Polycystic ovary syndrome (PCOS) is an endocrine abnormality with multiple diagnostic criteria due to its heterogenic manifestations. One of the diagnostic criterion includes analysis of ultrasound images of ovaries for the detection of number, size, and distribution of follicles within the ovary. This involves manual tracing of follicles on the ultrasound images to determine the presence of a polycystic ovary (PCO). A novel method that automates PCO morphology detection is described. Our algorithm involves automatic segmentation of follicles from ultrasound images, quantifying the attributes of the segmented follicles using stereology, storing follicle attributes as feature vectors, and finally classification of the feature vector into two categories. The classification categories are PCO morphology present and PCO morphology absent. An automatic PCO diagnostic tool would save considerable time spent on manual tracing of follicles and measuring the length and width of every follicle. Our procedure was able to achieve classification accuracy of 92.86% using a linear discriminant classifier. Our classifier will improve the rapidity and accuracy of PCOS diagnosis, and reduce the chance of the severe health implications that can arise from delayed diagnosis.

Polycystic ovary syndrome (PCOS) is an endocrine abnormality with multiple diagnostic criteria due to its heterogenic manifestations. One of the diagnostic criterion includes analysis of ultrasound images of ovaries for the detection of number, size, and distribution of follicles within the ovary. This involves manual tracing of follicles on the ultrasound images to determine the presence of a polycystic ovary (PCO). A novel method that automates PCO morphology detection is described. Our algorithm involves automatic segmentation of follicles from ultrasound images, quantifying the attributes of the segmented follicles using stereology, storing follicle attributes as feature vectors, and finally classification of the feature vector into two categories. The classification categories are PCO morphology present and PCO morphology absent. An automatic PCO diagnostic tool would save considerable time spent on manual tracing of follicles and measuring the length and width of every follicle. Our procedure was able to achieve classification accuracy of 92.86% using a linear discriminant classifier. Our classifier will improve the rapidity and accuracy of PCOS diagnosis, and reduce the chance of the severe health implications that can arise from delayed diagnosis.

No description available.

No description available.

