Automated software analysis of corneal micrographs for peripheral neuropathy

A Review On digital image processing techniques for in-Vivo confocal images of the cornea

This work reviews the scientific literature regarding digital image processing for in vivo confocal microscopy images of the cornea. We present and discuss a selection of prominent techniques designed for semi- and automatic analysis of four areas of the cornea (epithelium, sub-basal nerve plexus, stroma and endothelium). The main context is image enhancement, detection of structures of interest, and quantification of clinical information. We have found that the preprocessing stage lacks of quantitative studies regarding the quality of the enhanced image, or its effects in subsequent steps of the image processing. Threshold values are widely used in the reviewed methods, although generally, they are selected empirically and manually. The image processing results are evaluated in many cases through comparison with gold standards not widely accepted. It is necessary to standardize values to be quantified in terms of sensitivity and specificity of methods. Most of the reviewed studies do not show an estimation of the computational cost of the image processing. We conclude that reliable, automatic, computer-assisted image analysis of the cornea is still an open issue, constituting an interesting and worthwhile area of research.

Multi-discriminator adversarial convolutional network for nerve fiber segmentation in confocal corneal microscopy images

Quantitative measurements of corneal sub-basal nerves are biomarkers for many ocular surface disorders, and are also important for early diagnosis and assessment of progression of neurodegenerative diseases. This paper aims to develop an automatic method for nerve fiber segmentation from in vivo corneal confocal microscopy (CCM) images, which is fundamental for nerve morphology quantification. A novel multi-discriminator adversarial convolutional network (MDACN) is proposed, where both the generator and the two discriminators emphasize multi-scale feature representations. The generator is a U-shaped fully convolutional network with multi-scale split and concatenate blocks, and the two discriminators have different effective receptive fields, sensitive to features of different scales. A novel loss function is also proposed which enables the network to pay more attention to thin fibers. The MDACN framework was evaluated on four datasets. Experiment results show that our method has excellent segmentation performance for corneal nerve fibers and outperforms some state-of-the-art methods.

Generative Adversarial Network Based Automatic Segmentation of Corneal Subbasal Nerves on In Vivo Confocal Microscopy Images

Purpose

In vivo confocal microscopy (IVCM) is a noninvasive, reproducible, and inexpensive diagnostic tool for corneal diseases. However, widespread and effortless image acquisition in IVCM creates serious image analysis workloads on ophthalmologists, and neural networks could solve this problem quickly. We have produced a novel deep learning algorithm based on generative adversarial networks (GANs), and we compare its accuracy for automatic segmentation of subbasal nerves in IVCM images with a fully convolutional neural network (U-Net) based method.

Methods

We have collected IVCM images from 85 subjects. U-Net and GAN-based image segmentation methods were trained and tested under the supervision of three clinicians for the segmentation of corneal subbasal nerves. Nerve segmentation results for GAN and U-Net-based methods were compared with the clinicians by using Pearson's R correlation, Bland-Altman analysis, and receiver operating characteristics (ROC) statistics. Additionally, different noises were applied on IVCM images to evaluate the performances of the algorithms with noises of biomedical imaging.

Results

The GAN-based algorithm demonstrated similar correlation and Bland-Altman analysis results with U-Net. The GAN-based method showed significantly higher accuracy compared to U-Net in ROC curves. Additionally, the performance of the U-Net deteriorated significantly with different noises, especially in speckle noise, compared to GAN.

Conclusions

This study is the first application of GAN-based algorithms on IVCM images. The GAN-based algorithms demonstrated higher accuracy than U-Net for automatic corneal nerve segmentation in IVCM images, in patient-acquired images and noise applied images. This GAN-based segmentation method can be used as a facilitating diagnostic tool in ophthalmology clinics.

Translational Relevance

Generative adversarial networks are emerging deep learning models for medical image processing, which could be important clinical tools for rapid segmentation and analysis of corneal subbasal nerves in IVCM images.

Validation of a Novel Confocal Microscopy Imaging Protocol With Assessment of Reproducibility and Comparison of Nerve Metrics in Dry Eye Disease Compared With Controls

PURPOSE

The purposes of this study were to assess the reproducibility of a novel standardized technique for capturing corneal subbasal nerve plexus images with in vivo corneal confocal microscopy and to compare nerve metrics captured with this method in participants with dry eye and control participants.

