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

Role of artificial intelligence, machine learning and deep learning models in corneal disorders - A narrative review

In the last decade, artificial intelligence (AI) has significantly impacted ophthalmology, particularly in managing corneal diseases, a major reversible cause of blindness. This review explores AI's transformative role in the corneal subspecialty, which has adopted advanced technology for superior clinical judgment, early diagnosis, and personalized therapy. While AI's role in anterior segment diseases is less documented compared to glaucoma and retinal pathologies, this review highlights its integration into corneal diagnostics through imaging techniques like slit-lamp biomicroscopy, anterior segment optical coherence tomography (AS-OCT), and in vivo confocal biomicroscopy. AI has been pivotal in refining decision-making and prognosis for conditions such as keratoconus, infectious keratitis, and dystrophies. Multi-disease deep learning neural networks (MDDNs) have shown diagnostic ability in classifying corneal diseases using AS-OCT images, achieving notable metrics like an AUC of 0.910. AI's progress over two decades has significantly improved the accuracy of diagnosing conditions like keratoconus and microbial keratitis. For instance, AI has achieved a 90.7% accuracy rate in classifying bacterial and fungal keratitis and an AUC of 0.910 in differentiating various corneal diseases. Convolutional neural networks (CNNs) have enhanced the analysis of color-coded corneal maps, yielding up to 99.3% diagnostic accuracy for keratoconus. Deep learning algorithms have also shown robust performance in detecting fungal hyphae on in vivo confocal microscopy, with precise quantification of hyphal density. AI models combining tomography scans and visual acuity have demonstrated up to 97% accuracy in keratoconus staging according to the Amsler-Krumeich classification. However, the review acknowledges the limitations of current AI models, including their reliance on binary classification, which may not capture the complexity of real-world clinical presentations with multiple coexisting disorders. Challenges also include dependency on data quality, diverse imaging protocols, and integrating multimodal images for a generalized AI diagnosis. The need for interpretability in AI models is emphasized to foster trust and applicability in clinical settings. Looking ahead, AI has the potential to unravel the intricate mechanisms behind corneal pathologies, reduce healthcare's carbon footprint, and revolutionize diagnostic and management paradigms. Ethical and regulatory considerations will accompany AI's clinical adoption, marking an era where AI not only assists but augments ophthalmic care.

Three-Dimensional Reconstruction of Subbasal Nerve Density in Eyes With Limbal Stem Cell Deficiency: A Pilot Study

PURPOSE

Corneal subbasal nerve parameters have been previously reported using two-dimensional scans of in vivo laser scanning confocal microscopy (IVCM) in eyes with limbal stem cell deficiency (LSCD). This study aims to develop and validate a method to better quantify corneal subbasal nerve parameters and changes from reconstructed three-dimensional (3D) images.

METHODS

IVCM volume scans from 73 eyes with various degrees of LSCD (mild/moderate/severe) confirmed by multimodal anterior segment imaging including IVCM and 20 control subjects were included. Using ImageJ, the scans were manually aligned and compiled to generate a 3D reconstruction. Using filament-tracing semiautomated software (Imaris), subbasal nerve density (SND), corneal nerve fiber length, long nerves (>200 μm), and branch points were quantified and correlated with other biomarkers of LSCD.

RESULTS

3D SND decreased in eyes with LSCD when compared with control subjects. The decrease was significant for moderate and severe LSCD (P < 0.01). 3D SND was reduced by 3.7% in mild LSCD, 32.4% in moderate LSCD, and 96.5% in severe LSCD. The number of long nerves and points of branching correlated with the severity of LSCD (P < 0.0001) and with declining SND (R2 = 0.66 and 0.67, respectively). When compared with two-dimensional scans, 3D reconstructions yielded significant increases of SND and branch points in all conditions except severe LSCD. 3D analysis showed a 46% increase in long nerves only in mild LSCD (P < 0.01).

CONCLUSIONS

This proof-of-concept study validates the use of 3D reconstruction to better characterize the corneal subbasal nerve in eyes with LSCD. In the future, this concept could be used with machine learning to automate the measurements.

