Explore the vast range of titles available.

Aims/hypothesisCorneal 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.MethodsOur 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.ResultsThe 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/interpretationThese 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 availabilityThe publicly shared cornea nerve dataset (dataset 1) is available at http://bioimlab.dei.unipd.it/Corneal%20Nerve%20Tortuosity%20Data%20Set.htm and http://bioimlab.dei.unipd.it/Corneal%20Nerve%20Data%20Set.htm.

Introduction Corneal confocal microscopy (CCM) is a rapid non‐invasive ophthalmic imaging technique that identifies corneal nerve fiber damage. Small studies suggest that CCM could be used to assess patients with diabetic peripheral neuropathy (DPN). Aim To undertake a systematic review and meta‐analysis assessing the diagnostic utility of CCM for sub‐clinical DPN (DPN−) and established DPN (DPN+). Data sources Databases (PubMed, Embase, Central, ProQuest) were searched for studies using CCM in patients with diabetes up to April 2020. Study selection Studies were included if they reported on at least one CCM parameter in patients with diabetes. Data extraction Corneal nerve fiber density (CNFD), corneal nerve branch density (CNBD), corneal nerve fiber length (CNFL), and inferior whorl length (IWL) were compared between patients with diabetes with and without DPN and controls. Meta‐analysis was undertaken using RevMan V.5.3. Data synthesis Thirty‐eight studies including ~4,000 participants were included in this meta‐analysis. There were significant reductions in CNFD, CNBD, CNFL, and IWL in DPN− vs controls (P < 0.00001), DPN+ vs controls (P < 0.00001), and DPN+ vs DPN− (P < 0.00001). Conclusion This systematic review and meta‐analysis shows that CCM detects small nerve fiber loss in subclinical and clinical DPN and concludes that CCM has good diagnostic utility in DPN. This meta‐analysis of ~4,000 participants shows that corneal confocal microscopy is a rapid objective ophthalmic technique for the assessment of subclinical and clinical diabetic neuropathy. Forest plot of corneal nerve fiber length (CNFL) in patients with diabetic peripheral neuropathy (DPN+) and without diabetic peripheral neuropathy (DNP−).

Corneal confocal microscopy (CCM) is a rapid, non-invasive, reproducible technique that quantifies small nerve fibres. We have compared the diagnostic capability of CCM against a range of established measures of nerve damage in patients with diabetic neuropathy. In this cross sectional study, thirty subjects with Type 1 diabetes without neuropathy (T1DM), thirty one T1DM subjects with neuropathy (DSPN) and twenty seven non-diabetic healthy control subjects underwent detailed assessment of neuropathic symptoms and neurologic deficits, quantitative sensory testing (QST), electrophysiology, skin biopsy and corneal confocal microscopy (CCM). Subjects with DSPN were older (C vs T1DM vs DSPN: 41.0±14.9 vs 38.8±12.5 vs 53.3±11.9, P = 0.0002), had a longer duration of diabetes (P<0.0001), lower eGFR (P = 0.006) and higher albumin-creatinine ratio (P = 0.03) with no significant difference for HbA1c, BMI, lipids and blood pressure. Patients with DSPN were representative of subjects with diabetic neuropathy with clinical signs and symptoms of neuropathy and greater neuropathy deficits quantified by QST, electrophysiology, intra-epidermal nerve fibre density and CCM. Corneal nerve fibre density (CNFD) (Spearman's Rho = 0.60 P<0.0001) and IENFD (Spearman's Rho = 0.56 P<0.0001) were comparable when correlated with peroneal nerve conduction velocity. For the diagnosis of diabetic neuropathy the sensitivity for CNFD was 0.77 and specificity was 0.79 with an area under the ROC curve of 0.81. IENFD had a diagnostic sensitivity of 0.61, specificity of 0.80 and area under the ROC curve of 0.73. CCM is a valid accurate non-invasive method to identify small nerve fibre pathology and is able to diagnose DPN.

