Rozprawy doktorskie na temat „Diagnostic assisté par ordinateur (CAD)”
Utwórz poprawne odniesienie w stylach APA, MLA, Chicago, Harvard i wielu innych
Sprawdź 34 najlepszych rozpraw doktorskich naukowych na temat „Diagnostic assisté par ordinateur (CAD)”.
Przycisk „Dodaj do bibliografii” jest dostępny obok każdej pracy w bibliografii. Użyj go – a my automatycznie utworzymy odniesienie bibliograficzne do wybranej pracy w stylu cytowania, którego potrzebujesz: APA, MLA, Harvard, Chicago, Vancouver itp.
Możesz również pobrać pełny tekst publikacji naukowej w formacie „.pdf” i przeczytać adnotację do pracy online, jeśli odpowiednie parametry są dostępne w metadanych.
Przeglądaj rozprawy doktorskie z różnych dziedzin i twórz odpowiednie bibliografie.
Kachouri, Imen. "Description et classification des masses mammaires pour le diagnostic du cancer du sein". Thesis, Evry-Val d'Essonne, 2012. http://www.theses.fr/2012EVRY0017/document.
Pełny tekst źródłaThe computer-aided diagnosis of breast cancer is becoming increasingly a necessity given the exponential growth of performed mammograms. In particular, the breast mass diagnosis and classification arouse nowadays a great interest. Indeed, the complexity of processed forms and the difficulty to distinguish between them require the use of appropriate descriptors. In this work, characterization methods suitable for breast pathologies are proposed and the study of different classification methods is addressed. In order to analyze the mass shapes, a study about the different segmentation techniques in the context of breast mass detection is achieved. This study allows to adopt the level set model based on minimization of region-scalable fitting energy. Once the images are segmented, a study of various descriptors proposed inthe literature is conducted. Nevertheless, these proposals have some limitations such as sensitivity to noise, non invariance to geometric transformations and imprecise and general description of lesions. In this context, we propose a novel descriptor entitled the Skeleton End Points descriptor (SEP) in order to better characterize spiculations in mass contour while respecting the scale invariance. A second descriptor named the Protuberance Selection (PS) is proposed. It ensures also the same invariance criterion and the accurate description of the contour roughness. However, SEP and PS proposals are sensitive to noise. A third proposal entitled Spiculated Mass Descriptor (SMD) which has good robustness to noise is then carried out. In order to compare different descriptors, a comparative study between different classifiers is performed. The Support Vector Machine (SVM) provides for all considered descriptors the best classification result. Finally, the proposed descriptors and others commonly used in the breast cancer field are compared to test their ability to characterize the considered mass contours
Jaouen, Tristan. "Caractérisation du cancer de la prostate de haut grade à l’IRM multiparamétrique à l’aide d’un système de diagnostic assisté par ordinateur basé sur la radiomique et utilisé comme lecteur autonome ou comme second lecteur". Electronic Thesis or Diss., Lyon, 2022. http://www.theses.fr/2022LYSE1140.
Pełny tekst źródłaWe developed a region of interest-based (ROIs) computer-aided diagnosis system (CAD) to characterize International Society of Urological Pathology grade (ISUP) ≥2 prostate cancers at multiparametric MRI (mp-MRI). Image parameters from two multi-vendor datasets of 265 pre-prostatectomy and 112 pre-biopsy MRIs were combined using logistic regression. The best models used the ADC 2nd percentile (ADC2) and normalized wash-in rate (WI) in the peripheral zone (PZ) and the ADC 25th percentile (ADC25) in the transition zone (TZ). They were combined in the CAD system. The CAD was retrospectively assessed on two multi-vendor datasets containing respectively 158 and 105 pre-biopsy MRIs from our institution (internal test dataset) and another institution (external test dataset). Two radiologists independently outlined lesions targeted at biopsy. The Prostate Imaging-Reporting and Data System version 2 (PI-RADSv2) score prospectively assigned at biopsy and the CAD score were compared to biopsy findings. At patient level, the areas under the Receiver Operating Characteristic curve (AUC) of the PI-RADSv2 score were 82% (95% CI: 74-87) and 85% (95% CI: 79-91) in the internal and external test datasets respectively. For both radiologists, the CAD score had similar AUC results in the internal (82%, 95% CI: 76-89, p=1; 84%, 95% CI: 78-91, p=1) and external (82%, 95% CI: 76-89, p=0.82; 86%, 95% CI: 79-93, p=1) test