Objective Analysis of Corneal Nerves and Dendritic Cells

Corneal nerves and dendritic cells are increasingly being visualised to serve as clinical parameters in the diagnosis of ocular surface diseases using intravital confocal microscopy. In this review, different methods of image analysis are presented. The use of deep learning algorithms, which enable automated pattern recognition, is explained in detail using our own developments and compared with other established methods.

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.

Potential applications of artificial intelligence in image analysis in cornea diseases: a review

Artificial intelligence (AI) is an emerging field which could make an intelligent healthcare model a reality and has been garnering traction in the field of medicine, with promising results. There have been recent developments in machine learning and/or deep learning algorithms for applications in ophthalmology-primarily for diabetic retinopathy, and age-related macular degeneration. However, AI research in the field of cornea diseases is relatively new. Algorithms have been described to assist clinicians in diagnosis or detection of cornea conditions such as keratoconus, infectious keratitis and dry eye disease. AI may also be used for segmentation and analysis of cornea imaging or tomography as an adjunctive tool. Despite the potential advantages that these new technologies offer, there are challenges that need to be addressed before they can be integrated into clinical practice. In this review, we aim to summarize current literature and provide an update regarding recent advances in AI technologies pertaining to corneal diseases, and its potential future application, in particular pertaining to image analysis.

A deep learning-based model for automatic segmentation and evaluation of corneal neovascularization using slit-lamp anterior segment images

Background

Corneal neovascularization (CoNV) is a common sign in anterior segment eye diseases, the level of which can indicate condition changes. Current CoNV evaluation methods are time-consuming and some of them rely on equipment which is not widely available in hospitals. Thus, a fast and efficient evaluation method is now urgently required. In this study, a deep learning (DL)-based model was developed to automatically segment and evaluate CoNV using anterior segment images from a slit-lamp microscope.

Methods

A total of 80 cornea slit-lamp photographs (from 80 patients) with clinically manifested CoNV were collected from December 2021 to July 2022 at Tianjin Medical University Eye Hospital. Of these, 60 images were manually labelled by ophthalmologists using ImageJ software to train the vessel segmentation network IterNet. To evaluate the performance of this automated model, evaluation metrics including accuracy, precision, area under the receiver operating characteristic (ROC) curve (AUC), and F1 score were calculated between the manually labelled ground truth and the automatic segmentations of CoNV of 20 anterior segment images. Furthermore, the vessels pixel count was automatically calculated and compared with the manually labelled results to evaluate clinical usability of the automated segmentation network.

Results

The IterNet model achieved an AUC of 0.989, accuracy of 0.988, sensitivity of 0.879, specificity of 0.993, area under precision-recall of 0.921, and F1 score of 0.879. The Bland-Altman plot between manually labelled ground truth and automated segmentation results produced a concordance correlation coefficient of 0.989, 95% limits of agreement between 865.4 and -562.4, and the vessels pixel count's Pearson coefficient of correlation was 0.981 (P<0.01).

Conclusions

The fully automated network model IterNet provides a time-saving and efficient method to make a quantitative evaluation of CoNV using slit-lamp anterior segment images. This method demonstrates great value and clinical application potential for patient care and future research.

Open-Source Automated Segmentation of Neuronal Structures in Corneal Confocal Microscopy Images of the Subbasal Nerve Plexus With Accuracy on Par With Human Segmentation

PURPOSE

The aim of this study was to perform automated segmentation of corneal nerves and other structures in corneal confocal microscopy (CCM) images of the subbasal nerve plexus (SNP) in eyes with ocular surface diseases (OSDs).

METHODS

A deep learning-based 2-stage algorithm was designed to perform segmentation of SNP features. In the first stage, to address applanation artifacts, a generative adversarial network-enabled deep network was constructed to identify 3 neighboring corneal layers on each CCM image: epithelium, SNP, and stroma. This network was trained/validated on 470 images of each layer from 73 individuals. The segmented SNP regions were further classified in the second stage by another deep network as follows: background, nerve, neuroma, and immune cells. Twenty-one-fold cross-validation was used to assess the performance of the overall algorithm on a separate data set of 207 manually segmented SNP images from 43 patients with OSD.