La réalisation des néphrolithotomies percutanées est essentiellement conditionnée par la qualité dela ponction calicièle préalable. En effet, en cas d’échec de celle-ci, l’intervention ne peut avoir lieu.Réalisée le plus souvent sous échographie, sa qualité est fortement conditionnée par celle du retouréchographique, considéré comme essentiel par la deuxième consultation internationale sur la lithiase pour limiter les saignements consécutifs à l’intervention.L’imagerie échographique est largement plébiscitée en raison de son faible coût, de l’innocuité del’examen, liée à son caractère non invasif, de sa portabilité ainsi que de son excellente résolutiontemporelle ; elle possède toutefois une très faible résolution spatiale et souffre de nombreux artefacts tels que la mauvaise résolution des images, un fort bruit apparent et une forte dépendance àl’opérateur.L’objectif de cette thèse est de concevoir une méthode de filtrage des données échographiques ainsiqu’une méthode de segmentation et de suivi du rein sur des séquences ultrasonores, dans le butd’améliorer les conditions d’exécution d’interventions chirurgicales telles que les néphrolithotomiespercutanées.Le filtrage des données, soumis et publié dans SPIE 2010, est réalisé en exploitant le mode deformation des images : le signal radiofréquence est filtré directement, avant même la formation del’image 2D finale. Pour ce faire, nous utilisons une méthode basée sur les ondelettes, en seuillantdirectement les coefficients d’ondelettes aux différentes échelles à partir d’un algorithme de typesplit and merge appliqué avant reconstruction de l’image 2D.La méthode de suivi développée (une étude préliminaire a été publiée dans SPIE 2009), exploiteun premier contour fourni par le praticien pour déterminer, en utilisant des informations purementlocales, la position du contour sur l’image suivante de la séquence. L’image est transformée pourne plus être qu’un ensemble de vignettes caractérisées par leurs critères de texture et une premièresegmentation basée région est effectuée sur cette image des vignettes. Cette première étape effectuée, le contour de l’image précédente de la séquence est utilisé comme initialisation afin de recalculer le contour de l’image courante sur l’image des vignettes segmentée. L’utilisation d’informations locales nous a permis de développer une méthode facilement parallélisable, ce qui permettra de travailler dans une optique temps réel.La validation de la méthode de filtrage a été réalisée sur des signaux radiofréquence simulés. Laméthode a été comparée à différents algorithmes de l’état de l’art en terme de ratio signal sur bruitet de calcul de USDSAI. Les résultats ont montré la qualité de la méthode proposée comparativement aux autres. La méthode de segmentation, quant-à elle, a été validée sans filtrage préalable, sur des séquences 2D réelles pour un temps d’exécution sans optimisation, inférieur à la minute pour des images 512*512. / The achievement of percutaneous nephrolithotomies is mainly conditioned by the quality of the initial puncture. Indeed, if it is not well performed , the intervention cannot be fulfilled.In order to make it more accurate this puncture is often realized under ultrasound control. Thus the quality of the ultrasound feedback is very critical and when clear enough it greatly helps limiting bleeding.Thanks to its low cost, its non invasive nature and its excellent temporal resolution, ultrasound imaging is considered very appropriate for this purpose. However, this solution is not perfect it is characterized by a low spatial resolution and the results present artifacts due to a poor image resolution (compared to images provided by some other medical devices) and speckle noise.Finally this technic is greatly operator dependent.Aims of the work presented here are, first to design a filtering method for ultrasound data and then to develop a segmentation and tracking algorithm on kidney ultrasound sequences in order to improve the executing conditions of surgical interventions such as percutaneous nephrolithotomies.The results about data filtering was submitted and published in SPIE 2010. The method uses the way ultrasound images are formed to filter them: the radiofrequency signal is directly filtered, before the bi-dimensional reconstruction. In order to do so, a wavelet based method, thresholding directly wavelet coefficients at different scales has been developed. The method is based on a “split and merge” like algorithm.The proposed algorithm was validated on simulated signals and its results compared to the ones obtained with different state of the art algorithms. Experiments show that this new proposed approach is better.The segmentation and tracking method (of which a prospective study was published in SPIE 2009) uses a first contour given by a human expert and then determines, using only local informations, the position of the next contour on the following image of the sequence. The tracking technique was validated on real data with no previous filtering and successfully compared with state of the art methods.

Ovarian follicles are spherical structures inside the ovaries which contain developing eggs. Monitoring the development of follicles is necessary for both gynecological medicine (ovarian diseases diagnosis and infertility treatment), and veterinary medicine (determining when to introduce superstimulation in cattle, or dividing herds into different stages in the estrous cycle).<p>Ultrasound imaging provides a non-invasive method for monitoring follicles. However, manually detecting follicles from ovarian ultrasound images is time consuming and sensitive to the observer's experience. Existing (semi-) automatic follicle segmentation techniques show the power of automation, but are not widely used due to their limited success.<p>A new automated follicle segmentation method is introduced in this thesis. Human ovarian images acquired <i>in vivo</i> were smoothed using an adaptive neighbourhood median filter. Dark regions were initially segmented using geometric active contour models. Only part of these segmented dark regions were true follicles. A naïve Bayes classifier was applied to determine whether each segmented dark region was a true follicle or not. <p>The Hausdorff distance between contours of the automatically segmented regions and the gold standard was 2.43 ± 1.46 mm per follicle, and the average root mean square distance per follicle was 0.86 ± 0.49 mm. Both the average Hausdorff distance and the root mean square distance were larger than those reported in other follicle segmentation algorithms. The mean absolute distance between contours of the automatically segmented regions and the gold standard was 0.75 ± 0.32 mm, which was below that reported in other follicle segmentation algorithms.<p>The overall follicle recognition rate was 33% to 35%; and the overall image misidentification rate was 23% to 33%. If only follicles with diameter greater than or equal to 3 mm were considered, the follicle recognition rate increased to 60% to 63%, and the follicle misidentification rate increased slightly to 24% to 34%. The proposed follicle segmentation method is proved to be accurate in detecting a large number of follicles with diameter greater than or equal to 3 mm.