METHODS

Cases and controls were recruited based on their International Statistical Classification of Diseases and Related Health Problems (ICD-10) diagnoses. Participants completed the following 3 ocular symptom questionnaires: the Ocular Surface Disease Index, Neuropathic Pain Symptom Inventory, and Dry Eye Questionnaire 5. A novel eye fixation-grid system was used to capture 30 standardized confocal microscopy images of the central cornea. Each participant was imaged twice by different operators. Seven quantitative nerve metrics were analyzed using automated software (ACCmetrics, Manchester, United Kingdom) for all 30 images and a 6-image subset.

RESULTS

Forty-seven participants were recruited (25 classified as dry eye and 22 controls). The most reproducible nerve metrics were corneal nerve fiber length [intraclass correlation (ICC) = 0.86], corneal nerve fiber area (ICC = 0.86), and fractal dimension (ICC = 0.90). Although differences were not statistically significant, all mean nerve metrics were lower in those with dry eye compared with controls. Questionnaire scores did not significantly correlate with nerve metrics. Reproducibility of nerve metrics was similar when comparing the entire 30-image montage to a central 6-image subset.

CONCLUSIONS

A standardized confocal imaging technique coupled with quantitative assessment of corneal nerves produced reproducible corneal nerve metrics even with different operators. No statistically significant differences in in vivo corneal confocal microscopy nerve metrics were observed between participants with dry eye and control participants.

Application of Artificial Intelligence in the Diagnosis and Management of Corneal Diseases

Diagnosis and treatment planning in ophthalmology heavily depend on clinical examination and advanced imaging modalities, which can be time-consuming and carry the risk of human error. Artificial intelligence (AI) and deep learning (DL) are being used in different fields of ophthalmology and in particular, when running diagnostics and predicting outcomes of anterior segment surgeries. This review will evaluate the recent developments in AI for diagnostics, surgical interventions, and prognosis of corneal diseases. It also provides a brief overview of the newer AI dependent modalities in corneal diseases.

Automated Tortuosity Analysis of Nerve Fibers in Corneal Confocal Microscopy

Precise characterization and analysis of corneal nerve fiber tortuosity are of great importance in facilitating examination and diagnosis of many eye-related diseases. In this paper we propose a fully automated method for image-level tortuosity estimation, comprising image enhancement, exponential curvature estimation, and tortuosity level classification. The image enhancement component is based on an extended Retinex model, which not only corrects imbalanced illumination and improves image contrast in an image, but also models noise explicitly to aid removal of imaging noise. Afterwards, we take advantage of exponential curvature estimation in the 3D space of positions and orientations to directly measure curvature based on the enhanced images, rather than relying on the explicit segmentation and skeletonization steps in a conventional pipeline usually with accumulated pre-processing errors. The proposed method has been applied over two corneal nerve microscopy datasets for the estimation of a tortuosity level for each image. The experimental results show that it performs better than several selected state-of-the-art methods. Furthermore, we have performed manual gradings at tortuosity level of four hundred and three corneal nerve microscopic images, and this dataset has been released for public access to facilitate other researchers in the community in carrying out further research on the same and related topics.

A Deep Learning Model for Automated Sub-Basal Corneal Nerve Segmentation and Evaluation Using In Vivo Confocal Microscopy

Purpose

The purpose of this study was to establish a deep learning model for automated sub-basal corneal nerve fiber (CNF) segmentation and evaluation with in vivo confocal microscopy (IVCM).

Methods

A corneal nerve segmentation network (CNS-Net) was established with convolutional neural networks based on a deep learning algorithm for sub-basal corneal nerve segmentation and evaluation. CNS-Net was trained with 552 and tested on 139 labeled IVCM images as supervision information collected from July 2017 to December 2018 in Peking University Third Hospital. These images were labeled by three senior ophthalmologists with ImageJ software and then considered ground truth. The areas under the receiver operating characteristic curves (AUCs), mean average precision (mAP), sensitivity, and specificity were applied to evaluate the efficiency of corneal nerve segmentation. The relative deviation ratio (RDR) was leveraged to evaluate the accuracy of the corneal nerve fiber length (CNFL) evaluation task.