RESULTS

For the background, nerve, neuroma, and immune cell classes, the Dice similarity coefficients of the proposed automatic method were 0.992, 0.814, 0.748, and 0.736, respectively. The performance metrics for automatic segmentations were statistically better or equal as compared to human segmentation. In addition, the resulting clinical metrics had good to excellent intraclass correlation coefficients between automatic and human segmentations.

CONCLUSIONS

The proposed automatic method can reliably segment potential CCM biomarkers of OSD onset and progression with accuracy on par with human gradings in real clinical data, which frequently exhibited image acquisition artifacts. To facilitate future studies on OSD, we made our data set and algorithms freely available online as an open-source software package.

Automated identification and quantification of activated dendritic cells in central cornea using artificial intelligence

PURPOSE

To validate an algorithm quantifying activated dendritic cells (aDCs) using in-vivo confocal microscopy (IVCM) images.

METHODS

IVCM images obtained at the Miami Veterans Affairs Hospital were retrospectively analyzed. ADCs were quantified both with an automated algorithm and manually. Intra-class-correlation (ICC) and a Bland-Altman plot were used to compare automated and manual counts. As a secondary analysis, individuals were grouped by Dry Eye (DE) subtype: 1) aqueous-tear deficiency (ATD; Schirmer's test ≤5 mm); 2) evaporative DE (EDE; TBUT≤5s); or 3) control (Schirmer's test>5 mm; TBUT>5s) and ICCs were re-examined.

RESULTS

173 non-overlapping images from 86 individuals were included in this study. The mean age was 55.2 ± 16.7 years; 77.9% were male; 20 had ATD; 18 EDE and 37 were controls. The mean number of aDCs in the central cornea quantified automatically was 0.83 ± 1.33 cells/image and manually was 1.03 ± 1.65 cells/image. A total of 143 aDCs were identified by the automated algorithm and 178 aDCs were identified manually. While a Bland-Altman plot indicated a small difference between the two methods (0.19, p < 0.01), the ICC of 0.80 (p = 0.01) demonstrated excellent agreement. Secondarily, similar results were found by DE type with an ICC of 0.75 (p = 0.01) for the ATD group, 0.80 (p = 0.01) for EDE, and 0.82 (p = 0.01) for controls.

CONCLUSIONS

Quantification of aDCs within the central cornea may be successfully estimated using an automated machine learning based algorithm. While this study suggests that analysis using artificial intelligence has comparable results with manual quantification, further longitudinal research to validate our findings in more diverse populations may be warranted.

A deep learning model established for evaluating lid margin signs with colour anterior segment photography

OBJECTIVES

To evaluate the feasibility of applying a deep learning model to identify lid margin signs from colour anterior segment photography.

METHODS

We collected a total of 832 colour anterior segment photographs from 428 dry eye patients. Eight lid margin signs were labelled by human ophthalmologists. Eight deep learning models were constructed based on VGGNet-13 and trained to identify lid margin signs. Sensitivity, specificity, receiver operative characteristic (ROC) curves and area under the curve (AUC) were applied to evaluate the models.

RESULTS

The AUC for rounding of posterior lid margin was 0.979 and was 0.977 and 0.980 for lid margin irregularity and vascularization. For hyperkeratinization, the AUC was 0.964. The AUCs for meibomian gland orifice (MGO) retroplacement and plugging were 0.963 and 0.968. For the mucocutaneous junction (MCJ) anteroplacement and retroplacement model, the AUCs were 0.950 and 0.978. The sensitivity and specificity for rounding of posterior lid margin were 0.974 and 0.921. For irregularity, the sensitivity and specificity were 0.930 and 0.938, and those for vascularization were 0.923 and 0.961. The hyperkeratinization model achieved a sensitivity and specificity of 0.889 and 0.948. The model identifying MGO plugging and retroplacement achieved a sensitivity of 0.979 and 0.909 with a specificity of 0.867 and 0.967. The sensitivity of MCJ anteroplacement and retroplacement were 0.875/0.969, with a specificity of 0.966/0.888.

