Automatic segmentation and quantified analysis of meibomian glands from infrared images

Abstract

Purpose: An algorithm for automated segmentation of meibomian glands from infrared images obtained using a novel prototype infrared hand-held imager has been proposed in this study. Meibomian gland dysfunction (MGD) is quantified in terms of five clinically relevant metrics. A comparison of these metrics in patients with MGD has been presented against a sample of the normative healthy population. Methods: This is a prospective cross-sectional observational study. Patients presenting to the clinics were enrolled after written informed consent. The everted eyelids of 200 eyes of patients (of which 100 were healthy and 100 were diagnosed with MGD) were imaged using a prototype hand-held camera. The proposed algorithm was used to process the images using enhancement techniques and the glands were automatically segmented. A comparison of glands of normal eyes versus MGD-affected eyes is performed using five metrics presented in this study: (i) drop-out, (ii) length, (iii) width, (iv) the number of glands, and (v) the number of tortuous glands. Results: The 95% confidence interval for the metrics did not show any overlap between the two groups. In MGD patients, the drop-out ratio was higher than normal. The length and number of glands were significantly lesser than normal. A number of tortuous glands were more in the MGD group. The metrics for MGD versus healthy and cut-off ranges were computed in the results. Conclusion: The prototype infrared hand-held meibographer and the proposed automatic algorithm for gland segmentation and quantification are effective aids in MGD diagnosis. We present a set of five metrics, which are clinically relevant for guiding clinicians in the diagnosis of MGD.