Realce por similaridad local para la segmentación automática de la arteria aorta torácica en imágenes de tomografía computarizada cardiaca
No hay miniatura disponible
Fecha
2017
Autores
Contreras-Velásquez, Julio
Vera, Miguel
Huérfano, Yoleidy
Del Mar, Atilio
Wilches-Durán, Sandra
Graterol-Rivas, Modesto
Riaño-Wilches, Daniela
Rojas, Joselyn
Bermúdez, Valmore
Título de la revista
ISSN de la revista
Título del volumen
Editor
Cooperativa servicios y suministros 212518 RS
Resumen
Mediante este trabajo se propone una
estrategia para segmentar la arteria
aórtica torácica (TAA) en imágenes
tridimensionales (3-D) de tomografía computarizada multicapa.
Esta estrategia consta de las etapas de filtrado,
segmentación y entonación de parámetros. La etapa de
filtrado, se emplea una técnica denominada realce por
similaridad local (LSE) con el propósito de disminuir el impacto
de los artefactos y atenuar el ruido en la calidad de
las imágenes. Esta técnica, combina un filtro promediador,
un filtro detector de bordes (denominado black top
hat) y un filtro gaussiano (GF). Por otra parte, durante la
etapa de segmentación 3-D se implementa un algoritmo
de agrupamiento, denominado crecimiento de regiones
(RG), el cual es aplicado a las imágenes pre-procesadas.
Durante la entonación de parámetros de la estrategia
propuesta, el coeficiente de Dice (Dc) es utilizado para
comparar las segmentaciones, de la TAA, obtenidas automáticamente,
con la segmentación de la TAA generada,
manualmente, por un cardiólogo. La combinación de
parámetros que generó el Dc más elevado considerando
el instante de diástole se aplica luego a las 9 imágenes
tridimensionales restantes, obteniéndose un Dc promedio
superior a 0.92 lo cual indica una buena correlación entre
las segmentaciones generadas por el experto cardiólogo y
las producidas por la estrategia desarrollada.
This work proposes a strategy to segment the thoracic aortic artery (TAA) into three-dimensional (3-D) multi-layer computed tomography images. This strategy consists of the stages of filtering, segmentation and intonation of parameters. The filtering stage employs a technique called local similarity enhancement (LSE) in order to reduce the impact of the artifacts and attenuate noise in the quality of the images. This technique combines an averaging filter, an edge detector filter (called black top hat) and a Gaussian filter (GF). On the other hand, a clustering algorithm, called region growth (RG), is implemented during the 3-D segmentation stage, which is applied to the pre-processed images. During the intonation of parameters of the proposed strategy, the Dice coefficient (Dc) is used to compare the segmentations, of the TAA, obtained automatically, with the segmentation of the TAA generated, manually, by a cardiologist. The combination of parameters that generated the highest Dc considering the instant of diastole is then applied to the 9 remaining three-dimensional images, obtaining an average Dc higher than 0.92 which indicates a good correlation between the segmentations generated by the expert cardiologist and those produced by The strategy developed.
This work proposes a strategy to segment the thoracic aortic artery (TAA) into three-dimensional (3-D) multi-layer computed tomography images. This strategy consists of the stages of filtering, segmentation and intonation of parameters. The filtering stage employs a technique called local similarity enhancement (LSE) in order to reduce the impact of the artifacts and attenuate noise in the quality of the images. This technique combines an averaging filter, an edge detector filter (called black top hat) and a Gaussian filter (GF). On the other hand, a clustering algorithm, called region growth (RG), is implemented during the 3-D segmentation stage, which is applied to the pre-processed images. During the intonation of parameters of the proposed strategy, the Dice coefficient (Dc) is used to compare the segmentations, of the TAA, obtained automatically, with the segmentation of the TAA generated, manually, by a cardiologist. The combination of parameters that generated the highest Dc considering the instant of diastole is then applied to the 9 remaining three-dimensional images, obtaining an average Dc higher than 0.92 which indicates a good correlation between the segmentations generated by the expert cardiologist and those produced by The strategy developed.
Descripción
Palabras clave
Tomografía, Arteria aorta torácica, Realce por similaridad local, Segmentación, Tomography, Thoracic aorta artery, Local similarity enhancement, Segmentation