Results

The model achieved an AUC of 0.96 (95% confidence interval [CI] = 0.935-0.983) and an mAP of 94% with minimum dice coefficient loss at 0.12. For our dataset, the sensitivity was 96% and specificity was 75% in the CNF segmentation task, and an RDR of 16% was reported in the CNFL evaluation task. Moreover, the model was able to segment and evaluate as many as 32 images per second, much faster than skilled ophthalmologists.

Conclusions

We established a deep learning model, CNS-Net, which demonstrated a high accuracy and fast speed in sub-basal corneal nerve segmentation with IVCM. The results highlight the potential of the system in assisting clinical practice for corneal nerves segmentation and evaluation.

Translational Relevance

The deep learning model for IVCM images may enable rapid segmentation and evaluation of the corneal nerve and may provide the basis for the diagnosis and treatment of ocular surface diseases associated with corneal nerves.

Pathogenic Role of PPARα Downregulation in Corneal Nerve Degeneration and Impaired Corneal Sensitivity in Diabetes

The purpose of this study was to investigate the protective role of peroxisome proliferator-activated receptor α (PPARα) against diabetic keratopathy and corneal neuropathy. Corneal samples were obtained from human donors with and without diabetes. Streptozotocin-induced diabetic rats and mice were orally treated with PPARα agonist fenofibrate. As shown by immunohistochemistry and Western blotting, PPARα was downregulated in the corneas of humans with diabetes and diabetic rats. Immunostaining of β-III tubulin demonstrated that corneal nerve fiber metrics were decreased significantly in diabetic rats and mice, which were partially prevented by fenofibrate treatment. As evaluated using a Cochet-Bonnet aesthesiometer, corneal sensitivity was significantly decreased in diabetic mice, which was prevented by fenofibrate. PPARα ^-/- mice displayed progressive decreases in the corneal nerve fiber density. Consistently, corneal sensitivity was decreased in PPARα ^-/- mice relative to wild-type mice by 21 months of age. Diabetic mice showed increased incidence of spontaneous corneal epithelial lesion, which was prevented by fenofibrate while exacerbated by PPARα knockout. Western blot analysis revealed significantly altered neurotrophic factor levels in diabetic rat corneas, which were partially restored by fenofibrate treatment. These results indicate that PPARα protects the corneal nerve from degeneration induced by diabetes, and PPARα agonists have therapeutic potential in the treatment of diabetic keratopathy.

Emerging Biomarkers, Tools, and Treatments for Diabetic Polyneuropathy

Diabetic neuropathy, with its major clinical sequels, notably neuropathic pain, foot ulcers, and autonomic dysfunction, is associated with substantial morbidity, increased risk of mortality, and reduced quality of life. Despite its major clinical impact, diabetic neuropathy remains underdiagnosed and undertreated. Moreover, the evidence supporting a benefit for causal treatment is weak at least in patients with type 2 diabetes, and current pharmacotherapy is largely limited to symptomatic treatment options. Thus, a better understanding of the underlying pathophysiology is mandatory for translation into new diagnostic and treatment approaches. Improved knowledge about pathogenic pathways implicated in the development of diabetic neuropathy could lead to novel diagnostic techniques that have the potential of improving the early detection of neuropathy in diabetes and prediabetes to eventually embark on new treatment strategies. In this review, we first provide an overview on the current clinical aspects and illustrate the pathogenetic concepts of (pre)diabetic neuropathy. We then describe the biomarkers emerging from these concepts and novel diagnostic tools and appraise their utility in the early detection and prediction of predominantly distal sensorimotor polyneuropathy. Finally, we discuss the evidence for and limitations of the current and novel therapy options with particular emphasis on lifestyle modification and pathogenesis-derived treatment approaches. Altogether, recent years have brought forth a multitude of emerging biomarkers reflecting different pathogenic pathways such as oxidative stress and inflammation and diagnostic tools for an early detection and prediction of (pre)diabetic neuropathy. Ultimately, these insights should culminate in improving our therapeutic armamentarium against this common and debilitating or even life-threatening condition.

