Deep learning segmentation and quantification of Meibomian glands

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.

Temporal variations in meibomian gland structure-A pilot study

PURPOSE

To investigate whether there is a measurable change in meibomian gland morphological characteristics over the course of a day (12 h) and over a month.

METHODS

The study enrolled 15 participants who attended a total of 11 study visits spanning a 5-week period. To assess diurnal changes in meibomian glands, seven visits were conducted on a single day, each 2 h apart. For monthly assessment, participants attended an additional visit at the same time of the day every week for three consecutive weeks. Meibography using the LipiView® II system was performed at each visit, and meibomian gland morphological parameters were calculated using custom semi-automated software. Specifically, six central glands were analysed for gland length ratio, gland width, gland area, gland intensity and gland tortuosity.

RESULTS

The average meibomian gland morphological metrics did not exhibit significant changes during the course of a day or over a month. Nonetheless, certain individual gland metrics demonstrated notable variation over time, both diurnally and monthly. Specifically, meibomian gland length ratio, area, width and tortuosity exhibited significant changes both diurnally and monthly when assessed on a gland-by-gland basis.

CONCLUSIONS

Meibomian glands demonstrated measurable structural change over short periods of time (hours and days). These results have implications for innovation in gland imaging and for developing precision monitoring of gland structure to assess meibomian gland health more accurately.

Evaluation of Meibomian gland structure and appearance after therapeutic Meibomian gland expression

CLINICAL RELEVANCE

Evaluating how Meibomian glands can change in appearance has the potential to advance the understanding of Meibomian gland health and may lead to enhanced diagnosis and therapy.

BACKGROUND

This work aimed to investigate Meibomian gland appearance after therapeutic Meibomian gland expression.

METHODS

Fifteen subjects attended three study visits over a two-week period. Meibography was performed before and after therapeutic Meibomian gland expression, the following day, and 2 weeks after expression. Six central glands were used to calculate Meibomian gland morphological parameters such as gland length ratio, gland width, gland area, gland tortuosity, and gland contrast. A custom semi-automated image analysis software was used to calculate Meibomian gland metrics. Furthermore, a high-resolution imaging system was developed to capture clear images of the Meibomian glands, free of any artefacts, which were used for precise calculations of Meibomian gland contrast.

RESULTS

The expression procedure had a significant impact on Meibomian gland contrast and length ratio immediately afterwards. The least square mean difference (95% CI) from baseline for Michelson contrast was -0.006 (-0.010, -0.001) and -1.048 (-2.063, -0.033) for simple contrast. The least square mean ratio of the gland length ratio immediately after the expression to baseline was 0.758 (0.618, 0.931).

CONCLUSIONS

Following therapeutic expression, Meibomian glands exhibit reduced brightness and length. However, within 24 h, they appear to recover and return to their baseline state, indicating a relatively short recovery time. This sheds light on whether meibography is solely focused on capturing gland structure or if it also captures acinar activity. The hyperreflective properties of lipids suggest that the decrease in contrast observed after expression could be attributed to a reduction in the visualisation of acini activity. A decrease in Meibomian gland length ratio implies that the loss of gland structure following treatment may be indicative of a temporary structural alteration.

A Deep Learning Approach for Meibomian Gland Appearance Evaluation

Purpose

To develop and evaluate a deep learning algorithm for Meibomian gland characteristics calculation.

Design

Evaluation of diagnostic technology.

Subjects

A total of 1616 meibography images of both the upper (697) and lower (919) eyelids from a total of 282 individuals.

Methods

Images were collected using the LipiView II device. All the provided data were split into 3 sets: the training, validation, and test sets. Data partitions used proportions of 70/10/20% and included data from 2 optometry settings. Each set was separately partitioned with these proportions, resulting in a balanced distribution of data from both settings. The images were divided based on patient identifiers, such that all images collected for one participant could end up only in one set. The labeled images were used to train a deep learning model, which was subsequently used for Meibomian gland segmentation. The model was then applied to calculate individual Meibomian gland metrics. Interreader agreement and agreement between manual and automated methods for Meibomian gland segmentation were also carried out to assess the accuracy of the automated approach.

