Image-based quantitative analysis of tear film lipid layer thickness for meibomian gland evaluation

Abstract

Background: Dry eye syndrome is one of the most common ocular diseases, and meibomian gland dysfunction (MGD) is the leading cause of evaporative dry eye syndrome. When the tear film lipid layer becomes thin due to obstructive or hyposecretory meibomian gland dysfunction, the excessive evaporation of the aqueous layer can occur, and this causes evaporative dry eye syndrome. Thus, measuring the lipid layer thickness (LLT) is essential for accurate diagnosis and proper treatment of evaporative dry eye syndrome. Methods: We used a white LED panel with a slit lamp microscope to obtain videos of the lipid layer interference patterns on the cornea. To quantitatively analyze the LLT from interference colors, we developed a novel algorithm that can automatically perform the following processes on an image frame: determining the radius of the iris, locating the center of the pupil, defining region of interest (ROI), tracking the ROI, compensating for the color of iris and illumination, and producing comprehensive analysis output. A group of dry eye syndrome patients with hyposecretory MGD, dry eye syndrome without MGD, hypersecretory MGD, and healthy volunteers were recruited. Their LLTs were analyzed and statistical information-mean and standard deviation, the relative frequency of LLT at each time point, and graphical LLT visualization-were produced. Results: Using our algorithm, we processed the lipid layer interference pattern and automatically analyzed the LLT distribution of images from patients. The LLT of hyposecretory MGD was thinner (45.2 ± 11.6 nm) than that of dry eye syndrome without MGD (69.0 ± 9.4 nm) and healthy volunteers (68.3 ± 13.7 nm) while the LLT of hypersecretory MGD was thicker (93.5 ± 12.6 nm) than that of dry eye syndrome without MGD. Patients' LLTs were statistically analyzed over time, visualized with 3D surface plots, and displayed using 3D scatter plots of image pixel data for comprehensive assessment. Conclusions: We developed an image-based algorithm for quantitative measurement as well as statistical analysis of the LLT despite fluctuation and eye movement. This pilot study demonstrates that the quantitative LLT analysis of patients is consistent with the functions of meibomian glands clinically evaluated by an ophthalmologist. This approach is a significant step forward in developing a fully automated instrument for evaluating dry eye syndrome and for providing proper guidance of treatment.