The corneal subbasal nerve plexus and thickness of the retinal layers in pediatric type 1 diabetes and matched controls

Optical coherence tomography (OCT) of the retina and corneal confocal laser scanning microscopy (CLSM) of the subbasal nerve plexus (SBP) are noninvasive techniques for quantification of the ocular neurodegenerative changes in individuals with type 1 diabetes mellitus (T1DM). In adult T1DM patients these changes are hardly related to T1DM only. Instead, ageing and/or lifestyle associated comorbidities have to be considered as putative confounding variables. Therefore, we investigated pediatric T1DM patients (n = 28; 14.2 ± 2.51 y; duration of disease: 5.39 ± 4.16 y) without clinical signs of diabetic retina disease, neuropathy, vasculopathy or nephropathy and compared our findings with those obtained in healthy controls (n = 46; 14.8 ± 1.89 y). The SBP was characterized by the averaged length, thickness, and tortuosity of nerve fibers as well as the number of branching and connecting points. OCT was used to determine the total thickness of the retina (ALL) and the thickness of each retinal layer. Both methods revealed signs of early neurodegenerative changes, e.g. thinning of distinct retinal layers at the pericentral ring and shortening of corneal nerve fibers that are already present in pediatric T1DM patients. Standardization of instruments and algorithms are urgently required to enable uniform comparison between different groups and define normative values to introduce in the clinical setting.

Automatic analysis of corneal nerves imaged using in vivo confocal microscopy

Interest has grown over the past decade in using in vivo confocal microscopy to analyse the morphology of corneal nerves and their changes over time. Advances in computational modelling techniques have been applied to automate the estimation of sub-basal nerve structure. These objective methods have the potential to quantify nerve density (and length), tortuosity, variations in nerve thickness, as well as temporal changes in nerve fibres such as migration patterns. Different approaches to automated nerve analysis, methods proposed and how they were validated in previous literature are reviewed. Improved understanding of these approaches and their limitations will help improve the diagnostic leverage of emerging developments for monitoring the onset and progression of a broad class of systemic diseases, including diabetes.

[Morphometric characterization of the subbasal nerve plexus : Detection and analysis of networks of nerve fibers]

Confocal laser scanning microscopy is a versatile tool in medical research and enables noninvasive in vivo imaging of the corneal subbasal nerve plexus. The aim of this work is to provide a structured overview about the detection and quantification of nerve fibers of the subbasal nerve plexus from images acquired by confocal laser scanning microscopy. Relevant steps are explained and potential factors influencing the quality of the results are pointed out. Information obtained from the quantification of subbasal nerve fiber structure can be potentially used as clinical parameters in the context of diagnostics and therapy control of diabetic neuropathy.

A Novel Approach to Analyze the Progression of Measured Corneal Sub-Basal Nerve Fiber Length in Continuously Expanding Mosaic Images

Purpose/Aim of the study: A recently proposed technique enables the generation of continuously increasing mosaic images of the corneal sub-basal nerve plexus (SNP) using in vivo corneal confocal microscopy (CCM). The aim of the present study was to investigate the progression of the corneal nerve fiber length (CNFL) measured in the growing mosaic images with regard to their increasing area.

MATERIALS AND METHODS

Five large datasets from three healthy volunteers were examined using the proposed CCM technique. Intermediate mosaic images were created and assessed for CNFL.

RESULTS

The measured CNFL progression shows both over- and underestimation of the CNFL for small observed areas. Increasing the mosaic image area stabilizes the CNFL values and reduces the moving variance in all five datasets. The relative deviation of means from values of first and second examination of two of the subjects shows high differences for an observed area of <1.5 mm².

CONCLUSIONS

The present examination provides two measures to quantify different area-dependent aspects of the CNFL measured in an expanding mosaic image. The moving variance measures how stable the CNFL can be considered at a certain mosaic size. The relative deviation of means from two repeated CCM examinations on the other hand gives some indication on the level of reliability that can be expected from the measured CNFL. The progression of CNFL in the examined datasets manifests a potentially very high variability for mosaic sizes of less than about 1.5 mm². Above that size, CNFL progression and the intra-patient relative deviations both stabilize significantly in all five datasets. The results of the present examination suggest a recommendation for a minimum sampled area of the central SNP of 1.5 mm² for reliable and meaningful measurement of CNFL.