The Prostate is a male gland that is located around the urethra. Prostate Cancer is the second most diagnosed malignancy in men over the age of fifty. Typically, prostate cancer is diagnosed from clinical data, medical images, and biopsy. <br /><br /> Computer Aided Diagnosis (CAD) was introduced to help in the diagnosis in order to assist in the biopsy operations. Usually, CAD is carried out utilizing either the clinical data, using data mining techniques, or using features extracted from either TransRectal UltraSound (TRUS) images or the Radio Frequency (RF) signals. <br /><br /> The challenge is that TRUS images' quality is usually poor compared to either Magnetic Resonance Imaging (MRI) or the Computed Tomography (CT). On the other hand, ultrasound imaging is more convenient because of its simple instrumentation and mobility capability compared to either CT or MRI. Moreover, TRUS is far less expensive and does not need certain settings compared to either MRI or CT. Accordingly; the main motivation of this research is to enhance the outcome of TRUS images by extracting as much information as possible from it. The main objective of this research is to implement a powerful noninvasive CAD tool that integrates all the possible information gathered from the TRUS images in order to mimic the expert radiologist opinion and even go beyond his visual system capabilities, a process that will in turn assist the biopsy operation. In this sense, looking deep in the TRUS images by getting some mathematical measures that characterize the image and are not visible by the radiologist is required to achieve the task of cancer recognition. <br /><br /> This thesis presents several comprehensive algorithms for integrated feature analysis systems for the purpose of prostate tissue classification. The proposed algorithm is composed of several stages, which are: First, the regions that are highly suspicious are selected using the proposed Gabor filter based ROI identification algorithm. <br /><br /> Second, the selected regions are further examined by constructing different novel as well as typical feature sets. The novel constructed feature sets are composed of statistical feature sets, spectral feature sets and model based feature sets. <br /><br /> Next, the constructed features were further analyzed by selecting the best feature subset that identifies the cancereus regions. This task is achieved by proposing different dimensionality reduction methods which can be categorized into: Classifier dependent feature selection (Mutual Information based feature selection), classifier independent feature selection, which is based mainly on tailoring the Artificial life optimization techniques to fit the feature selection problem and Feature Extraction, which transforms the data to a new lower dimension space without any degradation in the information and with no correlation among the transformed lower dimensional features. <br /><br /> Finally, the last proposed fragment in this thesis is the Spectral Clustering algorithm, which is applied to the TRUS images. Spectral Clustering is a novel fast algorithm that can be used in order to obtain a fast initial estimate of the cancer regions. Moreover, it can be used to support the decision obtained by the proposed cancer recognition algorithm. This decision support process is crucial at this stage as the gold standards used in obtaining the results shown in this thesis is mainly the radiologist's markings on the TRUS images. This gold standards is not considered as credible since the radiologist's best accuracy is approximately 65 %. <br /><br /> In conclusion, this thesis introduces different novel complete algorithms for automatic cancerous regions detection in the prostate gland utilizing TRUS images. These proposed algorithms complement each other in which the results obtained using either of the proposed algorithms support each other by resulting in the same classification accuracy, sensitivity and specificity. This result proves the remarkable quality of the constructed features as well as the superiority of the introduced feature selection and feature extraction methods to detect cancerous regions in the prostate gland.

