouvant à la surface des objets à reconstruire. Les algorithmes SfM classiques utilisent des méthodes de détection et de mise en correspondance de points caractéristiques pour poursuivre les points homologues à travers les séquences d'images, chaque ensemble de points homologues correspondant à un point 3D à reconstruire. Les algorithmes SfM exploitent les correspondances entre des points homologues pour trouver la structure 3D de la scène et les poses successives de la caméra dans un repère monde arbitraire. Il existe différents algorithmes SfM de référence qui peuvent reconstruire efficacement différents types de scènes lorsque les images comportent suffisamment de textures ou de structures. Cependant, la plupart des solutions existantes ne sont pas appropriées, ou du moins pas optimales, lorsque les séquences d'images contiennent peu de textures. Cette thèse propose deux solutions de type SfM basées sur un flot optique dense pour reconstruire des scènes complexes à partir d’une séquence d’images avec peu de textures et acquises sous des conditions d'éclairage changeantes. Il est notamment montré comment un flot optique précis peut être utilisé de manière optimale grâce à une stratégie de sélection d'images qui maximise le nombre et la taille des groupes de points homologues tout en minimisant les erreurs de localisation des points homologues. La précision des méthodes de cartographie 3D est évaluée sur des fantômes avec des dimensions connues. L’intérêt et la robustesse des méthodes sont démontrés sur des scènes médicales complexes en utilisant un jeu de valeurs constantes pour les paramètres des algorithmes. Les solutions proposées ont permis de reconstruire des organes observés dans différents examens (surface épithéliale de la paroi interne de l'estomac, surface épithéliale interne de la vessie et surface de la peau en dermatologie) et dans diverses modalités (lumière blanche pour tous les examens, lumière vert-bleu en gastroscopie et fluorescence en cystoscopie)Structure from motion (SfM) algorithms represent an efficient means to construct extended 3D surfaces using images of a scene acquired from different viewpoints. SfM methods simultaneously determine the camera motion and a 3D point cloud lying on the surfaces to be recovered. Classical SfM algorithms use feature point detection and matching methods to track homologous points across the image sequences, each point track corresponding to a 3D point to be reconstructed. The SfM algorithms exploit the correspondences between homologous points to recover the 3D scene structure and the successive camera poses in an arbitrary world coordinate system. There exist different state-of-the-art SfM algorithms which can efficiently reconstruct different types of scenes, under the condition that the images include enough textures or structures. However, most of the existing solutions are inappropriate, or at least not optimal, when the sequences of images are without or only with few textures. This thesis proposes two dense optical flow (DOF)-based SfM solutions to reconstruct complex scenes using images with few textures and acquired under changing illumination conditions. It is notably shown how accurate DOF fields can be optimally used due to an image selection strategy which both maximizes the number and size of homologous point sets, and minimizes the errors in the homologous point localization. The accuracy of the proposed 3D cartography methods is assessed on phantoms with known dimensions. The robustness and the interest of the proposed methods are demonstrated on various complex medical scenes using a constant algorithm parameter set. The proposed solutions reconstructed organs seen in different medical examinations (epithelial surface of the inner stomach wall, inner epithelial bladder surface, and the skin surface in dermatology) and various imaging modalities (white light for all examinations, green-blue light in gastroscopy and fluorescence in cystoscopy)
7
Matthias, Steffen Felix [Verfasser]. "A flexible endoscopic structured light 3-D sensor: Design, models and image processing / Steffen Felix Matthias." Garbsen : TEWISS - Technik und Wissen GmbH, 2019. http://d-nb.info/1187277967/34.
Full text
8
Matthias, Steffen [Verfasser]. "A flexible endoscopic structured light 3-D sensor: Design, models and image processing / Steffen Felix Matthias." Garbsen : TEWISS - Technik und Wissen GmbH, 2019. http://nbn-resolving.de/urn:nbn:de:101:1-2019052812071833963147.
Full text
9
Cabras, Paolo. "3D Pose estimation of continuously deformable instruments in robotic endoscopic surgery." Thesis, Strasbourg, 2016. http://www.theses.fr/2016STRAD007/document.
Full textAbstract:
Connaître la position 3D d’instruments robotisés peut être très utile dans le contexte chirurgical. Nous proposons deux méthodes automatiques pour déduire la pose 3D d’un instrument avec une unique section pliable et équipé avec des marqueurs colorés, en utilisant uniquement les images fournies par la caméra monoculaire incorporée dans l'endoscope. Une méthode basée sur les graphes permet segmenter les marqueurs et leurs coins apparents sont extraits en détectant la transition de couleur le long des courbes de Bézier qui modélisent les points du bord. Ces primitives sont utilisées pour estimer la pose 3D de l'instrument en utilisant un modèle adaptatif qui prend en compte les jeux mécaniques du système. Pour éviter les limites de cette approche dérivants des incertitudes sur le modèle géométrique, la fonction image-position-3D peut être appris selon un ensemble d’entrainement. Deux techniques ont été étudiées et améliorées : réseau des fonctions à base radiale avec noyaux gaussiens et une régression localement pondérée. Les méthodes proposées sont validées sur une cellule expérimentale robotique et sur des séquences in-vivoKnowing the 3D position of robotized instruments can be useful in surgical context for e.g. their automatic control or gesture guidance. We propose two methods to infer the 3D pose of a single bending section instrument equipped with colored markers using only the images provided by the monocular camera embedded in the endoscope. A graph-based method is used to segment the markers. Their corners are extracted by detecting color transitions along Bézier curves fitted on edge points. These features are used to estimate the 3D pose of the instrument using an adaptive model that takes into account the mechanical plays of the system. Since this method can be affected by model uncertainties, the image-to-3d function can be learned according to a training set. We opted for two techniques that have been improved : Radial Basis Function Network with Gaussian kernel and Locally Weighted Projection. The proposed methods are validated on a robotic experimental cell and in in-vivo sequences
10
Kang, Wei. "3-D Volumetric Optical Coherence Tomography Imaging and Image Analysis of Barrett's Esophagus." Case Western Reserve University School of Graduate Studies / OhioLINK, 2011. http://rave.ohiolink.edu/etdc/view?acc_num=case1301501584.
Full text
11
Opilat, Victor [Verfasser]. "Swirl and blade wakes in the interaction between gas turbines and exhaust diffusers investigated by endoscopic particle image velocimetry / Victor Opilat." Hannover : Technische Informationsbibliothek und Universitätsbibliothek Hannover (TIB), 2012. http://d-nb.info/1024937984/34.
Full text
12
Ali, Sharib. "Total variational optical flow for robust and accurate bladder image mosaicing." Thesis, Université de Lorraine, 2016. http://www.theses.fr/2016LORR0006/document.
Full textAbstract:
La cystoscopie est l’examen de référence pour le diagnostic et le traitement du cancer de la vessie. Le champ de vue (CdV) réduit des endoscopes complique le diagnostic et le suivi des lésions. Les mosaïques d’images sont une solution à ce problème car elles visualisent des CdV étendus. Toutefois, pour la vessie, le mosaïque d’images est un véritable défi à cause du faible contraste dans les images, des textures peu prononcées, de la variabilité intra- et inter-patient et des changements d’illumination dans les séquences. Ce défi est également à relever dans d’autres modalités endoscopiques ou dans des scènes non médicales comme les vidéos sous-marines. Dans cette thèse, une énergie variationnelle totale a d’abord été minimisée à l’aide d’un algorithme primal-dual du premier ordre pour obtenir un flot optique fournissant une correspondance dense et précise entre les points homologues des paires d’images. Les correspondances sont ensuite utilisées pour déterminer les paramètres des transformations requises pour le placement des images dans le repère global de la mosaïque. Les méthodes proposées pour l’estimation du flot optique dense incluent un terme d’attache aux données qui minimise le nombre des vecteurs aberrants et un terme de régularisation conçu pour préserver les discontinuités du champ devecteurs. Un algorithme de flot optique qui est robuste vis-à-vis de changements d’illumination importants (et utilisable pour différentes modalités) a également été développé dans ce contexte. La précision et la robustesse des méthodes de recalage proposées ont été testées sur des jeux de données (de flot optique) publiquement accessibles et sur des fantômes de vessies et de la peau. Des résultats sur des données patients acquises avec des cystoscopes rigides et flexibles, en lumière blanche ou en fluorescence, montrent la robustesse des algorithmes proposés. Ces résultats sont complétés par ceux obtenus pour d’autres séquences endoscopiques réelles de dermatoscopie, de scène sous-marine et de données d’exploration spatialeCystoscopy is the reference procedure for the diagnosis and treatment of bladder cancer. The small field of view (FOV) of endoscopes makes both the diagnosis and follow-up of lesions difficult. Image mosaics are a solution to this problem since they visualize large FOVs of the bladder scene. However, due to low contrast, weak texture, inter- and intra-patient texture variability and illumination changes in these image sequences, the task of image mosaicing becomes challenging. This is also a major concern in other endoscopic data and non-medical scenes like underwater videos. In this thesis, a total variational energy has been first minimized using a first-order primal-dual algorithm in convex optimization to obtain optical flow vector fields giving a dense and accurate correspondence between homologous points of the image pairs. The correspondences are then used to obtain transformation parameters for registering the images to one global mosaic coordinate system. The proposed methods for dense optical flow estimation include a data-term which is modeled to minimize at most the outliers and a regularizer which is designed to preserve at their best the flow field discontinuities. An optical flow algorithm, which is robust to strong illumination changes (and which suits to different modalities), has also been developed in this framework. The registration accuracy and robustness of the proposed methods are tested on both publicly available datasets for optical flow estimation and on simulated bladder and skin phantoms. Results on patient data acquired with rigid and flexible cystoscopes under the white light and the fluorescence modality show the robustness of the proposed approaches. These results are also complemented with those of other real endoscopic data, dermoscopic sequences, underwater scenes and space exploration data
13
Winter, Marco. "Image-based incremental reconstruction, rendering and augmented visualization of surfaces for endoscopic surgery = Bildbasierte inkrementelle Rekonstruktion, Darstellung und erweiterte Visualisierung von Oberflächen für die endoskopische Chirurgie." kostenfrei, 2009. http://d-nb.info/1000613615/34.
Full text
14
Borchartt, Tiago Bonini. "Metodologia baseada em warping para correção de distorções em sistemas de endoscopia." Universidade Federal de Santa Maria, 2010. http://repositorio.ufsm.br/handle/1/5357.
