Automatic Corneal Nerves Recognition for Earlier Diagnosis and Follow-Up of Diabetic Neuropathy
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.
KeywordsCorneal nerves image segmentation diabetic neuropathy confocal microscopy
Unable to display preview. Download preview PDF.
- 7.Malik, R.A., Veves, A., Walker, D., Siddique, I., Lye, R.H., Schady, W., Boulton, A.J.M.: Sural nerve fibre pathology in diabetic patients with mild neuropathy: relationship to pain, quantitative sensory testing and peripheral nerve electrophysiology. Acta Neuropathologica 101, 367–374 (2001)Google Scholar
- 8.Holland, N.R., Stocks, A., Hauer, P., Cornblath, D.R., Griffin, J.W., McArthur, J.C.: Intraepidermal nerve fiber density in patients with painful sensory neuropathy. Neurology 48, 708–711 (1997)Google Scholar
- 10.Malik, R.A., Kallinikos, P., Abbott, C.A., van Schie, C.H.M., Morgan, P., Efron, N., Boulton, A.J.M.: Corneal confocal microscopy: a non-invasive surrogate of nerve fibre damage and repair in diabetic patients. Diabetologia 46, 683–688 (2003)Google Scholar
- 12.Popper, M., Quadrado, M.J., Morgado, A.M., Murta, J.N., Van Best, J.A., Muller, L.J.: Subbasal nerves and highly reflective cells in corneas of diabetic patients: In vivo evaluation by confocal microscopy. Investigative Ophthalmology & Visual Science 46, 879 (2005)Google Scholar
- 13.Midena, E., Brugin, E., Ghirlando, A., Sommavilla, M., et al.: Corneal diabetic neuropathy: A confocal microscopy study. Journal of Refractive Surgery 22, S1047–S1052 (2006)Google Scholar
- 18.Gonzalez, R.C., Woods, R.E., Eddins, S.L.: Digital Image Processing Using Matlab. Gatesmark Publishing (2009)Google Scholar
- 19.Kovesi, P.: Symmetry and Asymmetry from Local Phase. In: Tenth Australian Joint Conference on Artificial Intelligence, pp. 185–190 (1997)Google Scholar
- 20.Frangi, A.F., Niessen, W.J., et al.: Multiscale vessel enhancement filtering. In: Wells, W.M., Colchester, A.C.F., Delp, S.L. (eds.) MICCAI 1998. LNCS, vol. 1496, pp. 130–137. Springer, Heidelberg (1998)Google Scholar
- 21.Beichel, R., Pock, T., Janko, C., Zotter, R., et al.: Liver Segment Approximation in CT Data for Surgical Resection Planning. In: SPIE Medical Imaging 2004: Image Processing, vol. 5370, pp. 1435–1446 (2004)Google Scholar
- 22.Salem, N.M., Salem, S.A., Nandi, A.K.: Segmentation of Retinal Blood Vessels Based on Analysis of the Hessian Matrix and Clustering Algorithm. In: 15th European Signal Processing Conference, pp. 428–432 (2007)Google Scholar
- 23.Bland, J.M., Altman, D.G.: Statistical methods for assessing agreement between two methods of clinical measurement. Lancet 1, 307–310 (1986)Google Scholar