Segmentación computacional de la aurícula derecha en imágenes de tomografía cardiaca

Yoleidy Huérfano, Miguel Vera, Atilio Del Mar, María Vera, Williams Salazar, José Chacón, Sandra Wilches-Duran, Modesto Graterol-Rivas, Maritza Torres, Victor Arias, Joselyn Rojas, Carem Prieto, Wilson Siguencia, Lisse Angarita, Rina Ortiz, Diana Rojas-Gomez, Carlos Garicano, Maricarmen Chacín, Julio Contreras-Velásquez, Valmore BermúdezAntonio Bravo

Resultado de la investigación: Contribución a una revistaArtículorevisión exhaustiva

2 Citas (Scopus)

Resumen

strategy for right atrium (RA) 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-based technique 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 RA segmentation, the region growing algorithm is applied to the preprocessed 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 RA segmentations, obtained by the proposed strategy, and manually RA 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 more than 0.82 average Ds indicating a good correlation between the segmentations generated by an expert cardiologist and those produced by the strategy developed.

Título traducido de la contribuciónRight atrium computational segmentation in cardiac tomography images
Idioma originalEspañol
Páginas (desde-hasta)79-84
Número de páginas6
PublicaciónRevista Latinoamericana de Hipertension
Volumen10
N.º4
EstadoPublicada - 1 ene 2015

Palabras clave

  • Cardiac images
  • Global similarity enhancement
  • Right atrium
  • Segmentation

Áreas temáticas de ASJC Scopus

  • Medicina interna
  • Cardiología y medicina cardiovascular

Huella

Profundice en los temas de investigación de 'Segmentación computacional de la aurícula derecha en imágenes de tomografía cardiaca'. En conjunto forman una huella única.

Citar esto