A fully automatic nerve segmentation and morphometric parameter quantification system for early diagnosis of diabetic neuropathy in corneal images

Diabetic Peripheral Neuropathy (DPN) is one of the most common types of diabetes that can affect the cornea. An accurate analysis of the nerve structures can assist the early diagnosis of this disease. This paper proposes a robust, fast and fully automatic nerve segmentation and morphometric parameter quantification system for corneal confocal microscope images. The segmentation part consists of three main steps. First, a preprocessing step is applied to enhance the visibility of the nerves and remove noise using anisotropic diffusion filtering, specifically a Coherence filter followed by Gaussian filtering. Second, morphological operations are applied to remove unwanted objects in the input image such as epithelial cells and small nerve segments. Finally, an edge detection step is applied to detect all the nerves in the input image. In this step, an efficient algorithm for connecting discontinuous nerves is proposed. In the morphometric parameters quantification part, a number of features are extracted, including thickness, tortuosity and length of nerve, which may be used for the early diagnosis of diabetic polyneuropathy and when planning Laser-Assisted in situ Keratomileusis (LASIK) or Photorefractive keratectomy (PRK). The performance of the proposed segmentation system is evaluated against manually traced ground-truth images based on a database consisting of 498 corneal sub-basal nerve images (238 are normal and 260 are abnormal). In addition, the robustness and efficiency of the proposed system in extracting morphometric features with clinical utility was evaluated in 919 images taken from healthy subjects and diabetic patients with and without neuropathy. We demonstrate rapid (13 seconds/image), robust and effective automated corneal nerve quantification. The proposed system will be deployed as a useful clinical tool to support the expertise of ophthalmologists and save the clinician time in a busy clinical setting.

[1]  Dipika V Patel,et al.  Mapping the corneal sub-basal nerve plexus in keratoconus by in vivo laser scanning confocal microscopy. , 2006, Investigative ophthalmology & visual science.

[2]  N. Pritchard,et al.  Natural history of corneal nerve morphology in mild neuropathy associated with type 1 diabetes: development of a potential measure of diabetic peripheral neuropathy. , 2014, Investigative ophthalmology & visual science.

[3]  P. Hamrah,et al.  Corneal nerve alterations in acute Acanthamoeba and fungal keratitis: an in vivo confocal microscopy study , 2009, Eye.

[4]  Rami Qahwaji,et al.  An Automatic Corneal Subbasal Nerve Registration System Using FFT and Phase Correlation Techniques for an Accurate DPN Diagnosis , 2015, 2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing.

[5]  Alfredo Ruggeri,et al.  A fully-automatic fast segmentation of the sub-basal layer nerves in corneal images , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[6]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[7]  Alfredo Ruggeri,et al.  Automatic evaluation of corneal nerve tortuosity in images from in vivo confocal microscopy. , 2011, Investigative ophthalmology & visual science.

[8]  T. Tervo,et al.  Long-term corneal morphology after PRK by in vivo confocal microscopy. , 2003, Investigative ophthalmology & visual science.

[9]  Sanjay V. Patel,et al.  Confocal microscopy in vivo in corneas of long-term contact lens wearers. , 2002, Investigative ophthalmology & visual science.

[10]  R. Qahwaji,et al.  An efficient intelligent analysis system for confocal corneal endothelium images , 2015, Comput. Methods Programs Biomed..

[11]  Nathan Efron,et al.  Corneal Confocal Microscopy Detects Early Nerve Regeneration in Diabetic Neuropathy After Simultaneous Pancreas and Kidney Transplantation , 2012, Diabetes.

[12]  Elise M. Halpern,et al.  In vivo corneal confocal microscopy and prediction of future-incident neuropathy in type 1 diabetes: a preliminary longitudinal analysis. , 2015, Canadian journal of diabetes.

[13]  Peter Kulchyski.  and , 2015 .

[14]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Wenyuan Xu,et al.  Behavioral analysis of anisotropic diffusion in image processing , 1996, IEEE Trans. Image Process..

[16]  M. Meilă.  Comparing clusterings---an information based distance , 2007 .

[17]  M. Coroneo,et al.  In vivo confocal microscopy of the human cornea , 2003, The British journal of ophthalmology.

[18]  M. A. Dabbah,et al.  Automatic analysis of diabetic peripheral neuropathy using multi-scale quantitative morphology of nerve fibres in corneal confocal microscopy imaging , 2011, Medical Image Anal..

[19]  Max A. Viergever,et al.  Noise Reduction in Computed Tomography Scans Using 3-D Anisotropic Hybrid Diffusion With Continuous Switch , 2009, IEEE Transactions on Medical Imaging.

[20]  Yong Huang,et al.  Texture decomposition by harmonics extraction from higher order statistics , 2004, IEEE Trans. Image Process..

[21]  Mhd Saeed Sharif,et al.  Preparation of 2D sequences of corneal images for 3D model building , 2014, Comput. Methods Programs Biomed..

[22]  Mhd Saeed Sharif,et al.  An efficient system for preprocessing confocal corneal images for subsequent analysis , 2014, 2014 14th UK Workshop on Computational Intelligence (UKCI).

