OBJECTIVE: Quantitative assessment of small fiber damage is key to the early diagnosis and assessment of progression or regression of diabetic sensorimotor polyneuropathy (DSPN). Intraepidermal nerve fiber density (IENFD) is the current gold standard, but corneal confocal microscopy (CCM), an in vivo ophthalmic imaging modality, has the potential to be a noninvasive and objective image biomarker for identifying small fiber damage. The purpose of this study was to determine the diagnostic performance of CCM and IENFD by using the current guidelines as the reference standard. RESEARCH DESIGN AND METHODS: Eighty-nine subjects (26 control subjects and 63 patients with type 1 diabetes), with and without DSPN, underwent a detailed assessment of neuropathy, including CCM and skin biopsy. RESULTS: Manual and automated corneal nerve fiber density (CNFD) (P < 0.0001), branch density (CNBD) (P < 0.0001) and length (CNFL) (P < 0.0001), and IENFD (P < 0.001) were significantly reduced in patients with diabetes with DSPN compared with control subjects. The area under the receiver operating characteristic curve for identifying DSPN was 0.82 for manual CNFD, 0.80 for automated CNFD, and 0.66 for IENFD, which did not differ significantly (P = 0.14). CONCLUSIONS: This study shows comparable diagnostic efficiency between CCM and IENFD, providing further support for the clinical utility of CCM as a surrogate end point for DSPN.

OBJECTIVE: Corneal confocal microscopy is a novel diagnostic technique for the detection of nerve damage and repair in a range of peripheral neuropathies, in particular diabetic neuropathy. Normative reference values are required to enable clinical translation and wider use of this technique. We have therefore undertaken a multicenter collaboration to provide worldwide age-adjusted normative values of corneal nerve fiber parameters. RESEARCH DESIGN AND METHODS: A total of 1,965 corneal nerve images from 343 healthy volunteers were pooled from six clinical academic centers. All subjects underwent examination with the Heidelberg Retina Tomograph corneal confocal microscope. Images of the central corneal subbasal nerve plexus were acquired by each center using a standard protocol and analyzed by three trained examiners using manual tracing and semiautomated software (CCMetrics). Age trends were established using simple linear regression, and normative corneal nerve fiber density (CNFD), corneal nerve fiber branch density (CNBD), corneal nerve fiber length (CNFL), and corneal nerve fiber tortuosity (CNFT) reference values were calculated using quantile regression analysis. RESULTS: There was a significant linear age-dependent decrease in CNFD (−0.164 no./mm2 per year for men, P < 0.01, and −0.161 no./mm2 per year for women, P < 0.01). There was no change with age in CNBD (0.192 no./mm2 per year for men, P = 0.26, and −0.050 no./mm2 per year for women, P = 0.78). CNFL decreased in men (−0.045 mm/mm2 per year, P = 0.07) and women (−0.060 mm/mm2 per year, P = 0.02). CNFT increased with age in men (0.044 per year, P < 0.01) and women (0.046 per year, P < 0.01). Height, weight, and BMI did not influence the 5th percentile normative values for any corneal nerve parameter. CONCLUSIONS: This study provides robust worldwide normative reference values for corneal nerve parameters to be used in research and clinical practice in the study of diabetic and other peripheral neuropathies.

Aims/hypothesis: Corneal confocal microscopy is a rapid non-invasive ophthalmic imaging technique that identifies peripheral and central neurodegenerative disease. Quantification of corneal sub-basal nerve plexus morphology, however, requires either time-consuming manual annotation or a less-sensitive automated image analysis approach. We aimed to develop and validate an artificial intelligence-based, deep learning algorithm for the quantification of nerve fibre properties relevant to the diagnosis of diabetic neuropathy and to compare it with a validated automated analysis program, ACCMetrics.Methods: Our deep learning algorithm, which employs a convolutional neural network with data augmentation, was developed for the automated quantification of the corneal sub-basal nerve plexus for the diagnosis of diabetic neuropathy. The algorithm was trained using a high-end graphics processor unit on 1698 corneal confocal microscopy images; for external validation, it was further tested on 2137 images. The algorithm was developed to identify total nerve fibre length, branch points, tail points, number and length of nerve segments, and fractal numbers. Sensitivity analyses were undertaken to determine the AUC for ACCMetrics and our algorithm for the diagnosis of diabetic neuropathy.Results: The intraclass correlation coefficients for our algorithm were superior to those for ACCMetrics for total corneal nerve fibre length (0.933 vs 0.825), mean length per segment (0.656 vs 0.325), number of branch points (0.891 vs 0.570), number of tail points (0.623 vs 0.257), number of nerve segments (0.878 vs 0.504) and fractals (0.927 vs 0.758). In addition, our proposed algorithm achieved an AUC of 0.83, specificity of 0.87 and sensitivity of 0.68 for the classification of participants without (n= 90) and with (n= 132) neuropathy (defined by the Toronto criteria).Conclusions/interpretation: These results demonstrated that our deep learning algorithm provides rapid and excellent localisation performance for the quantification of corneal nerve biomarkers. This model has potential for adoption into clinical screening programmes for diabetic neuropathy.Data availability: The publicly shared cornea nerve dataset (dataset 1) is available athttp://bioimlab.dei.unipd.it/Corneal%20Nerve%20Tortuosity%20Data%20Set.htmandhttp://bioimlab.dei.unipd.it/Corneal%20Nerve%20Data%20Set.htm.