datasets. Combining PI-RADSv2 and CAD findings could have avoided 41-52% of biopsies while missing 6-10% of ISUP≥2 cancers. The CAD system confirmed its robustness showing good discrimination of ISUP ≥2 cancers in a multicentric study involving 22 different scanners with highly heterogeneous image protocols. In per patient analysis, the CAD and the PI-RADSv2 had similar AUC values (76%, 95% CI: 70-82 vs 79%, 95% CI: 73-86; p=0.34) and sensitivities (86%, 95% CI: 76-96 vs 89%, 95% CI: 79-98 for PI-RADSv2 ≥4). The specificity of the CAD (62%, 95% CI: 53-70 vs 49%, 95% CI: 39-59 for PI-RADSv2 ≥4) could be used to complement the PI-RADSv2 score and potentially avoid 50% of biopsies, while missing 13% of ISUP ≥2 cancers. These findings were very similar to those reported in the single center test cohorts. Given its robustness, the CAD could then be exploited in more specific applications. The CAD first provided good discrimination of ISUP ≥2 cancers in patients under Active Surveillance. Its AUC (80%, 95% CI: 74-86) was similar to that of the PI-RADS score prospectively assigned by specialized uro-radiologists at the time of biopsy (81%, 95% CI: 74-87; p=0.96). After dichotomization, the CAD was more specific than the PI-RADS ≥3 (p<0.001) and the PI-RADS ≥4 scores (p<0.001). It could offer a solution to select patients who could safely avoid confirmatory or follow-up biopsy during Active Surveillance (25%), while missing 5% of ISUP≥2 cancers. Finally, the CAD was tested with the pre-prostatectomy mp-MRIs of 56 Japanese patients, from a population which is geographically distant from its training population and which is of interest because of its low prostate cancer incidence and mortality. The CAD obtained an AUC similar to the PI-RADSv2 score assigned by an experience radiologist in the PZ (80%, 95% CI: 71-90 vs 80%, 95% CI: 71-89; p=0.886) and in the TZ (79%, 95% CI: 66-90 vs 93%, 95%CI: 82-96; p=0.051). These promising and robust results across heterogeneous datasets suggest that the CAD could be used in clinical routine as a second opinion reader to help select the patients who could safely avoid biopsy. This CAD may assist less experience readers in the characterization of prostate lesions
Debarre, Étienne. "Application du prototypage rapide à l'aide au diagnostic en chirurgie traumatologique et orthopédique". Thesis, Artois, 2011. http://www.theses.fr/2011ARTO0210/document.
Pełny tekst źródłaThe medical imaging technologies allow the visualization of diseases and injuries. However, even if dynamic perspective ones, these views remain a virtual 3D visualization because on a 2D screen. Real replicas have therefore a definite advantage: they can make palpable the notion of scale and volume and apparent hidden or ambiguous details and thus enhance or facilitate the diagnosis and the surgical solution.The rapid prototyping allows to achieve a replica from a CAD file issued from imaging data but this process is now only applied to specific cases. Our work shows that it can be applied with profit for complex but usual orthopaedic and trauma surgery cases. It can be so transfered from the research laboratory to the hospital.A methodology is defined to manufacture an ABS replica through rapid prototyping by fused deposition modelling from DICOM3 data and digital 3D reconstructions using dedicated software. The study of the capability, transferable to any process, quantifies the response and the accuracy of the machine and the optimal parameters. Three applications (from CT-scan) are presented through three clinical cases (osteotomy, arthroplasty and trochleoplasty) . The examples show that the method is appropriate (and economically reasonable) when it comes to complex geometry or assessment of bone volume. The objective representation of the volumes is the strength of the method and the interest is undeniable in many areas of orthopaedic surgery and traumatology
Chen, Dai. "Diagnostic des incohérences des systèmes de gestion de production assisté par ordinateur". Bordeaux 1, 1988. http://www.theses.fr/1988BOR10570.
Pełny tekst źródłaChevalier, Frédéric. "Le diagnostic assisté par ordinateur de l'image tomodensitométrique : étude de paramètres adaptés". Paris 12, 1991. http://www.theses.fr/1991PA120036.
Pełny tekst źródłaSebbe, Raphaël. "Diagnostic assisté par ordinateur de l'embolie pulmonaire en imagerie CT (computer tomography) opacifiée". Orléans, 2006. http://www.theses.fr/2006ORLE2066.
Pełny tekst źródłaGarcia, David. "Études exploratoires dédiées au diagnostic de corrosion assisté par ordinateur des structures de génie civil". Thesis, Toulouse 3, 2020. http://www.theses.fr/2020TOU30247.
