In order to better assist doctors in the diagnosis of dry eye and improve the ability of ophthalmologists to recognize the condition of meibomian gland, a meibomian gland image segmentation and enhancement method based on Mobile-U-Net network was proposed. Firstly, Mobile-Net is used as the coding part of U-Net for down sampling, and then features are extracted and fused with the features in decoder to guide image segmentation. Secondly, the segmentation of meibomian gland region is enhanced to assist doctors to judge the condition. Thirdly, a large number of meibomian gland images are collected to train and verify the semantic segmentation network, and the clarity evaluation index is used to verify the meibomian gland enhancement effect. The experimental results show that the similarity coefficient of the proposed method is stable at 92.71%, and the image clarity index is better than the similar dry eye detection instruments on the market.
Deep Learning ; Diagnostic Imaging ; Dry Eye Syndromes ; Humans ; Image Processing, Computer-Assisted ; Meibomian Glands/diagnostic imaging*

To assess the application of Keratograph 5M in evaluating tear film and meibomian gland function in patients with dry eye.A total of 144 eyes were recruited in the study, in which 72 eyes were from patients diagnosed with dry eye and 72 eyes were from healthy subjects. All subjects finished following tests or examinations:ocular surface disease index (OSDI) to evaluate eye symptoms; Keratograph 5M examination to obtain tear meniscus height (TMH), noninvasive tear break-up time (NIBUT) including first NIBUT (NIBUT-Fir) and average NIBUT (NIBUT-Ave), and infrared meibography; and fluorescein sodium staining to obtain fluorescein tearbreak-up time (FBUT).Dry eye group had higher OSDI score than healthy control group, but its TMH, NIBUT-Fir and NIBUT-Ave were lower than those in healthy control group (all<0.01). Total meiboscore in dry eye group was higher than that in healthy control group (<0.01), and it showed a significant correlation with NIBUT-Fir and NIBUT-Ave (=-0.449 and -0.398,<0.01), but no correlation with ages was observed (=0.031,>0.05). The NIBUT-Fir and NIBUT-Ave showed a significant correlation with FBUT (=0.833 and 0.727,<0.01).Keratograph 5M is a convenient, accurate and non-invasive method to assess the function of tear film and meibomian gland, and the new meibography scoring system can evaluate the function of meibomian gland objectively and succinctly.
Corneal Topography ; instrumentation ; Diagnostic Equipment ; Dry Eye Syndromes ; diagnostic imaging ; Female ; Humans ; Male ; Meibomian Glands ; diagnostic imaging ; Tears ; diagnostic imaging