In Vivo Confocal Microscopy in Different Types of Dry Eye and Meibomian Gland Dysfunction

In Vivo Confocal Microscopy for Automated Detection of Meibomian Gland Dysfunction: A Study Based on Deep Convolutional Neural Networks

The objectives of this study are to construct a deep convolutional neural network (DCNN) model to diagnose and classify meibomian gland dysfunction (MGD) based on the in vivo confocal microscope (IVCM) images and to evaluate the performance of the DCNN model and its auxiliary significance for clinical diagnosis and treatment. We extracted 6643 IVCM images from the three hospitals' IVCM database as the training set for the DCNN model and 1661 IVCM images from the other two hospitals' IVCM database as the test set to examine the performance of the model. Construction of the DCNN model was performed using DenseNet-169. The results of MGD classifications by three ophthalmologists were used to calculate the area under the receiver operating characteristic curve (AUROC), accuracy, precision, recall, true negative rate (TNR), true positive rate (TPR), and false positive rate (FPR) of the model. The deep learning (DL) was used to build the model to identify the IVCM images. Model accuracy and loss tests showed that the DCNN model had high accuracy, low loss, and no large fluctuations at an epoch of 175, indicating that DenseNet-169 could enable the dichotomization to proceed stably. The accuracy of each classification of the test set was above 90%, which was highly consistent with the ophthalmologists' diagnosis. The precision of the groups in each classification was more than 90%, or even close to 100%, except for the meibomian gland atrophy with obstruction group in the fifth classification. The recall ranged from 0.8728 to 0.9981, and the FPR was low in the screening and classification diagnoses. The application of DCNN can achieve accurate classification and diagnosis of MGD through IVCM images and has great potential during medical procedures.

Redefining our vision: an updated guide to the ocular immune system

Balanced immune responses in the eyes are crucial to preserve vision. The ocular immune system has long been considered distinct, owing to the so-called 'immune privilege' of its component tissues. More recently, intravital imaging and transcriptomic techniques have reshaped scientific understanding of the ocular immune landscape, such as revealing the specialization of immune cell populations in the various tissues of the eye. As knowledge of the phenotypes of corneal and retinal immune cells has evolved, links to both the systemic immune system, and the central and peripheral nervous systems, have been identified. Using intravital imaging, T cells have recently been found to reside in, and actively patrol, the healthy human cornea. Disease-associated retinal microglia with links to retinal degeneration have also been identified. This Review provides an updated guide to the ocular immune system, highlighting current knowledge of the immune cells that are present in steady-state and specific diseased ocular tissues, as well as evidence for their relationship to systemic disease. In addition, we discuss emerging intravital imaging techniques that can be used to visualize immune cell morphology and dynamics in living human eyes and how these could be applied to advance understanding of the human immune system.

A review of the application of in-vivo confocal microscopy on conjunctival diseases

Over the past few decades, the expanded applications of in-vivo confocal microscopy (IVCM) have greatly enhanced the knowledge of a variety of conjunctival diseases. IVCM allows non-invasively detailed observation of tarsal, palpebral and bulbar conjunctiva, from the superficial to the substantia propria at the cellular level. IVCM has been shown as a powerful tool for the assessment of morphological changes in both physiological and pathological conditions. High-resolution images of different cellular phenotypes, together with quantifiable results, open new insights into understanding the mechanisms of conjunctival diseases, as well as provide valuable and longitudinal information for the diagnosis and therapeutic evaluation. This review aims to provide an overview of the current knowledge on the applications of IVCM on conjunctival disorders, including aging changes, dry eye-related morphological changes, glaucoma and glaucoma surgery-related morphological changes, conjunctival neoplasm, pterygium, allergic conjunctivitis, trachomatous scarring, and the conjunctiva-associated lymphoid tissue (CALT) changes. In this review, we highlight the key findings of previous studies and discusses the current limitations and challenges of IVCM in assessing the structural characteristics of the conjunctiva. Furthermore, we consider possible future directions for unlocking the full potential of IVCM applications. The insights presented here will contribute to a more comprehensive understanding of the applications of IVCM in conjunctival diseases.