The Prostate is a male gland that is located around the urethra. Prostate Cancer is the second most diagnosed malignancy in men over the age of fifty. Typically, prostate cancer is diagnosed from clinical data, medical images, and biopsy. <br /><br /> Computer Aided Diagnosis (CAD) was introduced to help in the diagnosis in order to assist in the biopsy operations. Usually, CAD is carried out utilizing either the clinical data, using data mining techniques, or using features extracted from either TransRectal UltraSound (TRUS) images or the Radio Frequency (RF) signals. <br /><br /> The challenge is that TRUS images' quality is usually poor compared to either Magnetic Resonance Imaging (MRI) or the Computed Tomography (CT). On the other hand, ultrasound imaging is more convenient because of its simple instrumentation and mobility capability compared to either CT or MRI. Moreover, TRUS is far less expensive and does not need certain settings compared to either MRI or CT. Accordingly; the main motivation of this research is to enhance the outcome of TRUS images by extracting as much information as possible from it. The main objective of this research is to implement a powerful noninvasive CAD tool that integrates all the possible information gathered from the TRUS images in order to mimic the expert radiologist opinion and even go beyond his visual system capabilities, a process that will in turn assist the biopsy operation. In this sense, looking deep in the TRUS images by getting some mathematical measures that characterize the image and are not visible by the radiologist is required to achieve the task of cancer recognition. <br /><br /> This thesis presents several comprehensive algorithms for integrated feature analysis systems for the purpose of prostate tissue classification. The proposed algorithm is composed of several stages, which are: First, the regions that are highly suspicious are selected using the proposed Gabor filter based ROI identification algorithm. <br /><br /> Second, the selected regions are further examined by constructing different novel as well as typical feature sets. The novel constructed feature sets are composed of statistical feature sets, spectral feature sets and model based feature sets. <br /><br /> Next, the constructed features were further analyzed by selecting the best feature subset that identifies the cancereus regions. This task is achieved by proposing different dimensionality reduction methods which can be categorized into: Classifier dependent feature selection (Mutual Information based feature selection), classifier independent feature selection, which is based mainly on tailoring the Artificial life optimization techniques to fit the feature selection problem and Feature Extraction, which transforms the data to a new lower dimension space without any degradation in the information and with no correlation among the transformed lower dimensional features. <br /><br /> Finally, the last proposed fragment in this thesis is the Spectral Clustering algorithm, which is applied to the TRUS images. Spectral Clustering is a novel fast algorithm that can be used in order to obtain a fast initial estimate of the cancer regions. Moreover, it can be used to support the decision obtained by the proposed cancer recognition algorithm. This decision support process is crucial at this stage as the gold standards used in obtaining the results shown in this thesis is mainly the radiologist's markings on the TRUS images. This gold standards is not considered as credible since the radiologist's best accuracy is approximately 65 %. <br /><br /> In conclusion, this thesis introduces different novel complete algorithms for automatic cancerous regions detection in the prostate gland utilizing TRUS images. These proposed algorithms complement each other in which the results obtained using either of the proposed algorithms support each other by resulting in the same classification accuracy, sensitivity and specificity. This result proves the remarkable quality of the constructed features as well as the superiority of the introduced feature selection and feature extraction methods to detect cancerous regions in the prostate gland.