CONCLUSIONS

The deep learning model could identify lid margin signs with high sensitivity and specificity. The study provided the potentiality of applying artificial intelligence in lid margin evaluation to assist dry eye decision-making.

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.

A Deep Learning Model for Evaluating Meibomian Glands Morphology from Meibography

To develop a deep learning model for automatically segmenting tarsus and meibomian gland areas on meibography, we included 1087 meibography images from dry eye patients. The contour of the tarsus and each meibomian gland was labeled manually by human experts. The dataset was divided into training, validation, and test sets. We built a convolutional neural network-based U-net and trained the model to segment the tarsus and meibomian gland area. Accuracy, sensitivity, specificity, and receiver operating characteristic curve (ROC) were calculated to evaluate the model. The area under the curve (AUC) values for models segmenting the tarsus and meibomian gland area were 0.985 and 0.938, respectively. The deep learning model achieved a sensitivity and specificity of 0.975 and 0.99, respectively, with an accuracy of 0.985 for segmenting the tarsus area. For meibomian gland area segmentation, the model obtained a high specificity of 0.96, with high accuracy of 0.937 and a moderate sensitivity of 0.751. The present research trained a deep learning model to automatically segment tarsus and the meibomian gland area from infrared meibography, and the model demonstrated outstanding accuracy in segmentation. With further improvement, the model could potentially be applied to assess the meibomian gland that facilitates dry eye evaluation in various clinical and research scenarios.

Developing a Deep Learning Model to Evaluate Bulbar Conjunctival Injection with Color Anterior Segment Photographs

The present research aims to evaluate the feasibility of a deep-learning model in identifying bulbar conjunctival injection grading. Methods: We collected 1401 color anterior segment photographs demonstrating the cornea and bulbar conjunctival. The ground truth was bulbar conjunctival injection scores labeled by human ophthalmologists. Two convolutional neural network-based models were constructed and trained. Accuracy, precision, recall, F1-score, Kappa, and the area under the curve (AUC) were calculated to evaluate the efficiency of the deep learning models. The micro-average and macro-average AUC values for model grading bulbar conjunctival injection were 0.98 and 0.98, respectively. The deep learning model achieved a high accuracy of 87.12%, a precision of 87.13%, a recall of 87.12%, an F1-score of 87.07%, and Cohen's Kappa of 0.8153. The deep learning model demonstrated excellent performance in evaluating the severity of bulbar conjunctival injection, and it has the potential to help evaluate ocular surface diseases and determine disease progression and recovery.

Evaluation of a computer-aided diagnostic model for corneal diseases by analyzing in vivo confocal microscopy images

Objective

In order to automatically and rapidly recognize the layers of corneal images using in vivo confocal microscopy (IVCM) and classify them into normal and abnormal images, a computer-aided diagnostic model was developed and tested based on deep learning to reduce physicians' workload.

Methods

A total of 19,612 corneal images were retrospectively collected from 423 patients who underwent IVCM between January 2021 and August 2022 from Renmin Hospital of Wuhan University (Wuhan, China) and Zhongnan Hospital of Wuhan University (Wuhan, China). Images were then reviewed and categorized by three corneal specialists before training and testing the models, including the layer recognition model (epithelium, bowman's membrane, stroma, and endothelium) and diagnostic model, to identify the layers of corneal images and distinguish normal images from abnormal images. Totally, 580 database-independent IVCM images were used in a human-machine competition to assess the speed and accuracy of image recognition by 4 ophthalmologists and artificial intelligence (AI). To evaluate the efficacy of the model, 8 trainees were employed to recognize these 580 images both with and without model assistance, and the results of the two evaluations were analyzed to explore the effects of model assistance.

Results

The accuracy of the model reached 0.914, 0.957, 0.967, and 0.950 for the recognition of 4 layers of epithelium, bowman's membrane, stroma, and endothelium in the internal test dataset, respectively, and it was 0.961, 0.932, 0.945, and 0.959 for the recognition of normal/abnormal images at each layer, respectively. In the external test dataset, the accuracy of the recognition of corneal layers was 0.960, 0.965, 0.966, and 0.964, respectively, and the accuracy of normal/abnormal image recognition was 0.983, 0.972, 0.940, and 0.982, respectively. In the human-machine competition, the model achieved an accuracy of 0.929, which was similar to that of specialists and higher than that of senior physicians, and the recognition speed was 237 times faster than that of specialists. With model assistance, the accuracy of trainees increased from 0.712 to 0.886.