Full textAbstract:
Coordenação de Aperfeiçoamento de Pessoal de Nível SuperiorImages captured in endoscopy examinations show some distortion, the radial is the most visible. The radial distortion appears in images due to lens used in endoscopes. When a doctor or researcher is analyzing a distorted image, he can not see the exact size of an organ, tumor or lesion, due the magnification in the center of the image and a contraction in the peripheral regions caused by such distortion. This paper aims to propose a new method for correction of radial distortion in endoscopic images. The proposed method is based on concepts of Morphing and Warping, which are techniques widely used in computer graphics to transform the image of one person to another or to cause objects deformations. The system presents the advantage of automatic application of these techniques, since the vast majority of correction algorithms need user interaction. The proposed method uses a pattern image, created for the calibration of the transformations that are applied to the images of endoscopy. The developed system receives the pattern image captured by endoscope, divides the image into a triangular mesh, make the matching of each triangle of the meshes and store the affine transformations of each triangular region of the mesh separately. After calibration, the affine transformations of each triangular region are used in real image of endoscopic examinations performed by the same endoscope used for calibration to correct the images. Finally, the method was compared with others in the literature and has been made quantitative and qualitative analysis with the results.
Imagens capturadas em exames de endoscopia apresentam algumas distorções, sendo a distorção radial a principal. A distorção radial surge na imagem devido ao sistema de lentes utilizado nos endoscópios. Quando um médico ou pesquisador está analisando uma imagem distorcida, não consegue perceber qual o tamanho exato de um órgão, lesão ou tumor, pois tal distorção causa uma ampliação no centro da imagem e uma contração nas regiões periféricas. Este trabalho tem como objetivo propor um novo método para a correção de distorções radiais em imagens de endoscopia. O método proposto baseia-se em conceitos de Morphing e Warping, que são técnicas bastante utilizadas em computação gráfica para transformar a imagem de uma pessoa em outra ou para causar deformações em objetos. O sistema apresentado tem como diferencial a aplicação automática destas técnicas, visto que a grande maioria de algoritmos que fazem uso delas funciona com interação do usuário. O método proposto utiliza uma imagem padrão, criada para a calibração das transformações que serão aplicadas nas imagens de exames de endoscopia. O sistema desenvolvido recebe a imagem padrão capturada por endoscópio, divide a imagem em uma malha triangular, faz a correspondência de cada triângulo desta malha com a malha da imagem padrão original e armazena as transformações afins em cada região da malha separadamente, transformando assim a imagem capturada na imagem original. Após a calibração, as mesmas transformações afins armazenadas para cada elemento triangular da malha são utilizadas em imagem reais de exames endoscópicos feitos pelo mesmo endoscópio utilizado na calibração, para corrigir a deformação. Por fim, o método desenvolvido foi comparado com outros da literatura e foram feitas análises quantitativas e qualitativas dos resultados obtidos.
15
Karvonen, Tuukka Matias. "Towards Visuocomputational Endoscopy: Visual Computing for Multimodal and Multi-Articulated Endoscopy." Kyoto University, 2017. http://hdl.handle.net/2433/227661.
Full text
16
Drozdzal, Michal. "Sequential image analysis for computer-aided wireless endoscopy." Doctoral thesis, Universitat de Barcelona, 2014. http://hdl.handle.net/10803/145614.
Full textAbstract:
Wireless Capsule Endoscopy (WCE) is a technique for inner-visualization of the entire small intestine and, thus, offers an interesting perspective on intestinal motility. The two major drawbacks of this technique are: 1) huge amount of data acquired by WCE makes the motility analysis tedious and 2) since the capsule is the first tool that offers complete inner-visualization of the small intestine, the exact importance of the observed events is still an open issue. Therefore, in this thesis, a novel computer-aided system for intestinal motility analysis is presented. The goal of the system is to provide an easily-comprehensible visual description of motility-related intestinal events to a physician. In order to do it, several tools based either on computer vision concepts or on machine learning techniques are presented.
A method for transforming 3D video signal to a holistic image of intestinal motility, called motility bar, is proposed. The method calculates the optimal mapping from video into image from the intestinal motility point of view.
To characterize intestinal motility, methods for automatic extraction of motility information from WCE are presented. Two of them are based on the motility bar and two of them are based on frame-per-frame analysis. In particular, four algorithms dealing with the problems of intestinal contraction detection, lumen size estimation, intestinal content characterization and wrinkle frame detection are proposed and validated.
The results of the algorithms are converted into sequential features using an online statistical test. This test is designed to work with multivariate data streams. To this end, we propose a novel formulation of concentration inequality that is introduced into a robust adaptive windowing algorithm for multivariate data streams. The algorithm is used to obtain robust representation of segments with constant intestinal motility activity. The obtained sequential features are shown to be discriminative in the problem of abnormal motility characterization.
Finally, we tackle the problem of efficient labeling. To this end, we incorporate active learning concepts to the problems present in WCE data and propose two approaches. The first one is based the concepts of sequential learning and the second one adapts the partition-based active learning to an error-free labeling scheme. All these steps are sufficient to provide an extensive visual description of intestinal motility that can be used by an expert as decision support system.
17
Emerson, Matthew J. (Matthew John) 1972. "A method to analyze the malignant potention of colorectal polyps using endoscopic images." Thesis, Massachusetts Institute of Technology, 1998. http://hdl.handle.net/1721.1/46171.
Full text
18
Bricault, Ivan. "Endoscopie bronchique assistée par ordinateur : résolution multi-niveaux d'un problème d'optimisation scène/modèle." Université Joseph Fourier (Grenoble), 1997. http://www.theses.fr/1997GRE10243.
Full textAbstract:
Cette thèse décrit des travaux relevant du domaine de la vision par ordinateur, motivés par une application médicale novatrice : l'endoscopie bronchique assistée par ordinateur. Ce projet consiste en une fusion de deux types de données médicales : d'une part, un examen scanner pré-opératoire de la cage thoracique (mettant en évidence une lésion suspecte à ponctionner), et d'autre part des images endoscopiques per-opératoires, acquises lors d'une exploration de l'intérieur de l'arbre bronchique. Ceci permet de fournir une assistance pour une ponction à travers la paroi bronchique. Les problèmes posés par cette application de réalité augmentée se situent dans le cadre classique d'une analyse scène/modèle : il s'agit de mettre en correspondance une scène (une vue endoscopique 2D) avec un modèle (les coupes scanner 3D), sans utiliser de localisateur externe. Pour cela, des méthodes originales de traitement d'images sont proposées ; elles permettent de résoudre les problèmes posés par la segmentation, le recalage et la reconstruction 3D des images à analyser. Ces méthodes utilisent, en particulier, des outils de morphologie mathématique, un algorithme de recalage sans fonctionnelle (par « demons ») et un « model-based shape-from-shading ». De plus, face aux difficultés spécifiques soulevées par les données à traiter, une approche multi-niveaux est introduite dans cette thèse. Cette stratégie tire profit, pour chaque niveau d'analyse, du maximum d'informations a priori disponibles. Finalement, les résultats présentés montrent qu'il est possible de localiser précisément la position de l'endoscope par rapport aux données scanner. Ainsi, l'ordinateur est capable de calculer, quasiment en temps réel, la vue endoscopique virtuelle qui correspond a la vue réelle du moment.
19
Mohammed, Noor. "Role of image-enhanced endoscopy in the assessment of inflammatory bowel disease." Thesis, University of Leeds, 2018. http://etheses.whiterose.ac.uk/22279/.
Full textAbstract:
Introduction: Ulcerative colitis (UC) which is a form of inflammatory bowel disease (IBD) is characterised by a relapsing and remitting disease course. Clinical disease activity indices (DAIs) are used to assess the severity of the disease activity relying solely on the clinical symptomatology of the patients. Non-invasive biomarkers help in assessment and possibly predicting the disease relapse. Although faecal calprotectin (FCP) is one such biomarker that is extensively researched, its accuracy in assessment and prediction of relapse is only modest. Similarly endoscopy in IBD with white light examination (WLE) alone is not accurate in either the assessment of disease activity or the prediction of disease course. Narrow band imaging (NBI) allows examination of the vasculature and pit pattern of the mucosa in greater detail than WLE. Patients with colonic IBD also have a higher risk of developing dysplasia or colorectal cancer (CRC). Chromoendoscopy (CE) provides a contrast enhancement and aids in highlighting the dysplastic areas. Aims: Primary aim of the research is to assess the role of advanced endoscopy, NBI and Chromoendoscopy (CE) in assessment of disease activity and dysplasia detection respectively in UC. The secondary aim is to assess the role of DAIs in assessment of disease activity, their correlation with endoscopic & histological markers and overall outcomes during the follow up period. Methods We performed two different experiments using advanced endoscopic techniques for this research project; one is in assessment of inflammatory activity and second is in detection of dysplasia in UC. We performed retrospective analysis of our practice to identify if white light alone predicts relapse in patients with quiescent UC. Based on our findings we devised a prospective observational study to look at the effect of adding NBI to WLE in assessment of disease activity in patients with UC of varying grades of severity. As newer generation of NBI (H290 series of Olympus KeyMed®) endoscopes were being introduced into the UK market at the time of the study, we compared the effect of NBI in three generations of endoscope (Q240, H260 and H290 series). We also assessed the use of Raman spectroscopy in endoscopic and histological assessment of inflammation in UC. In another retrospective study we looked at the uptake of chromoendoscopy in surveillance colonoscopies in UC. A randomised controlled study (RCT) was also designed to compare high definition WLE (HDWLE) to high definition CE (HDCE) in detecting dysplasia in UC surveillance. As part of relapse-prediction work we also conducted a meta-analysis of published RCTs on FCP to analyse its predictive capability in IBD. Results: In the retrospective analysis, we found that the presence of either Mayo Endoscopic Subscore >1 or Geboes score ≥2.1, increases the risk of relapse up to 6 times in the subsequent twelve months period. In our comparative study of NBI in three different generations of endoscopes, we demonstrated that NBI is superior to WLE in the assessment of the presence of blood. We also noticed a significant improvement in NBI in the newer generation of endoscopes (H290 and H260) compared to the earlier endoscopes (Q240). From the meta-analysis of RCTs we found that the FCP can predict disease flare with an accuracy of up to 75% only. In the observational study we determined that addition of NBI to WLE did not provide additional value in either assessment of disease activity or predicting relapse. Among the clinical disease activity indices (DAIs), the simple clinical colitis index or Walmsley index with score of ≥3 correlated well with endoscopy and histological findings. From the Raman spectroscopy study we identified the intensities of peaks (carotenoid and the phospholipids) that were statistically significantly different between the Raman spectra of the inflamed and quiescent colonic tissue. In our second retrospective analysis CE was found to be superior to WLE in detecting all dysplastic lesions and the detection of endoscopically visible flat non-polypoid lesions. However CE was performed only in one third of the study population. In the RCT we found that HDCE has an incremental yield of about 12.7% with a NNT of about 8, suggesting that HDCE would detect one additional patient with a dysplastic lesion for every 8 patients on whom this procedure is done. Conclusion: The thesis has shown that endoscopic biomarkers and FCP do not reliably predict relapse in UC. Addition of NBI does not confer added benefit in assessment of disease activity. HDCE is superior to HDWLE and should be adapted as a standard practice in surveillance of dysplasia in UC.