Pełny tekst źródłaThe PhD thesis "Exploratory studies dedicated to computer-assisted corrosion diagnosis of civil engineering structures" deals with the phenomenology and modeling of corrosion of structural steel. The safety, societal and environmental impact of aging infrastructures makes this theme a major economic issue for the development of any country. The proposed developments focus mainly on the corrosion of reinforcements in reinforced concrete. The corrosion of buried metallic structures is also addressed concerning the problems related to galvanic couplings induced by the heterogeneity of soils and stray currents. The usual methods of investigation (measurements of steel potential, concrete resistivity or polarization resistance), combined with empirical hypotheses established by experience, lead to interpretations that are often uncertain or have only a qualitative value. The ambition of this thesis, motivated by the issues at stake, is to show how a better understanding of the physics of corrosion, combined with the power of finite element calculation, allows the construction of elaborate and robust models, useful for a quantified and reliable diagnosis and/or prognosis. The thesis is abundantly illustrated by real or numerical case studies and supported by original laboratory tests. In order to improve the understanding of the phenomena prevailing in the corrosion process, the key concepts of thermodynamics and electrochemical kinetics are recalled and contextualized. The assembly of different physical, chemical and electrochemical laws allows the elaboration of an advanced modeling approach, integrating in particular the diffusion of oxygen to the reinforcement in an unsaturated context, but also the production and precipitation of corrosion products and their influence on the dynamic equilibrium of a corrosion system. This modeling approach, necessarily three-dimensional or at least two-dimensional, gives rise to a transcription in a finite element calculation code. It is first applied to the numerical study of a first typical case of corrosion: a reinforced concrete pile partially submerged in the sea. The influence of the role of oxygen (availability and diffusion) on the dissolution kinetics of the steel and on the nature of the corrosion products formed is studied in particular. In order to illustrate the effective contribution of 3D modeling in the process of corrosion diagnosis, a real case study is proposed concerning a buried steel structure, in this case sheet piles used to support the abutments of a freeway overpass, located near a pipe buried under cathodic protection. Measurements carried out in-situ but also in the laboratory from judiciously chosen samples are used to feed the calculation model. The numerical model thus constructed, qualified as a digital twin, makes it possible to highlight the existence of stray currents circulating in the structure, but also the risk of galvanic corrosion induced by the heterogeneity of the soil. The electrochemical digital twin is then a powerful tool for estimating the kinetics and the corrosion facies of the structure and making a prognosis in terms of service life. Within a concrete structure, the presence of chlorides is associated with various effects, notably associated with the local electric field. If this phenomenon is ignored, the interpretation of field data, for example potential maps, can lead to a biased diagnosis. This thesis addresses the question of corrosion initiation.[...]
Darwesh, Aso. "Diagnostic cognitif en EIAH : le système PépiMep". Paris 6, 2010. http://www.theses.fr/2010PA066397.
Pełny tekst źródłaBlondel, François-Marie. "Diagnostic et aide en EIAO : étude d'un environnement d'aide à la résolution de problèmes en chimie". Nancy 1, 1996. http://docnum.univ-lorraine.fr/public/SCD_T_1996_0108_BLONDEL.pdf.
Pełny tekst źródłaZitouni, Djamel. "De la modelisation au traitement de l'information médicale". Antilles-Guyane, 2009. http://www.theses.fr/2010AGUY0382.
Pełny tekst źródłaThe intensive care unit is a complex environment ; the practice of medicine is specific. The handling of a patient during his/her stay should be done by care staffs with specific knowledge. To help care staffs in their tasks, a plethora of equipment is dedicated to them. These equipments evolve constantly. In the search of a continuous improvement in this activity, the use of automated increasingly appears as a major support and a future challenge for medical practices. Over the last thirty years, several attempts have been made to develop automated guidelines. However, most of these tools are prone to numerous unsolved issues, both in the translation of textual protocols to formal forms and in the treatment of information coming from biomedical monitors. To overcome biases of diagnosis support systems, we chose a different approach. We have defined a formalism that allows caregivers formalizing medical knowledge. We spent the last three years in the intensive care unit of the university hospital of Fort de France with the aim to develop a complete chain of data processing. The final goal was the automation of guidelines in the room, at the patient’s bedside. We propose a set of methods and tools to establish the complete chain of treatment follow-up for a patient, from admission to discharge. This methodology is based on a bedside experimental station: Aidiag (AIDe aux DIAGnostic). This station is a patient-centered tool that also adequately fits to medical routines. A genuine methodology for analyzing biomedical signals allows a first signal processing prior to their physiological interpretation. An artificial intelligence engine (Think!) and a new formalism (Oneah)
Jean-Daubias, Stéphanie. "PÉPITE : un système d'assistance au diagnostic de compétences". Phd thesis, Université du Maine, 2000. http://tel.archives-ouvertes.fr/edutice-00000237.
