SciELO - Scientific Electronic Library Online

 
vol.20 issue1Una revisión de la literatura Multiobjective optimization in biofuel supply chain management. A review of the literatureA Mobile Augmented Reality Application for Teaching the Classification of Living Things to Primary School's Children author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand

Journal

Article

Indicators

Related links

  • On index processCited by Google
  • Have no similar articlesSimilars in SciELO
  • On index processSimilars in Google

Share


Ingeniería

Print version ISSN 0121-750XOn-line version ISSN 2344-8393

Abstract

BALLESTEROS MALDONADO, Angee Paola; LOPEZ ALZA, Laura Catalina  and  HERRERA GARCIA, Rodrido Javier. Segmentation and nasal line counting in ultrasound fetal images at the 11-13+6 weeks of gestation. ing. [online]. 2015, vol.20, n.1, pp.21-34. ISSN 0121-750X.

This document introduces a method for nasal segmentation and the subsequent counting of lines corresponding to the skin, nasal bone and the tip of the nose in 2D fetal ultrasound images of the first gestational trimester from 11 to 13 weeks and 6 days (11- 13+6 weeks). Presence of the three lines in the nasal region is one of the features that should have the fetus on ultrasound image to ensure the reliability of the measurement of fetal nuchal translucency thickness; this measurement is used to identify the possible existence of syndromes or chromosomal abnormalities. The method is applied to the mid-sagittal head plane where the hyperintense regions have been identified. The segmentation is hierarchical: first, the nose is identified by the combination of a regional maxima and high eccentricity detection algorithms; then the aforementioned lines are identified using K-means clustering and mathematical morphology. Because of uncertainty between images with respect to fetal position, resolution, noise and dynamic range, the results ranging from cases in which the region of interest is not found, to those where the lines are clearly identifiable.

Keywords : Homomorphic filtering; H-maxima transform; morphological reconstruction; geodesic dilation; eccentricity and clustering.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )

 

Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License