20
Huusmann, Johan. "Real-time tracking of instruments : Visualizing endoscope position on placental vasculature image." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-209940.
Full textAbstract:
Twin-to-twin transfusion syndrome (TTTS) is a complication of blood flow among fetuses sharing a single placenta. TTTS is associated with high mortality rates; however there is treatment available which significantly increases the rate of survival. The treatment procedure is although far from perfect. Limited by a narrow field of view, it is a challenging task for the surgeon to mentally visualize the vascular structures of the placenta while trying to navigate across the areas of interest. Previous research within both medical imaging and tracking technologies has been conducted but there is no perfect solution on how to solve these issues. This paper is part of a two-part project attempting to provide an application which can make the surgical procedure easier. The two parts are image stitching and real-time tracking, this paper focusing on the latter. This is done by choosing an appropriate tracking method which can provide location and orientation of a small sensor. The 3D data gathered from the sensor is processed by various transformations so that the bounding box of the camera movement can be mapped directly onto the image generated by the stitching process. The same transformations are applied to data collected from the sensor at a rate of 60 Hz, resulting in a responsive system. By comparing the x-value and y-value of a calculated point to the bounding box, this point can be converted to its corresponding pixel in the image. The system is responsive and by visually comparing the digital position in the image to its corresponding real world position it seems accurate enough, even though a few pixels misalignment will occur.Tvillingstransfusionssyndrom (TTTS) är en komplikation av blodflöde som kan uppstå hos foster som delar placenta. TTTS associeras medhöga dödstal, emellertid finns det behandlingar som signifikant ökar chanserna för fostrens överlevnad. Behandlingsprocessen är docklångt ifrån perfekt. Begränsad av ett smalt synfält är det en utmanande uppgift för kirurgen att mentalt föreställa sig placentansvaskulärsystem samtidigt som denne försöker att navigera mellan alla intresseområden. Forskning inom både bildbehandling ochspårningsteknologier är inget främmande men det finns ännu ingen självklar lösning på dessa problem. Den här rapporten är en del av etttvåstegsprojekt vars mål är att framställa en applikation som kan underlätta behandlingen. De två delarna är image stitching ochrealtidsspårning, där den här rapporten fokuserar på det sistnämnda. Detta görs genom att välja en lämplig spårningsmetod som kan mätabåde position samt orientering av en sensor. 3D-datan från sensorn behandlas av olika matematiska transformationer så att denomskrivande rektangeln av kamerans rörelser kan placeras på bilden erhållen från stitchingprocessen. På samma sätt behandlas deninformation som hämtas från sensorn i realtid med en frekvens på 60 Hz, vilket resulterar i ett snabbreagerande system. Genom att jämförax-värde och y-värde från en beräknad punkt med den omskrivande rektangeln, kan den här punkten översättas till sin motsvarande pixel ibilden. Systemet reagerar snabbt på indata och genom att visuellt jämföra den digitala positionen i bilden mot den motsvarande positionen iden riktiga världen ger systemet ett tillfredställande resultat, även om punkten kommer att ha ett par pixlars felmarginal.
21
Granado, Talita Conte. "Narrow-Band Imaging (NBI) for endoscopic capsules: optical filters on light source or on imager?" Universidade de São Paulo, 2017. http://www.teses.usp.br/teses/disponiveis/18/18152/tde-17082017-144715/.
Full textAbstract:
The Narrow-Band Imaging (NBI) technique allows the detection of lesions not identified with white light. Medical studies revealed that the wavelengths of 415 nm and 540 nm of the electromagnetic spectrum correspond to the peaks of hemoglobin absorptions band. The wavelength of 415 nm is located in the blue region of the electromagnetic spectrum, allowing the visualization enhancement of superficial veins. Moreover, the wavelength of 540 nm is located in the green region of the spectrum, and it is related to the visualization of sub-epithelial vessels. Initially, this work aims the design, simulation, fabrication (as well as stablish all the ideal settings for the depositions) and characterization of optical filters for the wavelength around 415 nm and 540 nm, through the application of the Fabry-Perot principle. Additionally, this work aims the investigation of two hypotheses: the first one is test the optical filters on the image sensor, and the second one is to test them on the light sources, in order to determined which adaptation technique is better for improving the image contrast of the blood vessels.A técnica de Narrow-Band Imaging (NBI), ou imageamento por banda estreita, permite a detecção de lesões que não podem ser identificadas com a luz branca. Estudos clínicos revelaram que os comprimentos de onda de 415 nm e 540 nm do espectro eletromagnético correspondem aos picos de banda de absorção da hemoglobina. O comprimento de onda de 415 nm localiza-se na parte azul do espectro eletromagnético, o que permite uma melhor visualização de vasos superficiais. Além disso, o comprimento de onda 540 nm localiza-se na faixa verde do espectro e está relacionado com a visualização de vasos sub-epitheliais. O intuito deste trabalho é o projeto, simulação, fabricação (assim como estabelecer os parâmetros ideais para as deposições) e caracterização de filtros ópticos para os comprimentos de onda próximos de 415 nm e 540 nm, com aplicação do princípio físico de Fabry-Perot. Posteriormente, pretende-se investigar duas hipóteses: a primeira é a de testar os filtros ópticos no sensor de imagem, e o segundo é a de testá-los nas fontes de luz, para verificar qual técnica de adaptação seria melhor para aumentar o contraste entre os vasos sanguíneos.
22
Pu, Leonardo Zorrón Cheng Tao. "Comparação entre prótese plástica e metálica na paliação endoscópica da obstrução maligna da via biliar: revisão sistemática e metanálise baseadas em estudos randomizados." Universidade de São Paulo, 2016. http://www.teses.usp.br/teses/disponiveis/5/5168/tde-20062016-105345/.
Full textAbstract:
INTRODUÇÃO: A prótese biliar endoscópica é aceita em todo o mundo como a primeira escolha de tratamento paliativo na obstrução biliar maligna. Atualmente ainda persistem dois tipos de materiais utilizados em sua confecção: plástico e metal. Consequentemente, muitas dúvidas surgem quanto a qual deles é o mais benéfico para o paciente. Esta revisão reúne as informações disponíveis da mais alta qualidade sobre estes dois tipos de prótese, fornecendo informações em relação à disfunção, complicação, taxas de reintervenção, custos, sobrevida e tempo de permeabilidade; e pretende ajudar a lidar com a prática clínica nos dias de hoje. OBJETIVO: Analisar, através de metanálise, os benefícios de dois tipos de próteses na obstrução biliar maligna inoperável. MÉTODOS: Uma revisão sistemática de ensaios clínicos randomizados (RCT) foi conduzida, com a última atualização em março de 2015, utilizando EMBASE, CINAHL (EBSCO), Medline, Lilacs / Centro (BVS), Scopus, o CAPES (Brasil), e literatura cinzenta. As informações dos estudos selecionados foram extraídas tendo em vista seis desfechos: primariamente disfunção, taxas de reintervenção e complicações; e, secundariamente, custos, sobrevivência e tempo de permeabilidade. Os dados sobre as características dos participantes do RCT, critérios de inclusão e exclusão e tipos de próteses também foram extraídos. Os vieses foram avaliados principalmente através da escala de Jadad. Esta metanálise foi registrada no banco de dados PROSPERO pelo número CRD42014015078. A análise do risco absoluto dos resultados foi realizada utilizando o software RevMan 5, calculando as diferenças de risco (RD) de variáveis dicotômicas e média das diferenças (MD) de variáveis contínuas. Os dados sobre a RD e MD para cada desfecho primário foram calculados utilizando o teste de Mantel-Haenszel e a inconsistência foi avaliada com o teste Qui-quadrado (Chi2) e o método de Higgins (I2). A análise de sensibilidade foi realizada com a retirada de estudos discrepantes e a utilização do efeito aleatório. O teste t de Student foi utilizado para a comparação das médias aritméticas ponderadas, em relação aos desfechos secundários. RESULTADOS: Inicialmente foram identificados 3660 estudos; 3539 foram excluídos por título ou resumo, enquanto 121 estudos foram totalmente avaliados e foram excluídos, principalmente por não comparar próteses metálicas (SEMS) e próteses plásticas (PS), levando a treze RCT selecionados e 1133 indivíduos metanálise. A média de idade foi de 69,5 anos, e o câncer mais comum foi de via biliar (proximal) e pancreático (distal). O diâmetro de SEMS mais utilizado foi de 10 mm (30 Fr) e o diâmetro de PS mais utilizado foi de 10 Fr. Na metanálise, SEMS tiveram menor disfunção global em comparação com PS (21,6% versus 46,8% p < 0,00001) e menos reintervenções (21,6% versus 56,6% p < 0,00001), sem diferença nas complicações (13,7% versus 15,9% p = 0,16). Na análise secundária, a taxa média de sobrevida foi maior no grupo SEMS (182 contra 150 dias - p < 0,0001), com um período maior de permeabilidade (250 contra 124 dias - p < 0,0001) e um custo semelhante por paciente, embora menor no grupo SEMS (4.193,98 contra 4.728,65 Euros - p < 0,0985). CONCLUSÃO: SEMS estão associados com menor disfunção, menores taxas de reintervenção, melhor sobrevida e maior tempo de permeabilidade. Complicações e custos não apresentaram diferençaINTRODUCTION: Endoscopic stenting is accepted worldwide as the first choice palliative treatment for malignant biliary obstruction. There are still two types of materials currently being used, which are plastic and metal. Therefore, many doubts are raised as to which one is the most beneficial to the patient. This review gathers the highest quality information available about these two types of stent, giving information in regards to dysfunction, complication, reintervention rates, costs, survival, and patency time; and intends to help handle clinical practice nowadays. OBJECTIVE: To analyze through meta-analyses the benefits of two types of stents in the inoperable malignant biliary obstruction. METHODS: A systematic review of randomized clinical trials (RCT) was conducted, with the last update on March 2015, using EMBASE, CINAHL (EBSCO), MEDLINE, LILACS/CENTRAL (BVS), SCOPUS, CAPES (Brazil), and gray literature. Information of the selected studies was extracted in sight of six outcomes: primarily regarding dysfunction, reintervention and complication rates; and secondarily costs, survival, and patency time. The data about characteristics of trial participants, inclusion and exclusion criteria and types of stents were also extracted. The biases were mainly assessed through the Jadad scale. This meta-analysis was registered in the PROSPERO database by the number CRD42014015078. The analysis of the absolute risk of the outcomes was performed using the software RevMan 5, by computing risk differences (RD) of dichotomous variables and mean differences (MD) of continuous variables. Data on RD and MD for each primary outcome were calculated using the Mantel-Haenszel test and inconsistency was qualified and reported in Chisquared (Chi2) and the Higgins method (I2). Sensitivity analysis was performed withdrawing discrepant studies and using random effect. Student\'s t-test was used for the comparison of weighted arithmetic means regarding secondary outcomes. RESULTS: Initial searching identified 3660 studies; 3539 were excluded through title or abstract, while 121 studies were fully assessed and were excluded mainly because they did not compare Self Expanding Metal Stents (SEMS) and Plastic Stents (PS), leading to thirteen RCT selected and 1133 subjects meta-analyzed. The mean age was 69.5 years old, that were affected mostly by bile duct (proximal) and pancreatic tumors (distal). The preferred SEMS diameter used was the 10 mm (30 Fr) and the preferred PS diameter used was 10 Fr. In the meta-analysis, SEMS had lower overall stent dysfunction compared to PS (21.6% versus 46.8% p < 0.00001) and fewer reintervention (21.6% versus 56.6% p < 0.00001), with no difference in complications (13.7% versus 15.9% p=0.16). In the secondary analysis, the mean survival rate was higher in the SEMS group (182 versus 150 days - p < 0.0001), with a higher patency period (250 versus 124 days - p < 0.0001) and a similar cost per patient, although lower in the SEMS group (4193.98 versus 4728.65 Euros - p < 0.0985). CONCLUSION: SEMS are associated with lower stent dysfunction, lower reintervention rates, better survival, and higher patency time. Complications and costs do not show difference
23
França, Livia Gomes Pereira. "Endoscopia com magnificação de imagem, cromoscopia e uso do ácido acético no esôfago de Barrett." Universidade de São Paulo, 2004. http://www.teses.usp.br/teses/disponiveis/5/5154/tde-01112006-090231/.
