Computational methods for automated analysis of corneal nerve images: Lessons learned from retinal fundus image analysis

Decreased corneal subbasal nerve fiber length and density in diabetic dogs with cataracts using in vivo confocal microscopy

OBJECTIVE

To determine whether there is a difference in corneal sensitivity and corneal subbasal nerve plexus (CSNP) morphology in cataractous dogs with diabetes mellitus (DM) versus without DM.

ANIMALS STUDIED

Twenty six domestic dogs with cataracts of various breeds presented for phacoemulsification, 13 with DM and 13 without DM.

PROCEDURE

The inclusion criteria for the study were dogs with bilateral cataracts and no clinical evidence of corneal disease. The diabetic group had documented hyperglycemia and was currently treated with insulin. The non-diabetic group had no evidence of DM on examination and bloodwork. Complete ophthalmic examination, corneal esthesiometry, and in vivo confocal microscopy of the CSNP was performed for both eyes of each dog. The CSNP was evaluated using a semi-automated program and statistically analyzed.

RESULTS

The mean (±SD) CSNP fiber length was significantly decreased in diabetic (3.8 ± 3.0 mm/mm2 ) versus non-diabetic (6.7 ± 1.9 mm/mm2 ) dogs. Likewise, the mean (±SD) fiber density was significantly decreased in diabetic (8.3 ± 3.1 fibers/mm2 ) versus non-diabetic (15.5 ± 4.9 fibers/mm2 ) dogs. The corneal touch threshold was significantly reduced in diabetic (2.1 ± 0.8 cm) versus non-diabetic (2.8 ± 0.4 cm) dogs. There was a non-significant trend towards subclinical keratitis in diabetic (9/13) versus non-diabetic (4/13) dogs.

CONCLUSIONS

Morphological and functional abnormalities of the CSNP were present in dogs with DM, including decreased fiber length, fiber density, and corneal sensitivity. These findings are consistent with diabetic neuropathy and could contribute to clinically significant corneal complications after cataract surgery.

The determination of optimum segmentation parameters using genetic algorithms: Application to different segmentation algorithms and transmission electron microscopy tomography reconstructed volumes

A method for optimizing an automatic selection of values for parameters that feed segmentation algorithms is proposed. Evolutionary optimization techniques in combination with a fitness function based on a mutual information parameter have been used to find the optimal parameter values of region growing, fuzzy c-means and graph cut segmentation algorithms. To validate the method, the segmentation of two transmission electron microscopy tomography reconstructed volumes of a carbon black-reinforced rubber and a polylactic acid and clay nanocomposite is carried out (i) using evolutionary optimization techniques and (ii) manually by experts. The results confirm that the use of evolutionary optimization techniques, such as genetic algorithms, reduces the computational operation cost needed for a total grid search of segmentation parameters, reducing the probability of reaching a false optimum, and improving the segmentation quality. HIGHLIGHTS: A new approach to optimize 3D segmentation algorithms. Methodology to optimize segmentation parameters and improve segmentation quality. Improvement on the results when using region growing, fuzzy c-means and graph cuts algorithms.

Segmentation and Classification Approaches of Clinically Relevant Curvilinear Structures: A Review

Detection of curvilinear structures from microscopic images, which help the clinicians to make an unambiguous diagnosis is assuming paramount importance in recent clinical practice. Appearance and size of dermatophytic hyphae, keratitic fungi, corneal and retinal vessels vary widely making their automated detection cumbersome. Automated deep learning methods, endowed with superior self-learning capacity, have superseded the traditional machine learning methods, especially in complex images with challenging background. Automatic feature learning ability using large input data with better generalization and recognition capability, but devoid of human interference and excessive pre-processing, is highly beneficial in the above context. Varied attempts have been made by researchers to overcome challenges such as thin vessels, bifurcations and obstructive lesions in retinal vessel detection as revealed through several publications reviewed here. Revelations of diabetic neuropathic complications such as tortuosity, changes in the density and angles of the corneal fibers have been successfully sorted in many publications reviewed here. Since artifacts complicate the images and affect the quality of analysis, methods addressing these challenges have been described. Traditional and deep learning methods, that have been adapted and published between 2015 and 2021 covering retinal vessels, corneal nerves and filamentous fungi have been summarized in this review. We find several novel and meritorious ideas and techniques being put to use in the case of retinal vessel segmentation and classification, which by way of cross-domain adaptation can be utilized in the case of corneal and filamentous fungi also, making suitable adaptations to the challenges to be addressed.

