Automatic detection of microaneurysms in diabetic retinopathy fundus images using the L<sup>¿</sup>a<sup>¿</sup>b color space

Journal ar
Journal of the Optical Society of America A: Optics and Image Science, and Vision
  • Volumen: 33
  • Número: 1
  • Fecha: 01 January 2016
  • Páginas: 74-83
  • ISSN: 15208532 10847529
  • Source Type: Journal
  • DOI: 10.1364/JOSAA.33.000074
  • Document Type: Article
  • Publisher: OSA - The Optical Society
© 2015 Optical Society of America. We develop an automated image processing system for detecting microaneurysm (MA) in diabetic patients. Diabetic retinopathy is one of the main causes of preventable blindness in working age diabetic people with the presence of an MA being one of the first signs. We transform the eye fundus images to the L¿a¿b¿ color space in order to separately process the L¿ and a¿ channels, looking for MAs in each of them. We then fuse the results, and last send the MA candidates to a k-nearest neighbors classifier for final assessment. The performance of the method, measured against 50 images with an ophthalmologist's hand-drawn ground-truth, shows high sensitivity (100%) and accuracy (84%), and running times around 10 s. This kind of automatic image processing application is important in order to reduce the burden on the public health system associated with the diagnosis of diabetic retinopathy given the high number of potential patients that need periodic screening.

Author keywords

    Indexed keywords

      Funding details