[23]  G. Bitirgen,et al.  Corneal nerve fibre damage precedes diabetic retinopathy in patients with Type 2 diabetes mellitus , 2014, Diabetic medicine : a journal of the British Diabetic Association.

[24]  R. Malik,et al.  Evaluation of contact lens-induced changes in keratoconic corneas using in vivo confocal microscopy. , 2013, Investigative ophthalmology & visual science.

[25]  C. McGhee,et al.  Corneal innervation and cellular changes after corneal transplantation: an in vivo confocal microscopy study. , 2007, Investigative ophthalmology & visual science.

[26]  Jitendra Malik,et al.  A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[27]  Cornelis H. Slump,et al.  Optimized Anisotropic Rotational Invariant Diffusion Scheme on Cone-Beam CT , 2010, MICCAI.

[28]  A. Boulton,et al.  Corneal Nerve Loss Detected With Corneal Confocal Microscopy Is Symmetrical and Related to the Severity of Diabetic Polyneuropathy , 2013, Diabetes Care.

[29]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[30]  A S Frangakis,et al.  Noise reduction in electron tomographic reconstructions using nonlinear anisotropic diffusion. , 2001, Journal of structural biology.

[31]  Nathan Efron,et al.  Corneal Confocal Microscopy Predicts 4-Year Incident Peripheral Neuropathy in Type 1 Diabetes , 2015, Diabetes Care.

[32]  C. O'donnell,et al.  An evaluation of corneal nerve morphology and function in moderate keratoconus. , 2005, Contact lens & anterior eye : the journal of the British Contact Lens Association.

[33]  A. Boulton,et al.  Corneal Confocal Microscopy Detects Neuropathy in Subjects With Impaired Glucose Tolerance , 2014, Diabetes Care.

[34]  A. Boulton,et al.  Corneal Confocal Microscopy Identifies Small-Fiber Neuropathy in Subjects With Impaired Glucose Tolerance Who Develop Type 2 Diabetes , 2015, Diabetes Care.

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

[36]  Nathan Efron,et al.  Surrogate Markers of Small Fiber Damage in Human Diabetic Neuropathy , 2007, Diabetes.

[37]  A. Nettel-Aguirre,et al.  The Reliability and Reproducibility of Corneal Confocal Microscopy in Children. , 2015, Investigative ophthalmology & visual science.

[38]  Ali N. Akansu,et al.  A class of fast Gaussian binomial filters for speech and image processing , 1991, IEEE Trans. Signal Process..

[39]  Hanno Scharr,et al.  A Scheme for Coherence-Enhancing Diffusion Filtering with Optimized Rotation Invariance , 2002, J. Vis. Commun. Image Represent..

[40]  S. Plainis.  Contact Lens & Anterior Eye , 2013 .

[41]  R. Malik,et al.  In vivo corneal confocal microscopic analysis in patients with keratoconus. , 2015, International journal of ophthalmology.

[42]  E. LESTER SMITH,et al.  AND OTHERS , 2005 .

[43]  Xin Chen,et al.  Rapid automated diagnosis of diabetic peripheral neuropathy with in vivo corneal confocal microscopy. , 2014, Investigative ophthalmology & visual science.

[44]  Xin Chen,et al.  Repeatability of In Vivo Corneal Confocal Microscopy to Quantify Corneal Nerve Morphology , 2013, Cornea.

[45]  Ana Ferreira,et al.  A method for corneal nerves automatic segmentation and morphometric analysis , 2012, Comput. Methods Programs Biomed..

[46]  Alfredo Ruggeri,et al.  Automatic nerve tracking in confocal images of corneal subbasal epithelium , 2013, Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems.

[47]  Shruti Aggarwal,et al.  Tortuosity classification of corneal nerves images using a multiple-scale-multiple-window approach , 2014 .

[48]  A. Ruggeri,et al.  Analysis of corneal images for the recognition of nerve structures , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[49]  Mohammad A. Dabbah,et al.  Nerve fibre extraction in confocal corneal microscopy images for human diabetic neuropathy detection using gabor filters , 2009 .

[50]  Mohammad A. Dabbah,et al.  Small Nerve Fiber Quantification in the Diagnosis of Diabetic Sensorimotor Polyneuropathy: Comparing Corneal Confocal Microscopy With Intraepidermal Nerve Fiber Density , 2015, Diabetes Care.

[51]  M. A. Dabbah,et al.  Dual-Model Automatic Detection of Nerve-Fibres in Corneal Confocal Microscopy Images , 2010, MICCAI.

[52]  Bhabatosh Chanda,et al.  Enhancing effective depth-of-field by image fusion using mathematical morphology , 2006, Image Vis. Comput..

[53]  Joachim Weickert,et al.  Anisotropic diffusion in image processing , 1996 .

[54]  Sunil Agrawal,et al.  Integration of Clustering, Optimization and Partial Differential Equation Method for Improved Image Segmentation , 2012 .

[55]  António Miguel Morgado,et al.  Corneal nerves segmentation and morphometric parameters quantification for early detection of diabetic neuropathy , 2010 .