Main Outcome Measures

Meibomian gland metrics, including length ratio, area, tortuosity, intensity, and width, were measured. Additionally, the performance of the automated algorithms was evaluated using the aggregated Jaccard index.

Results

The proposed semantic segmentation-based approach achieved average aggregated Jaccard index of mean 0.4718 (95% confidence interval [CI], 0.4680-0.4771) for the 'gland' class and a mean of 0.8470 (95% CI, 0.8432-0.8508) for the 'eyelid' class. The result for object detection-based approach was a mean of 0.4476 (95% CI, 0.4426-0.4533). Both artificial intelligence-based algorithms underestimated area, length ratio, tortuosity, widthmean, widthmedian, width10th, and width90th. Meibomian gland intensity was overestimated by both algorithms compared with the manual approach. The object detection-based algorithm seems to be as reliable as the manual approach only for Meibomian gland width10th calculation.

Conclusions

The proposed approach can successfully segment Meibomian glands; however, to overcome problems with gland overlap and lack of image sharpness, the proposed method requires further development. The study presents another approach to utilizing automated, artificial intelligence-based methods in Meibomian gland health assessment that may assist clinicians in the diagnosis, treatment, and management of Meibomian gland dysfunction.

Financial Disclosures

The authors have no proprietary or commercial interest in any materials discussed in this article.

Role of instrumental factors in Meibomian gland contrast assessment

PURPOSE

Meibomian gland contrast has been suggested as a potential biomarker in Meibomian gland dysfunction. This study analysed the instrumental factors related to contrast. The objectives were to determine whether the mathematical equations used to compute gland contrast (e.g., Michelson or Yeh and Lin), impact the ability to identify abnormal individuals, to ascertain whether contrast between the gland and the background could be an effective biomarker and to assess whether using contrast-enhancement on the gland image improves its diagnostic efficacy.

METHODS

A total of 240 meibography images from 40 participants (20 controls and 20 having Meibomian gland dysfunction or blepharitis), were included. The Oculus Keratograph 5M was used to capture images from the upper and lower eyelids of each eye. The contrast of unprocessed images and those pre-processed with contrast-enhancement algorithms were analysed. Contrast was measured on the eight central glands. Two equations for contrast computation were used, and the contrast both between glands and within a gland were calculated.

RESULTS

Significant differences were found between the groups for inter-gland area in the upper (p = 0.01) and lower eyelids (p = 0.001) for contrast measured with the Michelson formula. Similar effects were observed when using the Yeh and Lin method in the upper (p = 0.01) and lower eyelids (p = 0.04). These results were obtained for images enhanced with the Keratograph 5M algorithm.

CONCLUSIONS

Meibomian gland contrast is a useful biomarker of disease related to the Meibomian glands. Contrast measurement should be determined using contrast-enhanced images in the inter-gland area. However, the method used to compute contrast did not influence the results.

Development of Artefact-Free Imaging System for Accurate Meibomian Gland Reflectivity Assessment

Purpose

To develop and evaluate a custom imaging system to provide high-resolution, wide depth-of-field, reflection-free, multispectral infrared (IR) imaging of the Meibomian glands.

Methods

Lower eyelids of 15 volunteers were everted to obtain multispectral images of the Meibomian glands with custom imaging setup. Photographs were captured at 10 different ISO settings (from underexposure to overexposure) and using nine IR imaging filters (ranging from 600 nm to 1000 nm in 50-nm steps). Meibomian gland contrast (simple and Michelson) was calculated for the images to choose an optimal wavelength for Meibomian gland imaging and to determine differences in contrast across individuals.

Results

The overall linear regression model showed a significant effect of wavelength on Meibomian gland contrast (Simple contrast: F = 7.24, P < 0.0001; Michelson contrast: F = 7.19, P < 0.0001). There was a significant negative correlation between Meibomian gland contrast and Meibomian gland depth for 750-nm IR filter (ρs= -0.579; P = 0.026).

Conclusions

Meibomian gland contrast varies across individuals and depends on Meibomian gland depth. IR filter of 750 nm is the optimal choice for Meibomian gland imaging because it provides images of greatest contrast.