Conclusion

A computer-aided diagnostic model was developed for IVCM images based on deep learning, which rapidly recognized the layers of corneal images and classified them as normal and abnormal. This model can increase the efficacy of clinical diagnosis and assist physicians in training and learning for clinical purposes.

Artificial intelligence-assisted diagnosis of ocular surface diseases

With the rapid development of computer technology, the application of artificial intelligence (AI) in ophthalmology research has gained prominence in modern medicine. Artificial intelligence-related research in ophthalmology previously focused on the screening and diagnosis of fundus diseases, particularly diabetic retinopathy, age-related macular degeneration, and glaucoma. Since fundus images are relatively fixed, their standards are easy to unify. Artificial intelligence research related to ocular surface diseases has also increased. The main issue with research on ocular surface diseases is that the images involved are complex, with many modalities. Therefore, this review aims to summarize current artificial intelligence research and technologies used to diagnose ocular surface diseases such as pterygium, keratoconus, infectious keratitis, and dry eye to identify mature artificial intelligence models that are suitable for research of ocular surface diseases and potential algorithms that may be used in the future.

Integration of Artificial Intelligence into the Approach for Diagnosis and Monitoring of Dry Eye Disease

Dry eye disease (DED) is one of the most common diseases worldwide that can lead to a significant impairment of quality of life. The diagnosis and treatment of the disease are often challenging because of the lack of correlation between the signs and symptoms, limited reliability of diagnostic tests, and absence of established consensus on the diagnostic criteria. The advancement of machine learning, particularly deep learning technology, has enabled the application of artificial intelligence (AI) in various anterior segment disorders, including DED. Currently, many studies have reported promising results of AI-based algorithms for the accurate diagnosis of DED and precise and reliable assessment of data obtained by imaging devices for DED. Thus, the integration of AI into clinical approaches for DED can enhance diagnostic and therapeutic performance. In this review, in addition to a brief summary of the application of AI in anterior segment diseases, we will provide an overview of studies regarding the application of AI in DED and discuss the recent advances in the integration of AI into the clinical approach for DED.

Change Patterns in Corneal Intrinsic Aberrations and Nerve Density after Cataract Surgery in Patients with Dry Eye Disease

This study aimed to evaluate the change patterns in corneal intrinsic aberrations and nerve density after cataract surgery in dry eye disease. The preoperative, 1- and 3-month postoperative dry eye-related parameters were obtained by the Oculus keratograph and the ocular surface disease index questionnaire. The corneal intrinsic aberrations were measured using the Pentacam HR system. In vivo confocal microscopy was performed to observe the vortical and peripheral corneal nerves. An artificial intelligence technique run by the deep learning model generated the corneal nerve parameters. Corneal aberrations on the anterior and total corneal surfaces were significantly increased at 1 month compared with the baseline (p < 0.05) but gradually returned to the baseline by 3 months (p > 0.05). However, the change in posterior corneal aberration lasted up to 3 months (p < 0.05). There was a significant decrease in the corneal vortical nerve maximum length and average density after the operation (p < 0.05), and this damage lasted approximately 3 months. The corneal vortical nerve maximum length and average density were negatively correlated with the anterior corneal surface aberrations before and 1 month after the operation (correlation coefficients, CC = −0.26, −0.25, −0.28; all p < 0.05). Corneal vortex provided a unique site to observe long-term corneal nerve injury related to eye dryness. The continuous damage to the corneal vortical nerve may be due to the continuous dry eye state.

Artificial intelligence and corneal diseases

PURPOSE OF REVIEW

Artificial intelligence has advanced rapidly in recent years and has provided powerful tools to aid with the diagnosis, management, and treatment of ophthalmic diseases. This article aims to review the most current clinical artificial intelligence applications in anterior segment diseases, with an emphasis on microbial keratitis, keratoconus, dry eye syndrome, and Fuchs endothelial dystrophy.

