Deep-learning models can predict common eyelid position abnormalities

Posted on

Deep-learning models can detect common eyelid position abnormalities from photographs, potentially helping aid diagnosis in the telemedicine setting, according to a study.

Researchers performed manual annotation of ocular landmarks on photos to train semantic segmentation of deep-learning networks. A total of 597 photos were annotated and diagnosed by 4 graders, and 557 and 40 of these images were used to train the deep-learning networks and validate the network, respectively.

The DeepLab v3+ was the best performing deep-learning network trained in this study. It had an F1 score of 0.93 and a receiver operating characteristic curve of 0.9999.

The network correctly diagnosed 71% of ptosis cases and 80% of eyelid retraction cases.  

Grob SR, et al. Automatic identification of eyelid position abnormalities using computer vision. Presented at: 2020 ASOPRS Virtual Meeting.

Related Articles
Gail Devers Partners with the Graves’ Community to Focus on Thyroid Eye Disease
Jul 15, 2021
Gail Devers, Three-Time Olympic Gold Medalist, Partners with the Graves’ Community to FOCUS on Thyroid Eye Disease
Jul 12, 2021
Mycophenolate mofetil appears to be effective second-line treatment for TED
Jun 01, 2021