NCT04665102

Pilot Study on Deep Learning in the Eye

Validation of a Transfer Learning Deep Learning Algorithm for Image Classification in Multiple Pathologies

• Status: Unknown
• Phase: —
• Study type: Observational
• Enrollment: 120 (estimated)
• Sponsor: CRG UZ Brussel · Academic / Other
• Sex: All
• Age: 18 Years – 100 Years
• Healthy volunteers: Accepted

Summary

Deep learning allows you to classify images using a self-learning algorithm. Transfer learning builds on an existing self-learning algorithm to enable image classification with fewer images. In this study, this technique will be applied to different image modalities in different syndromes. Retrospective study design.

Conditions

• Central Serous Chorioretinopathy
• Diabetic Retinopathy
• Cataract

Interventions

Type	Name	Description
OTHER	Image classification using deep learning algorithm	Image classification using deep learning algorithm

Timeline

• Start date: 2021-02-01
• Primary completion: 2021-12-01
• Completion: 2022-12-01
• First posted: 2020-12-11
• Last updated: 2021-01-07