Meibomian gland evaluation in patients with extended wear soft contact lens deposits

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.

A Novel Automated Approach for Infrared-Based Assessment of Meibomian Gland Morphology

Purpose

We present and validate a new methodology for analyzing, in an automated and objective fashion, infrared images of the meibomian glands (MG).

Methods

The developed algorithm consists of three main steps: selection of the region of interest, detection of MG, and analysis of MG morphometric parameters and dropout area (DOA). Additionally, a new approach to quantify the irregularity of MG is introduced. We recruited 149 adults from a general population. Infrared meibography, using Keratograph 5M, was performed. Images were assessed and graded subjectively (Meiboscore) by two experienced clinicians and objectively with the proposed automated method.

Results

The correlation of subjective DOA assessment between the two clinicians was poor and the average percentage of DOA estimated objectively for each Meiboscore group did not lie within their limits. The objective assessment showed lower variability of meibography grading than that obtained subjectively. Additionally, a new grading scale of MG DOA that reduces intraclass variation is proposed. Reported values of MG length and width were inversely proportional to the DOA. Gland irregularity was objectively quantified.

Conclusions

The proposed automatic and objective method provides accurate estimates of the DOA as well as additional morphologic parameters that could add valuable information in MG dysfunction understanding and diagnosis.

Translational Relevance

This approach highlights the shortcomings of currently used subjective methods, and provides the clinicians with an objective, quantitative and less variable alternative for assessing MG in a noninvasive and automated fashion. It provides a viable alternative to more time-consuming subjective methods.

Grading and baseline characteristics of meibomian glands in meibography images and their clinical associations in the Dry Eye Assessment and Management (DREAM) study

PURPOSE

To describe and evaluate a comprehensive grading system for meibomian gland (MG) digital infrared images developed for the Dry Eye Assessment and Management (DREAM) Study.

METHODS

Cross-sectional study. Reading Center (RC) certified readers independently evaluated MG features of both lids from meibography images of dry eye disease subjects. Dropout areas were measured using planimetry software. Inter-reader and grade-regrade agreement and comparison of meiboscale scores (Meiboscale^©; Pult) from clinical centers to RC percent dropout and of MG features with clinical parameters were evaluated.

RESULTS

Among 551 eyes of 277 patients at baseline, 62 (11%) upper lid and 5 (1%) lower lid images were missing. Lid eversion was poor in 63 (13%) of upper lids compared to 15 (3%) of lower lids. Intraclass correlation for inter-reader and grade-regrade agreement was moderate to substantial for most MG features. MG features were more frequent in the upper lid (p < 0.001), except for dropout glands, gaps, fluffy gland areas and dropout areas. Clinic meiboscale score was associated with RC percent dropout (p < 0.001), a clinic score of 0% having a mean RC score of 19%, and a clinic score of >75% having a mean RC score of 66%. MG plugging was associated with ghost glands (p = 0.009), dropout glands (p < 0.001) and a composite severity score (p = 0.02); turbid and absent secretions were associated with ghost glands (p = 0.046).

CONCLUSION

RC readers identified MG features with good reproducibility. Upper lids had more MG features. RC dropout areas correlated well with clinic meiboscale scores. Ghost glands were associated with paste like and absent meibomian secretions.

Objective image analysis of the meibomian gland area

Aims

To evaluate objectively the meibomian gland area using newly developed software for non-invasive meibography.

Methods

Eighty eyelids of 42 patients without meibomian gland loss (meiboscore=0), 105 eyelids of 57 patients with loss of less than one-third total meibomian gland area (meiboscore=1), 13 eyelids of 11 patients with between one-third and two-thirds loss of meibomian gland area (meiboscore=2) and 20 eyelids of 14 patients with two-thirds loss of meibomian gland area (meiboscore=3) were studied. Lid borders were automatically determined. The software evaluated the distribution of the luminance and, by enhancing the contrast and reducing image noise, the meibomian gland area was automatically discriminated. The software calculated the ratio of the total meibomian gland area relative to the total analysis area in all subjects. Repeatability of the software was also evaluated.

Results

The mean ratio of the meibomian gland area to the total analysis area in the upper/lower eyelids was 51.9±5.7%/54.7±5.4% in subjects with a meiboscore of 0, 47.7±6.0%/51.5±5.4% in those with a meiboscore of 1, 32.0±4.4%/37.2±3.5% in those with a meiboscore of 2 and 16.7±6.4%/19.5±5.8% in subjects with a meiboscore of 3.

Conclusions

The meibomian gland area was objectively evaluated using the developed software. This system could be useful for objectively evaluating the effect of treatment on meibomian gland dysfunction.