Examinando por Autor "Bravo, Antonio José"
Mostrando 1 - 2 de 2
Resultados por página
Opciones de ordenación
Ítem Semi-automated detection of aortic root in human heart MSCT images using nonlinear filtering and unsupervised clustering(Inderscience Publishers, 2021) Valbuena, Oscar; Vera, Miguel Ángel; Del Mar, Atilio; Roa, Felida Andreina; Bravo, Antonio JoséAbstract: A semiautomatic technique to detect the aortic root in three-dimensional multi-slice computerised tomography images is proposed. Three steps are considered: conditioning, filtering, and detection. The conditioning is based on multi-planar reconstruction and it is required for reformatting the information to orthogonal planes to the aortic root. During the filtering, three nonlinear filters based on similarity enhancement, median and weighted median are considered to reduce noise and enhance the reformatted images. In the detection, the filtered volumes are processed with a clustering technique. Dice score, the point-to-mesh and the Hausdorff distances are used to compare the obtained results with respect to ground truth traced by a cardiologist. A clinical dataset of 90 volumes from 45 patients is used to validate the technique. The maximum Dice score (0.92), the minimum average point-to-mesh distance (0.96 mm) and the minimum average Hausdorff distance (4.80 mm) are obtained during preprocessed volumes segmentation using similarity enhancement.Ítem A space-occupying lesion automatic quantification from abdominal contrast-enhanced computerized tomography images(Sociedad Venezolana de Farmacología Clínica y Terapéutica, 2020) Bravo, Antonio José; Vera, Miguel Ángel; Huérfano, Yoleidy KatherineSpace-occupying lessions represent a healt higt risk of subjects affected by this kind of pathology. From a medical point of view, the volume occupied by each of these lesions constitutes the most important descriptor when addressing them, and especially for the respective decision-making process that guides their control, mitigation or elimination. In such context, this paper proposes a strategy based on computer-aided image processing techniques to extract the three-dimensional morphology of a space-occupying lesion, of the amoebic liver abscess type, and calculate its volume. In this sense, in order to attenuate poissonian noise and improve the abscess edge information, the abdominal contrast computed tomography images are preprocessed using a Gaussian filter, and edge detector and a median filter, sequentially. Then, a clustering algorithm based on region growing procedure is applied to the enhanced images, obtaining the space occupying lesion three-dimensional shape. Additionally, the Dice coefficient is considered as a metric to establish the correlation between the shapes, automatic and manual lesion, the latter described by a mastologist. Then, in order to characterize the liver abscess, its volume is quantified considering both the voxels occupied by the lesion obtained by applying of the computer-aided image processing, and the physical dimensions of the voxel. Finally, the automatically calculated volume is compared to that generated manually by the medical specialist. The results reveal an excellent correspondence between manual results and those produced by the proposed technique. This type of technique can be used as a resource not only to obtain, precisely, the value of the aforementioned descriptor, but also to monitor the process of the abscess evolution by means imaging control.