Full textAbstract:
Esôfago de Barrett é definido como a substituição do epitélio escamoso normal por epitélio colunar com metaplasia intestinal especializada (MIE), tendo como causa a persistência do refluxo gastro-esofágico. Seu diagnóstico é baseado na identificação endoscópica e na confirmação histológica da presença de MIE. Esôfago de Barrett é a principal causa do desenvolvimento do adenocarcinoma esofágico. Aos pacientes com esôfago de Barrett é recomendada vigilância endoscópica com biópsias seriadas tentando-se diagnosticar, precocemente, lesões precursoras ou o adenocarcinoma em estágio precoce e factível de resposta à terapia. O aumento da incidência do adenocarcinoma tem contribuído para o estudo de novas técnicas endoscópicas visando melhorar a detecção destas lesões. Este estudo foi realizado objetivando-se avaliar a eficácia da cromoscopia com azul de metileno, associada a magnificação de imagem com ácido acético, na detecção de MIE, displasia e adenocarcinoma. Prospectivamente, 35 pacientes com diagnóstico de esôfago de Barrett em acompanhamento ambulatorial, com extensão superior a 2,0 cm, realizaram dois exames de endoscopia digestiva alta, sendo um convencional com biópsias seriadas e um segundo com aplicação de azul de metileno, seguida do ácido acético, magnificação de imagem e biópsias. Realizaram-se biópsias adicionais de qualquer alteração do relevo mucoso. A freqüência diagnóstica da metaplasia intestinal especializada foi de 71,4% e 77,1% para biópsias orientadas pelo método convencional e pelo método da cromoscopia/magnificação de imagem, respectivamente (p=0,41). Freqüência de displasia ou adenocarcinoma foi de 9% para as biópsias orientadas pelo método convencional e 6% para biópsias orientadas pela cromoscopia/magnifcação de imagem. Tanto os pacientes com displasia de alto grau quanto aqueles com adenocarcinoma apresentaram alterações em sua superfície mucosa visíveis em ambos os métodos endoscópicos. A sensibilidade e a especificidade da cromoscopia, quando avaliamos as áreas coradas em detectar MIE foi de 88% e 50%, respectivamente. A sensibilidade e a especificidade das áreas não coradas em detectar displasia e/ou adenocarcinoma foi de 75% e 100%, respectivamente. A sensibilidade e a especificidade da magnificação de imagem, quando avaliamos as áreas com padrão viliforme em detectar MIE foi 88% e 50%, respectivamente. Tanto a sensibilidade quanto a especificidade das áreas com padrão amorfo em detectar displasia e/ou adenocarcinoma foi de 100%. A sensibilidade e a especificidade da cromoscopia/magnificação de imagem, para padrão corado e viliforme, em detectar MIE foi de 83% e 50%, respectivamente. Já a sensibilidade e a especificidade das áreas não coradas e com padrão amorfo em detectar displasia e/ou adenocarcinoma teve seu cálculo prejudicado pela pequena amostra estudada. Na comparação dos dois métodos empregados, verificaram-se resultados similares na detecção de metaplasia intestinal, displasia e câncer. A realização de cromoscopia/magnificação de imagem proporcionou: alta sensibilidade e baixa especificidade na detecção da metaplasia intestinal especializada e baixa sensibilidade e alta especificidade na detecção de displasia ou adenocarcinoma. Alterações da superfície mucosa corresponderam as áreas neoplásicas.Barrett\'s esophagus is defined as the replacement of the normal squamous epithelium by columnar lined esophagus. The diagnosis requires endoscopically visible columnar lined esophagus and histologic identification of characteristic specialized intestinal-type metaplasia (SIM). Gastroesophageal reflux has been proposed as a risk factor for Barrett`s esophagus and this disease has been shown to be the main cause of esophageal adenocarcinoma. After the diagnosis of Barrett`s esophagus, endoscopy surveillance is recommended with multiple biopsies of the columnar lined esophagus at quadrants of 2 cm intervals to determine epithelial dysplasia or adenocarcinoma in early and curable stage. Due to the increase in the incidence of esophageal adenocarcinoma new techniques of endoscopic surveillance have been proposed. The aim of this study was to evaluate the efficacy of magnification chromoendoscopy with methylene blue and acetic acid for the detection of intestinal metaplasia, dysplasia and cancer. Prospectively, 35 patients with Barrett\'s esophagus extending for more than 2,0 cm, underwent two upper digestive endoscopy procedures, including one with conventional biopsies and other with chromoendoscopy using methylene blue and acetic acid instillation, magnification and biopsies. Biopsies were also taken from any suspicious mucosal area. The incidence of MIE were 71,4% e 77,1% from conventional biopsies and chromoendoscopy/magnification, respectively. Dysplasia and adenocarcinoma were diagnosed in 9% and 6% throught conventional biopsies and chromoendoscopy/magnification, respectively. Patients with high grade dysplasia or adenocarcinoma revealed mucosal alterations. The sensitivity and specificity rates for chromoendoscopy for stained areas for MIE were 88% and 50%, respectively. The sensitivity and specificity rates for non stained areas for dysplasia and cancer were 75% and 100%, respectively. The sensitivity and specificity rates for magnification for villous areas for MIE were 88% and 50%, respectively. The sensitivity and specificity rates for distorted areas for dysplasia and cancer were 100%. The sensitivity and specificity rates for chromoendoscopy/magnification (for stained and villous areas) for MIE were 83% and 50%, respectively. The sensitivity and specificity rates for non stained and distorted areas couldn?t be evaluated due to the small number of patients. In conclusion, results of the two methods were similar in detecting intestinal metaplasia, dysplasia and cancer. The chromoendoscopy/magnification method procedure provides high sensitivity and low specificity rates in detecting MIE and low sensitivity and high specificity rates in detecting dysplasia and adenocarcinoma. Alterations in the mucosa corresponded to cancer and dysplasia.
24
Rottier, Christiane. "Etude expérimentale de l'influence des mélanges gazeux sur la combustion sans flamme." Phd thesis, INSA de Rouen, 2010. http://tel.archives-ouvertes.fr/tel-00557903.
Full textAbstract:
Une étude expérimentale de l'influence des mélanges gazeux sur le régime de combustion sans flamme a été menée sur l'installation pilote du CORIA, en collaboration avec GDF SUEZ. La première partie de cette étude a été consacrée à la caractérisation détaillée de ce régime de combustion particulier au méthane pur avec et sans préchauffage de l'air comburant. Des mesures locales de température et concentrations d'espèces stables ont été réalisées à l'aide de thermocouples à fil fin et sonde de prélèvement. Une attention particulière a aussi été portée au développement et l'adaptation de techniques d'imagerie sur ce type de four : l'imagerie de chimiluminescence OH* pour la visualisation des zones de réaction et la PIV endoscopique afin d'obtenir des champs de vitesse de grandes dimensions malgré le fort confinement à haute température. L'analyse des résultats obtenus a permis de mettre en évidence le rôle principal de l'aérodynamique des jets turbulents de réactifs dans le four assurant l'obtention et la stabilisation de ce régime de combustion massivement diluée. Dans la seconde partie de cette étude, la faisabilité de l'utilisation d'hydrogène dans un four pilote fonctionnant en régime de combustion sans flamme a été démontrée. On retrouve toutes les caractéristiques intrinsèques à ce régime de combustion en termes de forte efficacité énergétique (lors du préchauffage de l'air) et très faibles émissions polluantes (CO et NOx) de ce régime massivement dilué, associé à la réduction des émissions de CO2 avec l'augmentation de la teneur en hydrogène dans le combustible. En fonctionnement à l'hydrogène pur et sans préchauffage de l?air, le four n?émet plus aucune espèce carbonée et quasiment pas de NOx ; on se rapproche d'un four à "zéro émission".
