Detecting dry eye from ocular surface videos based on deep learning

Rodent models for dry eye syndrome (DES)

Dry eye syndrome (DES) is a range of ophthalmic conditions characterized by compromised tear film homeostasis, resulting from various pathological factors and primarily manifesting as ocular discomfort and impaired ocular surface integrity. With the rise in screen time due to modern lifestyles, the prevalence of DES is increasing annually, posing a significant global public health challenge. Pathophysiologically, DES involves damage to the lacrimal functional unit (LFU), including the lacrimal glands, meibomian glands, and corneoconjunctival epithelium, highlighting its multifactorial etiology. Current treatments mainly focus on artificial tears for moisture replacement and anti-inflammatory therapies, but both are limited. Consequently, animal models are crucial for understanding the complex pathological mechanisms of DES and identifying potential therapeutic agents. Rodent eyes, with their structural and physiological similarities to human eyes and cost-effectiveness, have become widely used in DES research. This manuscript reviews the current understanding of DES pathogenesis and rodent models, discussing their strengths, weaknesses, and relevant genetic models. The aim is to furnish critical insights and provide a scholarly resource to propel future investigative endeavors into the pathogenesis of and therapy for DES.

An efficient enhanced stacked auto encoder assisted optimized deep neural network for forecasting Dry Eye Disease

Meibomian Gland Dysfunction (MGD) and Dry Eye Disease (DED) comprise two of the most significant eye diseases, impacting millions of sufferers worldwide. Several etiological factors influence the early symptoms of DED. Early diagnosis and treatment of erectile dysfunction may significantly improve the Quality of Life (QoL) for people. The current study introduces the ESAE-ODNN, an improved stacked autoencoder-aided optimised deep neural network, as a new way to predict DED using feature selection (FS), feature extraction (FE), and classification. The approach described here is novel because it merges chaotic maps into FS, employs SLSTM-STSA for improved classification accuracy (CA), and optimizes with the adaptive quantum rotation of the Enhanced Quantum Bacterial Foraging Optimisation Algorithm (EQBFOA). The present study enhances prediction functions by extracting MGD-related features and complicated relationships from the DED dataset. To ensure essential feature identification, the ESAE minimizes irrelevant and redundant features. To predict the DED, the ESAE first applies FE and then implements an ODNN classifier. This method fine-tunes the ODNN framework to enhance the effectiveness of the classification. The proposed ESAE-ODNN classification system efficiently assists in the early diagnosis of DED. Combining advanced Deep Learning (DL) methods with optimization can help us understand MGD features better and sort the data with the best accuracy (96.34%). The experimental evaluation with relevant performance metrics indicates that the proposed method is efficient in diverse aspects: accurate identification, reduced complexity, and fine-tuned performance. The ESAE-ODNN's robustness in handling intricate feature indications and high-dimensional data outperforms the existing state-of-the-art techniques.

Dual-Mode Imaging System for Early Detection and Monitoring of Ocular Surface Diseases

The global prevalence of ocular surface diseases (OSDs), such as dry eyes, conjunctivitis, and subconjunctival hemorrhage (SCH), is steadily increasing due to factors such as aging populations, environmental influences, and lifestyle changes. These diseases affect millions of individuals worldwide, emphasizing the importance of early diagnosis and continuous monitoring for effective treatment. Therefore, we present a deep learning-enhanced imaging system for the automated, objective, and reliable assessment of these three representative OSDs. Our comprehensive pipeline incorporates processing techniques derived from dual-mode infrared (IR) and visible (RGB) images. It employs a multi-stage deep learning model to enable accurate and consistent measurement of OSDs. This proposed method has achieved a 98.7% accuracy with an F1 score of 0.980 in class classification and a 96.2% accuracy with an F1 score of 0.956 in SCH region identification. Furthermore, our system aims to facilitate early diagnosis of meibomian gland dysfunction (MGD), a primary factor causing dry eyes, by quantitatively analyzing the meibomian gland (MG) area ratio and detecting gland morphological irregularities with an accuracy of 88.1% and an F1 score of 0.781. To enhance convenience and timely OSD management, we are integrating a portable IR camera for obtaining meibography during home inspections. Our system demonstrates notable improvements in expanding dual-mode image-based diagnosis for broader applicability, effectively enhancing patient care efficiency. With its automation, accuracy, and compact design, this system is well-suited for early detection and ongoing assessment of OSDs, contributing to improved eye healthcare in an accessible and comprehensible manner.