Translational Relevance

This study adds to our understanding of Meibomian gland imaging. It has successfully demonstrated that Meibomian glands that are deeper in the tarsal plate require longer wavelengths for imaging.

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.

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.

Is histogram manipulation always beneficial when trying to improve model performance across devices? Experiments using a Meibomian gland segmentation model

Meibomian gland dysfunction (MGD) is caused by abnormalities of the meibomian glands (MG) and is one of the causes of evaporative dry eye (DED). Precise MG segmentation is crucial for MGD-related DED diagnosis because the morphological parameters of MG are of importance. Deep learning has achieved state-of-the-art performance in medical image segmentation tasks, especially when training and test data come from the same distribution. But in practice, MG images can be acquired from different devices or hospitals. When testing image data from different distributions, deep learning models that have been trained on a specific distribution are prone to poor performance. Histogram specification (HS) has been reported as an effective method for contrast enhancement and improving model performance on images of different modalities. Additionally, contrast limited adaptive histogram equalization (CLAHE) will be used as a preprocessing method to enhance the contrast of MG images. In this study, we developed and evaluated the automatic segmentation method of the eyelid area and the MG area based on CNN and automatically calculated MG loss rate. This method is evaluated in the internal and external testing sets from two meibography devices. In addition, to assess whether HS and CLAHE improve segmentation results, we trained the network model using images from one device (internal testing set) and tested on images from another device (external testing set). High DSC (0.84 for MG region, 0.92 for eyelid region) for the internal test set was obtained, while for the external testing set, lower DSC (0.69-0.71 for MG region, 0.89-0.91 for eyelid region) was obtained. Also, HS and CLAHE were reported to have no statistical improvement in the segmentation results of MG in this experiment.

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.

Automation of dry eye disease quantitative assessment: A review

Dry eye disease (DED) is a common eye condition worldwide and a primary reason for visits to the ophthalmologist. DED diagnosis is performed through a combination of tests, some of which are unfortunately invasive, non‐reproducible and lack accuracy. The following review describes methods that diagnose and measure the extent of eye dryness, enabling clinicians to quantify its severity. Our aim with this paper is to review classical methods as well as those that incorporate automation. For only four ways of quantifying DED, we take a deeper look into what main elements can benefit from automation and the different ways studies have incorporated it. Like numerous medical fields, Artificial Intelligence (AI) appears to be the path towards quality DED diagnosis. This review categorises diagnostic methods into the following: classical, semi‐automated and promising AI‐based automated methods.

Latest developments in meibography: A review

Meibography is a visualisation technique that has been used for over 40 years. There have been significant improvements in image quality, examination technique and image interpretation over this period. Although meibography has received sporadic reviews in the past, an updated review is timely due to the rapid recent rise of relevant technology and advances in both image processing and artificial intelligence. The primary aim of this paper is to review recent research into Meibomian gland imaging and update the community about the most relevant technologies and approaches used in the field.

Artificial intelligence in dry eye disease

Dry eye disease (DED) has a prevalence of between 5 and 50%, depending on the diagnostic criteria used and population under study. However, it remains one of the most underdiagnosed and undertreated conditions in ophthalmology. Many tests used in the diagnosis of DED rely on an experienced observer for image interpretation, which may be considered subjective and result in variation in diagnosis. Since artificial intelligence (AI) systems are capable of advanced problem solving, use of such techniques could lead to more objective diagnosis. Although the term 'AI' is commonly used, recent success in its applications to medicine is mainly due to advancements in the sub-field of machine learning, which has been used to automatically classify images and predict medical outcomes. Powerful machine learning techniques have been harnessed to understand nuances in patient data and medical images, aiming for consistent diagnosis and stratification of disease severity. This is the first literature review on the use of AI in DED. We provide a brief introduction to AI, report its current use in DED research and its potential for application in the clinic. Our review found that AI has been employed in a wide range of DED clinical tests and research applications, primarily for interpretation of interferometry, slit-lamp and meibography images. While initial results are promising, much work is still needed on model development, clinical testing and standardisation.