25
Nawarathna, Ruwan D. "Detection of Temporal Events and Abnormal Images for Quality Analysis in Endoscopy Videos." Thesis, University of North Texas, 2013. https://digital.library.unt.edu/ark:/67531/metadc283849/.
Full textAbstract:
Recent reports suggest that measuring the objective quality is very essential towards the success of colonoscopy. Several quality indicators (i.e. metrics) proposed in recent studies are implemented in software systems that compute real-time quality scores for routine screening colonoscopy. Most quality metrics are derived based on various temporal events occurred during the colonoscopy procedure. The location of the phase boundary between the insertion and the withdrawal phases and the amount of circumferential inspection are two such important temporal events. These two temporal events can be determined by analyzing various camera motions of the colonoscope. This dissertation put forward a novel method to estimate X, Y and Z directional motions of the colonoscope using motion vector templates. Since abnormalities of a WCE or a colonoscopy video can be found in a small number of frames (around 5% out of total frames), it is very helpful if a computer system can decide whether a frame has any mucosal abnormalities. Also, the number of detected abnormal lesions during a procedure is used as a quality indicator. Majority of the existing abnormal detection methods focus on detecting only one type of abnormality or the overall accuracies are somewhat low if the method tries to detect multiple abnormalities. Most abnormalities in endoscopy images have unique textures which are clearly distinguishable from normal textures. In this dissertation a new method is proposed that achieves the objective of detecting multiple abnormalities with a higher accuracy using a multi-texture analysis technique. The multi-texture analysis method is designed by representing WCE and colonoscopy image textures as textons.
26
Lima, Sérgio Miguel Laranjeira. "Estudo de algoritmos para detectar pólipos em vídeo de endo-cápsula." Master's thesis, Universidade de Aveiro, 2008. http://hdl.handle.net/10773/2052.
Full textAbstract:
Mestrado em Engenharia Electrónica e TelecomunicaçõesA cápsula endoscópica está disponível para diagnóstico desde 2001, altura em que recebeu a aprovação da Food Drug and Administration (FDA) e a certificação CE. A sua utilização está a crescer criando um novo mercado para ferramentas tecnológicas de detecção automática de eventos, de forma a diminuir a necessidade de visualização do exame completo por parte dos médicos. O primeiro objectivo a extrair deste trabalho foi o desenvolvimento de uma ferramenta de software de catalogação de imagem de cápsula endoscópica para obter um conjunto de dados bem anotado para ajudar no desenvolvimento de algoritmos computacionais de ajuda ao diagnóstico automático. Um segundo objectivo deste trabalho foi a validação de duas metodologias de análise de textura aplicadas com o intuito de detectar eventos em vídeo endoscópico. Os resultados obtidos demonstram a dificuldade de utilização de tais meios para a detecção dos referidos eventos em vídeo de cápsula endoscópica. ABSTRACT: The endoscopic capsule is available for medical use since 2001, when FDA and CE gave their approval as means to diagnose gastrointestinal diseases. Its exponential use is creating a new market for computational tools that can detect events automatically. Therefore aiding doctors on diagnosing exams. The main goal of this work was the creation of a software tool for catalog images from endoscopic capsule video, obtaining a well annotated dataset for aiding the development of computer aided diagnosis algorithms. The next objective was the validation of two methodologies of image texture analysis applied and implemented to detect abnormal events on endoscopic video. The results had shown the difficulty of such means to detect those events using endoscopic capsule video.
27
Gómez-Mendoza, Juan Bernardo. "A contribution to mouth structure segmentation in images towards automatic mouth gesture recognition." Phd thesis, INSA de Lyon, 2012. http://tel.archives-ouvertes.fr/tel-00770660.
Full textAbstract:
This document presents a series of elements for approaching the task of segmenting mouth structures in facial images, particularly focused in frames from video sequences. Each stage is treated separately in different Chapters, starting from image pre-processing and going up to segmentation labeling post-processing, discussing the technique selection and development in every case. The methodological approach suggests the use of a color based pixel classification strategy as the basis of the mouth structure segmentation scheme, complemented by a smart pre-processing and a later label refinement. The main contribution of this work, along with the segmentation methodology itself, is based in the development of a color-independent label refinement technique. The technique, which is similar to a linear low pass filter in the segmentation labeling space followed by a nonlinear selection operation, improves the image labeling iteratively by filling small gaps and eliminating spurious regions resulting from a prior pixel classification stage. Results presented in this document suggest that the refiner is complementary to image pre-processing, hence achieving a cumulative effect in segmentation quality. At the end, the segmentation methodology comprised by input color transformation, preprocessing, pixel classification and label refinement, is put to test in the case of mouth gesture detection in images aimed to command three degrees of freedom of an endoscope holder.
28
Ramos, Danusa de Souza. "Elastografia hepatoesplênica para predizer varizes esofágicas em pacientes com hipertensão portal não cirrótica: estudo de acurácia diagnóstica." Universidade de São Paulo, 2018. http://www.teses.usp.br/teses/disponiveis/5/5168/tde-07112018-114450/.
Full textAbstract:
Introdução: elastografia ultrassônica é um método não invasivo validado e rotineiro para a determinação indireta do grau de fibrose hepática e em investigação para predizer a presença de varizes esofágicas. Entretanto, a elastografia foi validada somente em doenças que evoluem para cirrose. Na revisão de literatura que realizamos, observamos que há escassez de estudos de acurácia diagnóstica em pacientes com hipertensão portal não cirrótica. Objetivos: avaliar a acurácia diagnóstica das técnicas de elastografia hepatoesplênica (transitória por FibroScan e ARFI) para predizer a presença de varizes esofágicas e se as varizes são de risco de sangramento em pacientes com hipertensão portal não cirrótica. Avaliar a concordâncias das duas técnicas e correlacioná-las com outros índices (plaquetas/baço, APRI e FIB-4). Métodos: Foram incluídos pacientes com diagnóstico confirmado das seguintes condições: oclusão da veia porta extra-hepática, esquistossomose mansônica, hipertensão portal não cirrótica idiopática e fibrose hepática congênita. A endoscopia digestiva alta foi considerada como marcador da presença de hipertensão portal clinicamente significante. Critérios de inclusão: idade acima de um ano; diagnóstico etiológico definido; concordância do paciente ou responsável legal em participar do estudo. Critérios de exclusão: cirrose, confirmada pela combinação de critérios diagnósticos clínicos, de imagem e laboratoriais ou pela biópsia hepática quando o resultado estivesse disponível; hipertensão portal pós sinusoidal; condições que impeçam tecnicamente a realização da elastografia (ascite volumosa e insuficiência cardíaca); esplenectomia; gestação; carcinoma hepatocelular avançado. O desenho do estudo foi prospectivo, transversal, de acordo com a metodologia STARD, avaliando a acurácia, sensibilidade, especificidade, valores preditivos positivos e negativos e razões de verossimilhança positiva e negativa. Procedimentos no estudo: consulta aos dados de prontuário; ultrassonografia abdominal e elastografia hepatoesplênica com os equipamentos/métodos FibroScan e ARFI. Os pontos de corte foram determinados por curva ROC. Resultados: os valores de elastografia transitória hepática por FibroScan foram de 5,91 ± 1,87 kPa na oclusão da veia porta extra-hepática, 8,89 ± 3,96 kPa na esquistossomose, 10,60 ± 3,89 kPa na hipertensão portal não cirrótica idiopática e 10,30 ± 4,14 kPa na fibrose hepática congênita, enquanto os valores de ARFI foram de 1,27 ± 0,23 m/s; 1,35 ± 0,45 m/s; 1,43 ± 0,40 m/s; 1,55 ± 0,39 m/s; respectivamente. Os valores de elastografia transitória esplênica por FibroScan foram de 60,82 ± 20,56 kPa na oclusão da veia porta extra-hepática, 54,16 ± 22,94 kPa na esquistossomose, 52,64 kPa ± 21,97 kPa na hipertensão portal não cirrótica idiopática e 48,50 ± 24,86 kPa na fibrose hepática congênita, enquanto os valores de ARFI foram de 3,22 ± 0,62 m/s; 3,01 ± 0,74 m/s; 2,86 ± 0,53 m/s; 2,80 ± 0,55 m/s; respectivamente. A elastografia esplênica por FibroScan com ponto de corte 65,1 kPa apresentou acurácia de 0,62 (intervalo de confiança 95% 0,46-0,78; p=0,121) para presença de varizes. Para predizer varizes de alto risco de sangramento, o melhor ponto de corte foi 40,05 kPa, que apresentou acurácia de 0,63 (intervalo de confiança 95% 0,52-0,76; p=0,016). A elastografia esplênica ARFI com ponto de corte de 2,67m/s apresentou acurácia de 0,64 (intervalo de confiança 95%, 0,50-0,78; p=0,065) para presença de varizes. O melhor ponto de corte para predizer varizes de alto risco de sangramento com esse método foi de 3,17m/s, que apresentou acurácia de 0,61 (intervalo de confiança 95%, 0,51- 0,71; p=0,033). Conclusões: métodos de elastografia esplênica apresentaram uma acurácia moderada e valor preditivo positivo elevado para diagnosticar presença de varizes. A elastografia transitória esplênica por FibroScan quando associada à razão plaqueta/baço apresentou acurácia moderada com especificidade alta para predizer varizes de alto risco de sangramento. Entretanto, considerável superposição de valores foi observada entre pacientes com e sem varizes esofagianas, o que limita a aplicação a utilidade clínica do métodoBackground and rationale: transient elastography is a noninvasive, validated, method allowing evaluation of liver fibrosis by measurement of liver stiffness and under investigation to predict the presence of esophageal varices. However, elastography has been validated only in diseases that progress to cirrhosis. In a literature review we found few studies on diagnostic accuracy in patients with non-cirrhotic portal hypertension. Aims: to evaluate the accuracy of hepatosplenic elastography (FibroScan and ARFI) to predict the presence of esophageal varices and whether varices are at risk of bleeding in patients with non-cirrhotic portal hypertension. To evaluate the concordances of the two techniques and correlate them with other indexes such as the platelet /spleen diameter ratio, APRI and FIB-4. Methods: patients with confirmed diagnosis of the following conditions were included: extrahepatic portal vein occlusion, schistosomiasis, idiopathic non-cirrhotic portal