Conference Proceeding

Tortuosity classification of corneal nerves images using a multiple-scale-multiple-window approach

  • Roberto Annunziata (University of Dundee)
  • Ahmad Kheirkhah (Harvard Medical School)
  • Shruti Aggarwal (Harvard Medical School)
  • Bernardo M. Cavalcanti (Harvard Medical School)
  • Pedram Hamrah (Harvard Medical School)
  • Emanuele Trucco (University of Dundee)


Classify in vivo confocal microscopy corneal images by tortuosity is complicated by the presence of variable numbers of fibres of different tortuosity level. Instead of designing a function combining manually selected features into a single coefficient, as done in the literature, we propose a supervised approach which selects automatically the most relevant combination of shape features from a pre-defined dictionary. To our best knowledge, we are the first to consider features at different spatial scales and show experimentally their relevance in tortuosity modelling. Our results, obtained with a set of 100 images and 20 fold cross-validation, suggest that multinomial logistic ordinal regression, trained on consensus ground truth from 3 experts, yields an accuracy indistinguishable, overall, from that of experts when compared against each other.

How to Cite:

Annunziata, R. & Kheirkhah, A. & Aggarwal, S. & Cavalcanti, B. M. & Hamrah, P. & Trucco, E., (2014) “Tortuosity classification of corneal nerves images using a multiple-scale-multiple-window approach”, Proceedings of the Ophthalmic Medical Image Analysis International Workshop 1(2014), 113-120. doi:

Rights: Copyright © 2014, Roberto Annunziata, Ahmad Kheirkhah, Shruti Aggarwal, Bernardo M. Cavalcanti, Pedram Hamrah, and Emanuele Trucco.

Download pdf
View PDF



Published on
14 Sep 2014
Peer Reviewed