An Automatic Tool for Quantification of Nerve Fibers in Corneal Confocal Microscopy Images

OBJECTIVE

We describe and evaluate an automated software tool for nerve-fiber detection and quantification in corneal confocal microscopy (CCM) images, combining sensitive nerve- fiber detection with morphological descriptors.

METHOD

We have evaluated the tool for quantification of Diabetic Sensorimotor Polyneuropathy (DSPN) using both new and previously published morphological features. The evaluation used 888 images from 176 subjects (84 controls and 92 patients with type 1 diabetes). The patient group was further subdivided into those with ( n = 63) and without ( n = 29) DSPN.

RESULTS

We achieve improved nerve- fiber detection over previous results (91.7% sensitivity and specificity in identifying nerve-fiber pixels). Automatic quantification of nerve morphology shows a high correlation with previously reported, manually measured, features. Receiver Operating Characteristic (ROC) analysis of both manual and automatic measurement regimes resulted in similar results in distinguishing patients with DSPN from those without: AUC of about 0.77 and 72% sensitivity-specificity at the equal error rate point.

CONCLUSION

Automated quantification of corneal nerves in CCM images provides a sensitive tool for identification of DSPN. Its performance is equivalent to manual quantification, while improving speed and repeatability.

SIGNIFICANCE

CCM is a novel in vivo imaging modality that has the potential to be a noninvasive and objective image biomarker for peripheral neuropathy. Automatic quantification of nerve morphology is a major step forward in the early diagnosis and assessment of progression, and, in particular, for use in clinical trials to establish therapeutic benefit in diabetic and other peripheral neuropathies.

In Vivo Confocal Microscopy of the Cornea: New Developments in Image Acquisition, Reconstruction, and Analysis Using the HRT-Rostock Corneal Module

The optical sectioning ability of confocal microscopy allows high magnification images to be obtained from different depths within a thick tissue specimen and is thus ideally suited to the study of intact tissue in living subjects. In vivo confocal microscopy has been used in a variety of corneal research and clinical applications since its development over 25 years ago. In this article we review the latest developments in quantitative corneal imaging with the Heidelberg Retinal Tomograph with Rostock Corneal Module (HRT-RCM). We provide an overview of the unique strengths and weaknesses of the HRT-RCM. We discuss techniques for performing 3-D imaging with the HRT-RCM, including hardware and software modifications that allow full-thickness confocal microscopy through-focusing (CMTF) of the cornea, which can provide quantitative measurements of corneal sublayer thicknesses, stromal cell and extracellular matrix backscatter, and depth-dependent changes in corneal keratocyte density. We also review current approaches for quantitative imaging of the subbasal nerve plexus, which require a combination of advanced image acquisition and analysis procedures, including wide-field mapping and 3-D reconstruction of nerve structures. The development of new hardware, software, and acquisition techniques continues to expand the number of applications of the HRT-RCM for quantitative in vivo corneal imaging at the cellular level. Knowledge of these rapidly evolving strategies should benefit corneal clinicians and basic scientists alike.

Corneal confocal microscopy: Recent progress in the evaluation of diabetic neuropathy

The present brief review discusses recent progress with corneal confocal microscopy for the evaluation of diabetic sensorimotor polyneuropathy. Corneal confocal microscopy is a new, non-invasive and reproducible diagnostic modality, and it can also be easily applied for patient follow up. It enables new perspectives of studying the natural history of diabetic sensorimotor polyneuropathy, severity of nerve fiber pathology and documenting early nerve fiber regeneration after therapeutic intervention. It shows moderate to high sensitivity and specificity for the timely diagnosis of diabetic sensorimotor polyneuropathy. Currently, corneal confocal microscopy is mainly used in specialized centers, but deserves more widespread application for the assessment of diabetic sensorimotor polyneuropathy. Finally, further progress is required in terms of technical improvements for automated nerve fiber quantification and for analysis of larger images.

Fully automated, semiautomated, and manual morphometric analysis of corneal subbasal nerve plexus in individuals with and without diabetes

PURPOSE

The aim of the study was to determine the association, agreement, and detection capability of manual, semiautomated, and fully automated methods of corneal nerve fiber length (CNFL) quantification of the human corneal subbasal nerve plexus (SNP).