Accurately quantifying the progression of diabetic peripheral neuropathy is key to identify individuals who will progress to foot ulceration and to power clinical intervention trials. We have undertaken detailed neuropathy phenotyping to assess the longitudinal utility of different measures of neuropathy in patients with diabetes. Nineteen patients with diabetes (age 52.5 ± 14.7 years, duration of diabetes 26.0 ± 13.8 years) and 19 healthy controls underwent assessment of symptoms and signs of neuropathy, quantitative sensory testing, autonomic nerve function, neurophysiology, intra-epidermal nerve fibre density (IENFD) and corneal confocal microscopy (CCM) to quantify corneal nerve fibre density (CNFD), branch density (CNBD) and fibre length (CNFL). Mean follow-up was 6.5 years. Glycated haemoglobin ( p  = 0.04), low-density lipoprotein-cholesterol (LDL-C) ( p  = 0.0009) and urinary albumin creatinine ratio ( p  < 0.0001) improved. Neuropathy symptom profile ( p  = 0.03), neuropathy disability score ( p  = 0.04), vibration perception threshold ( p  = 0.02), cold perception threshold ( p  = 0.006), CNFD ( p  = 0.03), CNBD ( p  < 0.0001), CNFL ( p  < 0.0001), IENFD ( p  = 0.04), sural ( p  = 0.02) and peroneal motor nerve conduction velocity ( p  = 0.03) deteriorated significantly. Change (∆) in CNFL correlated with ∆CPT ( p  = 0.006) and ∆Expiration/Inspiration ratio ( p  = 0.002) and ∆IENFD correlated with ∆CNFD ( p  = 0.005), ∆CNBD ( p  = 0.02) and ∆CNFL ( p  = 0.01). This study shows worsening of diabetic neuropathy across a range of neuropathy measures, especially CCM, despite an improvement in HbA1c and LDL-C. It further supports the utility of CCM as a rapid, non-invasive surrogate measure of diabetic neuropathy.

Obesity and associated dyslipidemia may contribute to increased cardiovascular disease. Obesity has also been associated with neuropathy. We have investigated presence of peripheral nerve damage in patients with severe obesity without type 2 diabetes and the status of metabolic syndrome and lipoprotein abnormalities. 47participants with severe obesity and 30 age-matched healthy controls underwent detailed phenotyping of neuropathy and an assessment of lipoproteins and HDL-functionality. Participants with severe obesity had a higher neuropathy symptom profile, lower sural and peroneal nerve amplitudes, abnormal thermal thresholds, heart rate variability with deep breathing and corneal nerve parameters compared to healthy controls. Circulating apolipoprotein A1 ( P  = 0.009), HDL cholesterol (HDL-C) ( P  < 0.0001), cholesterol efflux ( P  = 0.002) and paroxonase-1 (PON-1) activity ( P  < 0.0001) were lower, and serum amyloid A (SAA) ( P  < 0.0001) was higher in participants with obesity compared to controls. Obese participants with small nerve fibre damage had higher serum triglycerides ( P  = 0.02), lower PON-1 activity ( P  = 0.002) and higher prevalence of metabolic syndrome (58% vs. 23%, P  = 0.02) compared to those without. However, HDL-C ( P  = 0.8), cholesterol efflux ( P  = 0.08), apoA1 ( P  = 0.8) and SAA ( P  = 0.8) did not differ significantly between obese participants with and without small nerve fibre damage . Small nerve fibre damage occurs in people with severe obesity. Patients with obesity have deranged lipoproteins and compromised HDL functionality compared to controls. Obese patients with evidence of small nerve fibre damage, compared to those without, had significantly higher serum triglycerides, lower PON-1 activity and a higher prevalence of metabolic syndrome.