hypertension and congenital hepatic fibrosis. Upper digestive endoscopy was considered as a marker of the presence of clinically significant portal hypertension. Inclusion criteria: age above one year; defined etiological diagnosis; agreement of the patient or legal guardian to participate in the study. Exclusion criteria: cirrhosis confirmed by combination of clinical, imaging and laboratory diagnostic criteria or by liver biopsy when the result was available; post sinusoidal portal hypertension; conditions that technically preclude the performance of elastography (massive ascites and heart failure); splenectomy; pregnancy; advanced hepatocellular carcinoma. The study design was prospective, transversal, according to the STARD methodology, evaluating the accuracy, sensitivity, specificity, positive and negative predictive values and positive and negative likelihood ratios. The procedures of the study were: review of medical records data, abdominal ultrasonography and hepatosplenic elastography with FibroScan and ARFI equipment / methods. Cut-off points for elastography were determined by ROC curves. Results: liver stiffness measurement by FibroScan were 5.91 ± 1.87 kPa in extrahepatic portal vein occlusion, 8.89 ± 3.96 kPa in schistosomiasis, 10.60 ± 3.89 kPa in portal hypertension non-cirrhotic idiopathic and 10.30 ± 4.14 kPa in congenital hepatic fibrosis, whereas by ARFI were 1.27 ± 0.23 m/s; 1.35 ± 0.45 m/s; 1.43 ± 0.40 m/s; 1.55 ± 0.39 m/s; respectively. Spleen stiffness measurement by FibroScan were 60.82 ± 20.56 kPa in extrahepatic portal vein occlusion, 54.16 ± 22.94 kPa in schistosomiasis, 52.64 ± 21.97 kPa in idiopathic non-cirrhotic portal hypertension, and 48.50 ± 24.86 kPa in congenital hepatic fibrosis, while by ARFI were 3.22 ± 0.62 m/s; 3.01 ± 0.74 m/s; 2.86 ± 0.53 m/s; 2.80 ± 0.55 m/s; respectively. Liver stiffness measurement by FibroScan with a cut-off of 65.1 kPa had an accuracy of 0.62 (95%confidence interval, 0.46-0.78, p=0.121) for the presence of esophageal varices. The best cut-off point for predicting the presence of varices at high risk of bleeding was 40.05 kPa (accuracy, 0.63, 95% confidence interval, 0.52-0.76, p = 0.016). The spleen stiffness measurement by ARFI with a cut-off of 2.67 m/s showed (accuracy, 0.64, 95% confidence interval, 0.50-0.78, p=0.065) for the presence of esophageal varices. The best cut-off point for predicting the presence of varices at high risk of bleeding was 3.17 m/s (accuracy, 0.61, 95% confidence interval, 0.51-0.71, p=0.033) for varices at high risk of bleeding. Conclusions: spleen stiffness measurement by transient elastography (FibroScan and ARFI) presented a moderate accuracy and a high positive predictive value to diagnose the presence of esophageal varices. Spleen stifness by FibroScan when associated with platelet/spleen diameter ratio, there is a moderate accuracy with a high specificity to predict varices at high risk of bleeding. However, overlapping values between patients with or without varices was high and this precludes the clinical applicability of these methods
29
Bernhardt, Sylvain. "Automatic localization of endoscope in intraoperative CT image : a simple approach to augmented reality guidance in laparoscopic surgery." Thesis, Strasbourg, 2016. http://www.theses.fr/2016STRAD008/document.
Full textAbstract:
Au cours des dernières décennies, la chirurgie mini invasive a progressivement gagné en popularité face à la chirurgie ouverte, grâce à de meilleurs bénéfices cliniques. Cependant, ce type d'intervention introduit une perte de vision directe sur la scène pour le chirurgien. L'introduction de la réalité augmentée en chirurgie mini invasive semble être une solution viable afin de remédier à ce problème et a donc été activement considérée par la recherche. Néanmoins, augmenter correctement une scène laparoscopique reste difficile à cause de la non-rigidité des tissus et organes abdominaux. En conséquence, la littérature ne fournit pas d'approche satisfaisante à la réalité augmentée en laparoscopie, car de telles méthodes manquent de précision ou requièrent un équipement supplémentaire, contraignant et onéreux. Dans ce contexte, nous présentons un nouveau paradigme à la réalité augmentée en chirurgie laparoscopique. Se reposant uniquement sur l'équipement standard d'une salle opératoire hybride, notre approche peut fournir la relation statique entre l'endoscope et un scan intraopératoire 3D. De nombreuses expériences sur un motif radio-opaque montrent quantitativement que nos augmentations sont exactes à moins d'un millimètre près. Des tests sur des données in vivo consolident la démonstration du potentiel clinique de notre approche dans plusieurs cas chirurgicaux réalistesOver the past decades, minimally invasive surgery has progressively become more popular than open surgery thanks to greater clinical benefits. However, this kind of intervention introduced a loss of direct vision upon the scene for the surgeon. Introducing augmented reality to minimally invasive surgery appears to be a viable solution to alleviate this drawback and has thus been an attractive topic for the research community. Yet, correctly augmenting a laparoscopic scene remains challenging, due to the non-rigidity of abdominal tissues and organs. Therefore, the literature does not report a satisfactory approach to laparoscopic augmented reality, as such methods lack accuracy or require expensive and impractical additional equipment. In light of this, we present a novel paradigm to augmented reality in abdominal minimally invasive surgery. Based only on standard hybrid operating room equipment, our approach can provide the static relationship between the endoscope and an intraoperative 3D scan. Extensive experiments on a radio-opaque pattern quantitatively show that the accuracy of our augmentations is less than one millimeter. Tests on in vivo data further demonstrates the clinical potential of our approach in several realistic surgical cases
30
Guímaro, Joana de Oliveira Marques. "Doença inflamatória crónica do intestino: estudo comparativo entre a imagem endoscópica e o resultado histopatológico em 73 canídeos." Bachelor's thesis, Universidade Técnica de Lisboa. Faculdade de Medicina Veterinária, 2010. http://hdl.handle.net/10400.5/1711.
Full textAbstract:
Dissertação de Mestrado Integrado em Medicina VeterináriaA doença inflamatória crónica do intestino (Inflammatory Bowel Disease - IBD) é um termo que designa um conjunto de entidades clínicas, caracterizadas por sinais gastrointestinais persistentes ou recorrentes em que haja evidência histológica, no material recolhido através de biopsia, de infiltração de células inflamatórias de várias origens a nível da lâmina própria, podendo, por vezes, estender-se à submucosa. A IBD é considerada actualmente uma das causas mais comuns de vómito e diarreia crónicas do cão, apesar de pouca informação estar disponível sobre alterações endoscópicas e histopatológicas. Neste trabalho pretendeu-se avaliar se existe alguma relação entre a gravidade das alterações endoscópicas e a classificação histológica. Com este objectivo foram avaliados 73 cães do Hospital Escolar de animais de companhia da Universidade de Viena, diagnosticados com IBD por meio de análise histológica. A cada cão foi atribuído um valor de 0 a 3, por ordem crescente de gravidade (sem alterações ou grau 0; alteração ligeira ou grau 1; moderada ou grau 2; e grave ou grau 3), para a endoscopia e histopatologia. Estes valores foram correlacionados e os resultados mostraram algum grau de associação entre a gravidade da imagem endoscópica e a gravidade histológica em relação ao intestino delgado (=0,323 com p <0,01), mas não o evidenciaram no estômago. Neste trabalho também se verificou que a maioria dos animais com IBD tem o intestino delgado afectado e a classificação em grau 2. O diagnóstico de IBD permanece subjectivo, sendo baseado sobretudo na celularidade da lâmina própria. Assim, a caracterização das biopsias é um componente muito importante para o diagnóstico e terapêutica da IBD. A falta de critérios standard que padronizem as alterações morfológicas e inflamatórias, dificulta a comparação entre estudos e nalguns casos limita mesmo a sua realização. Este trabalho vem reforçar a necessidade de uma padronização da doença tanto a nível clínico, como endoscópico e histológico.
ABSTRACT - CANINE IBD: COMPARATIVE STUDY BETWEEN ENDOSCOPIC EVALUATION AND HISTOPATHOLOGIC FINDINGS IN 73 DOGS - The term canine inflammatory bowel disease (IBD) is used to designate a group of clinical entities characterized by persistent or recurrent gastrointestinal signs where there is histological evidence, in biopsy material, of inflammatory cell infiltrate of various origins in the lamina propria mucosae, sometimes reaching the submucosa. Nowadays, IBD is considered one of the most common causes of vomit and chronic diarrhea in dogs, yet little information about endoscopic and histopathological changes is available. This study proposed to evaluate the relation between the severity of endoscopic lesions and their histological classification. For this purpose 73 dogs diagnosed with IBD by histological analysis at the Small Animals Teaching Hospital of the Vienna University were included. Each dog was given a value between 0 and 3 for endoscopic and histopathological lesions, by ascending severity (no changes or grade 0; slight changes or grade 1; moderate or grade 2; and severe or grade 3). These values were tested for statistic relationship and the results show association between endoscopic and histopathological values in the small intestine (=0,323; p <0,01), but not in the stomach. It was also possible to verify that the small intestine was the major affected organ and the changes were mainly classified as grade 2. The diagnosis of IBD remains subjective and thus the characterization of biopsies based on the cellularity of the lamina propria is important for both the diagnosis and the therapeutic of this disease. The lack of standard criteria for morphological and inflammatory changes makes it difficult, or even impossible, to compare between different studies. The results from this study reinforce the need to standardize this disease both at the clinical level, as well as the endoscopic and histopathological levels.
31
Chen, Hou Chuan, and 陳厚全. "Registration of Bronchoscope Image and CT Virtual Endoscopic Image." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/k3t579.
Full text
32
Alves, Ana Priscila Vieira. "Endoscopic image analysis of aberrant crypt foci." Dissertação, 2011. http://hdl.handle.net/10216/61739.
Full text
33
TANG, ZHENG-YUAN, and 唐政元. "Color endoscopic image analysis for auxiliary diagnosis." Thesis, 1991. http://ndltd.ncl.edu.tw/handle/26560688850950936164.
Full text
34
Alves, Ana Priscila Vieira. "Endoscopic image analysis of aberrant crypt foci." Master's thesis, 2011. http://hdl.handle.net/10216/61739.
Full text
35
Liu, Chun-Yen, and 劉俊延. "3D Calibration and Reconstruction from Endoscopic Image Sequence." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/92688007503768048910.