METHODS

Thirty-three participants with diabetes and 17 healthy controls underwent laser scanning corneal confocal microscopy. Eight central images of the SNP were selected for each participant and analyzed using manual (CCMetrics), semiautomated (NeuronJ), and fully automated (ACCMetrics) software to quantify the CNFL.

RESULTS

For the entire cohort, mean CNFL values quantified by CCMetrics, NeuronJ, and ACCMetrics were 17.4 ± 4.3 mm/mm, 16.0 ± 3.9 mm/mm, and 16.5 ± 3.6 mm/mm, respectively (P < 0.01). CNFL quantified using CCMetrics was significantly higher than those obtained by NeuronJ and ACCMetrics (P < 0.05). The 3 methods were highly correlated (correlation coefficients 0.87-0.98, P < 0.01). The intraclass correlation coefficients were 0.87 for ACCMetrics versus NeuronJ and 0.86 for ACCMetrics versus CCMetrics. Bland-Altman plots showed good agreement between the manual, semiautomated, and fully automated analyses of CNFL. A small underestimation of CNFL was observed using ACCMetrics with increasing the amount of nerve tissue. All 3 methods were able to detect CNFL depletion in diabetic participants (P < 0.05) and in those with peripheral neuropathy as defined by the Toronto criteria, compared with healthy controls (P < 0.05).

CONCLUSIONS

Automated quantification of CNFL provides comparable neuropathy detection ability to manual and semiautomated methods. Because of its speed, objectivity, and consistency, fully automated analysis of CNFL might be advantageous in studies of diabetic neuropathy.

In vivo confocal microscopy of the ocular surface: from bench to bedside

In vivo confocal microscopy (IVCM) is an emerging technology that provides minimally invasive, high resolution, steady-state assessment of the ocular surface at the cellular level. Several challenges still remain but, at present, IVCM may be considered a promising technique for clinical diagnosis and management. This mini-review summarizes some key findings in IVCM of the ocular surface, focusing on recent and promising attempts to move "from bench to bedside". IVCM allows prompt diagnosis, disease course follow-up, and management of potentially blinding atypical forms of infectious processes, such as acanthamoeba and fungal keratitis. This technology has improved our knowledge of corneal alterations and some of the processes that affect the visual outcome after lamellar keratoplasty and excimer keratorefractive surgery. In dry eye disease, IVCM has provided new information on the whole-ocular surface morphofunctional unit. It has also improved understanding of pathophysiologic mechanisms and helped in the assessment of prognosis and treatment. IVCM is particularly useful in the study of corneal nerves, enabling description of the morphology, density, and disease- or surgically induced alterations of nerves, particularly the subbasal nerve plexus. In glaucoma, IVCM constitutes an important aid to evaluate filtering blebs, to better understand the conjunctival wound healing process, and to assess corneal changes induced by topical antiglaucoma medications and their preservatives. IVCM has significantly enhanced our understanding of the ocular response to contact lens wear. It has provided new perspectives at a cellular level on a wide range of contact lens complications, revealing findings that were not previously possible to image in the living human eye. The final section of this mini-review provides a focus on advances in confocal microscopy imaging. These include 2D wide-field mapping, 3D reconstruction of the cornea and automated image analysis.

Corneal confocal microscopy: a new technique for early detection of diabetic neuropathy

Corneal confocal microscopy (CCM) is a noninvasive method for the study of human cornea in vivo. It has increasingly been used to assess the morphology of the sub-basal corneal nerve plexus. CCM has good reproducibility and may contribute to the early diagnosis of diabetic polyneuropathy. It may also be useful to document favorable changes in nerve fiber structure early after therapeutic intervention. Corneal nerve pathology is more pronounced in patients with diabetic polyneuropathy and is associated with its clinical severity. The sensitivity and specificity of CCM for the diagnosis of polyneuropathy is moderate to high. CCM now merits further use in large longitudinal studies to provide more information on the natural history of diabetic neuropathy and effects of treatment. Moreover, there is a need for a larger normative database. Finally, technical progress is expected to enable visualization of larger corneal areas and improve nerve fiber quantification, increasing diagnostic accuracy.

