Biologically-inspired supervised vasculature segmentation in SLO retinal fundus images

S. Abbasi-Sureshjani, I.M. Smit-Ockeloen, J. Zhang, B.M. ter Haar Romenij

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

43 Citations (Scopus)
1 Downloads (Pure)


We propose a novel Brain-Inspired Multi-Scales and Multi-Orientations (BIMSO) segmentation technique for the retinal images taken with laser ophthalmoscope (SLO) imaging cameras. Conventional retinal segmentation methods have been designed mainly for color RGB images and they often fail in segmenting the SLO images because of the presence of noise in these images. We suppress the noise and enhance the blood vessels by lifting the 2D image to a joint space of positions and orientations (SE(2)) using the directional anisotropic wavelets. Then a neural network classifier is trained and tested using several features including the intensity of pixels, filter response to the wavelet and multi-scale left-invariant Gaussian derivatives jet in SE(2). BIMSO is robust against noise, non-uniform luminosity and contrast variability. In addition to preserving the connections, it has higher sensitivity and detects the small vessels better compared to state-of-the-art methods for both RGB and SLO images.
Original languageEnglish
Title of host publicationImage Analysis and Recognition
Subtitle of host publication12th International Conference, ICIAR 2015, Niagara Falls, ON, Canada, July 22-24, 2015, Proceedings
Place of PublicationBerlin
Number of pages10
ISBN (Electronic)978-3-319-20801-5
ISBN (Print)978-3-319-20800-8
Publication statusPublished - 4 Jul 2015
Event12th International Conference on Image Analysis and Recognition (ICIAR 2015) - Niagara Falls, Canada
Duration: 22 Jul 201524 Jul 2015
Conference number: 12


Conference12th International Conference on Image Analysis and Recognition (ICIAR 2015)
Abbreviated titleICIAR 2015
CityNiagara Falls
Internet address


  • Scanning laser ophthalmoscope
  • Primary visual cortex
  • Anisotropic wavelets
  • Multi-scale Orientation score
  • Left-invariant Gaussian derivatives
  • Blood vessel segmentation
  • Diabetic retinopathy


Dive into the research topics of 'Biologically-inspired supervised vasculature segmentation in SLO retinal fundus images'. Together they form a unique fingerprint.

Cite this