This dataset includes 1,114 infrared images of upper eyelid meibomian glands collected between June 2020 and July 2024 in 600 participants aged 4 to 18 years. Images were pre-processed including denoising and normalized and manually annotated by 3 junior ophthalmologists and 1 senior ophthalmologist. Subsequently, segmentation is performed using an AI algorithm, and the results are reviewed and corrected by an experienced ophthalmologist. The dataset also includes demographic data and various quantitative parameters of meibomian glands. In addition, we also provide meibomian gland parameters for children and adolescents of different ages and genders to inform clinical practice.
Funding
Natural Science Foundation of Fujian Province, China [grant number: 2024J01122228]