Full textAbstract:
碩士國立成功大學
資訊工程學系碩博士班
91
Although endoscope was invented long ago, it has become popular and massively utilized recently. Endoscopes are usually equipped with wide-angle lens for obtaining a larger field of view through a narrow cut on humans’ body. Although more information could be obtained, the acquired images suffer from the barrel shape distortion. In addition, the three-dimensional (3-D) information is usually not available from the endoscopic images, and the surgeons need to imagine the 3-D geometry based on 2-D image variations. To overcome these disadvantages and provide a computer-aided system for physicians, in this thesis we propose a complete system that can correct the barrel shape distortion in endoscopic image sequence and reconstruct 3-D object models by utilizing a set of tracked points from the endoscopic image sequence. This system can be separated into three parts: the automatic distortion correction, the feature extraction and tracking, and the 3-D reconstruction. The automatic distortion correction mechanism corrects distorted images by using a calibration dot pattern and a simple mathematical model. It needs no prior knowledge about the optics of endoscopes. The distortion parameters and distortion center will be obtained and the distorted images can be corrected by these parameters. For a particular endoscope, this procedure only needs to be performed once. After distortion correction, the feature extraction and tracking procedure is applied. This procedure is revised from the Kanade-Lucas-Tomasi (KLT) feature tracker. We propose several modifications to adapt the KLT tracker to endoscopic image sequence and design a motion restriction strategy to eliminate erroneous tracking. Adopt the factorization method for 3-D reconstruction. A measurement matrix consists of a set of tracked points is treated as the input for the factorization method. The matrix is decomposed into two sub-matrices, motion and shape. For visualizing object’s 3-D model, we use the Delaunay Triangulation to build the connective relationship between each 3-D point, and the 3-D model can be refined by re-meshing the coarse results of Delaunay Triangulation.
36
Chen, Yuen-Yuan, and 陳淵源. "The Identification and Analysis of Lesion in Endoscopic Image." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/77346151765325572242.
Full textAbstract:
碩士大葉大學
電機工程研究所
90
The main purpose of “the Identification and Analysis of Lesion in Endoscopic Image” is to provide information concerning identification of endoscopic lesions, by making use of the high speed computing capability of computers and taking the distorted images from wide angle lens, through adjusting programs and incorporating image processing techniques and knowledge. The main purpose of “the Identification and Analysis of Lesion in Endoscopic Image” is to make use of the high speed computing capability of computers, take the distorted images from wide angle lens , through adjusting programs and incorporating image processing techniques and knowledge, and provide information concerning identification of endoscopic lesions. The research concentrates on endoscopic images, establishing a complete image managing process which includes investigation of color model transformation, counting of histogram, selection of image filter, edge detect , region grow , conversion of binary image, and the application of morphology. By setting up regions with distinct differences before the image managing process, images are divided and a clear-cut boundary is formed to provide identification of lesions in endoscopic images. All the images used in this research are unprocessed images. Through the examination of computer vision and premium image processing procedures, lesions are correctly identified and used as references for doctors’ prescriptions. Key words: histogram, image filter, edge detection, region grow, binary image , morphology
37
Chen, Chun-Ju, and 陳俊儒. "Surgical Instrument Recognition and Tracking Using Endoscopic Image Sequences." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/sd977m.
Full textAbstract:
碩士國立交通大學
電控工程研究所
101
The objective of this study is to design an image tracking algorithm for the endoscopic system in Minimally Invasive Surgery (MIS). The endoscopic robot autonomously adjusts its pose according to the position of the instruments in image plane, and moves the endoscope to provide a suitable field of view. A method is proposed to identify the tip of instruments without using extra artificial markers. We suggest to use texture and geometric features of laparoscopic instruments and to adopt the spiking neural network approach for object detection. Affection of light change can be reduced. The size change problem and deformation of the instrument can be handled by the neural network. To enhance tracking performance, we further employ region of interest(ROI) and Kalman filter to the neuro-based tracker. For the tracking control of surgical instrument, we propose to set a buffer zone in the center of the image frame to avoid redundant movement of the camera. In this way, the endoscopic system provides a stable view while the robot is tracking surgical instruments. By using endoscopic images, a recognition rate above 91% has been achieved for surgical instruments. Practical experiments on Huatuo robot further validate the effectiveness of the developed image tracking methods.
38
Chen, Shih-Hua, and 陳世華. "Identification of Early Cancerous Lesion of Esophagus with Endoscopic Images by Multispectral Image Technique." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/8a8z6v.
Full textAbstract:
碩士國立中正大學
機電光工程研究所
103
This study presents a method to identify early esophageal cancer within endoscope using hyperspectral imaging technology. The research samples are three kinds of endoscopic images including white light endoscopic, chromoendoscopic, and narrow-band endoscopic images with different stages of pathological changes (normal, dysplasia, dysplasia - esophageal cancer, and esophageal cancer). Research is divided into two parts: first, we analysis the reflectance spectra of endoscopic images with different stages to know the spectral responses by pathological changes. Second, we identified early cancerous lesion of esophagus by principal component analysis (PCA) of the reflectance spectra of endoscopic images. Based on the results, the use of hyperspectral imaging technology in the early endoscopic esophageal cancer lesion image recognition helps clinicians quickly diagnose. We hope for the future to have a relatively large amount of endoscopic image by establishing a hyperspectral imaging database system developed in this study, so the clinician can take this repository more efficiently preliminary diagnosis.
39
Gibbs, Jason David Higgins William E. "Three dimensional route planning for medical image reporting and endoscopic guidance." 2008. http://etda.libraries.psu.edu/theses/approved/WorldWideIndex/ETD-2932/index.html.
Full text
40
Rai, Lav Higgins William E. "Fusion and registration of 3D medical image data and endoscopic video." 2008. http://etda.libraries.psu.edu/theses/approved/WorldWideIndex/ETD-2899/index.html.
Full text
41
Chien, Ta-Yuan, and 簡大淵. "Auto-Calibration, Reconstruction and Assessment of Clinical Lesions from Endoscopic Image Sequence." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/cnhr8a.
Full textAbstract:
碩士國立成功大學
資訊工程學系碩博士班
90
In the last 30 years, the progresses in optical engineering, computer science and electronic techniques have made the endoscopy an invaluable tool in both internal clinics and surgical operations. As its applications increase exponentially, it has even become a specialized division in the clinical medicine. The image analysis technique provides important aids to the processing of clinical endoscopic images. However, traditional image analyses emphasize the 2-D image distortion calibration and assessment for endoscopic images. In this thesis, we use the computer vision algorithm to reconstruct the 3-D model from the endoscopic image sequence, texture mapping with real images are then employed to enhance the visualization of the reconstructed tubular scene. For obtaining a larger field of view inside a small and narrow pipeline, the endoscope is usually equipped with wide-angle lens. Therefore, the acquired images are often with certain degrees of shape distortion. Before 3-D reconstruction, our system provides a fast mechanism for correcting the wide-angle lens distortion. Using a calibration pattern, the nonlinear distortion is corrected with a simple mathematic model for the endoscopic images. Once the endoscopic lens is calibrated, the same calibration parameters can be utilized repeatedly for the calibrated instrument. On the other hand, how to extract and track the correspondent features from the image sequence is one of the most important tasks in 3-D reconstruction. Our systems use the high-pass filter to extract the edge feature and the Kanade-Lucas-Tomasi (KLT) feature tracking algorithm to obtain the feature correspondences. The color information, zoom-out characteristic and distortion factor of endoscope image sequence are all taken into account for improving the feature tracking results. Thereafter, the multiple frame auto-calibration is used to obtain the camera parameters. The 3-D coordinates of the detected feature points are then computed from the multiple images to reconstruct the 3D scene inside the tubular structure. At last, texture mapping with real endoscopic images is adopted to visualize the realistic 3D scene inside the reconstructed tubular structure of the observed organ.
42
曾國揚. "The Design of Diagnosis System for Vocal Fold Vibrations in Endoscopic Image Series." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/58823237244634334197.
Full text
43
Vilaça, Jaime Daniel Pacheco Martinho. "Minimal invasive surgery: contribution of three dimensional image on single-site endoscopic surgery." Doctoral thesis, 2021. http://hdl.handle.net/1822/75788.
Full textAbstract:
Tese de doutoramento em MedicinaOs sistemas endoscópicos são usados em medicina ha mais de duzentos anos. Durante as três últimas décadas houve um esforço tecnológico considerável para desenvolver sistemas de imagem tridimensional para uso em cirurgia endoscópica. Os atuais sistemas disponíveis têm alta definição de imagem e são fáceis de usar, pois apenas necessitam que o cirurgião coloque uns óculos leves com lentes polarizadas. A cirurgia por acesso único apareceu no início deste milénio como uma proposta para diminuir ainda mais o trauma da cirurgia endoscópica e melhorar o resultado estético. Combinando este dois elementos, colocou-se a hipótese que a imagem 3D pudesse melhorar o desempenho na execução de procedimentos por acesso único. O principal objetivo desta tese é comparar em ambiente laboratorial o desempenho de principiantes e de cirurgiões experimentados na execução de cirurgia por acesso único usando sistemas de imagem 3D e 2D. Para cumprir este objetivo, dois estudos foram realizados, o primeiro usando exercícios validados com modelos inanimados e o segundo, um modelo orgânico. Vantagens na execução, aprendizagem e preferencia pelo sistema 3D foram significativas, e os resultados foram publicados. Para além disso, uma revisão baseada na evidencia foi feita para avaliar os possíveis benefícios clínicos da imagem 3D em cirurgia endoscópica de múltiplas portas. Ganhos na execução, curva de aprendizagem e redução do cansaço em favor do uso 3D foram encontrados. Nesta tese, o conhecimento destas áreas é revisto, a evolução tecnológica, as indicações para cirurgia de acesso único e as perspectivas futuras são criticamente analisadas. Conclui-se que a cirurgia por acesso único tem sido um motor de desenvolvimento na cirurgia minimamente invasiva e que a imagem 3D possivelmente beneficia a maioria dos executantes independentemente da sua experiência.