Autonomic and somatic denervation is well established in Parkinson's disease (PD). (1) To determine whether corneal confocal microscopy (CCM) can non-invasively demonstrate small nerve fiber damage in PD. (2) To identify relationships between corneal nerve parameters, intraepidermal nerve fiber density (IENFD) and clinical features of PD. Twenty-six PD patients and 26 controls underwent CCM of both eyes. 24/26 PD patients and 10/26 controls underwent skin biopsies from the dorsa of both feet. PD patients underwent assessment of parasympathetic function [deep breathing heart rate variability (DB-HRV)], autonomic symptoms [scale for outcomes in Parkinson's disease - autonomic symptoms (SCOPA-AUT)], motor symptoms [UPDRS-III "ON"] and cumulative Levodopa dose. PD patients had significantly reduced corneal nerve fiber density (CNFD) with increased corneal nerve branch density (CNBD) and corneal nerve fiber length (CNFL) compared to controls. CNBD and CNFL but not CNFD correlated inversely with UPDRS-III and SCOPA-AUT. All CCM parameters correlated strongly with DB-HRV. There was no correlation between CCM parameters and disease duration, cumulative Levodopa dose or pain. IENFD was significantly reduced in PD compared to controls and correlated with CNFD and UPDRS-III. However, unlike CCM measures, IENFD correlated with disease duration and cumulative Levodopa dose but not with autonomic dysfunction. CCM identifies corneal nerve fiber pathology, which correlates with autonomic symptoms, parasympathetic deficits and motor scores in patients with PD. IENFD is also reduced and correlates with CNFD and motor symptoms but not parasympathetic deficits, indicating it detects different aspects of peripheral nerve pathology in PD.

OBJECTIVE: Impaired glucose tolerance (IGT) through to type 2 diabetes is thought to confer a continuum of risk for neuropathy. Identification of subjects at high risk of developing type 2 diabetes and, hence, worsening neuropathy would allow identification and risk stratification for more aggressive management. RESEARCH DESIGN AND METHODS: Thirty subjects with IGT and 17 age-matched control subjects underwent an oral glucose tolerance test, assessment of neuropathic symptoms and deficits, quantitative sensory testing, neurophysiology, skin biopsy, and corneal confocal microscopy (CCM) to quantify corneal nerve fiber density (CNFD), branch density (CNBD), and fiber length (CNFL) at baseline and annually for 3 years. RESULTS: Ten subjects who developed type 2 diabetes had a significantly lower CNFD (P = 0.003), CNBD (P = 0.04), and CNFL (P = 0.04) compared with control subjects at baseline and a further reduction in CNFL (P = 0.006), intraepidermal nerve fiber density (IENFD) (P = 0.02), and mean dendritic length (MDL) (P = 0.02) over 3 years. Fifteen subjects who remained IGT and 5 subjects who returned to normal glucose tolerance had no significant baseline abnormality on CCM or IENFD but had a lower MDL (P < 0.0001) compared with control subjects. The IGT subjects showed a significant decrease in IENFD (P = 0.02) but no change in MDL or CCM over 3 years. Those who returned to NGT showed an increase in CNFD (P = 0.05), CNBD (P = 0.04), and CNFL (P = 0.05), but a decrease in IENFD (P = 0.02), over 3 years. CONCLUSIONS: CCM and skin biopsy detect a small-fiber neuropathy in subjects with IGT who develop type 2 diabetes and also show a dynamic worsening or improvement in corneal and intraepidermal nerve morphology in relation to change in glucose tolerance status.