Corneal Confocal Microscopy to Image Small Nerve Fiber Degeneration: Ophthalmology Meets Neurology

Neuropathic pain has multiple etiologies, but a major feature is small fiber dysfunction or damage. Corneal confocal microscopy (CCM) is a rapid non-invasive ophthalmic imaging technique that can image small nerve fibers in the cornea and has been utilized to show small nerve fiber loss in patients with diabetic and other neuropathies. CCM has comparable diagnostic utility to intraepidermal nerve fiber density for diabetic neuropathy, fibromyalgia and amyloid neuropathy and predicts the development of diabetic neuropathy. Moreover, in clinical intervention trials of patients with diabetic and sarcoid neuropathy, corneal nerve regeneration occurs early and precedes an improvement in symptoms and neurophysiology. Corneal nerve fiber loss also occurs and is associated with disease progression in multiple sclerosis, Parkinson's disease and dementia. We conclude that corneal confocal microscopy has good diagnostic and prognostic capability and fulfills the FDA criteria as a surrogate end point for clinical trials in peripheral and central neurodegenerative diseases.

Neuronal-epithelial cell alignment: A determinant of health and disease status of the cornea

PURPOSE

How sensory neurons and epithelial cells interact with one another, and whether this association can be considered an indicator of health or disease is yet to be elucidated.

METHODS

Herein, we used the cornea, Confetti mice, a novel image segmentation algorithm for intraepithelial corneal nerves which was compared to and validated against several other analytical platforms, and three mouse models to delineate this paradigm. For aging, eyes were collected from 2 to 52 week-old normal C57BL/6 mice (n ≥ 4/time-point). For wound-healing and limbal stem cell deficiency, 7 week-old mice received a limbal-sparing or limbal-to-limbal epithelial debridement to their right cornea, respectively. Eyes were collected 2-16 weeks post-injury (n=4/group/time-point), corneas procured, immunolabelled with βIII-tubulin, flat-mounted, imaged by scanning confocal microscopy and analyzed for nerve and epithelial-specific parameters.

RESULTS

Our data indicate that nerve features are dynamic during aging and their curvilinear arrangement align with corneal epithelial migratory tracks. Moderate corneal injury prompted axonal regeneration and recovery of nerve fiber features. Limbal stem cell deficient corneas displayed abnormal nerve morphology, and fibers no longer aligned with corneal epithelial migratory tracks. Mechanistically, we discovered that nerve pattern restoration relies on the number and distribution of stromal-epithelial nerve penetration sites.

CONCLUSIONS

Microstructural changes to innervation may explain corneal complications related to aging and/or disease and facilitate development of new assays for diagnosis and/or classification of ocular and systemic diseases.

Retinal fundus image enhancement with image decomposition and visual adaptation

Retinal fundus photography has been widely used to diagnose various prevalent diseases because many important diseases manifest themselves on the retina. However, the quality of fundus images obtained from practical clinical environments is not always good enough for diagnosis due to uneven illumination, blurring, low contrast, etc. In this paper, we propose a simple yet efficient method for fundus image enhancement. We first conduct image decomposition to divide the input image into three layers: base, detail, and noise layers; and then illumination correction, detail enhancement and denoising are conducted respectively at these three layers. Specifically, a simple visual adaptation model is used to correct the uneven illumination at the base layer and a weighted fusion is employed to enhance details and suppress noise and artifacts. The proposed method was evaluated on public datasets (DIARETDB0 and DIARETDB1), and also on some challenging images collected by us from the hospital. In addition, quality assessments by ophthalmologists were implemented to further verify the contribution of the proposed method in helping make diagnosis. Experimental results show that the proposed method outperforms other related methods and can simultaneously handle the tasks of illumination correction, detail enhancement and noise (and artifact) suppression.