Pełny tekst źródłaBartolin, Robert. "Aide au diagnostic médical par mesures de comparaisons floues et pouvoir séparateur : approche linguistique des profils protéiques inflammatoires biologiques". Aix-Marseille 2, 1987. http://www.theses.fr/1987AIX21909.
Pełny tekst źródłaCres, François-Noël. "Contribution des systèmes à bases de connaissances en sciences de l'eau : PROMISE, un simulateur de projet ; MOISE, un système de diagnostic en assainissement autonome". Paris, ENMP, 1989. http://tel.archives-ouvertes.fr/docs/00/81/53/33/PDF/1989_Cres_Francois-Noel.pdf.
Pełny tekst źródłaCauvin, Jean-Michel. "Raisonnement médical et aide à la décision en endoscopie digestive". Rennes 1, 2001. http://www.theses.fr/2001REN1B052.
Pełny tekst źródłaFerraz, Simha Cláudia. "Sacre : Système d'aide au contrôle de résultats expérimentaux". Paris 13, 1993. http://www.theses.fr/1993PA132031.
Pełny tekst źródłaNguyen, Paul. "Aide informatique au diagnostic des lombalgies". Nantes, 1993. http://www.theses.fr/1993NANT057M.
Pełny tekst źródłaFiard, Gaëlle. "Apprentissage des biopsies prostatiques par la simulation : vers la validation du simulateur Biopsym". Thesis, Université Grenoble Alpes (ComUE), 2018. http://www.theses.fr/2018GREAS037/document.
Pełny tekst źródłaProstate cancer is the most common malignancy and the 3rd cause of death among men in France. It is a major public health problem with around 50 000 new cases diagnosed each year. The diagnosis is suspected based on an abnormal digital rectal examination or an increase in the prostatic specific antigen level (PSA). Systematic, randomized, ultrasound-guided prostate biopsies are currently recommended first-line to confirm the diagnosis and define the tumor location, volume, and aggressiveness using the Gleason grading system. The conventional training method, based on mentoring, without quantitative feedback on the distribution of the biopsies, has limitations which can partly explain the lack of precision offered by systematic prostate biopsies.The Biopsym simulator was designed in this context to enhance prostate biopsy teaching through 7 exercises and a module replicating the performance of a 12-core systematic biopsy scheme. Several levels of assistance can be offered and a performance feedback is provided. A first validation study allowed to validate face, content and reliability of the simulator, but failed to prove its ability to discriminate between experts and novices (construct validity), in part due to a lack of realism. Two new validation studies on the new version of the simulator were set up during this thesis. The first one allowed for validation of the construct. The second one was able to demonstrate the transfer of skills acquired on the simulator under real-life conditions
Kouvahe, Amélé Eyram Florence. "Etude du remodelage vasculaire pathologique : de la caractérisation macroscopique en imagerie TDM à l’analyse en microscopie numérique". Electronic Thesis or Diss., Institut polytechnique de Paris, 2020. http://www.theses.fr/2020IPPAS019.