Machine learning-based prediction of tear osmolarity for contact lens practice

PURPOSE

This study addressed the utilisation of machine learning techniques to estimate tear osmolarity, a clinically significant yet challenging parameter to measure accurately. Elevated tear osmolarity has been observed in contact lens wearers and is associated with contact lens-induced dry eye, a common cause of discomfort leading to discontinuation of lens wear.

METHODS

The study explored machine learning, regression and classification techniques to predict tear osmolarity using routine clinical parameters. The data set consisted of 175 participants, primarily healthy subjects eligible for soft contact lens wear. Various clinical assessments were performed, including symptom assessment with the Ocular Surface Disease Index and 5-Item Dry Eye Questionnaire (DEQ-5), tear meniscus height (TMH), tear osmolarity, non-invasive keratometric tear film break-up time (NIKBUT), ocular redness, corneal and conjunctival fluorescein staining and Meibomian glands loss.

RESULTS

The results revealed that simple linear regression was insufficient for accurate osmolarity prediction. Instead, more advanced regression models achieved a moderate level of predictive power, explaining approximately 32% of the osmolarity variability. Notably, key predictors for osmolarity included NIKBUT, TMH, ocular redness, Meibomian gland coverage and the DEQ-5 questionnaire. In classification tasks, distinguishing between low (<299 mOsmol/L), medium (300-307 mOsmol/L) and high osmolarity (>308 mOsmol/L) levels yielded an accuracy of approximately 80%. Key parameters for classification were similar to those in regression models, emphasising the importance of NIKBUT, TMH, ocular redness, Meibomian glands coverage and the DEQ-5 questionnaire.

CONCLUSIONS

This study highlights the potential benefits of integrating machine learning into contact lens research and practice. It suggests the clinical utility of assessing Meibomian glands and NIKBUT in contact lens fitting and follow-up visits. Machine learning models can optimise contact lens prescriptions and aid in early detection of conditions like dry eye, ultimately enhancing ocular health and the contact lens wearing experience.

Automated tear film break-up time measurement for dry eye diagnosis using deep learning

In the realm of ophthalmology, precise measurement of tear film break-up time (TBUT) plays a crucial role in diagnosing dry eye disease (DED). This study aims to introduce an automated approach utilizing artificial intelligence (AI) to mitigate subjectivity and enhance the reliability of TBUT measurement. We employed a dataset of 47 slit lamp videos for development, while a test dataset of 20 slit lamp videos was used for evaluating the proposed approach. The multistep approach for TBUT estimation involves the utilization of a Dual-Task Siamese Network for classifying video frames into tear film breakup or non-breakup categories. Subsequently, a postprocessing step incorporates a Gaussian filter to smooth the instant breakup/non-breakup predictions effectively. Applying a threshold to the smoothed predictions identifies the initiation of tear film breakup. Our proposed method demonstrates on the evaluation dataset a precise breakup/non-breakup classification of video frames, achieving an Area Under the Curve of 0.870. At the video level, we observed a strong Pearson correlation coefficient (r) of 0.81 between TBUT assessments conducted using our approach and the ground truth. These findings underscore the potential of AI-based approaches in quantifying TBUT, presenting a promising avenue for advancing diagnostic methodologies in ophthalmology.

Performance of ChatGPT in Diagnosis of Corneal Eye Diseases

PURPOSE

The aim of this study was to assess the capabilities of ChatGPT-4.0 and ChatGPT-3.5 for diagnosing corneal eye diseases based on case reports and compare with human experts.

METHODS

We randomly selected 20 cases of corneal diseases including corneal infections, dystrophies, and degenerations from a publicly accessible online database from the University of Iowa. We then input the text of each case description into ChatGPT-4.0 and ChatGPT-3.5 and asked for a provisional diagnosis. We finally evaluated the responses based on the correct diagnoses, compared them with the diagnoses made by 3 corneal specialists (human experts), and evaluated interobserver agreements.

RESULTS

The provisional diagnosis accuracy based on ChatGPT-4.0 was 85% (17 correct of 20 cases), whereas the accuracy of ChatGPT-3.5 was 60% (12 correct cases of 20). The accuracy of 3 corneal specialists compared with ChatGPT-4.0 and ChatGPT-3.5 was 100% (20 cases, P = 0.23, P = 0.0033), 90% (18 cases, P = 0.99, P = 0.6), and 90% (18 cases, P = 0.99, P = 0.6), respectively. The interobserver agreement between ChatGPT-4.0 and ChatGPT-3.5 was 65% (13 cases), whereas the interobserver agreement between ChatGPT-4.0 and 3 corneal specialists was 85% (17 cases), 80% (16 cases), and 75% (15 cases), respectively. However, the interobserver agreement between ChatGPT-3.5 and each of 3 corneal specialists was 60% (12 cases).

