Filtering and Segmentation of Retinal OCT Images

  • Miguel Alemán-FloresEmail author
  • Rafael Alemán-Flores
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10672)


This work presents a method for the segmentation of optical coherence tomography images of the retina. Before segmenting the tomography, anisotropic diffusion is applied to reduce noise, but preserve the relevant edges. Afterward, the intensity profile of the images is analyzed to extract an initial approximation for the segmentation of three bands within the retina. Finally, a combination of attraction and regularization terms is used to refine the segmentation by fitting the limits of the bands to the highest gradients and smoothing their shapes to make them more regular. From the bands extracted in the different slices of the tomography, a three-dimensional reconstruction is performed for a better visualization of the results.


  1. 1.
    Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 12(7), 629–639 (1990)CrossRefGoogle Scholar
  2. 2.
    Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contours. Int. J. Comput. Vis. 22(1), 61–79 (1997)CrossRefzbMATHGoogle Scholar
  3. 3.
    Alemán-Flores, M., Álvarez-León, L., Caselles, V.: Texture-oriented anisotropic filtering and geodesic active contours in breast tumor ultrasound segmentation. J. Math. Imaging Vis. 28(1), 81–97 (2007)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Alvarez, L., Baumela, L., Márquez-Neila, P., Henríquez, P.: A real time morphological snakes algorithm. Image Process. On Line 2, 1–7 (2012)CrossRefGoogle Scholar
  5. 5.
    Alvarez, L., Baumela, L., Henríquez, P., Márquez-Neila, P.: Morphological snakes. In: Proceedings CVPR, pp. 2197–2202 (2010)Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.Departamento de Informática y SistemasUniversidad de Las Palmas de Gran CanariaLas PalmasSpain
  2. 2.Departamento de MorfologíaUniversidad de Las Palmas de Gran CanariaLas PalmasSpain

Personalised recommendations