Pełny tekst źródłaThis research focuses on the study of the vascular network in general, in several imaging modalities and several anatomo-pathological configurations. Its objective is to discriminate vascular structures in image data and to detect and quantify the presence of morphological modifications (remodeling) related to a pathology. The proposed generic analysis framework exploits a priori knowledge of the geometry of blood vessels and their contrast with respect to the surrounding tissue. The originality of the developed approach consists in exploiting a multidirectional locally connected filter (LCF) adapted to the dimension of the data space (2D or 3D). This filter allows the selection of curvilinear structures in positive contrast in images whose cross-sectional size does not exceed the size of the filtering window. This selection remains effective even at the level of vessel subdivision. The multi-resolution approach makes it possible to overcome the difference in vascular calibers in the network and to segment the entire vascular structure, even in the presence of a local caliber change. The proposed segmentation approach is general. It can be easily adapted to different imaging modalities that preserve a contrast (positive or negative) between the vessels and their environment. This has been demonstrated in different types of imaging, such as thoracic CT with and without contrast agent injection, hepatic perfusion data, eye fundus imaging and infrared microscopy (for fiber segmentation in mouse brain).From an accurate and robust segmentation of the vascular network, it is possible to detect and characterize the presence of remodeling due to a pathology. This is achieved by analyzing the vessel caliber variation along the central axis which provides both a global view on the caliber distribution in the studied organ (to be compared with a "healthy" reference) and a local detection of shape remodeling. The latter case has been applied for the detection and quantification of pulmonary arteriovenous malformations (PAVM).Initially planned in a study of tumor angiogenesis, the segmentation method developed above was not applicable to infrared microscopy because of lack of vascular contrast in the spectral bands analyzed. Instead, it was exploited for the extraction of brain fibers as a support element for image interpolation aiming the 3D reconstruction of the brain volume from the 2D sub-sampled data. In this respect, a 2D-2D interpolation with realignment of the structures was developed as a second methodological contribution of the thesis. We proposed a geometric interpolation approach controlled by a prior mapping of the corresponding structures in the images, which in our case were the tumor region, the fibers, the brain ventricles and the contour of the brain. An atlas containing the unique labels of the structures to be matched is thus built up for each image. Labels of the same value are aligned using a field of directional vectors established at the level of their contours, in a higher dimensional space (3D here). The diffusion of this field of vectors results in a smooth directional flow from one image to the other, which represents the homeomorphic transformation between the two images. The proposed method has two advantages: it is general, which is demonstrated on different image modalities (microscopy, CT, MRI, atlas) and it allows controlling the alignment of structures whose correspondence is targeted in priority
Briot, Jérôme. "Contribution à la quantification objective des pathologies ostéo-articulaires par une approche interdisciplinaire en imagerie et biomécanique". Toulouse 3, 2005. http://www.theses.fr/2005TOU30161.
Pełny tekst źródłaAarabi, Ardalan. "Détection et classification spatiotemporelle automatique d'évènements EEG pour l'analyse de sources d'activité cérébrale chez le nouveau-né et l'enfant". Amiens, 2007. http://www.theses.fr/2007AMIED002.
Pełny tekst źródłaNeonates, especially the premature ones, are at high risk of brain damage and life-long cognitive disability. Concerning the full-term neonates, neurological pathologies are often accompanied by epileptic manifestations. These newborns may be impaired in other domains including coordination, cognition and behavior. EEG is a useful non-invasive tool to measure the electrical activity of the brain. In this thesis, we developed tools to identify normal and pathological EEG events in neonates and children. We paid a special attention to detect (i) seizures by using specific age-dependant features of the newborn EEG, (ii) brain epileptic states and (iii) short-term events like spikes and spike-and-waves for each state. We characterized EEG events by extracting a set of contextual features in order to classify them. Then, the location of cerebral generators was found and tracked by spatial clustering of the equivalent dipoles of the EEG events in different brain states. The results showed good sensitivities and selectivities with a low false detection rates in neonates and children
Zuluaga, Valencia Maria Alejandra. "Méthodes d'automatisation de la détection des lésions vasculaires dans des images de tomodensitométrie". Phd thesis, Université Claude Bernard - Lyon I, 2011. http://tel.archives-ouvertes.fr/tel-00860825.
Pełny tekst źródłaQuatrehomme, Auréline. "Caractérisation des lésions hépatiques focales sur des acquisitions scanner multiphasiques". Thesis, Montpellier 2, 2013. http://www.theses.fr/2013MON20207/document.
Pełny tekst źródłaMedical imaging acquisition has taken benefits from recent advances and is becoming more and more important in the patient care process. New needs raise, which are related to image processing. Hepatic lesion recognition is a hot topic, especially because liver cancer is wide-spread and leads to death, most of the time because of the diagnosis which is made too late. In this context is born this manuscrit research project, a collaboration between IMAIOS company and the Laboratory of Informatics, Robotics and Micro-electronics ofMontpellier (LIRMM).This thesis presents a complete and automated system that extracts visual features from lesion images in the medical format DICOM, then differenciate them on these features.The various described contributions are: intensity normalization using healthy liver values, analysis and experimentations around new visual features, which use temporal information or tissue density, different kind of caracterisation of the lesions. This work has been done on multi-phase Computed Tomography acquisitions
Traore, Lamine. "Semantic modeling of an histopathology image exploration and analysis tool". Thesis, Paris 6, 2017. http://www.theses.fr/2017PA066621/document.