CONCLUSIONS

The accuracy of ChatGPT-4.0 in diagnosing patients with various corneal conditions was markedly improved than ChatGPT-3.5 and promising for potential clinical integration. A balanced approach that combines artificial intelligence-generated insights with clinical expertise holds a key role for unveiling its full potential in eye care.

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.

Keratoconus Detection-based on Dynamic Corneal Deformation Videos Using Deep Learning

Objective

To assess the performance of convolutional neural networks (CNNs) for automated detection of keratoconus (KC) in standalone Scheimpflug-based dynamic corneal deformation videos.

Design

Retrospective cohort study.

Participants

We retrospectively analyzed datasets with records of 734 nonconsecutive, refractive surgery candidates, and patients with unilateral or bilateral KC.

Methods

We first developed a video preprocessing pipeline to translate dynamic corneal deformation videos into 3-dimensional pseudoimage representations and then trained a CNN to directly identify KC from pseudoimages. We calculated the model's KC probability score cut-off and evaluated the performance by subjective and objective accuracy metrics using 2 independent datasets.

Main Outcome Measures

Area under the receiver operating characteristics curve (AUC), accuracy, specificity, sensitivity, and KC probability score.

Results

The model accuracy on the test subset was 0.89 with AUC of 0.94. Based on the external validation dataset, the AUC and accuracy of the CNN model for detecting KC were 0.93 and 0.88, respectively.

Conclusions

Our deep learning-based approach was highly sensitive and specific in separating normal from keratoconic eyes using dynamic corneal deformation videos at levels that may prove useful in clinical practice.

Financial Disclosures

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Deep learning algorithms for classification and detection of recurrent aphthous ulcerations using oral clinical photographic images

Background/purpose

The application of artificial intelligence diagnosis based on deep learning in the medical field has been widely accepted. We aimed to evaluate convolutional neural networks (CNNs) for automated classification and detection of recurrent aphthous ulcerations (RAU), normal oral mucosa, and other common oral mucosal diseases in clinical oral photographs.

Materials and methods

The study included 785 clinical oral photographs, which was divided into 251 images of RAU, 271 images of the normal oral mucosa, and 263 images of other common oral mucosal diseases. Four and three CNN models were used for the classification and detection tasks, respectively. 628 images were randomly selected as training data. In addition, 78 and 79 images were assigned as validating and testing data. Main outcome measures included precision, recall, F1, specificity, sensitivity and area under the receiver operating characteristics curve (AUC).

Results

In the classification task, the Pretrained ResNet50 model had the best performance with a precision of 92.86%, a recall of 91.84%, an F1 score of 92.24%, a specificity of 96.41%, a sensitivity of 91.84% and an AUC of 98.95%. In the detection task, the Pretrained YOLOV5 model had the best performance with a precision of 98.70%, a recall of 79.51%, an F1 score of 88.07% and an AUC of Precision-Recall curve 90.89%.

Conclusion

The Pretrained ResNet50 and the Pretrained YOLOV5 algorithms were shown to have superior performance and acceptable potential in the classification and detection of RAU lesions based on non-invasive oral images, which may prove useful in clinical practice.

Performance of ChatGPT in Diagnosis of Corneal Eye Diseases

Introduction

Assessing the capabilities of ChatGPT-4.0 and ChatGPT-3.5 for diagnosing corneal eye diseases based on case reports and compare with human experts.

Methods

We randomly selected 20 cases of corneal diseases including corneal infections, dystrophies, degenerations, and injuries from a publicly accessible online database from the University of Iowa. We then input the text of each case description into ChatGPT-4.0 and ChatGPT3.5 and asked for a provisional diagnosis. We finally evaluated the responses based on the correct diagnoses then compared with the diagnoses of three cornea specialists (Human experts) and evaluated interobserver agreements.

Results

The provisional diagnosis accuracy based on ChatGPT-4.0 was 85% (17 correct out of 20 cases) while the accuracy of ChatGPT-3.5 was 60% (12 correct cases out of 20). The accuracy of three cornea specialists were 100% (20 cases), 90% (18 cases), and 90% (18 cases), respectively. The interobserver agreement between ChatGPT-4.0 and ChatGPT-3.5 was 65% (13 cases) while the interobserver agreement between ChatGPT-4.0 and three cornea specialists were 85% (17 cases), 80% (16 cases), and 75% (15 cases), respectively. However, the interobserver agreement between ChatGPT-3.5 and each of three cornea specialists was 60% (12 cases).

Conclusions

The accuracy of ChatGPT-4.0 in diagnosing patients with various corneal conditions was markedly improved than ChatGPT-3.5 and promising for potential clinical integration.