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.

[1]  Maria João Quadrado,et al.  Subbasal Nerves and Highly Reflective Cells in Corneas of Diabetic Patients: In vivo Evaluation by Confocal Microscopy , 2005 .

[2]  C. Gooch,et al.  The Diabetic Neuropathies , 2004, The neurologist.

[3]  Alejandro F. Frangi,et al.  Muliscale Vessel Enhancement Filtering , 1998, MICCAI.

[4]  W. Rathmann,et al.  How should peripheral neuropathy be assessed in people with diabetes in primary care? A population‐based comparison of four measures , 2003, Diabetic medicine : a journal of the British Diabetic Association.

[5]  M. Engelgau,et al.  Diabetes trends in the U.S.: 1990-1998. , 2000, Diabetes care.

[6]  Rafael C. González,et al.  Digital image processing using MATLAB , 2006 .

[7]  Peter Kovesi,et al.  Symmetry and Asymmetry from Local Phase , 1997 .

[8]  W. Schady,et al.  Sural nerve fibre pathology in diabetic patients with mild neuropathy: relationship to pain, quantitative sensory testing and peripheral nerve electrophysiology , 2001, Acta Neuropathologica.

[9]  T. Park,et al.  Can diabetic neuropathy be prevented? , 2004, Diabetes research and clinical practice.

[10]  A. Beckett,et al.  AKUFO AND IBARAPA. , 1965, Lancet.

[11]  D. Altman,et al.  STATISTICAL METHODS FOR ASSESSING AGREEMENT BETWEEN TWO METHODS OF CLINICAL MEASUREMENT , 1986, The Lancet.

[12]  B. Masters,et al.  Three-dimensional confocal microscopy of the living human eye. , 2002, Annual review of biomedical engineering.

[13]  William M. Wells,et al.  Medical Image Computing and Computer-Assisted Intervention — MICCAI’98 , 1998, Lecture Notes in Computer Science.

[14]  Nathan Efron,et al.  Corneal nerve tortuosity in diabetic patients with neuropathy. , 2004, Investigative ophthalmology & visual science.

[15]  Dipika V Patel,et al.  Mapping of the normal human corneal sub-Basal nerve plexus by in vivo laser scanning confocal microscopy. , 2005, Investigative ophthalmology & visual science.

[16]  C. McGhee,et al.  Assessing the sub‐basal nerve plexus of the living healthy human cornea by in vivo confocal microscopy , 2002, Clinical & experimental ophthalmology.

[17]  Re Gonzalez,et al.  R.C. Eddins, Digital image processing using MATLAB, vol. Gatesmark Publishing Knoxville , 2009 .

[18]  Enrico Grisan,et al.  Automatic recognition of corneal nerve structures in images from confocal microscopy. , 2008, Investigative ophthalmology & visual science.

[19]  J. McArthur,et al.  Intraepidermal nerve fiber density in patients with painful sensory neuropathy , 1997, Neurology.

[20]  Milan Sonka,et al.  Liver segment approximation in CT data for surgical resection planning , 2004, SPIE Medical Imaging.

[21]  Edoardo Midena,et al.  Corneal diabetic neuropathy: a confocal microscopy study. , 2006, Journal of refractive surgery.

[22]  J. McLaren,et al.  Keratocyte Density: Comparison of Two Confocal Microscopes , 2004, Eye & contact lens.

[23]  R. A. Malik,et al.  Corneal confocal microscopy: a non-invasive surrogate of nerve fibre damage and repair in diabetic patients , 2003, Diabetologia.

[24]  E. Feldman,et al.  New developments in diabetic neuropathy , 2005, Current opinion in neurology.

[25]  Sameh A. Salem,et al.  Segmentation of retinal blood vessels based on analysis of the hessian matrix and Clustering Algorithm , 2007, 2007 15th European Signal Processing Conference.