Neuropathic Corneal Pain: Tear Proteomic and Neuromediator Profiles, Imaging Features, and Clinical Manifestations.

PURPOSE: To investigate the tear proteomic and neuromediator profiles, in vivo confocal microscopy (IVCM) imaging features, and clinical manifestations in neuropathic corneal pain (NCP) patients. DESIGN: Cross-sectional study. METHODS: A total of 20 NCP patients and 20 age-matched controls were recruited. All subjects were evaluated by corneal sensitivity, Schirmer test, tear break-up time, and corneal and ocular surface staining, Ocular Surface Disease Index and Ocular Pain Assessment Survey questionnaires were administered, as well as IVCM examinations for corneal nerves, microneruomas, and epithelial and dendritic cells. Tears were collected for neuromediator and proteomic analysis using enzyme-linked immunosorbent assay and data-independent acquisition mass spectrometry. RESULTS: Burning and sensitivity to light were the 2 most common symptoms in NCP. A total of 188 significantly dysregulated proteins, such as elevated metallothionein-2, creatine kinases B-type, vesicle-associated membrane protein 2, neurofilament light polypeptide, and myelin basic protein, were identified in the NCP patients. The top 10 dysregulated biological pathways in NCP include neurotoxicity, axonal signaling, wound healing, neutrophil degradation, apoptosis, thrombin signaling mitochondrial dysfunction, and RHOGDI and P70S6K signaling pathways. Compared to controls, the NCP cohort presented with significantly decreased corneal sensitivity (P < .001), decreased corneal nerve fiber length (P = .003), corneal nerve fiber density (P = .006), and nerve fiber fractal dimension (P = .033), as well as increased corneal nerve fiber width (P = .002), increased length, total area and perimeter of microneuromas (P < .001, P < .001, P = .019), smaller corneal epithelial size (P = .017), and higher nerve growth factor level in tears (P = .006). CONCLUSIONS: These clinical manifestations, imaging features, and molecular characterizations would contribute to the diagnostics and potential therapeutic targets for NCP.

Deep learning for detection of Fuchs endothelial dystrophy from widefield specular microscopy imaging: a pilot study.

BACKGROUND: To describe the diagnostic performance of a deep learning (DL) algorithm in detecting Fuchs endothelial corneal dystrophy (FECD) based on specular microscopy (SM) and to reliably detect widefield peripheral SM images with an endothelial cell density (ECD) > 1000 cells/mm2. METHODS: Five hundred and forty-seven subjects had SM imaging performed for the central cornea endothelium. One hundred and seventy-three images had FECD, while 602 images had other diagnoses. Using fivefold cross-validation on the dataset containing 775 central SM images combined with ECD, coefficient of variation (CV) and hexagonal endothelial cell ratio (HEX), the first DL model was trained to discriminate FECD from other images and was further tested on an external set of 180 images. In eyes with FECD, a separate DL model was trained with 753 central/paracentral SM images to detect SM with ECD > 1000 cells/mm2 and tested on 557 peripheral SM images. Area under curve (AUC), sensitivity and specificity were evaluated. RESULTS: The first model achieved an AUC of 0.96 with 0.91 sensitivity and 0.91 specificity in detecting FECD from other images. With an external validation set, the model achieved an AUC of 0.77, with a sensitivity of 0.69 and specificity of 0.68 in differentiating FECD from other diagnoses. The second model achieved an AUC of 0.88 with 0.79 sensitivity and 0.78 specificity in detecting peripheral SM images with ECD > 1000 cells/mm2. CONCLUSIONS: Our pilot study developed a DL model that could reliably detect FECD from other SM images and identify widefield SM images with ECD > 1000 cells/mm2 in eyes with FECD. This could be the foundation for future DL models to track progression of eyes with FECD and identify candidates suitable for therapies such as Descemet stripping only.

Impact of Age on the Characteristics of Corneal Nerves and Corneal Epithelial Cells in Healthy Adults.

PURPOSE: The aim of this study was to investigate age-related changes in corneal nerves and corneal epithelial cell parameters and to establish age-adjusted reference values. METHODS: A total of 7025 corneal nerve images and 4215 corneal epithelial images obtained using in vivo confocal microscopy from 281 eyes of 143 healthy participants were included. Seven corneal nerve parameters and 3 corneal epithelial cell parameters were quantified using 2 automatic analytic software and analyzed across 6 age groups ranging from 21 to 80 years. RESULTS: There was a declining trend in all 7 nerve parameters with advancing age. In particular, corneal nerve fiber length and corneal nerve fiber density demonstrated a significant decrease in subjects aged 65 years or older compared with subjects younger than 65 years (10.8 ± 2.6 mm/mm 2 vs. 9.9 ± 2.0 mm/mm 2 , P = 0.011 in corneal nerve fiber length; 15.8 ± 5.2 fibers/mm 2 vs. 14.4 ± 4.3 fibers/mm 2 , P = 0.046 in corneal nerve fiber density), whereas corneal nerve fractal dimension demonstrated a borderline significant decrease ( P = 0.057). Similarly, there was a general declining trend in all epithelial cell parameters with advancing age. Corneal epithelial cell circularity was significantly lower in subjects aged 65 years and older as compared to subjects younger than 65 years (0.722 ± 0.021 µm 2 vs. 0.714 ± 0.021 µm 2 ; P = 0.011). CONCLUSIONS: Advancing age results in reduced corneal nerve metrics and alteration of corneal cell morphology. Aging effects should be considered when evaluating patients with corneal neuropathy.