Pełny tekst źródłaSemantic modelling of a histopathology image exploration and analysis tool. Recently, anatomic pathology (AP) has seen the introduction of several tools such as high-resolution histopathological slide scanners, efficient software viewers for large-scale histopathological images and virtual slide technologies. These initiatives created the conditions for a broader adoption of computer-aided diagnosis based on whole slide images (WSI) with the hope of a possible contribution to decreasing inter-observer variability. Beside this, automatic image analysis algorithms represent a very promising solution to support pathologist’s laborious tasks during the diagnosis process. Similarly, in order to reduce inter-observer variability between AP reports of malignant tumours, the College of American Pathologists edited 67 organ-specific Cancer Checklists and associated Protocols (CAP-CC&P). Each checklist includes a set of AP observations that are relevant in the context of a given organ-specific cancer and have to be reported by the pathologist. The associated protocol includes interpretation guidelines for most of the required observations. All these changes and initiatives bring up a number of scientific challenges such as the sustainable management of the available semantic resources associated to the diagnostic interpretation of AP images by both humans and computers. In this context, reference vocabularies and formalization of the associated knowledge are especially needed to annotate histopathology images with labels complying with semantic standards. In this research work, we present our contribution in this direction. We propose a sustainable way to bridge the content, features, performance and usability gaps between histopathology and WSI analysis
Pan, Xiaoxi. "Towards FDG-PET image characterization and classification : application to Alzheimer's disease computer-aided diagnosis". Thesis, Ecole centrale de Marseille, 2019. http://www.theses.fr/2019ECDM0008.
Pełny tekst źródłaAlzheimer's disease (AD) is becoming the dominant type of neurodegenerative brain disease in elderly people, which is incurable and irreversible for now. It is expected to diagnose its early stage, Mild Cognitive Impairment (MCI), then interventions can be applied to delay the onset. Fluorodeoxyglucose positron emission tomography (FDG-PET) is considered as a significant and effective modality to diagnose AD and the corresponding early phase since it can capture metabolic changes in the brain thereby indicating abnormal regions. Therefore, this thesis is devoted to identify AD from Normal Control (NC) and predict MCI conversion under FDG-PET modality. For this purpose, three independent novel methods are proposed. The first method focuses on developing connectivities among anatomical regions involved in FDG-PET images which are rarely addressed in previous methods. Such connectivities are represented by either similarities or graph measures among regions. Then combined with each region's properties, these features are fed into a designed ensemble classification framework to tackle problems of AD diagnosis and MCI conversion prediction. The second method investigates features to characterize FDG-PET images from the view of spatial gradients, which can link the commonly used features, voxel-wise and region-wise features. The spatial gradient is quantified by a 2D histogram of orientation and expressed in a multiscale manner. The results are given by integrating different scales of spatial gradients within different regions. The third method applies Convolutional Neural Network (CNN) techniques to three views of FDG-PET data, thereby designing the main multiview CNN architecture. Such an architecture can facilitate convolutional operations, from 3D to 2D, and meanwhile consider spatial relations, which is benefited from a novel mapping layer with cuboid convolution kernels. Then three views are combined and make a decision jointly. Experiments conducted on public dataset show that the three proposed methods can achieve significant performance and moreover, outperform most state-of-the-art approaches
Cuingnet, Rémi. "Contributions à l'apprentissage automatique pour l'analyse d'images cérébrales anatomiques". Phd thesis, Université Paris Sud - Paris XI, 2011. http://tel.archives-ouvertes.fr/tel-00602032.
Pełny tekst źródłaBraham, Najoua. "Organisation d'un système de simulation de cas autour d'un système expert en hématologie". Compiègne, 1986. http://www.theses.fr/1986COMPS144.
Pełny tekst źródłaWazaefi, Yanal. "Automatic diagnosis of melanoma from dermoscopic images of melanocytic tumors : Analytical and comparative approaches". Thesis, Aix-Marseille, 2013. http://www.theses.fr/2013AIXM4106.
Pełny tekst źródłaMelanoma is the most serious type of skin cancer. This thesis focused on the development of two different approaches for computer-aided diagnosis of melanoma: analytical approach and comparative approach. The analytical approach mimics the dermatologist’s behavior by first detecting malignancy features based on popular analytical methods, and in a second step, by combining these features. We investigated to what extent the melanoma diagnosis can be impacted by an automatic system using dermoscopic images of pigmented skin lesions. The comparative approach, called Ugly Duckling (UD) concept, assumes that nevi in the same patient tend to share some morphological features so that dermatologists identify a few similarity clusters. UD is the nevus that does not fit into any of those clusters, likely to be suspicious. The goal was to model the ability of dermatologists to build consistent clusters of pigmented skin lesions in patients
Brunet, Eric. "Conception et réalisation d'un système expert d'aide à l'interprétation des chocs mécaniques en centrale nucléaire". Compiègne, 1988. http://www.theses.fr/1988COMPD113.