Ovarian follicles are spherical structures inside the ovaries which contain developing eggs. Monitoring the development of follicles is necessary for both gynecological medicine (ovarian diseases diagnosis and infertility treatment), and veterinary medicine (determining when to introduce superstimulation in cattle, or dividing herds into different stages in the estrous cycle).<p>Ultrasound imaging provides a non-invasive method for monitoring follicles. However, manually detecting follicles from ovarian ultrasound images is time consuming and sensitive to the observer's experience. Existing (semi-) automatic follicle segmentation techniques show the power of automation, but are not widely used due to their limited success.<p>A new automated follicle segmentation method is introduced in this thesis. Human ovarian images acquired <i>in vivo</i> were smoothed using an adaptive neighbourhood median filter. Dark regions were initially segmented using geometric active contour models. Only part of these segmented dark regions were true follicles. A naïve Bayes classifier was applied to determine whether each segmented dark region was a true follicle or not. <p>The Hausdorff distance between contours of the automatically segmented regions and the gold standard was 2.43 ± 1.46 mm per follicle, and the average root mean square distance per follicle was 0.86 ± 0.49 mm. Both the average Hausdorff distance and the root mean square distance were larger than those reported in other follicle segmentation algorithms. The mean absolute distance between contours of the automatically segmented regions and the gold standard was 0.75 ± 0.32 mm, which was below that reported in other follicle segmentation algorithms.<p>The overall follicle recognition rate was 33% to 35%; and the overall image misidentification rate was 23% to 33%. If only follicles with diameter greater than or equal to 3 mm were considered, the follicle recognition rate increased to 60% to 63%, and the follicle misidentification rate increased slightly to 24% to 34%. The proposed follicle segmentation method is proved to be accurate in detecting a large number of follicles with diameter greater than or equal to 3 mm.

L'imagerie ultrasonore est une modalité d'acquisition privilégiée en imagerie médicale en raison de son innocuité, sa simplicité d'utilisation et son coût modéré d'utilisation. Néanmoins, la résolution limitée et le faible contraste limitent son utilisation dans certaines d'applications. C'est dans ce contexte que différentes techniques de post-traitement visant à améliorer la qualité de telles images sont proposées dans ce manuscrit. Dans un premier temps, nous proposons d'aborder le problème conjoint de la déconvolution et de la segmentation d'images ultrasonores en exploitant l'interaction entre ces deux problèmes. Le problème, énoncé dans un cadre bayésien, est résolu à l'aide d'un algorithme MCMC en raison de la complexité de la loi a posteriori des paramètres d'intérêt. Dans un second temps, nous proposons une nouvelle méthode rapide de super-résolution fondée sur la résolution analytique d'un problème de minimisation l2-l2. Il convient de remarquer que les deux approches proposées peuvent être appliquées aussi bien à des images ultrasonores qu'à des images naturelles ou constantes par morceaux. Enfin, nous proposons une méthode de déconvolution aveugle basée sur un modèle paramétrique de la réponse impulsionelle de l'instrument ou du noyau de flou. / In the field of medical image analysis, ultrasound is a core imaging modality employed due to its real time and easy-to-use nature, its non-ionizing and low cost characteristics. Ultrasound imaging is used in numerous clinical applications, such as fetus monitoring, diagnosis of cardiac diseases, flow estimation, etc. Classical applications in ultrasound imaging involve tissue characterization, tissue motion estimation or image quality enhancement (contrast, resolution, signal to noise ratio). However, one of the major problems with ultrasound images, is the presence of noise, having the form of a granular pattern, called speckle. The speckle noise in ultrasound images leads to the relative poor image qualities compared with other medical image modalities, which limits the applications of medical ultrasound imaging. In order to better understand and analyze ultrasound images, several device-based techniques have been developed during last 20 years. The object of this PhD thesis is to propose new image processing methods allowing us to improve ultrasound image quality using postprocessing techniques. First, we propose a Bayesian method for joint deconvolution and segmentation of ultrasound images based on their tight relationship. The problem is formulated as an inverse problem that is solved within a Bayesian framework. Due to the intractability of the posterior distribution associated with the proposed Bayesian model, we investigate a Markov chain Monte Carlo (MCMC) technique which generates samples distributed according to the posterior and use these samples to build estimators of the ultrasound image. In a second step, we propose a fast single image super-resolution framework using a new analytical solution to the l2-l2 problems (i.e., $\ell_2$-norm regularized quadratic problems), which is applicable for both medical ultrasound images and piecewise/ natural images. In a third step, blind deconvolution of ultrasound images is studied by considering the following two strategies: i) A Gaussian prior for the PSF is proposed in a Bayesian framework. ii) An alternating optimization method is explored for blind deconvolution of ultrasound.