Browsing by Author "Siguencia Cruz, Wilson Marcelo"

Now showing 1 - 3 of 3

Computational model of the pulmonary valve in hypertensive contexts [Modelo computacional de la válvula pulmonar en contextos hipertensivos]
(SOCIEDAD LATINOAMERICANA DE HIPERTENSION, 2016-01-01) Siguencia Cruz, Wilson Marcelo; Torres Valdez, Maritza Auxiliadora
Astrategy for pulmonary valve (PV) three-dimensional segmentation is proposed using 20 cardiac imaging multilayer computed tomography, for entire cardiac cycle of a subject. This strategy is global similarity enhancement technique based on and it comprises of pre-processing, segmentation and parameter tuning stages. The pre-processing stage is split into two phases called filtering and definition of a region of interest. These phases are preliminarily applied to end-diastole cardiac-phase and they address the noise, artifacts and low contrast images problems. During PV segmentation, the region growing algorithm is applied to the pre-processed images and it is initialized using a voxel detected with least squares support vector machines. During the parameters tuning, the Dice score (Ds) is used to compare the PV segmentations, obtained by the proposed strategy, and manually PV segmentation, generated by a cardiologist. The combination of filtering techniques that generated the highest Ds considering the end-diastole phase is then applied to the others 19 3-D images, yielding an average Ds comparable with the Ds reported in the literature.
Medical imaging: Foundations and scope [Imagenología médica: Fundamentos y alcance]
(SOCIEDAD LATINOAMERICANA DE HIPERTENSION, 2016-01-01) Siguencia Cruz, Wilson Marcelo; Torres Valdez, Maritza Auxiliadora
Nowdays, several forms of medical imaging are usefulness in clinical support for both diagnostics diseases generation and treatment planning designed to provide an alternative solution to people who, for one or another reason, manifest an imbalance in your health. Among the imaging modalities that frequently are used in the medical field may include: Ultra sound (US), magnetic resonance imaging (MRI), simple computed tomography (CT) and multilayer computed tomography (MSCT), CT positron emission tomography (PET) Computed tomography and single photon emission (SPECT). In this sense, this article presents an orderly, coherent and systematic description of these modalities and it establishes relationship with the MSCT modality and clinical situations closely related to cardiac anatomy and hypertension processes. The reason emphasis on MSCT is done is because, on the one hand, we have a large number of databases both physiological subjects and pathological subjects and, on the other, we plan to present a set of computational techniques that will be explored in future research, in the context of cardiologic anatomical aspects, with directly or indirectly influence in the emergence, development and prevalence of hypertensive processes.
Therapeutic utility of the tumor segmentation process, applied to PET-CT images [Utilidad terapéutica: Del proceso de segmentación tumoral, aplicado a imágenes de PET-CT]
(SOCIEDAD LATINOAMERICANA DE HIPERTENSION, 2016-01-01) Siguencia Cruz, Wilson Marcelo; Torres Valdez, Maritza Auxiliadora
In this work findings derived from the application of radiotherapy and chemotherapy, in a patient with tumors, are identified. The tumors require of segmentation and quantification process before and after those therapies. In order to obtain the morphology of such tumors and their volumes, a computational technique used in 3D images of positron emission tomography (PET) fused with computed tomography (CT), belonging to a pediatric patient diagnosed with non-Hodgkin lymphoma (NHL), is proposed. The proposed technique is divided into two stages: pre-processing and segmentation. The pre-processing is based on the application of a filtering process based on global enhancement similarity (GSE) to raise the quality of the information in the images. For tumors segmentation a technique based on region growing is considered. The NHL volumes derived from segmentation, are useful for both clinical monitoring lymphoma and analysis of therapeutic procedure.