RECENT FINDINGS

Most current artificial intelligence approaches have focused on developing deep learning algorithms based on various imaging modalities. Algorithms have been developed to detect and differentiate microbial keratitis classes and quantify microbial keratitis features. Artificial intelligence may aid with early detection and staging of keratoconus. Many advances have been made to detect, segment, and quantify features of dry eye syndrome and Fuchs. There is significant variability in the reporting of methodology, patient population, and outcome metrics.

SUMMARY

Artificial intelligence shows great promise in detecting, diagnosing, grading, and measuring diseases. There is a need for standardization of reporting to improve the transparency, validity, and comparability of algorithms.

Corneal Confocal Microscopy as a Quantitative Imaging Biomarker of Diabetic Peripheral Neuropathy: A Review

Distal symmetric polyneuropathy (DPN), particularly chronic sensorimotor DPN, represents one of the most frequent complications of diabetes, affecting 50% of diabetic patients and causing an enormous financial burden. Whilst diagnostic methods exist to detect and monitor this condition, they have significant limitations, mainly due to their high subjectivity, invasiveness, and non-repeatability. Corneal confocal microscopy (CCM) is an in vivo, non-invasive, and reproducible diagnostic technique for the study of all corneal layers including the sub-basal nerve plexus, which represents part of the peripheral nervous system. We reviewed the current literature on the use of CCM as an instrument in the assessment of diabetic patients, particularly focusing on its role in the study of sub-basal nerve plexus alterations as a marker of DPN. CCM has been demonstrated to be a valid in vivo tool to detect early sub-basal nerve plexus damage in adult and pediatric diabetic patients, correlating with the severity of DPN. Despite its great potential, CCM has still limited application in daily clinical practice, and more efforts still need to be made to allow the dissemination of this technique among doctors taking care of diabetic patients.

DXM-TransFuse U-net: Dual cross-modal transformer fusion U-net for automated nerve identification

Accurate nerve identification is critical during surgical procedures to prevent damage to nerve tissues. Nerve injury can cause long-term adverse effects for patients, as well as financial overburden. Birefringence imaging is a noninvasive technique derived from polarized images that have successfully identified nerves that can assist during intraoperative surgery. Furthermore, birefringence images can be processed under 20 ms with a GPGPU implementation, making it a viable image modality option for real-time processing. In this study, we first comprehensively investigate the usage of birefringence images combined with deep learning, which can automatically detect nerves with gains upwards of 14% over its color image-based (RGB) counterparts on the F2 score. Additionally, we develop a deep learning network framework using the U-Net architecture with a Transformer based fusion module at the bottleneck that leverages both birefringence and RGB modalities. The dual-modality framework achieves 76.12 on the F2 score, a gain of 19.6 % over single-modality networks using only RGB images. By leveraging and extracting the feature maps of each modality independently and using each modality's information for cross-modal interactions, we aim to provide a solution that would further increase the effectiveness of imaging systems for enabling noninvasive intraoperative nerve identification.

In vivo Confocal Microscopic Evaluation of Previously Neglected Oval Cells in Corneal Nerve Vortex: An Inflammatory Indicator of Dry Eye Disease

This study aimed to investigate the association of between previously neglected oval cells located in the corneal vortex and dry eye disease (DED). This was an observational, prospective study involving 168 patients with different degrees of DED. In vivo confocal microscopy was used to observe the corneal subbasal nerves and Langerhans cells (LCs) in the corneal vortex and periphery. Bright and oval cells were also observed in the corneal vortex. An artificial intelligence technique was used to generate subbasal nerve fiber parameters. The patients were divided into the three groups based on the presence of inflammatory cells. Group 2 patients showed a significant increase in the corneal peripheral nerve maximum length and average corneal peripheral nerve density. Patients in group 3 had more LCs than other patients. A bright and oval cell was identified in the corneal vortex, which might be a type of immature LC related to the disease severity of DED.