Endoscopic systems are more than 200 years old and have always relied on a two-dimensional image. In the late 1980´s, the advent of video-assisted surgery ushered in the era of minimally invasive surgery. The past three decades have seen a technological effort to provide endoscopic surgery with three-dimensional imaging. Currently 3D systems are high definition and easy to use with polarized and lightweight glasses. Single-site surgery is a proposal to further reduce trauma and improve the aesthetic result of endoscopic surgery, an option that started to develop at the beginning of this millennium. Combining these two elements, we hypothesize that a 3D imaging system can bring about better performance in executing single-site endoscopic procedures. The main objective of this thesis is to compare the performance of beginners and experts in a laboratory environment while conducting single-site surgery using a 3D system or a 2D system. To this end, two studies were carried out, using validated phantom exercises and an organic model. Benefits in performance, learning and user preference proved significant, and the results were published. Apart from this, an evidence-based review was carried out to assess the possible clinical benefits of 3D technology in multi-port endoscopic surgery. Gains in execution, learning curve and decreased workload were found. In this thesis, the knowledge of this area is reviewed, along with the technological evolution, the indications for single-site surgery and critical analysis of its foreseeable future implementation. We conclude that single-site surgery has been a driver for the development of minimally invasive surgery and that a 3D image likely benefits most performers regardless of their experience.
44
Hu, Yu-Chuang, and 胡祐莊. "The Application of Color and Texture Feature in Wireless Capsule Endoscopic Image for the Detection of Ulcer." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/81480709302838193186.
Full textAbstract:
碩士中原大學
生物醫學工程研究所
98
Capsule endoscopy compared with traditional colonoscopy is more easily observed irregularities in the small intestine, such as large yellow-green abnormal areas, bleeding and ulcer, the most disadvantage of wireless capsule endoscopy was that physicians will take 2-3 hours to diagnose 56,000 images for one patient so that it caused physicians heavy burden. Therefore, developing an automatic image recognition system of the capsule endoscope will reduce the physicians needed to view images of the number of checkup so that it can help physicians to save a lot of diagnostic time. In this study, the development of capsule endoscopy ulcer automatic image recognition system, the HSIC2 four kinds of color space conversion were used to highlight area on the image ulcers, gray histogram analysis and co-occurrence matrix feature so that those could be as texture parameters of the pathological symptoms of intestinal ulcers. First, doing an independent t-test analysis, the 35 parameters with distinguishable features were identified into support vector machines to conduct training and analysis. Among of those of parameters, HSIC2 of Common parameters were intensity, mean, variance, standard, skew and kurtosis; Non-common parameters H were energy and homogeneity；Non-common parameters S were energy and contrast；Non-common parameters I were energy, entropy, contrast and homogeneity；Non-common parameters C2 were entropy, contrast and homogeneity. The support vector machine was introduced to do training and analysis which used 520 images of ulcers and 3300 the normal image. And it could be read from a suspicious ulcer patients by simple user interface. A real case was used to test this system, the batch treating with picking up the complete patient information spent 8 minutes equally; however, it probably needs 150 minutes to read the AVI file according to the movie arrangement order and carry out ulcer's judgment principle. The result was that ulcer's judgment principle's accuracy was 82.87%, sensitivities was 94.94%, effectiveness was 81.20% and kappa value was 0.48. This study has established a set of automated ulcer detection system. This system could offer physicians on clinical diagnose ulcer besides the tradition by the naked eye interpret capsule endoscope phantom, also provide physicians a accurate and trustworthy the detection system. Therefore, this system could be a clinical diagnosis reference to physicians, and then increase efficiency of interpret time of capsule endoscope phantom.
45
LIN, SHU-JING, and 林叔靜. "Using Sparse Point Disparity Estimation and Superpixel Segmentation to Construct Dense Depth Map for Stereo Endoscopic Image." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/3b79sa.
Full text
46
Shih-LunChen and 陳世綸. "Adaptive Image Scalar and Corrector in Real-Time Video-Endoscopic System for Low Power Wireless Body Sensor Network." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/28256435973665275826.
Full text
47
"A study on computer-aided diagnosis for wireless capsule endoscopy images." Thesis, 2008. http://library.cuhk.edu.hk/record=b6074670.
Full textAbstract:
A feature extraction approach based on color is firstly proposed. Exploiting color histogram of an image, we can obtain distribution of different colors in images. Then we employ minimum distance classifier based on a new distance criterion to judge status of regions. In this section, we also validate benefits of WCE image enhancement to the proposed CAD system.Finally, we propose a new approach of chrominance moment as another kind of feature to discriminate normal regions from abnormal regions, which makes full use of Tchebichef polynomials and HSI color space. This new feature extraction scheme preserves illumination invariance without numerical approximation.
In conclusion, this thesis investigates several major and challenging problems such as WCE images enhancement and feature extractions in CAD for WCE images, and proposes several novel schemes to solve those problems. Extensive experiments are reported to demonstrate effectiveness of the proposed algorithms.
Next, we investigate automatic diseases detection for WCE images to partially solve the second problem. In this part we explore different features that are suitable for detection of diseases from three viewpoints, i.e., color, texture and chromaticity, because clinicians mainly use these clues to diagnose. At the same time, we introduce their corresponding classifiers.
We further advance a new texture feature extraction method, curvelet based local binary pattern, to detect abnormal regions in WCE images. This method takes advantage of curvelet transform and local binary pattern to describe textural features of WCE images.
Wireless capsule endoscopy (WCE) is a state-of-the-art technology to diagnose gastrointestinal (GI) tract diseases without invasiveness. However, there exist two major problems concerning WCE images. One problem is that many images for diagnosis have rather low contrast and are noisy, which causes difficulties to diagnosis and also to computer-aided detection, so it is necessary to enhance these images. The other one is that the viewing process of video data per examination is very time consuming because of the great amount of video data. If we can use computerized methods to help the physicians detect some abnormal regions in WCE images, it will certainly reduce the burden of physicians. Focusing on these two goals, this thesis mainly studies some main challenging problems in computer-aided diagnosis (CAD) system for WCE images. To solve the first problem, we put forward an adaptive curvature strength diffusion method to enhance WCE images. Based on local characteristics analysis of WCE images, we propose a new concept of curvature strength. Then, we employ curvature strength diffusion to enhance WCE images with an adaptive choice of conductance parameter. Finally, we extend the curvature strength diffusion to color space since WCE images are color images.
Li, Baopu.
Adviser: Max Q. H. Meng.
Source: Dissertation Abstracts International, Volume: 70-06, Section: B, page: 3640.
Thesis (Ph.D.)--Chinese University of Hong Kong, 2008.
Includes bibliographical references (leaves 126-150).
Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web.
Electronic reproduction. [Ann Arbor, MI] : ProQuest Information and Learning, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web.
Abstracts in English and Chinese.
School code: 1307.
48
Yu, Ming-Jyun, and 余明駿. "Markers Based 3D Position Estimation for Rod Shaped Object Using 2D Image and Its Application In Endoscopic MIS Instrument Tracking." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/mwg4jq.
Full textAbstract:
碩士國立雲林科技大學
電機工程系
103
This aim of our research is to use a uniform circular rod-shaped object (such as the endoscopic surgical instruments), it is under the single-lens cameras shooting. We were labeled two markers on the rod-shaped object. All markers have the same shape, but the color is in different. Base on the digital image processing we can detect these markers and estimate 2D information of the rod-shaped object more efficiently. We can estimate 3D position information of the rod-shaped object more quickly, through the lens mapping on the camera sensor imaging positions geometric relationships. The 3D position information of the rod-shaped object total have seven parameters. Parameters are 3D of coordinate (X,Y,Z) and In-plane, out-plane angles (alpha,beta,gamma). We propose using the binary encoding to estimate rotation angle(theta).
49
Rao, Swetcha. "3D ENDOSCOPY VIDEO GENERATED USING DEPTH INFERENCE: CONVERTING 2D TO 3D." 2013. http://hdl.handle.net/1805/3443.
Full textAbstract:
Indiana University-Purdue University Indianapolis (IUPUI)A novel algorithm was developed to convert raw 2-dimensional endoscope videos into 3-dimensional view. Minimally invasive surgeries aided with 3D view of the invivo site have shown to reduce errors and improve training time compared to those with 2D view. The novelty of this algorithm is that two cues in the images have been used to develop the 3D. Illumination is the rst cue used to nd the darkest regions in the endoscopy images in order to locate the vanishing point(s). The second cue is the presence of ridge-like structures in the in-vivo images of the endoscopy image sequence. Edge detection is used to map these ridge-like structures into concentric ellipses with their common center at the darkest spot. Then, these two observations are used to infer the depth of the endoscopy videos; which then serves to convert them from 2D to 3D. The processing time is between 21 seconds to 20 minutes for each frame, on a 2.27GHz CPU. The time depends on the number of edge pixels present in the edge-detection image. The accuracy of ellipse detection was measured to be 98.98% to 99.99%. The algorithm was tested on 3 truth images with known ellipse parameters and also on real bronchoscopy image sequences from two surgical procedures. Out of 1020 frames tested in total, 688 frames had single vanishing point while 332 frames had two vanishing points. Our algorithm detected the single vanishing point in 653 of the 688 frames and two vanishing points in 322 of the 332 frames.
50
SYU, JIA-CYUAN, and 許家銓. "Double-Rings Markers Based 3D Complete Eight Quadrants Position Estimation for Rod Shaped Object Using 2D Image and Its Application In Endoscopic MIS Instrument Tracking." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/92550082240203623869.
Full textAbstract:
碩士國立雲林科技大學
電機工程系
104
This paper is based on the results of Mr. Ming-Jyun Yu’s master thesis from our laborotary in 2015 titled “Markers Based 3D Position Estimation for Rod Shaped Object Using 2D Image and Its Application In Endoscopic MIS Instrument Tracking” which features fast and accurate estimation of the six 3D position parameters using just a single 2D image through a set of deterministic formulars (equations). In this thesis, we completed four research goals. Firstly, we extend the original formular for one particular pose to formulars for any pose. Secondly, we select the colors of the two rings as well as the RGB thresholds for fast and accurate ring shape extraction from the 2D image by analyzing a large amount of laparoscopic images. Thirdly, we propose an algorithm with a 2D laparoscopic image as the input and the corresponding six (6) 3D pose parameters as the output. We aslo verify the correctness of the proposed formulars and algorithm by conducting extensive experiments to measure (by human observers) and estimate (by proposed algorithm) the six 3D parameters and analyze their differences for various poses. The results of analysis can be used for further accuracy improvements for the propsed method. Finally, we demonstrate the possibility of sychronizing the motion of a real rod-shaped body and its Unity3D based 3D model for further application in Augmented Reality. The six 3D pose parameters of a real rod-shaped body is estimated by the proposed system and transmitted to drive its 3D model in the remote. Compared to other existing MIS pose estimation methods, the proposed Double-Ring marker based algorithm is accurate and computationally very efficient.