Advances in artificial intelligence for meibomian gland evaluation: A comprehensive review

Meibomian gland dysfunction (MGD) is increasingly recognized as a critical contributor to evaporative dry eye, significantly impacting visual quality. With a global prevalence estimated at 35.8 %, it presents substantial challenges for clinicians. Conventional manual evaluation techniques for MGD face limitations characterized by inefficiencies, high subjectivity, limited big data processing capabilities, and a dearth of quantitative analytical tools. With rapidly advancing artificial intelligence (AI) techniques revolutionizing ophthalmology, studies are now leveraging sophisticated AI methodologies--including computer vision, unsupervised learning, and supervised learning--to facilitate comprehensive analyses of meibomian gland (MG) evaluations. These evaluations employ various techniques, including slit lamp examination, infrared imaging, confocal microscopy, and optical coherence tomography. This paradigm shift promises enhanced accuracy and consistency in disease evaluation and severity classification. While AI has achieved preliminary strides in meibomian gland evaluation, ongoing advancements in system development and clinical validation are imperative. We review the evolution of MG evaluation, juxtapose AI-driven methods with traditional approaches, elucidate the specific roles of diverse AI technologies, and explore their practical applications using various evaluation techniques. Moreover, we delve into critical considerations for the clinical deployment of AI technologies and envisages future prospects, providing novel insights into MG evaluation and fostering technological and clinical progress in this arena.

Confocal Microscopy of the Cornea in Aqueous-Deficient Dry Eye Disease-A Literature Review

BACKGROUND

In vivo confocal microscopy (IVCM) is a vital tool in studying dry eye disease (DED), providing insights into morphological changes at ocular surface unit levels. This review presents the main differences in corneal structure between aqueous-deficient dry eye disease (AD-DED) and normal eyes.

METHODS

A comprehensive search of PubMed, Web of Science, Embase, and MEDLINE databases from January 2000 to December 2023 was conducted. The study selection process, as well as data selection and examination, were independently performed by two members of the review team.

RESULTS

The review reveals a consistent decrease in corneal surface epithelial cell density in AD-DED cases compared to a control group, but conflicting data on basal epithelial cell density. Notably, the abnormal hyperreflectivity of keratocytes in patients with Sjogren's syndrome was recorded, and there was a significant keratocyte density in AD-DED subjects compared to evaporative DED and control groups. Studies also found a decrease in sub-basal nerve density, increased tortuosity, and the fragmentation of nerve fibers. Dendritic cell density and dendritic cell dendrites increase in AD-DED patients compared to healthy subjects.

CONCLUSIONS

IVCM is a powerful tool for enhancing our understanding of the pathophysiological mechanisms underlying DED. However, the review underscores the urgent need to standardize the terminology, analysis, and units used for accurate interpretation, a crucial step in advancing our knowledge of DED.

Imaging assessment of conjunctival goblet cells in dry eye disease

Dry eye disease (DED) is a widespread, multifactorial, and chronic disorder of the ocular surface with disruption of tear film homeostasis as its core trait. Conjunctival goblet cells (CGCs) are specialised secretory cells found in the conjunctival epithelium that participate in tear film formation by secreting mucin. Changes in both the structure and function of CGCs are hallmarks of DED, and imaging assessment of CGCs is important for the diagnosis, classification, and severity evaluation of DED. Existing imaging methods include conjunctival biopsy, conjunctival impression cytology and in vivo confocal microscopy, which can be used to assess the morphology, distribution, and density of the CGCs. Recently, moxifloxacin-based fluorescence microscopy has emerged as a novel technique that enables efficient, non-invasive and in vivo imaging of CGCs. This article presents a comprehensive overview of both the structure and function of CGCs and their alterations in the context of DED, as well as current methods of CGCs imaging assessment. Additionally, potential directions for the visual evaluation of CGCs are discussed.

Amyloids, amorphous aggregates and assemblies of peptides - Assessing aggregation

Amyloid and amorphous aggregates represent the two major categories of aggregates associated with diseases, and although exhibiting distinct features, researchers often treat them as equivalent, which demonstrates the need for more thorough characterization. Here, we compare amyloid and amorphous aggregates based on their biochemical properties, kinetics, and morphological features. To further decipher this issue, we propose the use of peptide self-assemblies as minimalistic models for understanding the aggregation process. Peptide building blocks are significantly smaller than proteins that participate in aggregation, however, they make a plausible means to bridge the gap in discerning the aggregation process at the more complex, protein level. Additionally, we explore the potential use of peptide-inspired models to research the liquid-liquid phase separation as a feasible mechanism preceding amyloid formation. Connecting these concepts can help clarify our understanding of aggregation-related disorders and potentially provide novel drug targets to impede and reverse these serious illnesses.

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.