Segmentation and Evaluation of Corneal Nerves and Dendritic Cells From In Vivo Confocal Microscopy Images Using Deep Learning

Purpose

Segmentation and evaluation of in vivo confocal microscopy (IVCM) images requires manual intervention, which is time consuming, laborious, and non-reproducible. The aim of this research was to develop and validate deep learning–based methods that could automatically segment and evaluate corneal nerve fibers (CNFs) and dendritic cells (DCs) in IVCM images, thereby reducing processing time to analyze larger volumes of clinical images.

Methods

CNF and DC segmentation models were developed based on U-Net and Mask R-CNN architectures, respectively; 10-fold cross-validation was used to evaluate both models. The CNF model was trained and tested using 1097 and 122 images, and the DC model was trained and tested using 679 and 75 images, respectively, at each fold. The CNF morphology, number of nerves, number of branching points, nerve length, and tortuosity were analyzed; for DCs, number, size, and immature–mature cells were analyzed. Python-based software was written for model training, testing, and automatic morphometric parameters evaluation.

Results

The CNF model achieved on average 86.1% sensitivity and 90.1% specificity, and the DC model achieved on average 89.37% precision, 94.43% recall, and 91.83% F₁ score. The interclass correlation coefficient (ICC) between manual annotation and automatic segmentation were 0.85, 0.87, 0.95, and 0.88 for CNF number, length, branching points, and tortuosity, respectively, and the ICC for DC number and size were 0.95 and 0.92, respectively.

Conclusions

Our proposed methods demonstrated reliable consistency between manual annotation and automatic segmentation of CNF and DC with rapid speed. The results showed that these approaches have the potential to be implemented into clinical practice in IVCM images.

Translational Relevance

The deep learning–based automatic segmentation and quantification algorithm significantly increases the efficiency of evaluating IVCM images, thereby supporting and potentially improving the diagnosis and treatment of ocular surface disease associated with corneal nerves and dendritic cells.

Change patterns in the corneal sub-basal nerve and corneal aberrations in patients with dry eye disease: An artificial intelligence analysis

We aimed to investigate the change patterns in corneal sub-basal nerve morphology and corneal intrinsic aberrations in dry eye disease (DED). Our study included 229 eyes of 155 patients with DED and 40 eyes of 20 healthy control. We used the Oculus keratograph and the ocular surface disease index questionnaire to assess their signs and symptoms. In vivo confocal microscopy was used to observe the corneal sub-basal nerves, corneal endothelial cells, and Langerhans cells (LCs). An artificial intelligence (AI) technique run by the deep learning model generated the sub-basal nerve fibre parameters. Furthermore, we used the Pentacam HR system to measure the corneal intrinsic aberrations and corneal surface regularity indices. DED patients more frequently had increased anterior and total corneal aberrations than controls (P < 0.05). In addition, DED had decreased average density and maximum length of corneal nerve. (Both P < 0.01) The LC number was significantly correlated with maximum length (CC = -0.19, P = 0.01) of the sub-basal nerve fibre. Furthermore, the corneal nerve average density was negatively correlated with IHD, and anterior, posterior, and total corneal aberrations (All P < 0.05) especially the higher-order aberrations. Significant correlations were seen between corneal nerve morphology changes, analysed by AI and corneal intrinsic aberrations, particularly higher-order aberrations.

Advances in Imaging of Subbasal Corneal Nerves With Micro-Optical Coherence Tomography

Purpose

To investigate the most peripheral corneal nerve plexus using high-resolution micro-optical coherence tomography (µOCT) imaging and to assess µOCT's clinical potential as a screening tool for corneal and systemic diseases.

Methods

An experimental high-resolution (1.5 × 1.5 × 1 µm) µOCT setup was applied for three-dimensional imaging of the subbasal nerve plexus in nonhuman primates (NHPs) and swine within 3 hours postmortem. Morphologic features of subbasal nerves in µOCT were compared to β3 tubulin-stained fluorescence confocal microscopy (FCM). Parameters such as nerve density, nerve distribution, and imaging repeatability were evaluated, using semiautomatic image analysis in form of a custom corneal surface segmentation algorithm and NeuronJ.

