Automatic corneal nerves recognition for earlier diagnosis and follow-up of diabetic neuropathy

  • Authors:

  • Ana Ferreira;António Miguel Morgado;José Silvestre Silva

  • Affiliations:

  • IBILI – Institute of Biomedical Research in Light and Image, Faculty of Medicine, University of Coimbra, Portugal;IBILI – Institute of Biomedical Research in Light and Image, Faculty of Medicine, University of Coimbra, Portugal;Department of Physics, Faculty of Sciences and Technology, University of Coimbra, Portugal

  • Venue:
  • ICIAR'10 Proceedings of the 7th international conference on Image Analysis and Recognition - Volume Part II
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Peripheral diabetic neuropathy is a major cause of chronic disability in diabetic patients. Morphometric parameters of corneal nerves may be the basis of an ideal method for early diagnosis and assessment of diabetic neuropathy. We developed a fully automatic algorithm for corneal nerve segmentation and morphometric parameters extraction. Luminosity equalization was done using local methods. Images structures were enhanced through phase-shift analysis, followed by Hessian matrix computation for structure classification. Nerves were then reconstructed using morphological methods. The algorithm was evaluated using 10 images of corneal nerves, by comparing with manual tracking. The average percent of nerve correctly segmented was 88.5% ± 7.2%. The percent of false nerve segments was 3.9% ± 2.2%. The average difference between automatic and manual nerve lengths was -28.0 ± 30.3 μm. Running times were around 3 minutes. The algorithm produced good results similar to those reported in the literature.