Imaging and quantification of subbasal nerve plexus in healthy volunteers and diabetic patients with or without retinopathy

BACKGROUND

The alterations of subbasal nerve plexus (SBP) innervation and corneal sensation were estimated non-invasively and compared with the values in healthy volunteers. Additionally, this study addressed the relation of SBP changes to the retinal status, glycemic control and diabetes duration.

METHODOLOGY/PRINCIPAL FINDINGS

Eighteen eyes of diabetic patients with peripheral diabetic neuropathy aged 68.8±8.8 years and twenty eyes of healthy volunteers aged 66.3±13.3 yrs. were investigated with in vivo confocal laser-scanning microscopy (CLSM). An adapted algorithm for image analysis was used to quantify the morphological and topological properties of SBP. These properties were correlated to incidence of diabetic retinopathy (DR) and corneal sensation (Cochet-Bonnet esthesiometer). The developed algorithm allows a fully automated analysis of pre-segmented SBP structures. Altogether, 10 parameters were analysed, and all of them revealed significant differences between diabetic patients and healthy volunteers. The nerve fibre density, total fibre length and nerve branches were found to be significantly lower in patients with diabetes than those of control subjects (nerve fibre density 0.006±0.002 vs. 0.020±0.007 mm/mm(2); total fibre length 6223±2419 vs. 19961±6553 µm; nerve branches 25.3±28.6 vs. 141.9±85.7 in healthy volunteers). Also the corneal sensation was significantly lower in diabetic group when compared to controls (43±11 vs. 59±18 mm). There was found no difference in SBP morphology or corneal sensation in the subgroups with (DR) or without (NDR) diabetic retinopathy.

CONCLUSIONS/SIGNIFICANCE

SBP parameters were significantly reduced in diabetic patients, compared to control group. Interestingly, the SBP impairment could be shown even in the diabetic patients without DR. Although automatic adapted image analysis simplifies the evaluation of in vivo CLSM data, image acquisition and quantitative analysis should be optimised for the everyday clinical practice.

A method for corneal nerves automatic segmentation and morphometric analysis

The segmentation and morphometric analysis of corneal sub-basal nerves, from corneal confocal microscopy images, has gained recently an increased interest. This interest arises from the possibility of using changes in these nerves as the basis of a simple and non-invasive method for early detection and follow-up of peripheral diabetic neuropathy, a major cause of chronic disability in diabetic patients. Here, we propose one method for automatic segmentation and analysis of corneal nerves from images obtained in vivo through corneal confocal microscopy. The method is capable of segmenting corneal nerves, with sensitivity near 90% and a percentage of false recognitions with an average of 5.3%. The nerves tortuosity was calculated and shows statistically significant differences between healthy controls and diabetic individuals, in accordance to what is reported in the literature.

The Glenn A. Fry award lecture 2010: Ophthalmic markers of diabetic neuropathy

Diabetic peripheral neuropathy (DPN) is a debilitating condition that affects about 50% of diabetic patients. The symptoms of DPN include numbness, tingling, or pain in the arms and legs. Patients with numbness may be unaware of foot trauma, which could develop into a foot ulcer. If left untreated, this may ultimately require amputation. Currently, the only method of directly examining peripheral nerves is to conduct skin punch or sural/peroneal nerve biopsies, which are uncomfortable and invasive. Indirect methods include quantitative sensory testing (assessing responses to heat, cold, and vibration) and nerve electrophysiology. Here, I describe research undertaken in my laboratory, investigating the possibility of using a range of ophthalmic markers to assess DPN. Corneal nerve structure and function can be assessed using corneal confocal microscopy and non-contact corneal esthesiometry, respectively. Retinal nerve structure and visual function can be evaluated using optical coherence tomography and perimetry, respectively. These techniques have been used to demonstrate that DPN is associated with morphological degradation of corneal nerves, reduced corneal sensitivity, retinal nerve fiber layer thinning, and peripheral visual field loss. With further validation, these ophthalmic markers could become established as rapid, painless, non-invasive, sensitive, reiterative, cost-effective, and clinically accessible means of screening for early detection, diagnosis, staging severity, and monitoring progression of DPN, as well as assessing the effectiveness of possible therapeutic interventions. Looking to the future, this research may pave the way for an expanded role for the ophthalmic professions in diabetes management.