Pełny tekst źródłaThe main purpose of this research work was the design of a Diagnostic Expert System work bench (MIGRE) and, from it, the realization of a system to aid the interpretation of mechanical impacts in nuclear power plants. The central problem for knowledge based system is related to the concept of “knowledge”. MIGRE proposes a three-level classification of knowledge. The first level is concerned with basic or descriptive knowledge and is formalised in an Entity-Relation model. The second level associates the basic concepts with specific information (“Knowledge Vector”). The last level deals with inference knowledge. Each element of expertise is represented by a “marked” rule (strategy, inference, definition,. . . ). MIGRE provides tools support the activities of application development. Thus, the knowledge base editor includes a Specialized Natural Language Interface, whose aim is to understand the “meaning” of a sentence, and in particular to look for “implicit” knowledge. The parser is a semantic one, using a Definite Clause Grammar. Problem solution is guided by the answers given by the knowledge Exploitation module to a number of tasks extended dynamically during the reasoning. The results show that the two “intellectual” activities of understanding sentences and reasoning to solve a problem require a common core of knowledge
Cheikhrouhou, Imen. "Description et classification des masses mammaires pour le diagnostic du cancer du sein". Phd thesis, Université d'Evry-Val d'Essonne, 2012. http://tel.archives-ouvertes.fr/tel-00875976.
Pełny tekst źródłaZribi, Abir. "Apprentissage par noyaux multiples : application à la classification automatique des images biomédicales microscopiques". Thesis, Rouen, INSA, 2016. http://www.theses.fr/2016ISAM0001.
Pełny tekst źródłaThis thesis arises in the context of computer aided analysis for subcellular protein localization in microscopic images. The aim is the establishment of an automatic classification system allowing to identify the cellular compartment in which a protein of interest exerts its biological activity. In order to overcome the difficulties in attempting to discern the cellular compartments in microscopic images, the existing state-of-art systems use several descriptors to train an ensemble of classifiers. In this thesis, we propose a different classification scheme wich better cope with the requirement of genericity and flexibility to treat various image datasets. Aiming to provide an efficient image characterization of microscopic images, a new feature system combining local, frequency-domain, global, and region-based features is proposed. Then, we formulate the problem of heterogeneous feature fusion as a kernel selection problem. Using multiple kernel learning, the problems of optimal feature sets selection and classifier training are simultaneously resolved. The proposed combination scheme leads to a simple and a generic framework capable of providing a high performance for microscopy image classification. Extensive experiments were carried out using widely-used and best known datasets. When compared with the state-of-the-art systems, our framework is more generic and outperforms other classification systems. To further expand our study on multiple kernel learning, we introduce a new formalism for learning with multiple kernels performed in two steps. This contribution consists in proposing three regularized terms with in the minimization of kernels weights problem, formulated as a classification problem using Separators with Vast Margin on the space of pairs of data. The first term ensures that kernels selection leads to a sparse representation. While the second and the third terms introduce the concept of kernels similarity by using a correlation measure. Experiments on various biomedical image datasets show a promising performance of our method compared to states of art methods
Zuluaga, Valencia Maria Alejandra. "Methods for automation of vascular lesions detection in computed tomography images". Thesis, Lyon 1, 2011. http://www.theses.fr/2011LYO10010/document.
Pełny tekst źródłaThis thesis presents a framework for the detection and diagnosis of vascular lesions with a special emphasis on coronary heart disease. Coronary heart disease remains to be the first cause of mortality worldwide. Typically, the problem of vascular lesion identification has been solved by trying to model the abnormalities (lesions). The main drawback of this approach is that lesions are highly heterogeneous, which makes the detection of previously unseen abnormalities difficult. We have selected not to model lesions directly, but to treat them as anomalies which are seen as low probability density points. We propose the use of two classification frameworks based on support vector machines (SVM) for the density level detection problem. The main advantage of these two methods is that the learning stage does not require labeled data representing lesions, which is always difficult to obtain. The first method is completely unsupervised, whereas the second one only requires a limited number of labels for normality. The use of these anomaly detection algorithms requires the use of features such that anomalies are represented as points with low probability density. For this purpose, we developed an intensity based metric, denoted concentric rings, designed to capture the nearly symmetric intensity profiles of healthy vessels, as well as discrepancies with respect to the normal behavior. Moreover, we have selected a large set of alternative candidate features to use as input for the classifiers. Experiments on synthetic data and cardiac CT data demonstrated that our metric has a good performance in the detection of anomalies, when used with the selected classifiers. Combination of other features with the concentric rings metric has potential to improve the classification performance. We defined an unsupervised feature selection scheme that allows the definition of an optimal subset of features. We compared it with existent supervised feature selection methods. These experiments showed that, in general, the combination of features improves the classifiers performance, and that the best results are achieved with the combination selected by our scheme, associated with the proposed anomaly detection algorithms. Finally, we propose to use image registration in order to compare the classification results at different cardiac phases. The objective here is to match the regions detected as anomalous in different time-frames. In this way, more than attract the physician's attention to the anomaly detected as potential lesion, we want to aid in validating the diagnosis by automatically displaying the same suspected region reconstructed in different time-frames
Zuluaga, Valencia Maria Alejandra. "Methods for automation of vascular lesions detection in computed tomography images". Electronic Thesis or Diss., Lyon 1, 2011. http://www.theses.fr/2011LYO10010.