Results

Swine and NHP corneas showed the species-specific nerve morphology in both imaging modalities. Most fibers showed a linear course, forming a highly parallel pattern, converging in a vortex with overall nerve densities varying between 9.51 and 24.24 mm/mm2. The repeatability of nerve density quantification of the µOCT scans as approximately 88% in multiple image recordings of the same cornea.

Conclusions

Compared to the current gold standard of FCM, µOCT's larger field of view of currently 1 × 1 mm increases the conclusiveness of density measurements, which, coupled with µOCT's feature of not requiring direct contact, shows promise for future clinical application. The nerve density quantification may be relevant for screening for systemic disease (e.g., peripheral neuropathy).

Translational Relevance

Technological advances in OCT technology may enable a quick assessment of corneal nerve density, which could be valuable evaluating ophthalmic and systemic peripheral innervation.

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.

Artificial Intelligence in Cornea, Refractive Surgery, and Cataract: Basic Principles, Clinical Applications, and Future Directions

ABSTRACT

Corneal diseases, uncorrected refractive errors, and cataract represent the major causes of blindness globally. The number of refractive surgeries, either cornea- or lens-based, is also on the rise as the demand for perfect vision continues to increase. With the recent advancement and potential promises of artificial intelligence (AI) technologies demonstrated in the realm of ophthalmology, particularly retinal diseases and glaucoma, AI researchers and clinicians are now channeling their focus toward the less explored ophthalmic areas related to the anterior segment of the eye. Conditions that rely on anterior segment imaging modalities, including slit-lamp photography, anterior segment optical coherence tomography, corneal tomography, in vivo confocal microscopy and/or optical biometers, are the most commonly explored areas. These include infectious keratitis, keratoconus, corneal grafts, ocular surface pathologies, preoperative screening before refractive surgery, intraocular lens calculation, and automated refraction, among others. In this review, we aimed to provide a comprehensive update on the utilization of AI in anterior segment diseases, with particular emphasis on the recent advancement in the past few years. In addition, we demystify some of the basic principles and terminologies related to AI, particularly machine learning and deep learning, to help improve the understanding, research and clinical implementation of these AI technologies among the ophthalmologists and vision scientists. As we march toward the era of digital health, guidelines such as CONSORT-AI, SPIRIT-AI, and STARD-AI will play crucial roles in guiding and standardizing the conduct and reporting of AI-related trials, ultimately promoting their potential for clinical translation.

A deep transfer learning framework for the automated assessment of corneal inflammation on in vivo confocal microscopy images

Purpose

Infiltration of activated dendritic cells and inflammatory cells in cornea represents an important marker for defining corneal inflammation. Deep transfer learning has presented a promising potential and is gaining more importance in computer assisted diagnosis. This study aimed to develop deep transfer learning models for automatic detection of activated dendritic cells and inflammatory cells using in vivo confocal microscopy images.

Methods

A total of 3453 images was used to train the models. External validation was performed on an independent test set of 558 images. A ground-truth label was assigned to each image by a panel of cornea specialists. We constructed a deep transfer learning network that consisted of a pre-trained network and an adaptation layer. In this work, five pre-trained networks were considered, namely VGG-16, ResNet-101, Inception V3, Xception, and Inception-ResNet V2. The performance of each transfer network was evaluated by calculating the area under the curve (AUC) of receiver operating characteristic, accuracy, sensitivity, specificity, and G mean.

Results

The best performance was achieved by Inception-ResNet V2 transfer model. In the validation set, the best transfer system achieved an AUC of 0.9646 (P<0.001) in identifying activated dendritic cells (accuracy, 0.9319; sensitivity, 0.8171; specificity, 0.9517; and G mean, 0.8872), and 0.9901 (P<0.001) in identifying inflammatory cells (accuracy, 0.9767; sensitivity, 0.9174; specificity, 0.9931; and G mean, 0.9545).

Conclusions

The deep transfer learning models provide a completely automated analysis of corneal inflammatory cellular components with high accuracy. The implementation of such models would greatly benefit the management of corneal diseases and reduce workloads for ophthalmologists.

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.