IntroductionSubjects with obesity have metabolic risk factors for nerve fibre damage. Because bariatric surgery improves these risk factors we have assessed whether this can ameliorate nerve fibre damage.MethodsTwenty-six obese subjects without diabetes (age: 46.23 ± 8.6, BMI: 48.7 ± 1.5, HbA1c: 38.0 ± 4.5) and 20 controls (age: 48.3 ± 6.2, BMI: 26.8 ± 4.2, HbA1c: 39.1 ± 2.6) underwent detailed assessment of neuropathy at baseline and 12 months after bariatric surgery.ResultsObese subjects had normal peroneal (45.9 ± 5.5 vs. 48.1 ± 4.5, P = 0.1) and sural (46.9 ± 7.6 vs. 47.9 ± 10.6, P = 0.1) nerve conduction velocity, but a significantly higher neuropathy symptom profile (NSP) (4.3 ± 5.7 vs. 0.3 ± 0.6, P = 0.001), vibration perception threshold (VPT) (V) (10.2 ± 6.8 vs. 4.8 ± 2.7, P < 0.0001), warm threshold (C°) (40.4 ± 3.5 vs. 37.2 ± 1.8, P = 0.003) and lower peroneal (3.8 ± 2.2 vs. 4.9 ± 2.2, P = 0.02) and sural (8.9 ± 5.8 vs. 15.2 ± 8.5, P < 0.0001) nerve amplitude, deep breathing-heart rate variability (DB-HRV) (beats/min) (21.7 ± 4.1 vs. 30.1 ± 14, P = 0.001), corneal nerve fibre density (CNFD) (n/mm2) (25.6 ± 5.3 vs. 32.0 ± 3.1, P < 0.0001), corneal nerve branch density (CNBD) (n/mm2) (56.9 ± 27.5 vs. 111.4 ± 30.7, P < 0.0001) and corneal nerve fibre length (CNFL) (mm/mm2) (17.9 ± 4.1 vs. 29.8 ± 4.9, P < 0.0001) compared to controls at baseline. In control subjects there was no change in neuropathy measures over 12 months. However, 12 months after bariatric surgery there was a significant reduction in BMI (33.7 ± 1.7 vs. 48.7 ± 1.5, P = 0.001), HbA1c (34.3 ± 0.6 vs. 38.0 ± 4.5, P = 0.0002), triglycerides (mmol/l) (1.3 ± 0.6 vs. 1.6 ± 0.8, P = 0.005) and low-density lipoprotein cholesterol (mmol/l) (2.7 ± 0.7 vs. 3.1 ± 0.9, P = 0.02) and an increase in high-density lipoprotein cholesterol (mmol/l) (1.2 ± 0.3 vs. 1.04 ± 0.2, P = 0.002). There was a significant improvement in NSP (1.6 ± 2.7 vs. 4.3 ± 5.7, P = 0.004), neuropathy disability score (0.3 ± 0.9 vs. 1.3 ± 2.0, P = 0.03), CNFD (28.2 ± 4.4 vs. 25.6 ± 5.3, P = 0.03), CNBD (64.7 ± 26.1 vs. 56.9 ± 27.5, P = 0.04) and CNFL (20.4 ± 1.2 vs. 17.9 ± 4.1, P = 0.02), but no change in cold and warm threshold, VPT, DB-HRV or nerve conduction velocity and amplitude. Increase in CNFD correlated with a decrease in triglycerides (r = –0.45, P = 0.04).ConclusionObese subjects have evidence of neuropathy, and bariatric surgery leads to an improvement in weight, HbA1c, lipids, neuropathic symptoms and deficits and small nerve fibre regeneration without a change in quantitative sensory testing, autonomic function or neurophysiology.

There are potentially many ways of assessing diabetic peripheral neuropathy (DPN). However, they do not fulfill U.S. Food and Drug Administration (FDA) requirements in relation to their capacity to assess therapeutic benefit in clinical trials of DPN. Over the past several decades symptoms and signs, quantitative sensory and electrodiagnostic testing have been strongly endorsed, but have consistently failed as surrogate end points in clinical trials. Therefore, there is an unmet need for reliable biomarkers to capture the onset and progression and to facilitate drug discovery in DPN. Corneal confocal microscopy (CCM) is a non-invasive ophthalmic imaging modality for evaluation of sensory C-fibers. An increasing body of evidence from multiple centers worldwide suggests that CCM fulfills the FDA criteria as a surrogate endpoint of DPN.

