Segmentación computacional de la vena cava superior y procesos hipertensivos

Yoleidy Huérfano, Miguel Vera, Atilio Del Mar, María Vera, José Chacón, Sandra Wilches-Duran, Modesto Graterol-Rivas, Maritza Torres, Víctor Arias, Joselyn Rojas, Carem Prieto, Wilson Siguencia, Lisse Angarita, Rina Ortiz, Diana Rojas-Gomez, Carlos Garicano, Daniela Riaño-Wilches, Maricarmen Chacín, Julio Contreras-Velásquez, Valmore Bermúdez & 1 otros Antonio Bravo

Resultado de la investigación: Research - revisión exhaustivaArticle

  • 1 Citas

Resumen

Astrategy for superior vena cava (SVC) 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 SVC 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 SVC segmentations, obtained by the proposed strategy, and manually SVC 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 0.9 average Ds indicating an excellent correlation between the segmentations generated by an expert cardiologist and those produced by the strategy developed.

IdiomaSpanish
Páginas25-29
Número de páginas5
PublicaciónRevista Latinoamericana de Hipertension
Volumen11
Número de edición2
EstadoPublished - 2016

Keywords

    ASJC Scopus subject areas

    • Internal Medicine
    • Cardiology and Cardiovascular Medicine

    Citar esto

    Huérfano, Y., Vera, M., Del Mar, A., Vera, M., Chacón, J., Wilches-Duran, S., ... Bravo, A. (2016). Segmentación computacional de la vena cava superior y procesos hipertensivos. Revista Latinoamericana de Hipertension, 11(2), 25-29.
    Huérfano, Yoleidy ; Vera, Miguel ; Del Mar, Atilio ; Vera, María ; Chacón, José ; Wilches-Duran, Sandra ; Graterol-Rivas, Modesto ; Torres, Maritza ; Arias, Víctor ; Rojas, Joselyn ; Prieto, Carem ; Siguencia, Wilson ; Angarita, Lisse ; Ortiz, Rina ; Rojas-Gomez, Diana ; Garicano, Carlos ; Riaño-Wilches, Daniela ; Chacín, Maricarmen ; Contreras-Velásquez, Julio ; Bermúdez, Valmore ; Bravo, Antonio. / Segmentación computacional de la vena cava superior y procesos hipertensivos. En: Revista Latinoamericana de Hipertension. 2016 ; Vol. 11, N.º 2. pp. 25-29
    @article{b46b327a4e56473499e1cf7ef37ca575,
    title = "Segmentación computacional de la vena cava superior y procesos hipertensivos",
    abstract = "Astrategy for superior vena cava (SVC) 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 SVC 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 SVC segmentations, obtained by the proposed strategy, and manually SVC 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 0.9 average Ds indicating an excellent correlation between the segmentations generated by an expert cardiologist and those produced by the strategy developed.",
    keywords = "Global similarity enhancement, Segmentation., Superior vena cava",
    author = "Yoleidy Huérfano and Miguel Vera and {Del Mar}, Atilio and María Vera and José Chacón and Sandra Wilches-Duran and Modesto Graterol-Rivas and Maritza Torres and Víctor Arias and Joselyn Rojas and Carem Prieto and Wilson Siguencia and Lisse Angarita and Rina Ortiz and Diana Rojas-Gomez and Carlos Garicano and Daniela Riaño-Wilches and Maricarmen Chacín and Julio Contreras-Velásquez and Valmore Bermúdez and Antonio Bravo",
    year = "2016",
    volume = "11",
    pages = "25--29",
    journal = "Revista Latinoamericana de Hipertension",
    issn = "1856-4550",
    publisher = "Sociedad Latinoamericana de Hipertension",
    number = "2",

    }

    Huérfano, Y, Vera, M, Del Mar, A, Vera, M, Chacón, J, Wilches-Duran, S, Graterol-Rivas, M, Torres, M, Arias, V, Rojas, J, Prieto, C, Siguencia, W, Angarita, L, Ortiz, R, Rojas-Gomez, D, Garicano, C, Riaño-Wilches, D, Chacín, M, Contreras-Velásquez, J, Bermúdez, V & Bravo, A 2016, 'Segmentación computacional de la vena cava superior y procesos hipertensivos' Revista Latinoamericana de Hipertension, vol. 11, n.º 2, pp. 25-29.

    Segmentación computacional de la vena cava superior y procesos hipertensivos. / Huérfano, Yoleidy; Vera, Miguel; Del Mar, Atilio; Vera, María; Chacón, José; Wilches-Duran, Sandra; Graterol-Rivas, Modesto; Torres, Maritza; Arias, Víctor; Rojas, Joselyn; Prieto, Carem; Siguencia, Wilson; Angarita, Lisse; Ortiz, Rina; Rojas-Gomez, Diana; Garicano, Carlos; Riaño-Wilches, Daniela; Chacín, Maricarmen; Contreras-Velásquez, Julio; Bermúdez, Valmore; Bravo, Antonio.

    En: Revista Latinoamericana de Hipertension, Vol. 11, N.º 2, 2016, p. 25-29.

    Resultado de la investigación: Research - revisión exhaustivaArticle

    TY - JOUR

    T1 - Segmentación computacional de la vena cava superior y procesos hipertensivos

    AU - Huérfano,Yoleidy

    AU - Vera,Miguel

    AU - Del Mar,Atilio

    AU - Vera,María

    AU - Chacón,José

    AU - Wilches-Duran,Sandra

    AU - Graterol-Rivas,Modesto

    AU - Torres,Maritza

    AU - Arias,Víctor

    AU - Rojas,Joselyn

    AU - Prieto,Carem

    AU - Siguencia,Wilson

    AU - Angarita,Lisse

    AU - Ortiz,Rina

    AU - Rojas-Gomez,Diana

    AU - Garicano,Carlos

    AU - Riaño-Wilches,Daniela

    AU - Chacín,Maricarmen

    AU - Contreras-Velásquez,Julio

    AU - Bermúdez,Valmore

    AU - Bravo,Antonio

    PY - 2016

    Y1 - 2016

    N2 - Astrategy for superior vena cava (SVC) 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 SVC 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 SVC segmentations, obtained by the proposed strategy, and manually SVC 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 0.9 average Ds indicating an excellent correlation between the segmentations generated by an expert cardiologist and those produced by the strategy developed.

    AB - Astrategy for superior vena cava (SVC) 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 SVC 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 SVC segmentations, obtained by the proposed strategy, and manually SVC 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 0.9 average Ds indicating an excellent correlation between the segmentations generated by an expert cardiologist and those produced by the strategy developed.

    KW - Global similarity enhancement

    KW - Segmentation.

    KW - Superior vena cava

    UR - http://www.scopus.com/inward/record.url?scp=85019025892&partnerID=8YFLogxK

    M3 - Article

    VL - 11

    SP - 25

    EP - 29

    JO - Revista Latinoamericana de Hipertension

    T2 - Revista Latinoamericana de Hipertension

    JF - Revista Latinoamericana de Hipertension

    SN - 1856-4550

    IS - 2

    ER -

    Huérfano Y, Vera M, Del Mar A, Vera M, Chacón J, Wilches-Duran S y otros. Segmentación computacional de la vena cava superior y procesos hipertensivos. Revista Latinoamericana de Hipertension. 2016;11(2):25-29.