Quantifying Meibomian Gland Morphology Using Artificial Intelligence

SIGNIFICANCE

Quantifying meibomian gland morphology from meibography images is used for the diagnosis, treatment, and management of meibomian gland dysfunction in clinics. A novel and automated method is described for quantifying meibomian gland morphology from meibography images.

PURPOSE

Meibomian gland morphological abnormality is a common clinical sign of meibomian gland dysfunction, yet there exist no automated methods that provide standard quantifications of morphological features for individual glands. This study introduces an automated artificial intelligence approach to segmenting individual meibomian gland regions in infrared meibography images and analyzing their morphological features.

METHODS

A total of 1443 meibography images were collected and annotated. The dataset was then divided into development and evaluation sets. The development set was used to train and tune deep learning models for segmenting glands and identifying ghost glands from images, whereas the evaluation set was used to evaluate the performance of the model. The gland segmentations were further used to analyze individual gland features, including gland local contrast, length, width, and tortuosity.

RESULTS

A total of 1039 meibography images (including 486 upper and 553 lower eyelids) were used for training and tuning the deep learning model, whereas the remaining 404 images (including 203 upper and 201 lower eyelids) were used for evaluations. The algorithm on average achieved 63% mean intersection over union in segmenting glands, and 84.4% sensitivity and 71.7% specificity in identifying ghost glands. Morphological features of each gland were also fed to a support vector machine for analyzing their associations with ghost glands. Analysis of model coefficients indicated that low gland local contrast was the primary indicator for ghost glands.

CONCLUSIONS

The proposed approach can automatically segment individual meibomian glands in infrared meibography images, identify ghost glands, and quantitatively analyze gland morphological features.

Deep learning-based automatic meibomian gland segmentation and morphology assessment in infrared meibography

Meibomian glands (MG) are large sebaceous glands located below the tarsal conjunctiva and the abnormalities of these glands cause Meibomian gland dysfunction (MGD) which is responsible for evaporative dry eye disease (DED). Accurate MG segmentation is a key prerequisite for automated imaging based MGD related DED diagnosis. However, Automatic MG segmentation in infrared meibography is a challenging task due to image artifacts. A deep learning-based MG segmentation has been proposed which directly learns MG features from the training image dataset without any image pre-processing. The model is trained and evaluated using 728 anonymized clinical meibography images. Additionally, automatic MG morphometric parameters, gland number, length, width, and tortuosity assessment were proposed. The average precision, recall, and F1 score were achieved 83%, 81%, and 84% respectively on the testing dataset with AUC value of 0.96 based on ROC curve and dice coefficient of 84%. Single image segmentation and morphometric parameter evaluation took on average 1.33 s. To the best of our knowledge, this is the first time that a validated deep learning-based approach is applied in MG segmentation and evaluation for both upper and lower eyelids.

Image based analysis of meibomian gland dysfunction using conditional generative adversarial neural network

Objective

Meibomian gland dysfunction (MGD) is a primary cause of dry eye disease. Analysis of MGD, its severity, shapes and variation in the acini of the meibomian glands (MGs) is receiving much attention in ophthalmology clinics. Existing methods for diagnosing, detection and analysing meibomianitis are not capable to quantify the irregularities to IR (infrared) images of MG area such as light reflection, interglands and intraglands boundaries, the improper focus of the light and positioning, and eyelid eversion.

Methods and analysis

We proposed a model that is based on adversarial learning that is, conditional generative adversarial network that can overcome these blatant challenges. The generator of the model learns the mapping from the IR images of the MG to a confidence map specifying the probabilities of being a pixel of MG. The discriminative part of the model is responsible to penalise the mismatch between the IR images of the MG and confidence map. Furthermore, the adversarial learning assists the generator to produce a qualitative confidence map which is transformed into binary images with the help of fixed thresholding to fulfil the segmentation of MG. We identified MGs and interglands boundaries from IR images.

Results

This method is evaluated by meiboscoring, grading, Pearson correlation and Bland-Altman analysis. We also judged the quality of our method through average Pompeiu-Hausdorff distance, and Aggregated Jaccard Index.

Conclusions

This technique provides a significant improvement in the quantification of the irregularities to IR. This technique has outperformed the state-of-art results for the detection and analysis of the dropout area of MGD.