Artificial-Intelligence-Enhanced Analysis of In Vivo Confocal Microscopy in Corneal Diseases: A Review

Artificial intelligence (AI) has seen significant progress in medical diagnostics, particularly in image and video analysis. This review focuses on the application of AI in analyzing in vivo confocal microscopy (IVCM) images for corneal diseases. The cornea, as an exposed and delicate part of the body, necessitates the precise diagnoses of various conditions. Convolutional neural networks (CNNs), a key component of deep learning, are a powerful tool for image data analysis. This review highlights AI applications in diagnosing keratitis, dry eye disease, and diabetic corneal neuropathy. It discusses the potential of AI in detecting infectious agents, analyzing corneal nerve morphology, and identifying the subtle changes in nerve fiber characteristics in diabetic corneal neuropathy. However, challenges still remain, including limited datasets, overfitting, low-quality images, and unrepresentative training datasets. This review explores augmentation techniques and the importance of feature engineering to address these challenges. Despite the progress made, challenges are still present, such as the "black-box" nature of AI models and the need for explainable AI (XAI). Expanding datasets, fostering collaborative efforts, and developing user-friendly AI tools are crucial for enhancing the acceptance and integration of AI into clinical practice.

Inflammation mechanism and anti-inflammatory therapy of dry eye

Dry eye is a widespread chronic inflammatory disease that causes fatigue, tingling, burning, and other symptoms. Dry eye is attributed to rheumatic diseases, diabetes, hormone disorders, and contact lenses, which activate inflammatory pathways: mitogen-activated protein kinases (MAPK) and nuclear factor-B (NF-κB), promote macrophage inflammatory cell and T cell activation, and inflammation factors. Clinicians use a combination of anti-inflammatory drugs to manage different symptoms of dry eye; some of these anti-inflammatory drugs are being developed. This review introduces the dry eye inflammation mechanisms and the involved inflammatory factors. We also elucidate the anti-inflammatory drug mechanism and the detection limits.

International survey on dry eye diagnosis by experts

Purpose

To evaluate patterns and opinion from international experts with respect to dry eye disease (DED) diagnosis in clinical practice.

Methods

An online survey was distributed to worldwide DED experts. The use of diagnosis tests was evaluated including: symptoms questionnaires, functional tests, tear stability, tear volume, tear composition, surface damage and inflammation, and eyelid assessment. After the subjective importance of symptoms, tear break up time (TBUT), non-invasive TBUT, Schirmer's test, tear meniscus height, tear osmolarity, tear metalloproteinase 9, blepharitis assessment and non-contact meibography was evaluated according to likert scale.

Results

The survey was sent to 109 experts, and 77 completed the questionnaire (rate of response = 70.6%). Most of the participants were from North America (27%) and Europe (40%). A majority of respondents (73%) diagnose DED using clinical signs and symptoms, but not fulfilling a specific criteria. Seventy-six participants (98.7%) use symptoms questionnaires. All participants evaluate damage to ocular surface, and fluorescein staining is the most frequent method used (92%). Also, all the respondents perform meibomian gland and blepharitis assessment. On the other hand, only 69.8% evaluate tear composition, being osmolarity the most common test used (66.2%). Regarding to the importance of tests, TBUT (p = 0.002) and Schirmer's (p = 0.021) were found to be more important to experts from Europe than North America. No differences were found in any other test (p > 0.05).

Conclusions

This survey offers updated and day-to-day diagnostic clinical practice by DED worldwide experts. The results highlight the importance of symptoms and clinical signs, but not necessarily following a strict criteria.

Enhancing Clinical Decision-Making in Complex Corneal Disorders: The Role of In-Vivo Confocal Microscopy

This study aims to describe how in-vivo confocal microscopy (ICVM) results improved diagnosis and treatment in three patients with complex corneal disorders at a single institution. Case one was a 36-year-old woman contact lens wearer referred to the hospital eye service (HES) by her community optician for a suspected corneal ulcer in her left eye. The case demonstrated that where laboratory cell culture was inconclusive, IVCM imaging improved diagnosis and more importantly adjusted the initial treatment till the complete resolution of the case. Case two was a shared-care 66-year-old keratoconus patient under a complex immunosuppression regime who had developed a recent series of post-surgical complications of fungal origin and was experiencing eye pain. IVCM was able to differentiate between an immune-mediated response and fungal keratitis and guide the clinicians towards an optimized treatment. Case three was a long-standing dry eye disease in a 64-year-old woman diagnosed with primary Sjögren’s syndrome where previous treatments failed to improve her symptomatology. IVCM was crucial for prescribing allogeneic serum eyedrops by anticipating early immune changes in the sub-basal corneal nerve plexus. In-vivo confocal microscopy can be an essential non-invasive imaging technique for improving clinicians’ diagnostic precision by adding a layer of certainty that other techniques may lack. Additionally, IVCM allows adjustment of the treatment accordingly, by instantly following any pathologic changes at the cellular level.