Examinando por Autor "Vera, M."
Mostrando 1 - 6 de 6
Resultados por página
Opciones de ordenación
Ítem An automatic technique for left ventricle segmentation from msct cardiac volumes(IOP Publishing, 2019) Vera, M.; Medina, R.; Del Mar, A.; Arellano, J.; Huerfano, Y.; Bravo, A.In this research, an automatic technique to segment the left ventricle from the heart information in multislice computed tomography images is proposed. A preprocessing stage is considered as a necessary preliminary task for diminishing the artifacts impact in the image analysis. With this idea, a similarity enhancement that combines a smoothed version of the original volume with a processed volume using mathematical morphology is used. This preprocessing approach is compared with respect to other strategies. After, a volume-of-interest is defined in order to isolate the cavity using two cropping planes detected with least squares support vector machines. Finally, the segmentations are obtained using both a region growing algorithm and a level sets algorithm. The robustness of each enhancement strategy is validated by performing the segmentation of images. This evaluation considered the Dice score, and both volume and surface errors. A clinical dataset from 12 patients is used in the inter- and intra subject evaluation. During intra-subject validation the proposed scheme achieves the best results, while a modified version of this scheme achieved the best performance during inter-subject validation.Ítem A computational strategy for the identification of pulmonary squamous cell carcinoma in computerized tomography images(IOP Publishing, 2019) Huerfano, Y.; Vera, M.; Gelvez, E.; Salazar, J.; Del Mar, A.; Valbuena, O.; Molina, V.The objective of the work is to propose a computational strategy to identify lung squamous cell carcinoma in three-dimensional databases (3D) of multislice computerized tomography. This strategy consists of the pre-processing, segmentation, and post-processing stages. During pre-processing, an anisotropic, gradient-based diffusion algorithm and a filter bank are used to address artifact and image noise issues. During segmentation, the technique called region growing is applied to pre-processed images. Finally, in the post-processing, a morphological dilation filter is used to process the segmented images. In order to make value judgments about the performance of the proposed strategy, the relative percentage error is used to compare the dilated segmentations of the squamous cell carcinoma with the segmentations of the squamous cell carcinoma generated, manually, by a pulmonologist. The combination of parameters linked to the highest PrE, allows establishing the optimal parameters of each of the algorithms that make up the proposed strategy.Ítem Computational strategy for the segmentation of the aortic annulus in cardiac computed tomography images(IOP Publishing, 2019) Valbuena, O.; Vera, M.; Huérfano, Y.; Gelvez, E.; Salazar, J.; Molina, V.; Sáenz, F.; Vera, M I.; Salazar, W.The purpose of this research is to segment the aortic annulus, present in cardiac computed tomography images, from a computational strategy generated using global similarity enhancement, vector least squares support machines and a segmentation technique named region growing. This enhancement is obtained by applying the following steps: a) Obtain an image of similarity by calculating the absolute value of the arithmetic subtraction that considers the original image and an image of contours. The image of contours is obtained by processing the original image with a filter based on the magnitude of the gradient. b) Is is processed with a Gaussian filter, generating a smoothed similarity image. On the other hand, considering the smoothed similarity image, the least squares support machines are used both to construct two cutting planes (that isolate the aortic artery) and to detect the coordinates of a seed voxel. In order to produce the morphology of the aortic valve annulus, the seed voxel initializes the technique of growth of regions during the segmentation process. From this morphology, some useful quantitative descriptors are calculated for the aortic ring characterization.Ítem Integrating a gradient–based difference operator with machine learning techniques in right heart segmentation(IOP Publishing, 2019) Huérfano, Y.; Vera, M.; Mar, A.; Bravo, A.In this research a three step method for right heart segmentation based on a gradient– based difference operator and machine learning techniques is reported. The proposed method is applied to human heart multi–slice computerized tomography (MSCT) volumes. The first step is the preprocessing, where a gradient–based difference operator is applied to exploit the functional relationship between the original input image and its edge enhanced version. In the second step, the least squares support vector machines (LSSVM) are used with a double purpose. First, an appropriate volume-of-interest is automatically established in order to isolate the structure to segment. Second, another LSSVM is trained for locating the voxels required for initializing the seed based clustering procedure. In the third step (segmentation step), the preprocessed volumes are subsequently processed with an unsupervised clustering technique based on simple linkage region growing. Dice score is used as a metric function to compare the segmentations obtained using the proposed method with respect to ground truth volumes traced by a cardiologist. The right atrium, pulmonary valve, right ventricle and venae cavae are segmented from 80 cardiac MSCT volumes. Reported metrics confirm that this method is a promising technique for right heart segmentation.Ítem Isotropic versus anisotropic techniques in cardiac computed tomography images processing(IOP Publishing, 2019) Barrera, D.; Valbuena, O.; Vera, M.; Huérfano, Y.; Gelvez, E.; Salazar, J.; Molina, V.; Sáenz, F.; Vera, M I.; Salazar, W.The objective of the work is to compare the performance of two filters, one isotropic and another one of anisotropic diffusion based on gradient. To do this, experiments are carried out to establish which of the filters exhibits a better behavior against the imperfections that characterize the computed tomography images. The structure of the experiments is as follows: a) The parameters linked to the aforementioned filters are identified. b) The ranges of valuesof these parameters and the way to use them are established. c) A database of three-dimensional cardiac images is filtered by applying, independently, the aforementioned filters considering a pre-established subset of values associated with the parameters. d) All the filtered images are addressed by a segmentation process, based on the growth of regions, which allows extracting the 3D morphology of the thoracic external aorta. e) As a metric to evaluate the performance of each technique, the Jaccard similarity index (JSI) is used. f) The one that generates the lowest calculated JSI is selected as the best technique when comparing a reference segmentation with all generated segmentations. The results indicate that the anisotropic diffusion filter, based on a gradient, obtained the best performance.Ítem Segmentation of brain tumors using a semi-automatic computational strategy(IOP Publishing, 2019) Vera, M.; Huérfano, Y.; Gelvez, E.; Valbuena, O.; Salazar, J.; Molina, V.; Vera, M I.; Salazar, W.; Sáenz, F.In this work, a semi-automatic computational strategy is proposed for brain tumor segmentation. The filtering (erosion + gaussian filters), segmentation (level set technique) and quantification (BT volume) stages are applied to magnetic resonance imaging in order to generate the three-dimensional morphology of brain tumors. The Jaccard's Similarity Index is considered to contrast manual segmentation with semi-automatic segmentations of brain tumor. In this sense, the highest Jaccard's Similarity Index provides the best parameters of the techniques that constitute the semi-automatic computational strategy. Results are promising, showing an excellent correlation between these segmentations. The volume is used for the brain tumors characterization.