Akademik Veri Yönetim Sistemi
32nd IEEE Conference on Signal Processing and Communications Applications, SIU 2024, Mersin, Türkiye, 15 - 18 Mayıs 2024
The aim of this study is to provide automatic segmentation of the meibomian gland and the eyelid areas where the meibomian glands are located, which is an important step in the diagnosis of meibomian gland dysfunction. In this context, both traditional image processing methods and deep learning models have been analyzed. When selecting deep learning models, factors such as complexity and the need for retraining were taken into account. The results were analyzed using open source data and evaluated using Jaccard index and F1 score metrics.