Segmentación automática de la arteria aorta ascendente y la válvula aórtica en imágenes de tomografía computarizada cardiaca.

Saved in:

Bibliographic Details
Title:	Segmentación automática de la arteria aorta ascendente y la válvula aórtica en imágenes de tomografía computarizada cardiaca.
Alternate Title:	Automatic segmentation of the ascending aorta and aortic valve in computed tomography images.
Authors:	Vera, Miguel^1,2 veramig@gmail.com, Huérfano, Yoleidy¹, Contreras-Velásquez, Julio², Del Mar, Atilio³, Rodríguez, Johel², Bautista, Nahid², Wilches-Durán, Sandra², Graterol-Rivas, Modesto², Riaño-Wilches, Daniela⁴, Rojas, Joselyn⁵, Bermúdez, Valmore^2,6
Source:	Revista Latinoamericana de Hipertensión. 2017, Vol. 12 Issue 2, p70-78. 9p.
Abstract (English):	The present work proposes a technique for the automatic segmentation of the anatomic set consisting of the ascending aorta + aortic valve (AAAV) in 10 three-dimensional (3-D) cardiac images of multi-cut computed tomography, belonging to the same subject. The mentioned technique consists of the stages of pre-processing and segmentation. The pre-processing stage includes two phases: the first, minimizes both Poisson noise and the impact of the staircase artifact, we use a technique called global similarity enhancement, this type of enhancement consists of the application of a bank of filters, softeners And a border detector, whose purpose is to generate an image in which the information of the anatomical structures, which make up the original images, is grouped together; the second phase, considering the filtered images, uses a priori information about the location of the aortic valve and a learning paradigm, based on vector support machines, to define a region of interest that isolates AAAV from neighboring anatomical structures. On the other hand, to generate the 3-D morphology of the TAA, a segmentation stage is applied which considers the filtered images and a clustering algorithm based on regions growth. The proposed strategy generates the 3-D segmentations of AAAV in all the images that make up the complete cardiac cycle of the subject considered. In order to quantify the performance of the referred technique, the Dice coefficient was considered, obtaining a good correlation between the automatic segmentations and the manual ones generated by a cardiologist. Automatically generated segmentations may be helpful in detecting certain pathologies that affect both the aorta and anatomical structures associated with it, such as the aorta and left ventricle. [ABSTRACT FROM AUTHOR]
Abstract (Spanish):	Mediante el presente trabajo se propone una técnica para la segmentación automática del conjunto anatómico constituido por la arteria aorta ascendente + la válvula aórtica (AAAV) en 10 imágenes cardiacas tridimensionales (3-D) de tomografía computarizada multi-corte, pertenecientes a un mismo sujeto. La mencionada técnica consta de las etapas de pre-procesamiento y segmentación. La etapa de pre-procesamiento incluye dos fases: la primera, minimiza tanto el ruido Poisson como el impacto del artefacto escalera, se emplea una técnica denominada realce por similaridad global, este tipo de realce consiste en la aplicación de un banco de filtros, suavizadores y un detector de bordes, cuyo propósito es generar una imagen en la cual se agrupa la información de las estructuras anatómicas, que conforman las imágenes originales; la segunda fase, considerando las imágenes filtradas, se utiliza información a priori acerca de la localización de la válvula aórtica y un paradigma de aprendizaje, basado en máquinas de soporte vectorial, para definir una región de interés que aísla la AAAV de estructuras anatómicas vecinas. Por otra parte, para generar la morfología 3-D de la TAA, se aplica una etapa de segmentación la cual considera las imágenes filtradas y un algoritmo de agrupamiento basado en crecimiento de regiones. La estrategia propuesta genera las segmentaciones 3-D de la AAAV en todas las imágenes que conforman el ciclo cardiaco completo del sujeto considerado. Para cuantificar el desempeño de la referida técnica se consideró el coeficiente de Dice obteniéndose una buena correlación entre las segmentaciones automáticas y las manuales generadas por un cardiólogo. Las segmentaciones generadas automáticamente pueden ser útiles en la detección de ciertas patologías que afectan tanto la arteria aorta como estructuras anatómicas, asociadas con ella, tales como la válvula aorta y el ventrículo izquierdo. [ABSTRACT FROM AUTHOR]
	Copyright of Revista Latinoamericana de Hipertensión is the property of Revista Latinoamericana de Hipertension and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	MedicLatina

Description
Abstract:	The present work proposes a technique for the automatic segmentation of the anatomic set consisting of the ascending aorta + aortic valve (AAAV) in 10 three-dimensional (3-D) cardiac images of multi-cut computed tomography, belonging to the same subject. The mentioned technique consists of the stages of pre-processing and segmentation. The pre-processing stage includes two phases: the first, minimizes both Poisson noise and the impact of the staircase artifact, we use a technique called global similarity enhancement, this type of enhancement consists of the application of a bank of filters, softeners And a border detector, whose purpose is to generate an image in which the information of the anatomical structures, which make up the original images, is grouped together; the second phase, considering the filtered images, uses a priori information about the location of the aortic valve and a learning paradigm, based on vector support machines, to define a region of interest that isolates AAAV from neighboring anatomical structures. On the other hand, to generate the 3-D morphology of the TAA, a segmentation stage is applied which considers the filtered images and a clustering algorithm based on regions growth. The proposed strategy generates the 3-D segmentations of AAAV in all the images that make up the complete cardiac cycle of the subject considered. In order to quantify the performance of the referred technique, the Dice coefficient was considered, obtaining a good correlation between the automatic segmentations and the manual ones generated by a cardiologist. Automatically generated segmentations may be helpful in detecting certain pathologies that affect both the aorta and anatomical structures associated with it, such as the aorta and left ventricle. [ABSTRACT FROM AUTHOR]
ISSN:	18564550