Pełny tekst źródłaThis thesis presents a framework for the detection and diagnosis of vascular lesions with a special emphasis on coronary heart disease. Coronary heart disease remains to be the first cause of mortality worldwide. Typically, the problem of vascular lesion identification has been solved by trying to model the abnormalities (lesions). The main drawback of this approach is that lesions are highly heterogeneous, which makes the detection of previously unseen abnormalities difficult. We have selected not to model lesions directly, but to treat them as anomalies which are seen as low probability density points. We propose the use of two classification frameworks based on support vector machines (SVM) for the density level detection problem. The main advantage of these two methods is that the learning stage does not require labeled data representing lesions, which is always difficult to obtain. The first method is completely unsupervised, whereas the second one only requires a limited number of labels for normality. The use of these anomaly detection algorithms requires the use of features such that anomalies are represented as points with low probability density. For this purpose, we developed an intensity based metric, denoted concentric rings, designed to capture the nearly symmetric intensity profiles of healthy vessels, as well as discrepancies with respect to the normal behavior. Moreover, we have selected a large set of alternative candidate features to use as input for the classifiers. Experiments on synthetic data and cardiac CT data demonstrated that our metric has a good performance in the detection of anomalies, when used with the selected classifiers. Combination of other features with the concentric rings metric has potential to improve the classification performance. We defined an unsupervised feature selection scheme that allows the definition of an optimal subset of features. We compared it with existent supervised feature selection methods. These experiments showed that, in general, the combination of features improves the classifiers performance, and that the best results are achieved with the combination selected by our scheme, associated with the proposed anomaly detection algorithms. Finally, we propose to use image registration in order to compare the classification results at different cardiac phases. The objective here is to match the regions detected as anomalous in different time-frames. In this way, more than attract the physician's attention to the anomaly detected as potential lesion, we want to aid in validating the diagnosis by automatically displaying the same suspected region reconstructed in different time-frames
Cuingnet, Rémi. "Contributions à l’apprentissage automatique pour l’analyse d’images cérébrales anatomiques". Thesis, Paris 11, 2011. http://www.theses.fr/2011PA112033/document.
Pełny tekst źródłaBrain image analyses have widely relied on univariate voxel-wise methods. In such analyses, brain images are first spatially registered to a common stereotaxic space, and then mass univariate statistical tests are performed in each voxel to detect significant group differences. However, the sensitivity of theses approaches is limited when the differences involve a combination of different brain structures. Recently, there has been a growing interest in support vector machines methods to overcome the limits of these analyses.This thesis focuses on machine learning methods for population analysis and patient classification in neuroimaging. We first evaluated the performances of different classification strategies for the identification of patients with Alzheimer's disease based on T1-weighted MRI of 509 subjects from the ADNI database. However, these methods do not take full advantage of the spatial distribution of the features. As a consequence, the optimal margin hyperplane is often scattered and lacks spatial coherence, making its anatomical interpretation difficult. Therefore, we introduced a framework to spatially regularize support vector machines for brain image analysis based on Laplacian regularization operators. The proposed framework was then applied to the analysis of stroke and of Alzheimer's disease. The results demonstrated that the proposed classifier generates less-noisy and consequently more interpretable feature maps with no loss of classification performance
Auxepaules, Ludovic. "Analyse des diagrammes de l'apprenant dans un EIAH pour la modélisation orientée objet - Le système ACDC". Phd thesis, Université du Maine, 2009. http://tel.archives-ouvertes.fr/tel-00455992.
Pełny tekst źródła