Diabetic neuropathy is associated with increased morbidity and mortality. To date, limited data in subjects with impaired glucose tolerance and diabetes demonstrate nerve fiber repair after intervention. This may reflect a lack of efficacy of the interventions but may also reflect difficulty of the tests currently deployed to adequately assess nerve fiber repair, particularly in short-term studies. Corneal confocal microscopy (CCM) represents a novel noninvasive means to quantify nerve fiber damage and repair. Fifteen type 1 diabetic patients undergoing simultaneous pancreas–kidney transplantation (SPK) underwent detailed assessment of neurologic deficits, quantitative sensory testing (QST), electrophysiology, skin biopsy, corneal sensitivity, and CCM at baseline and at 6 and 12 months after successful SPK. At baseline, diabetic patients had a significant neuropathy compared with control subjects. After successful SPK there was no significant change in neurologic impairment, neurophysiology, QST, corneal sensitivity, and intraepidermal nerve fiber density (IENFD). However, CCM demonstrated significant improvements in corneal nerve fiber density, branch density, and length at 12 months. Normalization of glycemia after SPK shows no significant improvement in neuropathy assessed by the neurologic deficits, QST, electrophysiology, and IENFD. However, CCM shows a significant improvement in nerve morphology, providing a novel noninvasive means to establish early nerve repair that is missed by currently advocated assessment techniques.

Pial collateral blood flow is a major determinant of the outcomes of acute ischemic stroke. This study was undertaken to determine whether retinal vessel metrics can predict the pial collateral status and stroke outcomes in patients. Thirty-five patients with acute stroke secondary to middle cerebral artery (MCA) occlusion underwent grading of their pial collateral status from computed tomography angiography and retinal vessel analysis from retinal fundus images. The NIHSS (14.7 ± 5.5 vs 10.1 ± 5.8, p = 0.026) and mRS (2.9 ± 1.6 vs 1.9 ± 1.3, p = 0.048) scores were higher at admission in patients with poor compared to good pial collaterals. Retinal vessel multifractals: D0 (1.673±0.028vs1.652±0.025, p = 0.028), D1 (1.609±0.027vs1.590±0.025, p = 0.044) and f(α)max (1.674±0.027vs1.652±0.024, p = 0.019) were higher in patients with poor compared to good pial collaterals. Furthermore, support vector machine learning achieved a fair sensitivity (0.743) and specificity (0.707) for differentiating patients with poor from good pial collaterals. Age (p = 0.702), BMI (p = 0.422), total cholesterol (p = 0.842), triglycerides (p = 0.673), LDL (p = 0.952), HDL (p = 0.366), systolic blood pressure (p = 0.727), HbA1c (p = 0.261) and standard retinal metrics including CRAE (p = 0.084), CRVE (p = 0.946), AVR (p = 0.148), tortuosity index (p = 0.790), monofractal Df (p = 0.576), lacunarity (p = 0.531), curve asymmetry (p = 0.679) and singularity length (p = 0.937) did not differ between patients with poor compared to good pial collaterals. This is the first translational study to show increased retinal vessel multifractal dimensions in patients with acute ischemic stroke and poor pial collaterals. A retinal vessel classifier was developed to differentiate between patients with poor and good pial collaterals and may allow rapid non-invasive identification of patients with poor pial collaterals.

Diagnosing early diabetic peripheral neuropathy remains a challenge due to deficiencies in currently advocated end points. The cornea is densely innervated with small sensory fibers, which are structurally and functionally comparable to intraepidermal nerve fibers. Corneal confocal microscopy is a method for rapid, noninvasive scanning of the living cornea with high resolution and magnification. This narrative review presents the framework for the development of biomarkers and the literature on the use and adoption of corneal confocal microscopy as an objective, diagnostic biomarker in experimental and clinical studies of diabetic peripheral neuropathy. A search was performed on PubMed and Google Scholar based on the terms “corneal confocal microscopy,” “diabetic neuropathy,” “corneal sensitivity,” and “clinical trials.” A substantial body of evidence underpins the thesis that corneal nerve loss predicts incident neuropathy and progresses with the severity of diabetic peripheral neuropathy. Corneal confocal microscopy also identifies early corneal nerve regeneration, strongly arguing for its inclusion as a surrogate end point in clinical trials of disease-modifying therapies. There are sufficient diagnostic and prospective validation studies to fulfill the US Food and Drug Administration criteria for a biomarker to support the inclusion of corneal confocal microscopy as a primary end point in clinical trials of disease-modifying therapies in diabetic neuropathy.